diff --git a/CHANGELOG.md b/CHANGELOG.md index ce4cfde91..c3693393c 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,7 @@ ## Changelog +### CUDA 12.5 + ### CUDA 12.4 * Added graphConditionalNodes Sample diff --git a/Common/helper_multiprocess.cpp b/Common/helper_multiprocess.cpp index 937830e35..61fe0855f 100644 --- a/Common/helper_multiprocess.cpp +++ b/Common/helper_multiprocess.cpp @@ -168,7 +168,7 @@ int waitProcess(Process *process) { #endif } -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) int ipcCreateSocket(ipcHandle *&handle, const char *name, const std::vector &processes) { int server_fd; @@ -262,41 +262,48 @@ int ipcRecvShareableHandle(ipcHandle *handle, ShareableHandle *shHandle) { // Union to guarantee alignment requirements for control array union { struct cmsghdr cm; - char control[CMSG_SPACE(sizeof(int))]; + // This will not work on QNX as QNX CMSG_SPACE calls __cmsg_alignbytes + // And __cmsg_alignbytes is a runtime function instead of compile-time macros + // char control[CMSG_SPACE(sizeof(int))] + char* control; } control_un; + size_t sizeof_control = CMSG_SPACE(sizeof(int)) * sizeof(char); + control_un.control = (char*) malloc(sizeof_control); struct cmsghdr *cmptr; ssize_t n; int receivedfd; char dummy_buffer[1]; ssize_t sendResult; - msg.msg_control = control_un.control; - msg.msg_controllen = sizeof(control_un.control); + msg.msg_controllen = sizeof_control; iov[0].iov_base = (void *)dummy_buffer; iov[0].iov_len = sizeof(dummy_buffer); msg.msg_iov = iov; msg.msg_iovlen = 1; - if ((n = recvmsg(handle->socket, &msg, 0)) <= 0) { perror("IPC failure: Receiving data over socket failed"); + free(control_un.control); return -1; } if (((cmptr = CMSG_FIRSTHDR(&msg)) != NULL) && (cmptr->cmsg_len == CMSG_LEN(sizeof(int)))) { if ((cmptr->cmsg_level != SOL_SOCKET) || (cmptr->cmsg_type != SCM_RIGHTS)) { + free(control_un.control); return -1; } memmove(&receivedfd, CMSG_DATA(cmptr), sizeof(receivedfd)); *(int *)shHandle = receivedfd; } else { + free(control_un.control); return -1; } + free(control_un.control); return 0; } @@ -340,9 +347,12 @@ int ipcSendShareableHandle(ipcHandle *handle, union { struct cmsghdr cm; - char control[CMSG_SPACE(sizeof(int))]; + char* control; } control_un; + size_t sizeof_control = CMSG_SPACE(sizeof(int)) * sizeof(char); + control_un.control = (char*) malloc(sizeof_control); + struct cmsghdr *cmptr; ssize_t readResult; struct sockaddr_un cliaddr; @@ -360,7 +370,7 @@ int ipcSendShareableHandle(ipcHandle *handle, int sendfd = (int)shareableHandles[data]; msg.msg_control = control_un.control; - msg.msg_controllen = sizeof(control_un.control); + msg.msg_controllen = sizeof_control; cmptr = CMSG_FIRSTHDR(&msg); cmptr->cmsg_len = CMSG_LEN(sizeof(int)); @@ -380,9 +390,11 @@ int ipcSendShareableHandle(ipcHandle *handle, ssize_t sendResult = sendmsg(handle->socket, &msg, 0); if (sendResult <= 0) { perror("IPC failure: Sending data over socket failed"); + free(control_un.control); return -1; } + free(control_un.control); return 0; } diff --git a/Common/helper_multiprocess.h b/Common/helper_multiprocess.h index 9ea927d43..5c7607186 100644 --- a/Common/helper_multiprocess.h +++ b/Common/helper_multiprocess.h @@ -84,7 +84,7 @@ int waitProcess(Process *process); #define checkIpcErrors(ipcFuncResult) \ if (ipcFuncResult == -1) { fprintf(stderr, "Failure at %u %s\n", __LINE__, __FILE__); exit(EXIT_FAILURE); } -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) struct ipcHandle_st { int socket; char *socketName; diff --git a/README.md b/README.md index 692f6bcc0..daecee33e 100644 --- a/README.md +++ b/README.md @@ -1,27 +1,12 @@ # CUDA Samples -Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads). +Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads). ## Release Notes This section describes the release notes for the CUDA Samples on GitHub only. -### CUDA 12.4 - -- Hopper Confidential Computing Modes do not support Video samples, nor do they support host-pinned memory due to the restrictions created by CPU IOMMUs. The following Samples are affected: - - convolutionTexture - - cudaNvSci - - dct8x8 - - lineOfSight - - simpleCubemapTexture - - simpleIPC - - simpleLayeredTexture - - simplePitchLinearTexture - - simpleStream - - simpleTexture - - simpleTextureDrv - - watershedSegmentationNPP - +### CUDA 12.5 ### [older versions...](./CHANGELOG.md) @@ -29,7 +14,7 @@ This section describes the release notes for the CUDA Samples on GitHub only. ### Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. For system requirements and installation instructions of cuda toolkit, please refer to the [Linux Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-linux/), and the [Windows Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html). ### Getting the CUDA Samples diff --git a/Samples/0_Introduction/UnifiedMemoryStreams/Makefile b/Samples/0_Introduction/UnifiedMemoryStreams/Makefile index c1ea802a3..ff5ace7f4 100644 --- a/Samples/0_Introduction/UnifiedMemoryStreams/Makefile +++ b/Samples/0_Introduction/UnifiedMemoryStreams/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/UnifiedMemoryStreams/README.md b/Samples/0_Introduction/UnifiedMemoryStreams/README.md index d5980924e..f4d669abf 100644 --- a/Samples/0_Introduction/UnifiedMemoryStreams/README.md +++ b/Samples/0_Introduction/UnifiedMemoryStreams/README.md @@ -28,7 +28,7 @@ cudaStreamDestroy, cudaFree, cudaMallocManaged, cudaStreamAttachMemAsync, cudaSe ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj index d6c4e88fc..6e5348cce 100644 --- a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj +++ b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj index d5f74d958..d3ecb0e02 100644 --- a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj +++ b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj index 66895d6d7..5c45da003 100644 --- a/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj +++ b/Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/asyncAPI/Makefile b/Samples/0_Introduction/asyncAPI/Makefile index 3b9985af1..2cb94844a 100644 --- a/Samples/0_Introduction/asyncAPI/Makefile +++ b/Samples/0_Introduction/asyncAPI/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/asyncAPI/README.md b/Samples/0_Introduction/asyncAPI/README.md index 034bee6f5..0771cf135 100644 --- a/Samples/0_Introduction/asyncAPI/README.md +++ b/Samples/0_Introduction/asyncAPI/README.md @@ -27,7 +27,7 @@ cudaProfilerStop, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaMallocHost, cudaPro ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.vcxproj b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.vcxproj index 32510413a..09ead4913 100644 --- a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.vcxproj +++ b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.vcxproj b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.vcxproj index b8d2da1c6..a3885ed80 100644 --- a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.vcxproj +++ b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.vcxproj b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.vcxproj index 75f97cea0..3f28901cb 100644 --- a/Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.vcxproj +++ b/Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/c++11_cuda/Makefile b/Samples/0_Introduction/c++11_cuda/Makefile index 3defa3735..135bb299b 100644 --- a/Samples/0_Introduction/c++11_cuda/Makefile +++ b/Samples/0_Introduction/c++11_cuda/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/c++11_cuda/README.md b/Samples/0_Introduction/c++11_cuda/README.md index b5d313563..9829f7d13 100644 --- a/Samples/0_Introduction/c++11_cuda/README.md +++ b/Samples/0_Introduction/c++11_cuda/README.md @@ -30,7 +30,7 @@ cudaMalloc, cudaMemcpy, cudaMemset, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.vcxproj b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.vcxproj index de0b22e32..b1cb188a7 100644 --- a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.vcxproj +++ b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.vcxproj b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.vcxproj index 29eb0cb00..458ab9564 100644 --- a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.vcxproj +++ b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.vcxproj b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.vcxproj index 3e41e156a..5956254d5 100644 --- a/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.vcxproj +++ b/Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/clock/Makefile b/Samples/0_Introduction/clock/Makefile index 625190084..a10dabd5c 100644 --- a/Samples/0_Introduction/clock/Makefile +++ b/Samples/0_Introduction/clock/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/clock/README.md b/Samples/0_Introduction/clock/README.md index 2936534c8..d7e1a47d3 100644 --- a/Samples/0_Introduction/clock/README.md +++ b/Samples/0_Introduction/clock/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/clock/clock_vs2017.vcxproj b/Samples/0_Introduction/clock/clock_vs2017.vcxproj index adeba8de0..2665281e3 100644 --- a/Samples/0_Introduction/clock/clock_vs2017.vcxproj +++ b/Samples/0_Introduction/clock/clock_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/clock/clock_vs2019.vcxproj b/Samples/0_Introduction/clock/clock_vs2019.vcxproj index 35d1213f0..f35dff0d1 100644 --- a/Samples/0_Introduction/clock/clock_vs2019.vcxproj +++ b/Samples/0_Introduction/clock/clock_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/clock/clock_vs2022.vcxproj b/Samples/0_Introduction/clock/clock_vs2022.vcxproj index c1e1b62fe..363b2b0a5 100644 --- a/Samples/0_Introduction/clock/clock_vs2022.vcxproj +++ b/Samples/0_Introduction/clock/clock_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/clock_nvrtc/Makefile b/Samples/0_Introduction/clock_nvrtc/Makefile index 5eb485ec4..908488c59 100644 --- a/Samples/0_Introduction/clock_nvrtc/Makefile +++ b/Samples/0_Introduction/clock_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/clock_nvrtc/README.md b/Samples/0_Introduction/clock_nvrtc/README.md index 7b6dfc68c..f42090ea2 100644 --- a/Samples/0_Introduction/clock_nvrtc/README.md +++ b/Samples/0_Introduction/clock_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2017.vcxproj index def5e0c78..c0b592a72 100644 --- a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2019.vcxproj index 0eb1dbc97..9366faf9f 100644 --- a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2022.vcxproj index 52890c16c..4abb584b9 100644 --- a/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/clock_nvrtc/clock_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/concurrentKernels/Makefile b/Samples/0_Introduction/concurrentKernels/Makefile index 42cefe0d3..2034a18cf 100644 --- a/Samples/0_Introduction/concurrentKernels/Makefile +++ b/Samples/0_Introduction/concurrentKernels/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/concurrentKernels/README.md b/Samples/0_Introduction/concurrentKernels/README.md index c35e94bb7..4f4162e68 100644 --- a/Samples/0_Introduction/concurrentKernels/README.md +++ b/Samples/0_Introduction/concurrentKernels/README.md @@ -27,7 +27,7 @@ cudaStreamDestroy, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaMallocHost, cudaEv ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2017.vcxproj b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2017.vcxproj index c60451300..8f763ca7c 100644 --- a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2017.vcxproj +++ b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2019.vcxproj b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2019.vcxproj index 27ab6f83e..19c9ef896 100644 --- a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2019.vcxproj +++ b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2022.vcxproj b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2022.vcxproj index 00658c642..27f8e5fce 100644 --- a/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2022.vcxproj +++ b/Samples/0_Introduction/concurrentKernels/concurrentKernels_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/cppIntegration/Makefile b/Samples/0_Introduction/cppIntegration/Makefile index fa6a8f7ce..05856802b 100644 --- a/Samples/0_Introduction/cppIntegration/Makefile +++ b/Samples/0_Introduction/cppIntegration/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/cppIntegration/README.md b/Samples/0_Introduction/cppIntegration/README.md index a5a5fd8f3..9aad8ada0 100644 --- a/Samples/0_Introduction/cppIntegration/README.md +++ b/Samples/0_Introduction/cppIntegration/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2017.vcxproj b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2017.vcxproj index f6cddcb06..92f3da7d9 100644 --- a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2017.vcxproj +++ b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2019.vcxproj b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2019.vcxproj index 734c4170b..28b9b5625 100644 --- a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2019.vcxproj +++ b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2022.vcxproj b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2022.vcxproj index df318c2e0..27d385657 100644 --- a/Samples/0_Introduction/cppIntegration/cppIntegration_vs2022.vcxproj +++ b/Samples/0_Introduction/cppIntegration/cppIntegration_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/0_Introduction/cppOverload/Makefile b/Samples/0_Introduction/cppOverload/Makefile index 0fff096c2..c6856a44d 100644 --- a/Samples/0_Introduction/cppOverload/Makefile +++ b/Samples/0_Introduction/cppOverload/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/cppOverload/README.md b/Samples/0_Introduction/cppOverload/README.md index 87770ff9c..dafa4af6b 100644 --- a/Samples/0_Introduction/cppOverload/README.md +++ b/Samples/0_Introduction/cppOverload/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFuncSetCacheConfig, cudaFree, cudaMallocHost, cudaSetDevice, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/cppOverload/cppOverload_vs2017.vcxproj b/Samples/0_Introduction/cppOverload/cppOverload_vs2017.vcxproj index aa5d1ccb6..69f6e844f 100644 --- a/Samples/0_Introduction/cppOverload/cppOverload_vs2017.vcxproj +++ b/Samples/0_Introduction/cppOverload/cppOverload_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/cppOverload/cppOverload_vs2019.vcxproj b/Samples/0_Introduction/cppOverload/cppOverload_vs2019.vcxproj index f6b643405..afceeec78 100644 --- a/Samples/0_Introduction/cppOverload/cppOverload_vs2019.vcxproj +++ b/Samples/0_Introduction/cppOverload/cppOverload_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/cppOverload/cppOverload_vs2022.vcxproj b/Samples/0_Introduction/cppOverload/cppOverload_vs2022.vcxproj index b8dc6fed8..e7929d374 100644 --- a/Samples/0_Introduction/cppOverload/cppOverload_vs2022.vcxproj +++ b/Samples/0_Introduction/cppOverload/cppOverload_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/cudaOpenMP/Makefile b/Samples/0_Introduction/cudaOpenMP/Makefile index 6e1993f42..ac9b315f4 100644 --- a/Samples/0_Introduction/cudaOpenMP/Makefile +++ b/Samples/0_Introduction/cudaOpenMP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/cudaOpenMP/README.md b/Samples/0_Introduction/cudaOpenMP/README.md index a957032bf..63ac988c8 100644 --- a/Samples/0_Introduction/cudaOpenMP/README.md +++ b/Samples/0_Introduction/cudaOpenMP/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaGetLastError, cudaSetDevice, cudaG ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2017.vcxproj b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2017.vcxproj index 085c6771a..52eac9f4b 100644 --- a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2017.vcxproj +++ b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2019.vcxproj b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2019.vcxproj index 0f723d40f..6bd63cfdf 100644 --- a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2019.vcxproj +++ b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2022.vcxproj b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2022.vcxproj index 5ab734eaa..c9ea7301d 100644 --- a/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2022.vcxproj +++ b/Samples/0_Introduction/cudaOpenMP/cudaOpenMP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/fp16ScalarProduct/Makefile b/Samples/0_Introduction/fp16ScalarProduct/Makefile index 74b5adb66..fbe28187a 100644 --- a/Samples/0_Introduction/fp16ScalarProduct/Makefile +++ b/Samples/0_Introduction/fp16ScalarProduct/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/fp16ScalarProduct/README.md b/Samples/0_Introduction/fp16ScalarProduct/README.md index 176cb4050..b91345aa0 100644 --- a/Samples/0_Introduction/fp16ScalarProduct/README.md +++ b/Samples/0_Introduction/fp16ScalarProduct/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaMallocHost, cudaFreeHost, cudaMalloc, cudaGetDevicePro ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2017.vcxproj b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2017.vcxproj index ea629117b..2e938be41 100644 --- a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2017.vcxproj +++ b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2019.vcxproj b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2019.vcxproj index 3e4e145d3..a97f8665e 100644 --- a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2019.vcxproj +++ b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2022.vcxproj b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2022.vcxproj index 643e4ad58..741b93d34 100644 --- a/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2022.vcxproj +++ b/Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/matrixMul/Makefile b/Samples/0_Introduction/matrixMul/Makefile index eab4472ec..7f0d467f7 100644 --- a/Samples/0_Introduction/matrixMul/Makefile +++ b/Samples/0_Introduction/matrixMul/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/matrixMul/README.md b/Samples/0_Introduction/matrixMul/README.md index 74093d77e..d6c029b32 100644 --- a/Samples/0_Introduction/matrixMul/README.md +++ b/Samples/0_Introduction/matrixMul/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaProfilerStop, cudaMalloc, cudaFree, cudaMallocHos ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/matrixMul/matrixMul_vs2017.vcxproj b/Samples/0_Introduction/matrixMul/matrixMul_vs2017.vcxproj index bfd5f7beb..a31aed07d 100644 --- a/Samples/0_Introduction/matrixMul/matrixMul_vs2017.vcxproj +++ b/Samples/0_Introduction/matrixMul/matrixMul_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/matrixMul/matrixMul_vs2019.vcxproj b/Samples/0_Introduction/matrixMul/matrixMul_vs2019.vcxproj index 976abd290..63e2c1324 100644 --- a/Samples/0_Introduction/matrixMul/matrixMul_vs2019.vcxproj +++ b/Samples/0_Introduction/matrixMul/matrixMul_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/matrixMul/matrixMul_vs2022.vcxproj b/Samples/0_Introduction/matrixMul/matrixMul_vs2022.vcxproj index d8630eb9a..290236ec1 100644 --- a/Samples/0_Introduction/matrixMul/matrixMul_vs2022.vcxproj +++ b/Samples/0_Introduction/matrixMul/matrixMul_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDrv/Makefile b/Samples/0_Introduction/matrixMulDrv/Makefile index f9ad912cd..520b4a377 100644 --- a/Samples/0_Introduction/matrixMulDrv/Makefile +++ b/Samples/0_Introduction/matrixMulDrv/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/matrixMulDrv/README.md b/Samples/0_Introduction/matrixMulDrv/README.md index 728972742..0b141e1ac 100644 --- a/Samples/0_Introduction/matrixMulDrv/README.md +++ b/Samples/0_Introduction/matrixMulDrv/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuDeviceGetName, cuDeviceTotalMem, c ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2017.vcxproj b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2017.vcxproj index 7fdbe3f38..fae4fa68d 100644 --- a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2017.vcxproj +++ b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2019.vcxproj b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2019.vcxproj index 06e39510f..4a6d0e744 100644 --- a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2019.vcxproj +++ b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2022.vcxproj b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2022.vcxproj index 0c979db55..61a208201 100644 --- a/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2022.vcxproj +++ b/Samples/0_Introduction/matrixMulDrv/matrixMulDrv_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDynlinkJIT/Makefile b/Samples/0_Introduction/matrixMulDynlinkJIT/Makefile index 1b78b2998..9f81b76f5 100644 --- a/Samples/0_Introduction/matrixMulDynlinkJIT/Makefile +++ b/Samples/0_Introduction/matrixMulDynlinkJIT/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/matrixMulDynlinkJIT/README.md b/Samples/0_Introduction/matrixMulDynlinkJIT/README.md index fddb2c74d..9428da914 100644 --- a/Samples/0_Introduction/matrixMulDynlinkJIT/README.md +++ b/Samples/0_Introduction/matrixMulDynlinkJIT/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuDeviceGetName, cuParamSeti, cuModuleLoadDataEx, cuModuleGetFunct ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2017.vcxproj b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2017.vcxproj index ecf61f954..1ef02556b 100644 --- a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2017.vcxproj +++ b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -116,6 +116,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2019.vcxproj b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2019.vcxproj index b2744de03..0bc0d3cc6 100644 --- a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2019.vcxproj +++ b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2022.vcxproj b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2022.vcxproj index 9f81aa72a..b1104d61e 100644 --- a/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2022.vcxproj +++ b/Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/0_Introduction/matrixMul_nvrtc/Makefile b/Samples/0_Introduction/matrixMul_nvrtc/Makefile index 5750def29..d81d15fa0 100644 --- a/Samples/0_Introduction/matrixMul_nvrtc/Makefile +++ b/Samples/0_Introduction/matrixMul_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/matrixMul_nvrtc/README.md b/Samples/0_Introduction/matrixMul_nvrtc/README.md index cc60f1a18..00dc0ae72 100644 --- a/Samples/0_Introduction/matrixMul_nvrtc/README.md +++ b/Samples/0_Introduction/matrixMul_nvrtc/README.md @@ -30,7 +30,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuCtxSynchronize, cuMemAlloc, cuMemF ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2017.vcxproj index 697f9cce9..c2300ec3a 100644 --- a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -113,6 +113,6 @@ xcopy /y /e /s "$(CudaToolkitDir)include\cooperative_groups" .\cooperative_group - + diff --git a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2019.vcxproj index 3cbf8d6cd..2a3d15b1f 100644 --- a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ xcopy /y /e /s "$(CudaToolkitDir)include\cooperative_groups" .\cooperative_group - + diff --git a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2022.vcxproj index 43210accd..c78926f3a 100644 --- a/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/matrixMul_nvrtc/matrixMul_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ xcopy /y /e /s "$(CudaToolkitDir)include\cooperative_groups" .\cooperative_group - + diff --git a/Samples/0_Introduction/mergeSort/Makefile b/Samples/0_Introduction/mergeSort/Makefile index 33fdba186..b0f1ed0c3 100644 --- a/Samples/0_Introduction/mergeSort/Makefile +++ b/Samples/0_Introduction/mergeSort/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/mergeSort/README.md b/Samples/0_Introduction/mergeSort/README.md index 916ff4a37..0865f1aef 100644 --- a/Samples/0_Introduction/mergeSort/README.md +++ b/Samples/0_Introduction/mergeSort/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/mergeSort/mergeSort_vs2017.vcxproj b/Samples/0_Introduction/mergeSort/mergeSort_vs2017.vcxproj index 7aabd7c6f..2e88e6b0a 100644 --- a/Samples/0_Introduction/mergeSort/mergeSort_vs2017.vcxproj +++ b/Samples/0_Introduction/mergeSort/mergeSort_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/0_Introduction/mergeSort/mergeSort_vs2019.vcxproj b/Samples/0_Introduction/mergeSort/mergeSort_vs2019.vcxproj index fda7eb264..7a3664adc 100644 --- a/Samples/0_Introduction/mergeSort/mergeSort_vs2019.vcxproj +++ b/Samples/0_Introduction/mergeSort/mergeSort_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/mergeSort/mergeSort_vs2022.vcxproj b/Samples/0_Introduction/mergeSort/mergeSort_vs2022.vcxproj index 6c3223ddb..9788c718e 100644 --- a/Samples/0_Introduction/mergeSort/mergeSort_vs2022.vcxproj +++ b/Samples/0_Introduction/mergeSort/mergeSort_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleAWBarrier/Makefile b/Samples/0_Introduction/simpleAWBarrier/Makefile index e0b09e0bc..ecc1a81a7 100644 --- a/Samples/0_Introduction/simpleAWBarrier/Makefile +++ b/Samples/0_Introduction/simpleAWBarrier/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAWBarrier/README.md b/Samples/0_Introduction/simpleAWBarrier/README.md index 6ee52f1d1..699b2d05c 100644 --- a/Samples/0_Introduction/simpleAWBarrier/README.md +++ b/Samples/0_Introduction/simpleAWBarrier/README.md @@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaFree, cudaDeviceGetAttribute, cudaMallocHost, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2017.vcxproj b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2017.vcxproj index 04891e79a..bb0d370e7 100644 --- a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2019.vcxproj b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2019.vcxproj index 285b84106..dbee7ab47 100644 --- a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2022.vcxproj b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2022.vcxproj index 58daef61d..46890ff8a 100644 --- a/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAWBarrier/simpleAWBarrier_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert/Makefile b/Samples/0_Introduction/simpleAssert/Makefile index 970513829..c5bda3571 100644 --- a/Samples/0_Introduction/simpleAssert/Makefile +++ b/Samples/0_Introduction/simpleAssert/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAssert/README.md b/Samples/0_Introduction/simpleAssert/README.md index f5199bd92..9db260694 100644 --- a/Samples/0_Introduction/simpleAssert/README.md +++ b/Samples/0_Introduction/simpleAssert/README.md @@ -27,7 +27,7 @@ cudaDeviceSynchronize, cudaGetErrorString ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2017.vcxproj b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2017.vcxproj index 32bc9ed59..b1c2d63a7 100644 --- a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2019.vcxproj b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2019.vcxproj index ce25e9c87..030afce1a 100644 --- a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2022.vcxproj b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2022.vcxproj index 7841bf679..a8b9f9067 100644 --- a/Samples/0_Introduction/simpleAssert/simpleAssert_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAssert/simpleAssert_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert_nvrtc/Makefile b/Samples/0_Introduction/simpleAssert_nvrtc/Makefile index cf55bdc2d..a8a096974 100644 --- a/Samples/0_Introduction/simpleAssert_nvrtc/Makefile +++ b/Samples/0_Introduction/simpleAssert_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAssert_nvrtc/README.md b/Samples/0_Introduction/simpleAssert_nvrtc/README.md index 587d2b07a..5a633d762 100644 --- a/Samples/0_Introduction/simpleAssert_nvrtc/README.md +++ b/Samples/0_Introduction/simpleAssert_nvrtc/README.md @@ -30,7 +30,7 @@ cuModuleGetFunction, cuLaunchKernel, cuCtxSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2017.vcxproj index cdc057ada..d9e8ef6c8 100644 --- a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2019.vcxproj index d28b3e125..e723140e6 100644 --- a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2022.vcxproj index 351efb75e..998b46bd9 100644 --- a/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAssert_nvrtc/simpleAssert_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics/Makefile b/Samples/0_Introduction/simpleAtomicIntrinsics/Makefile index 9de4a6a95..31be5b085 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics/Makefile +++ b/Samples/0_Introduction/simpleAtomicIntrinsics/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics/README.md b/Samples/0_Introduction/simpleAtomicIntrinsics/README.md index 99177ff46..f584d3de0 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics/README.md +++ b/Samples/0_Introduction/simpleAtomicIntrinsics/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaFree, cudaMallocHost, cudaFreeHost, cudaStreamSyn ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2017.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2017.vcxproj index 2d9027f66..2f316522c 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2019.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2019.vcxproj index 063c5bdcb..c9812b1d6 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2022.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2022.vcxproj index 3ec20b8f9..2a511d706 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics/simpleAtomicIntrinsics_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/Makefile b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/Makefile index 73ada20b8..f70e2d3c3 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/Makefile +++ b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/README.md b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/README.md index b8829eb40..753c5c9d7 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/README.md +++ b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2017.vcxproj index 21cb7fcef..257610544 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2019.vcxproj index 5dbd093ce..5f7cabf2f 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2022.vcxproj index 323163a07..9bcdf7fc1 100644 --- a/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAtomicIntrinsics_nvrtc/simpleAtomicIntrinsics_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleAttributes/Makefile b/Samples/0_Introduction/simpleAttributes/Makefile index 5e2459ce1..1e6a1a488 100644 --- a/Samples/0_Introduction/simpleAttributes/Makefile +++ b/Samples/0_Introduction/simpleAttributes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleAttributes/README.md b/Samples/0_Introduction/simpleAttributes/README.md index 082d69335..cba3752e4 100644 --- a/Samples/0_Introduction/simpleAttributes/README.md +++ b/Samples/0_Introduction/simpleAttributes/README.md @@ -27,7 +27,7 @@ cudaFree, cudaMallocHost, cudaFreeHost, cudaStreamSynchronize, cudaStreamSetAttr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2017.vcxproj b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2017.vcxproj index 731c0fdc7..838513f54 100644 --- a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2019.vcxproj b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2019.vcxproj index 5f0e908e4..71673c72a 100644 --- a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2022.vcxproj b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2022.vcxproj index 27a963331..2609e1359 100644 --- a/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleAttributes/simpleAttributes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleCUDA2GL/Makefile b/Samples/0_Introduction/simpleCUDA2GL/Makefile index 14de6141b..ef6d02281 100644 --- a/Samples/0_Introduction/simpleCUDA2GL/Makefile +++ b/Samples/0_Introduction/simpleCUDA2GL/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleCUDA2GL/README.md b/Samples/0_Introduction/simpleCUDA2GL/README.md index bbf274770..6c17427f5 100644 --- a/Samples/0_Introduction/simpleCUDA2GL/README.md +++ b/Samples/0_Introduction/simpleCUDA2GL/README.md @@ -30,7 +30,7 @@ cudaHostAlloc, cudaGraphicsUnmapResources, cudaMalloc, cudaFree, cudaGraphicsRes ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2017.vcxproj b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2017.vcxproj index 651d829a4..d4f9e60d1 100644 --- a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2019.vcxproj b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2019.vcxproj index b4ee9c5ac..1e349c6ca 100644 --- a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2022.vcxproj b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2022.vcxproj index 75c0b7363..63a46adf9 100644 --- a/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/0_Introduction/simpleCallback/Makefile b/Samples/0_Introduction/simpleCallback/Makefile index f8a661130..7e64be2b7 100644 --- a/Samples/0_Introduction/simpleCallback/Makefile +++ b/Samples/0_Introduction/simpleCallback/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleCallback/README.md b/Samples/0_Introduction/simpleCallback/README.md index 3f7bdddcf..2dd97e18a 100644 --- a/Samples/0_Introduction/simpleCallback/README.md +++ b/Samples/0_Introduction/simpleCallback/README.md @@ -27,7 +27,7 @@ cudaHostAlloc, cudaStreamDestroy, cudaFree, cudaSetDevice, cudaGetDeviceCount, c ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2017.vcxproj b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2017.vcxproj index e34a6867c..6542b9e7c 100644 --- a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2019.vcxproj b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2019.vcxproj index 9f2743ad7..8b9087fe2 100644 --- a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2022.vcxproj b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2022.vcxproj index dfc3e5f4e..cdb95825d 100644 --- a/Samples/0_Introduction/simpleCallback/simpleCallback_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleCallback/simpleCallback_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleCooperativeGroups/Makefile b/Samples/0_Introduction/simpleCooperativeGroups/Makefile index baa1349ea..68c718fb0 100644 --- a/Samples/0_Introduction/simpleCooperativeGroups/Makefile +++ b/Samples/0_Introduction/simpleCooperativeGroups/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleCooperativeGroups/README.md b/Samples/0_Introduction/simpleCooperativeGroups/README.md index e39b39e55..ebb1a9a59 100644 --- a/Samples/0_Introduction/simpleCooperativeGroups/README.md +++ b/Samples/0_Introduction/simpleCooperativeGroups/README.md @@ -27,7 +27,7 @@ cudaDeviceSynchronize, cudaGetErrorString ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2017.vcxproj b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2017.vcxproj index afe9cacf5..31385b13f 100644 --- a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2019.vcxproj b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2019.vcxproj index 261d57c75..7611542c6 100644 --- a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2022.vcxproj b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2022.vcxproj index 570f71461..01a13b676 100644 --- a/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleCooperativeGroups/simpleCooperativeGroups_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleCubemapTexture/Makefile b/Samples/0_Introduction/simpleCubemapTexture/Makefile index 8ff8ef721..6f6a37bf6 100644 --- a/Samples/0_Introduction/simpleCubemapTexture/Makefile +++ b/Samples/0_Introduction/simpleCubemapTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleCubemapTexture/README.md b/Samples/0_Introduction/simpleCubemapTexture/README.md index 775b444dc..87e4a5cba 100644 --- a/Samples/0_Introduction/simpleCubemapTexture/README.md +++ b/Samples/0_Introduction/simpleCubemapTexture/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaCreateChannelDesc, cudaFreeArray, cudaFree, cudaPitchedPtr, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2017.vcxproj b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2017.vcxproj index 68588c2d7..594ad5c88 100644 --- a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2019.vcxproj b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2019.vcxproj index 33876489d..eeab65c0c 100644 --- a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2022.vcxproj b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2022.vcxproj index 36e1d8400..fd5a497c2 100644 --- a/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleCubemapTexture/simpleCubemapTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleDrvRuntime/Makefile b/Samples/0_Introduction/simpleDrvRuntime/Makefile index e16068373..700b865ee 100644 --- a/Samples/0_Introduction/simpleDrvRuntime/Makefile +++ b/Samples/0_Introduction/simpleDrvRuntime/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleDrvRuntime/README.md b/Samples/0_Introduction/simpleDrvRuntime/README.md index 570629a07..52a2ed1ef 100644 --- a/Samples/0_Introduction/simpleDrvRuntime/README.md +++ b/Samples/0_Introduction/simpleDrvRuntime/README.md @@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaFree, cudaMallocHost, cudaFreeHost, cudaStreamSyn ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2017.vcxproj b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2017.vcxproj index 9bee33370..bafc145d5 100644 --- a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2019.vcxproj b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2019.vcxproj index ad82ef762..ee2639bc5 100644 --- a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2022.vcxproj b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2022.vcxproj index 31c723240..ca0dcbf70 100644 --- a/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleDrvRuntime/simpleDrvRuntime_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleHyperQ/Makefile b/Samples/0_Introduction/simpleHyperQ/Makefile index 14b34ace6..ef839105f 100644 --- a/Samples/0_Introduction/simpleHyperQ/Makefile +++ b/Samples/0_Introduction/simpleHyperQ/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleHyperQ/README.md b/Samples/0_Introduction/simpleHyperQ/README.md index 0473f04b0..fcbe2e980 100644 --- a/Samples/0_Introduction/simpleHyperQ/README.md +++ b/Samples/0_Introduction/simpleHyperQ/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaStreamDestroy, cudaMalloc, cudaFree, cudaMallocHost, cudaEventSy ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2017.vcxproj b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2017.vcxproj index d2069877d..d01592cee 100644 --- a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2019.vcxproj b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2019.vcxproj index 5a122c714..7d0be42c5 100644 --- a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2022.vcxproj b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2022.vcxproj index ce864e35e..f70085be3 100644 --- a/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleHyperQ/simpleHyperQ_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleIPC/Makefile b/Samples/0_Introduction/simpleIPC/Makefile index a4d1b8857..a860c59fa 100644 --- a/Samples/0_Introduction/simpleIPC/Makefile +++ b/Samples/0_Introduction/simpleIPC/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleIPC/README.md b/Samples/0_Introduction/simpleIPC/README.md index 0bd5381ed..bd80ca7e9 100644 --- a/Samples/0_Introduction/simpleIPC/README.md +++ b/Samples/0_Introduction/simpleIPC/README.md @@ -30,7 +30,7 @@ cudaSetDevice, cudaIpcCloseMemHandle, cudaEventDestroy, cudaGetDeviceCount, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2017.vcxproj b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2017.vcxproj index 26b2f325b..53cbc7645 100644 --- a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2019.vcxproj b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2019.vcxproj index b9285fdfc..d71adcb26 100644 --- a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2022.vcxproj b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2022.vcxproj index 785644006..3660d6995 100644 --- a/Samples/0_Introduction/simpleIPC/simpleIPC_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleIPC/simpleIPC_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleLayeredTexture/Makefile b/Samples/0_Introduction/simpleLayeredTexture/Makefile index b1a0b9dd7..03781a5ae 100644 --- a/Samples/0_Introduction/simpleLayeredTexture/Makefile +++ b/Samples/0_Introduction/simpleLayeredTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleLayeredTexture/README.md b/Samples/0_Introduction/simpleLayeredTexture/README.md index 521e0e1c1..f13fae266 100644 --- a/Samples/0_Introduction/simpleLayeredTexture/README.md +++ b/Samples/0_Introduction/simpleLayeredTexture/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaCreateChannelDesc, cudaFreeArray, cudaFree, cudaPitchedPtr, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2017.vcxproj b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2017.vcxproj index 229f4be96..4e44f6221 100644 --- a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2019.vcxproj b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2019.vcxproj index 503dde2d7..65c2c9471 100644 --- a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2022.vcxproj b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2022.vcxproj index c951db568..b78741594 100644 --- a/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleLayeredTexture/simpleLayeredTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleMPI/Makefile b/Samples/0_Introduction/simpleMPI/Makefile index 3cd4f240b..86eda321a 100644 --- a/Samples/0_Introduction/simpleMPI/Makefile +++ b/Samples/0_Introduction/simpleMPI/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -277,15 +290,9 @@ ifeq ($(TARGET_ARCH),armv7l) SAMPLE_ENABLED := 0 endif -# This sample is not supported on aarch64 -ifeq ($(TARGET_ARCH),aarch64) - $(info >>> WARNING - simpleMPI is not supported on aarch64 - waiving sample <<<) - SAMPLE_ENABLED := 0 -endif - -# This sample is not supported on sbsa -ifeq ($(TARGET_ARCH),sbsa) - $(info >>> WARNING - simpleMPI is not supported on sbsa - waiving sample <<<) +# This sample is not supported on QNX +ifeq ($(TARGET_OS),qnx) + $(info >>> WARNING - simpleMPI is not supported on QNX - waiving sample <<<) SAMPLE_ENABLED := 0 endif diff --git a/Samples/0_Introduction/simpleMPI/README.md b/Samples/0_Introduction/simpleMPI/README.md index de7f9a740..1a8a152ae 100644 --- a/Samples/0_Introduction/simpleMPI/README.md +++ b/Samples/0_Introduction/simpleMPI/README.md @@ -18,7 +18,7 @@ Linux, Windows ## Supported CPU Architecture -x86_64, ppc64le +x86_64, ppc64le, aarch64 ## CUDA APIs involved @@ -30,7 +30,7 @@ cudaMalloc, cudaGetLastError, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run @@ -52,9 +52,9 @@ $ cd $ make ``` The samples makefiles can take advantage of certain options: -* **TARGET_ARCH=** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le. +* **TARGET_ARCH=** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le, aarch64. By default, TARGET_ARCH is set to HOST_ARCH. On a x86_64 machine, not setting TARGET_ARCH is the equivalent of setting TARGET_ARCH=x86_64.
-`$ make TARGET_ARCH=x86_64`
`$ make TARGET_ARCH=ppc64le`
+`$ make TARGET_ARCH=x86_64`
`$ make TARGET_ARCH=ppc64le`
`$ make TARGET_ARCH=aarch64`
See [here](http://docs.nvidia.com/cuda/cuda-samples/index.html#cross-samples) for more details. * **dbg=1** - build with debug symbols ``` diff --git a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2017.vcxproj b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2017.vcxproj index 478d99f1f..f54002260 100644 --- a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2019.vcxproj b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2019.vcxproj index f65e9ff40..609623d22 100644 --- a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2022.vcxproj b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2022.vcxproj index 2de0bb629..a3fdbe3ad 100644 --- a/Samples/0_Introduction/simpleMPI/simpleMPI_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleMPI/simpleMPI_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiCopy/Makefile b/Samples/0_Introduction/simpleMultiCopy/Makefile index 2db215868..69a8d6066 100644 --- a/Samples/0_Introduction/simpleMultiCopy/Makefile +++ b/Samples/0_Introduction/simpleMultiCopy/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleMultiCopy/README.md b/Samples/0_Introduction/simpleMultiCopy/README.md index 83017ed93..d531a50ce 100644 --- a/Samples/0_Introduction/simpleMultiCopy/README.md +++ b/Samples/0_Introduction/simpleMultiCopy/README.md @@ -27,7 +27,7 @@ cudaHostAlloc, cudaStreamDestroy, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaSet ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2017.vcxproj b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2017.vcxproj index da5010b67..421cd5869 100644 --- a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2019.vcxproj b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2019.vcxproj index 3822a9966..ca10e64f6 100644 --- a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2022.vcxproj b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2022.vcxproj index b7911f33f..47f9f6ecd 100644 --- a/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleMultiCopy/simpleMultiCopy_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiGPU/Makefile b/Samples/0_Introduction/simpleMultiGPU/Makefile index 02a154c5b..3ede2ba05 100644 --- a/Samples/0_Introduction/simpleMultiGPU/Makefile +++ b/Samples/0_Introduction/simpleMultiGPU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleMultiGPU/README.md b/Samples/0_Introduction/simpleMultiGPU/README.md index 5d4e51531..3fc5e0b30 100644 --- a/Samples/0_Introduction/simpleMultiGPU/README.md +++ b/Samples/0_Introduction/simpleMultiGPU/README.md @@ -27,7 +27,7 @@ cudaStreamDestroy, cudaFree, cudaMallocHost, cudaSetDevice, cudaFreeHost, cudaSt ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2017.vcxproj b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2017.vcxproj index 04dbe5b02..451fff957 100644 --- a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2019.vcxproj b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2019.vcxproj index b3c91b602..74770e5fa 100644 --- a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2022.vcxproj b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2022.vcxproj index 25abe00c4..b1a4cb76f 100644 --- a/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleMultiGPU/simpleMultiGPU_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleOccupancy/Makefile b/Samples/0_Introduction/simpleOccupancy/Makefile index a0542a700..9a593fecb 100644 --- a/Samples/0_Introduction/simpleOccupancy/Makefile +++ b/Samples/0_Introduction/simpleOccupancy/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleOccupancy/README.md b/Samples/0_Introduction/simpleOccupancy/README.md index 792bbba66..2f327a6eb 100644 --- a/Samples/0_Introduction/simpleOccupancy/README.md +++ b/Samples/0_Introduction/simpleOccupancy/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaEventRecord, cudaGetDevice, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2017.vcxproj b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2017.vcxproj index e994ee587..10d6e40b2 100644 --- a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2019.vcxproj b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2019.vcxproj index 3e63206bf..32e8e61f6 100644 --- a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2022.vcxproj b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2022.vcxproj index 09ddb2442..c80c61473 100644 --- a/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleOccupancy/simpleOccupancy_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleP2P/Makefile b/Samples/0_Introduction/simpleP2P/Makefile index f2fdab24f..7e420c95a 100644 --- a/Samples/0_Introduction/simpleP2P/Makefile +++ b/Samples/0_Introduction/simpleP2P/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleP2P/README.md b/Samples/0_Introduction/simpleP2P/README.md index 8c6f4f410..15179b35f 100644 --- a/Samples/0_Introduction/simpleP2P/README.md +++ b/Samples/0_Introduction/simpleP2P/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaMalloc, cudaFree, cudaMallocHost, cudaEventCreateWithFlags, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2017.vcxproj b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2017.vcxproj index ac3c8d0ca..5c8dbaea3 100644 --- a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2019.vcxproj b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2019.vcxproj index b015cb9d2..77e81b2be 100644 --- a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2022.vcxproj b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2022.vcxproj index add2eb24a..97c851af6 100644 --- a/Samples/0_Introduction/simpleP2P/simpleP2P_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleP2P/simpleP2P_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simplePitchLinearTexture/Makefile b/Samples/0_Introduction/simplePitchLinearTexture/Makefile index 956ee1eeb..fece95a5a 100644 --- a/Samples/0_Introduction/simplePitchLinearTexture/Makefile +++ b/Samples/0_Introduction/simplePitchLinearTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simplePitchLinearTexture/README.md b/Samples/0_Introduction/simplePitchLinearTexture/README.md index 30aff62bf..921f38919 100644 --- a/Samples/0_Introduction/simplePitchLinearTexture/README.md +++ b/Samples/0_Introduction/simplePitchLinearTexture/README.md @@ -27,7 +27,7 @@ cudaMallocArray, cudaFreeArray, cudaFree, cudaMallocPitch, cudaDestroyTextureObj ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2017.vcxproj b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2017.vcxproj index ac8b3493c..d776730d5 100644 --- a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2017.vcxproj +++ b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2019.vcxproj b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2019.vcxproj index 543b83d5a..55786b7b8 100644 --- a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2019.vcxproj +++ b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2022.vcxproj b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2022.vcxproj index 7ca473b0f..82797c879 100644 --- a/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2022.vcxproj +++ b/Samples/0_Introduction/simplePitchLinearTexture/simplePitchLinearTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simplePrintf/Makefile b/Samples/0_Introduction/simplePrintf/Makefile index 45f43aa68..ff66e2de9 100644 --- a/Samples/0_Introduction/simplePrintf/Makefile +++ b/Samples/0_Introduction/simplePrintf/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simplePrintf/README.md b/Samples/0_Introduction/simplePrintf/README.md index db910ee09..69dba7a29 100644 --- a/Samples/0_Introduction/simplePrintf/README.md +++ b/Samples/0_Introduction/simplePrintf/README.md @@ -27,7 +27,7 @@ cudaGetDeviceProperties, cudaDeviceSynchronize, cudaGetDevice ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2017.vcxproj b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2017.vcxproj index 76824ecfa..7ec3664dc 100644 --- a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2017.vcxproj +++ b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2019.vcxproj b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2019.vcxproj index 3105be185..edcc68af7 100644 --- a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2019.vcxproj +++ b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2022.vcxproj b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2022.vcxproj index 4a26d560b..8e9a45dd8 100644 --- a/Samples/0_Introduction/simplePrintf/simplePrintf_vs2022.vcxproj +++ b/Samples/0_Introduction/simplePrintf/simplePrintf_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleSeparateCompilation/Makefile b/Samples/0_Introduction/simpleSeparateCompilation/Makefile index cca7ac695..7e16c0c07 100644 --- a/Samples/0_Introduction/simpleSeparateCompilation/Makefile +++ b/Samples/0_Introduction/simpleSeparateCompilation/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleSeparateCompilation/README.md b/Samples/0_Introduction/simpleSeparateCompilation/README.md index 78f15355e..0fc290623 100644 --- a/Samples/0_Introduction/simpleSeparateCompilation/README.md +++ b/Samples/0_Introduction/simpleSeparateCompilation/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaMemcpyFromSymbol, cudaFree, cudaGetLastError, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2017.vcxproj b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2017.vcxproj index 8bd58918f..45d5b9397 100644 --- a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2019.vcxproj b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2019.vcxproj index 5fd526290..8870c6b6a 100644 --- a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2022.vcxproj b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2022.vcxproj index 97ed81211..1300538f7 100644 --- a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/0_Introduction/simpleStreams/Makefile b/Samples/0_Introduction/simpleStreams/Makefile index f59124a2b..1972fe54f 100644 --- a/Samples/0_Introduction/simpleStreams/Makefile +++ b/Samples/0_Introduction/simpleStreams/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleStreams/README.md b/Samples/0_Introduction/simpleStreams/README.md index 108d9f9e3..439f733a1 100644 --- a/Samples/0_Introduction/simpleStreams/README.md +++ b/Samples/0_Introduction/simpleStreams/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaSetDeviceFlags, cudaSetDevice, cudaEventDestroy, cudaStreamCreat ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2017.vcxproj b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2017.vcxproj index cc497a190..97b2ca7ae 100644 --- a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2019.vcxproj b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2019.vcxproj index 2d5d9aadd..3fb865a5d 100644 --- a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2022.vcxproj b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2022.vcxproj index 972e6b4e7..3c7ecd2fd 100644 --- a/Samples/0_Introduction/simpleStreams/simpleStreams_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleStreams/simpleStreams_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleSurfaceWrite/Makefile b/Samples/0_Introduction/simpleSurfaceWrite/Makefile index 89f6dfc63..fdc32d5fb 100644 --- a/Samples/0_Introduction/simpleSurfaceWrite/Makefile +++ b/Samples/0_Introduction/simpleSurfaceWrite/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleSurfaceWrite/README.md b/Samples/0_Introduction/simpleSurfaceWrite/README.md index d1396a437..a61c1d2ec 100644 --- a/Samples/0_Introduction/simpleSurfaceWrite/README.md +++ b/Samples/0_Introduction/simpleSurfaceWrite/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaCreateChannelDesc, cudaMallocArray, cudaFreeArray, cudaFree, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2017.vcxproj b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2017.vcxproj index 6142e3cd0..c324440c8 100644 --- a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2019.vcxproj b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2019.vcxproj index b5973a72f..2e5bea8a5 100644 --- a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2022.vcxproj b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2022.vcxproj index 2cd546582..c80a558e1 100644 --- a/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleSurfaceWrite/simpleSurfaceWrite_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates/Makefile b/Samples/0_Introduction/simpleTemplates/Makefile index 410c37deb..db7c590f8 100644 --- a/Samples/0_Introduction/simpleTemplates/Makefile +++ b/Samples/0_Introduction/simpleTemplates/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleTemplates/README.md b/Samples/0_Introduction/simpleTemplates/README.md index 07fbba699..5ab565a0b 100644 --- a/Samples/0_Introduction/simpleTemplates/README.md +++ b/Samples/0_Introduction/simpleTemplates/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaGetDeviceProperties, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2017.vcxproj b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2017.vcxproj index 996c9cbd7..ec166d6f3 100644 --- a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2019.vcxproj b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2019.vcxproj index 1afdd93f7..7a43b57d9 100644 --- a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2022.vcxproj b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2022.vcxproj index 663374272..c0d0da5f7 100644 --- a/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleTemplates/simpleTemplates_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates_nvrtc/Makefile b/Samples/0_Introduction/simpleTemplates_nvrtc/Makefile index 78ab245c2..24a5bd91b 100644 --- a/Samples/0_Introduction/simpleTemplates_nvrtc/Makefile +++ b/Samples/0_Introduction/simpleTemplates_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleTemplates_nvrtc/README.md b/Samples/0_Introduction/simpleTemplates_nvrtc/README.md index d0c83eecc..09f983620 100644 --- a/Samples/0_Introduction/simpleTemplates_nvrtc/README.md +++ b/Samples/0_Introduction/simpleTemplates_nvrtc/README.md @@ -30,7 +30,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuCtxSynchronize, cuMemAlloc, cuMemF ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2017.vcxproj index 24b7f31bc..6e0878999 100644 --- a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2019.vcxproj index acd83544f..3f04d3458 100644 --- a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2022.vcxproj index a9adfad13..d39331449 100644 --- a/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleTemplates_nvrtc/simpleTemplates_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture/Makefile b/Samples/0_Introduction/simpleTexture/Makefile index bc6e97f5e..f6e4cde67 100644 --- a/Samples/0_Introduction/simpleTexture/Makefile +++ b/Samples/0_Introduction/simpleTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleTexture/README.md b/Samples/0_Introduction/simpleTexture/README.md index 901e3b15a..fdca8911a 100644 --- a/Samples/0_Introduction/simpleTexture/README.md +++ b/Samples/0_Introduction/simpleTexture/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaCreateChannelDesc, cudaMallocArray, cudaFreeArray, cudaFree, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2017.vcxproj b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2017.vcxproj index f4140e6a8..676a5f502 100644 --- a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2019.vcxproj b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2019.vcxproj index 9824a29e8..9f154c4e2 100644 --- a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2022.vcxproj b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2022.vcxproj index 4aacd5ca8..d74f28655 100644 --- a/Samples/0_Introduction/simpleTexture/simpleTexture_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleTexture/simpleTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture3D/Makefile b/Samples/0_Introduction/simpleTexture3D/Makefile index 93124c222..fd8987cc5 100644 --- a/Samples/0_Introduction/simpleTexture3D/Makefile +++ b/Samples/0_Introduction/simpleTexture3D/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleTexture3D/README.md b/Samples/0_Introduction/simpleTexture3D/README.md index 5aaa8d7d8..48f9961c2 100644 --- a/Samples/0_Introduction/simpleTexture3D/README.md +++ b/Samples/0_Introduction/simpleTexture3D/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFreeArray, cudaFree, cudaPitchedPtr, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2017.vcxproj b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2017.vcxproj index e3412d29c..e1efe32b3 100644 --- a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2019.vcxproj b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2019.vcxproj index 6531811ae..a928284cc 100644 --- a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2022.vcxproj b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2022.vcxproj index 0e40b7686..cfd623aa2 100644 --- a/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleTexture3D/simpleTexture3D_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/0_Introduction/simpleTextureDrv/Makefile b/Samples/0_Introduction/simpleTextureDrv/Makefile index d57e1596d..b11d18476 100644 --- a/Samples/0_Introduction/simpleTextureDrv/Makefile +++ b/Samples/0_Introduction/simpleTextureDrv/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleTextureDrv/README.md b/Samples/0_Introduction/simpleTextureDrv/README.md index e918d88ca..461d408c6 100644 --- a/Samples/0_Introduction/simpleTextureDrv/README.md +++ b/Samples/0_Introduction/simpleTextureDrv/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuModuleLoadData, cuDeviceGetName, cuDeviceGetAttr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2017.vcxproj b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2017.vcxproj index b1c2fd0e7..04e3ac728 100644 --- a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2019.vcxproj b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2019.vcxproj index de277452e..6652d2a63 100644 --- a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2022.vcxproj b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2022.vcxproj index 44d37eae3..cb683fd34 100644 --- a/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics/Makefile b/Samples/0_Introduction/simpleVoteIntrinsics/Makefile index 8e30c98ba..4e338815b 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics/Makefile +++ b/Samples/0_Introduction/simpleVoteIntrinsics/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleVoteIntrinsics/README.md b/Samples/0_Introduction/simpleVoteIntrinsics/README.md index 81df332fe..7558f2596 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics/README.md +++ b/Samples/0_Introduction/simpleVoteIntrinsics/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2017.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2017.vcxproj index edc305607..0d9aa253c 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2019.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2019.vcxproj index 64e031c22..f1074a431 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2022.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2022.vcxproj index dc5fec0ba..0ce06db4d 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics/simpleVoteIntrinsics_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/Makefile b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/Makefile index 538ddbca1..4999d92b8 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/Makefile +++ b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/README.md b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/README.md index 55bcc1c78..a3487a987 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/README.md +++ b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/README.md @@ -30,7 +30,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuCtxSynchronize, cuMemAlloc, cuMemF ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2017.vcxproj index 9e4b7391c..24a1590bd 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2019.vcxproj index fb4d7730e..e0ab48c8a 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2022.vcxproj index e638c1767..c71c942cc 100644 --- a/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleVoteIntrinsics_nvrtc/simpleVoteIntrinsics_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleZeroCopy/Makefile b/Samples/0_Introduction/simpleZeroCopy/Makefile index 79cb6a85e..000824947 100644 --- a/Samples/0_Introduction/simpleZeroCopy/Makefile +++ b/Samples/0_Introduction/simpleZeroCopy/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/simpleZeroCopy/README.md b/Samples/0_Introduction/simpleZeroCopy/README.md index 08e02fa76..faf5b4079 100644 --- a/Samples/0_Introduction/simpleZeroCopy/README.md +++ b/Samples/0_Introduction/simpleZeroCopy/README.md @@ -27,7 +27,7 @@ cudaHostAlloc, cudaSetDeviceFlags, cudaHostRegister, cudaSetDevice, cudaGetDevic ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2017.vcxproj b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2017.vcxproj index dc529e966..5f085b826 100644 --- a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2017.vcxproj +++ b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2019.vcxproj b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2019.vcxproj index 3f89ba081..ad045a0fc 100644 --- a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2019.vcxproj +++ b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2022.vcxproj b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2022.vcxproj index 1631f981c..128d6fb24 100644 --- a/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2022.vcxproj +++ b/Samples/0_Introduction/simpleZeroCopy/simpleZeroCopy_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/systemWideAtomics/Makefile b/Samples/0_Introduction/systemWideAtomics/Makefile index ce22b7960..13efbdbea 100644 --- a/Samples/0_Introduction/systemWideAtomics/Makefile +++ b/Samples/0_Introduction/systemWideAtomics/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/systemWideAtomics/README.md b/Samples/0_Introduction/systemWideAtomics/README.md index e9e22eb7f..35d4886ec 100644 --- a/Samples/0_Introduction/systemWideAtomics/README.md +++ b/Samples/0_Introduction/systemWideAtomics/README.md @@ -30,7 +30,7 @@ cudaDeviceSynchronize, cudaMallocManaged, cudaGetDeviceProperties, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/template/Makefile b/Samples/0_Introduction/template/Makefile index 5bb987e9d..dfc9ff87d 100644 --- a/Samples/0_Introduction/template/Makefile +++ b/Samples/0_Introduction/template/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/template/README.md b/Samples/0_Introduction/template/README.md index ded8e64dc..af7fa7579 100644 --- a/Samples/0_Introduction/template/README.md +++ b/Samples/0_Introduction/template/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/template/template_vs2017.vcxproj b/Samples/0_Introduction/template/template_vs2017.vcxproj index 600260f81..119b05e43 100644 --- a/Samples/0_Introduction/template/template_vs2017.vcxproj +++ b/Samples/0_Introduction/template/template_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/template/template_vs2019.vcxproj b/Samples/0_Introduction/template/template_vs2019.vcxproj index 797a4ef3f..6ff2612f3 100644 --- a/Samples/0_Introduction/template/template_vs2019.vcxproj +++ b/Samples/0_Introduction/template/template_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/template/template_vs2022.vcxproj b/Samples/0_Introduction/template/template_vs2022.vcxproj index 597a4ac5e..bc8427293 100644 --- a/Samples/0_Introduction/template/template_vs2022.vcxproj +++ b/Samples/0_Introduction/template/template_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd/Makefile b/Samples/0_Introduction/vectorAdd/Makefile index 4ac555e79..ea1439658 100644 --- a/Samples/0_Introduction/vectorAdd/Makefile +++ b/Samples/0_Introduction/vectorAdd/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/vectorAdd/README.md b/Samples/0_Introduction/vectorAdd/README.md index d0030dc14..bcafb84a8 100644 --- a/Samples/0_Introduction/vectorAdd/README.md +++ b/Samples/0_Introduction/vectorAdd/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaGetLastError, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2017.vcxproj b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2017.vcxproj index 8bf1ac17f..849298092 100644 --- a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2017.vcxproj +++ b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2019.vcxproj b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2019.vcxproj index 8a12b05c4..b94d33f05 100644 --- a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2019.vcxproj +++ b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2022.vcxproj b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2022.vcxproj index 4622684cb..e1632be2c 100644 --- a/Samples/0_Introduction/vectorAdd/vectorAdd_vs2022.vcxproj +++ b/Samples/0_Introduction/vectorAdd/vectorAdd_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddDrv/Makefile b/Samples/0_Introduction/vectorAddDrv/Makefile index c163e969e..99154c3b2 100644 --- a/Samples/0_Introduction/vectorAddDrv/Makefile +++ b/Samples/0_Introduction/vectorAddDrv/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/vectorAddDrv/README.md b/Samples/0_Introduction/vectorAddDrv/README.md index 14884af7f..ededa2aca 100644 --- a/Samples/0_Introduction/vectorAddDrv/README.md +++ b/Samples/0_Introduction/vectorAddDrv/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuModuleLoadData, cuCtxSynchronize, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2017.vcxproj b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2017.vcxproj index 0e1ea43fc..d9af8d396 100644 --- a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2017.vcxproj +++ b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2019.vcxproj b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2019.vcxproj index 8c375560b..3addd31e1 100644 --- a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2019.vcxproj +++ b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2022.vcxproj b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2022.vcxproj index fca354cb3..f50024ec1 100644 --- a/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2022.vcxproj +++ b/Samples/0_Introduction/vectorAddDrv/vectorAddDrv_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddMMAP/Makefile b/Samples/0_Introduction/vectorAddMMAP/Makefile index a9ede4b71..8bddeb072 100644 --- a/Samples/0_Introduction/vectorAddMMAP/Makefile +++ b/Samples/0_Introduction/vectorAddMMAP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/vectorAddMMAP/README.md b/Samples/0_Introduction/vectorAddMMAP/README.md index 15ff121eb..701e08e37 100644 --- a/Samples/0_Introduction/vectorAddMMAP/README.md +++ b/Samples/0_Introduction/vectorAddMMAP/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuDeviceCanAccessPeer, cuModuleGetFunction, cuMemSetAccess, cuMemR ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2017.vcxproj b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2017.vcxproj index 61d096f54..369a90075 100644 --- a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2017.vcxproj +++ b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2019.vcxproj b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2019.vcxproj index 53db107f7..4c278e7c5 100644 --- a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2019.vcxproj +++ b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2022.vcxproj b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2022.vcxproj index 04bc86aaf..174356b23 100644 --- a/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2022.vcxproj +++ b/Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd_nvrtc/Makefile b/Samples/0_Introduction/vectorAdd_nvrtc/Makefile index bf27a0583..fe5923123 100644 --- a/Samples/0_Introduction/vectorAdd_nvrtc/Makefile +++ b/Samples/0_Introduction/vectorAdd_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/0_Introduction/vectorAdd_nvrtc/README.md b/Samples/0_Introduction/vectorAdd_nvrtc/README.md index d291647a1..863f4c5a3 100644 --- a/Samples/0_Introduction/vectorAdd_nvrtc/README.md +++ b/Samples/0_Introduction/vectorAdd_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2017.vcxproj b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2017.vcxproj index 481f7382d..d798dd6f5 100644 --- a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2017.vcxproj +++ b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2019.vcxproj b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2019.vcxproj index ab08b3e5f..274fda17f 100644 --- a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2019.vcxproj +++ b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2022.vcxproj b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2022.vcxproj index 0a3755dc7..cec326eb1 100644 --- a/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2022.vcxproj +++ b/Samples/0_Introduction/vectorAdd_nvrtc/vectorAdd_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/bandwidthTest/Makefile b/Samples/1_Utilities/bandwidthTest/Makefile index 3132ee588..d7a50c57a 100644 --- a/Samples/1_Utilities/bandwidthTest/Makefile +++ b/Samples/1_Utilities/bandwidthTest/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/1_Utilities/bandwidthTest/README.md b/Samples/1_Utilities/bandwidthTest/README.md index a0e944436..392e48975 100644 --- a/Samples/1_Utilities/bandwidthTest/README.md +++ b/Samples/1_Utilities/bandwidthTest/README.md @@ -27,7 +27,7 @@ cudaHostAlloc, cudaMemcpy, cudaMalloc, cudaMemcpyAsync, cudaFree, cudaGetErrorSt ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2017.vcxproj b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2017.vcxproj index a883411cf..6e44223ce 100644 --- a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2017.vcxproj +++ b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2019.vcxproj b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2019.vcxproj index 9eedbf306..b297efade 100644 --- a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2019.vcxproj +++ b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2022.vcxproj b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2022.vcxproj index 94c05285b..28997ae9b 100644 --- a/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2022.vcxproj +++ b/Samples/1_Utilities/bandwidthTest/bandwidthTest_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/deviceQuery/Makefile b/Samples/1_Utilities/deviceQuery/Makefile index c1f2ab457..89446f20d 100644 --- a/Samples/1_Utilities/deviceQuery/Makefile +++ b/Samples/1_Utilities/deviceQuery/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/1_Utilities/deviceQuery/README.md b/Samples/1_Utilities/deviceQuery/README.md index a21c297fd..cce647607 100644 --- a/Samples/1_Utilities/deviceQuery/README.md +++ b/Samples/1_Utilities/deviceQuery/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaGetErrorString, cudaDeviceCanAccessPeer, cudaSetDevic ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2017.vcxproj b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2017.vcxproj index 115deff44..a3af850e4 100644 --- a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2017.vcxproj +++ b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2019.vcxproj b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2019.vcxproj index 5fd4e6d64..2da4aff86 100644 --- a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2019.vcxproj +++ b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2022.vcxproj b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2022.vcxproj index e29d50b4d..e76868202 100644 --- a/Samples/1_Utilities/deviceQuery/deviceQuery_vs2022.vcxproj +++ b/Samples/1_Utilities/deviceQuery/deviceQuery_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/deviceQueryDrv/Makefile b/Samples/1_Utilities/deviceQueryDrv/Makefile index a99867d4c..a5305e225 100644 --- a/Samples/1_Utilities/deviceQueryDrv/Makefile +++ b/Samples/1_Utilities/deviceQueryDrv/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/1_Utilities/deviceQueryDrv/README.md b/Samples/1_Utilities/deviceQueryDrv/README.md index 75bbdb7ae..e71a2c746 100644 --- a/Samples/1_Utilities/deviceQueryDrv/README.md +++ b/Samples/1_Utilities/deviceQueryDrv/README.md @@ -30,7 +30,7 @@ cudaSetDevice ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2017.vcxproj b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2017.vcxproj index 1cf2343be..8dce62cb4 100644 --- a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2017.vcxproj +++ b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2019.vcxproj b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2019.vcxproj index eae851369..6fc822229 100644 --- a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2019.vcxproj +++ b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2022.vcxproj b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2022.vcxproj index 8295af486..494cd7966 100644 --- a/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2022.vcxproj +++ b/Samples/1_Utilities/deviceQueryDrv/deviceQueryDrv_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/topologyQuery/Makefile b/Samples/1_Utilities/topologyQuery/Makefile index ff050adf3..4c3ee47e7 100644 --- a/Samples/1_Utilities/topologyQuery/Makefile +++ b/Samples/1_Utilities/topologyQuery/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/1_Utilities/topologyQuery/README.md b/Samples/1_Utilities/topologyQuery/README.md index abc31e63b..6f0c48e82 100644 --- a/Samples/1_Utilities/topologyQuery/README.md +++ b/Samples/1_Utilities/topologyQuery/README.md @@ -27,7 +27,7 @@ cudaGetDeviceCount, cudaDeviceGetAttribute ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2017.vcxproj b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2017.vcxproj index 4d1e149ef..d7accfa50 100644 --- a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2017.vcxproj +++ b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2019.vcxproj b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2019.vcxproj index 8ec1ecd32..be5ffb305 100644 --- a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2019.vcxproj +++ b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2022.vcxproj b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2022.vcxproj index 882066db5..199697690 100644 --- a/Samples/1_Utilities/topologyQuery/topologyQuery_vs2022.vcxproj +++ b/Samples/1_Utilities/topologyQuery/topologyQuery_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/Makefile b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/Makefile index 178e8458d..19bb66492 100644 --- a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/Makefile +++ b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/README.md b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/README.md index 49768f8cc..d753a3141 100644 --- a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/README.md +++ b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaMalloc, cudaProducerPresentFrame, cudaFree, cudaGetErrorString, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/Makefile b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/Makefile index c70bcc3b8..d061a5889 100644 --- a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/Makefile +++ b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/README.md b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/README.md index d7e938912..3dda94ded 100644 --- a/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/README.md +++ b/Samples/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/README.md @@ -33,7 +33,7 @@ cudaProducerReadYUVFrame, cudaProducerTest, cudaProducerDeinit, cudaDeviceCreate ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/Makefile b/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/Makefile index 0241761a8..f4384df12 100644 --- a/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/Makefile +++ b/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/README.md b/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/README.md index 71780f876..9668be56d 100644 --- a/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/README.md +++ b/Samples/2_Concepts_and_Techniques/EGLSync_CUDAEvent_Interop/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaDeviceSynchronize, cudaGetValueMis ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2017.vcxproj index 54064e642..cb7a6cff7 100644 --- a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2019.vcxproj index 5b17e0d69..b05ac5407 100644 --- a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2022.vcxproj index 5e90a300a..786a01595 100644 --- a/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/FunctionPointers/Makefile b/Samples/2_Concepts_and_Techniques/FunctionPointers/Makefile index e7b1ebab1..62e075d9b 100644 --- a/Samples/2_Concepts_and_Techniques/FunctionPointers/Makefile +++ b/Samples/2_Concepts_and_Techniques/FunctionPointers/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/FunctionPointers/README.md b/Samples/2_Concepts_and_Techniques/FunctionPointers/README.md index bd5f9ebc7..883676dfe 100644 --- a/Samples/2_Concepts_and_Techniques/FunctionPointers/README.md +++ b/Samples/2_Concepts_and_Techniques/FunctionPointers/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2017.vcxproj index 004481289..c0e3a3d30 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2019.vcxproj index e0ff27e73..1111fea70 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2022.vcxproj index baecaf800..13c12d129 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/MC_EstimatePiInlineP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/Makefile b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/Makefile index ebb1ba53d..7287ec6a3 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/Makefile +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/README.md b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/README.md index d9bd5496e..e534a2af8 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/README.md +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineP/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaSetDevice, cudaGetDeviceCount, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2017.vcxproj index dc8b864b4..112f2f96d 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2019.vcxproj index 3966e3e25..6dd7acd1d 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2022.vcxproj index b0076d1d9..2b7801453 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/MC_EstimatePiInlineQ_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/Makefile b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/Makefile index cbef91719..8725a3256 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/Makefile +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/README.md b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/README.md index 18edc893a..7de22e0ce 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/README.md +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiInlineQ/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaSetDevice, cudaGetDeviceCount, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2017.vcxproj index 6831478f0..de2f2ffd9 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2019.vcxproj index 82e2de5ee..fca132d87 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2022.vcxproj index 88b2c63e6..09bdd5d9c 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/MC_EstimatePiP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/Makefile b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/Makefile index 9baf49b5d..7f921e799 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/Makefile +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/README.md b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/README.md index 51cc0299f..43c16ba47 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/README.md +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiP/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaSetDevice, cudaGetDeviceCount, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2017.vcxproj index fb05b83c7..378dac27d 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2019.vcxproj index d3d6c035c..23c30ef72 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2022.vcxproj index d9623eb5f..ff3765005 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/MC_EstimatePiQ_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/Makefile b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/Makefile index 9a2f2d3a8..40c895155 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/Makefile +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/README.md b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/README.md index 5855ec67d..a26ae785a 100644 --- a/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/README.md +++ b/Samples/2_Concepts_and_Techniques/MC_EstimatePiQ/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaSetDevice, cudaGetDeviceCount, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2017.vcxproj index 6172e5a6d..399b3422d 100644 --- a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2019.vcxproj index b5fb4530d..812091d72 100644 --- a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2022.vcxproj index 1e14b94db..89d23c013 100644 --- a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/MC_SingleAsianOptionP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/Makefile b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/Makefile index 85eacfd19..860f57799 100644 --- a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/Makefile +++ b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/README.md b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/README.md index 147b8c0ea..4984ce2a1 100644 --- a/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/README.md +++ b/Samples/2_Concepts_and_Techniques/MC_SingleAsianOptionP/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaSetDevice, cudaGetDeviceCount, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/boxFilter/Makefile b/Samples/2_Concepts_and_Techniques/boxFilter/Makefile index 09ae6e240..1f4275f8a 100644 --- a/Samples/2_Concepts_and_Techniques/boxFilter/Makefile +++ b/Samples/2_Concepts_and_Techniques/boxFilter/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/boxFilter/README.md b/Samples/2_Concepts_and_Techniques/boxFilter/README.md index cd7e5737b..9ed5b0e4f 100644 --- a/Samples/2_Concepts_and_Techniques/boxFilter/README.md +++ b/Samples/2_Concepts_and_Techniques/boxFilter/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaCreateChannelDesc, cudaMallocArray, cudaFreeArra ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2017.vcxproj index 2ca9d0e21..a6e28e9bc 100644 --- a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2019.vcxproj index 15e20ab61..9674a20e5 100644 --- a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -115,6 +115,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2022.vcxproj index 2d57f772b..97e9675a2 100644 --- a/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/boxFilter/boxFilter_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -115,6 +115,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionSeparable/Makefile b/Samples/2_Concepts_and_Techniques/convolutionSeparable/Makefile index 781fb328b..baca6908a 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionSeparable/Makefile +++ b/Samples/2_Concepts_and_Techniques/convolutionSeparable/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/convolutionSeparable/README.md b/Samples/2_Concepts_and_Techniques/convolutionSeparable/README.md index f7cb1045a..c79eb31ad 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionSeparable/README.md +++ b/Samples/2_Concepts_and_Techniques/convolutionSeparable/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMemcpyToSymbol, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2017.vcxproj index 7f2abb7a2..51d47a0cc 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2019.vcxproj index 51bfba1a3..29479be79 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2022.vcxproj index 8b59e3e80..fe26e0015 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionTexture/Makefile b/Samples/2_Concepts_and_Techniques/convolutionTexture/Makefile index f2b678b6d..ad059e93d 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionTexture/Makefile +++ b/Samples/2_Concepts_and_Techniques/convolutionTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/convolutionTexture/README.md b/Samples/2_Concepts_and_Techniques/convolutionTexture/README.md index 773a30d00..5e5ffb268 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionTexture/README.md +++ b/Samples/2_Concepts_and_Techniques/convolutionTexture/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree, cudaMemcpyToArray, cudaDev ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2017.vcxproj index e73eefb69..29d9c841e 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2019.vcxproj index e7d49b941..975a15ca7 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2022.vcxproj index 07a46bcf9..d962dd89c 100644 --- a/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/cuHook/Makefile b/Samples/2_Concepts_and_Techniques/cuHook/Makefile index 9f0cf2f8f..9ccdd509f 100644 --- a/Samples/2_Concepts_and_Techniques/cuHook/Makefile +++ b/Samples/2_Concepts_and_Techniques/cuHook/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/cuHook/README.md b/Samples/2_Concepts_and_Techniques/cuHook/README.md index 3139a5546..7427c465f 100644 --- a/Samples/2_Concepts_and_Techniques/cuHook/README.md +++ b/Samples/2_Concepts_and_Techniques/cuHook/README.md @@ -32,7 +32,7 @@ cudaDeviceReset, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/dct8x8/Makefile b/Samples/2_Concepts_and_Techniques/dct8x8/Makefile index 285446d0f..181007c9a 100644 --- a/Samples/2_Concepts_and_Techniques/dct8x8/Makefile +++ b/Samples/2_Concepts_and_Techniques/dct8x8/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/dct8x8/README.md b/Samples/2_Concepts_and_Techniques/dct8x8/README.md index a9b76320f..22ee26989 100644 --- a/Samples/2_Concepts_and_Techniques/dct8x8/README.md +++ b/Samples/2_Concepts_and_Techniques/dct8x8/README.md @@ -27,7 +27,7 @@ cudaMallocArray, cudaFreeArray, cudaFree, cudaMallocPitch, cudaDestroyTextureObj ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2017.vcxproj index de5ff96d5..a9725ce1f 100644 --- a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -115,6 +115,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2019.vcxproj index 1b6c3019c..c3b57f437 100644 --- a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2022.vcxproj index c45920a0d..b768ea111 100644 --- a/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/dct8x8/dct8x8_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/eigenvalues/Makefile b/Samples/2_Concepts_and_Techniques/eigenvalues/Makefile index 67505f65f..560b4a4e3 100644 --- a/Samples/2_Concepts_and_Techniques/eigenvalues/Makefile +++ b/Samples/2_Concepts_and_Techniques/eigenvalues/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/eigenvalues/README.md b/Samples/2_Concepts_and_Techniques/eigenvalues/README.md index 7f5e05cf6..235fac217 100644 --- a/Samples/2_Concepts_and_Techniques/eigenvalues/README.md +++ b/Samples/2_Concepts_and_Techniques/eigenvalues/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2017.vcxproj index 197d0ba51..3a64c9387 100644 --- a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -122,6 +122,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2019.vcxproj index 105d42b17..c0cdb0584 100644 --- a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2022.vcxproj index f73eb0d1d..b400c36af 100644 --- a/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/eigenvalues/eigenvalues_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/histogram/Makefile b/Samples/2_Concepts_and_Techniques/histogram/Makefile index 0aff0de02..6d85b831a 100644 --- a/Samples/2_Concepts_and_Techniques/histogram/Makefile +++ b/Samples/2_Concepts_and_Techniques/histogram/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/histogram/README.md b/Samples/2_Concepts_and_Techniques/histogram/README.md index accddad95..a6088c65f 100644 --- a/Samples/2_Concepts_and_Techniques/histogram/README.md +++ b/Samples/2_Concepts_and_Techniques/histogram/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2017.vcxproj index 99ec61c13..2aaf05f54 100644 --- a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2019.vcxproj index c88213d21..d8d3088fc 100644 --- a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2022.vcxproj index d271430f2..200790fef 100644 --- a/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/histogram/histogram_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/imageDenoising/Makefile b/Samples/2_Concepts_and_Techniques/imageDenoising/Makefile index ecbf667de..00f062c26 100644 --- a/Samples/2_Concepts_and_Techniques/imageDenoising/Makefile +++ b/Samples/2_Concepts_and_Techniques/imageDenoising/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/imageDenoising/README.md b/Samples/2_Concepts_and_Techniques/imageDenoising/README.md index 967440ed4..9242b34fd 100644 --- a/Samples/2_Concepts_and_Techniques/imageDenoising/README.md +++ b/Samples/2_Concepts_and_Techniques/imageDenoising/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2017.vcxproj index eef04d37d..4c3ad4117 100644 --- a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -123,6 +123,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2019.vcxproj index 5c35ac7b5..7ec5d28a0 100644 --- a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2022.vcxproj index 67dcf5343..2fd97ad9b 100644 --- a/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/imageDenoising/imageDenoising_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX/Makefile b/Samples/2_Concepts_and_Techniques/inlinePTX/Makefile index d05a24d2d..e2d4c251f 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX/Makefile +++ b/Samples/2_Concepts_and_Techniques/inlinePTX/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX/README.md b/Samples/2_Concepts_and_Techniques/inlinePTX/README.md index 60c7b0f21..2760047cc 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX/README.md +++ b/Samples/2_Concepts_and_Techniques/inlinePTX/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaMallocHost, cudaGetLastError, cudaGridSize, cudaBlockS ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2017.vcxproj index 5ff4b037c..13a492e08 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2019.vcxproj index dd8c00c29..614f178a3 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2022.vcxproj index 55bba92ac..505f4e81f 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX/inlinePTX_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/Makefile b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/Makefile index 291d48543..c358fb0ba 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/Makefile +++ b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/README.md b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/README.md index 78a272573..6e535bd53 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/README.md +++ b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2017.vcxproj index 1ebd81ca9..0ea3ea6e6 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2019.vcxproj index 1583691c2..7563d0195 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2022.vcxproj index d8965838d..62ce6a5d5 100644 --- a/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/inlinePTX_nvrtc/inlinePTX_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/interval/Makefile b/Samples/2_Concepts_and_Techniques/interval/Makefile index 9e369a5dc..b2e314c7a 100644 --- a/Samples/2_Concepts_and_Techniques/interval/Makefile +++ b/Samples/2_Concepts_and_Techniques/interval/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/interval/README.md b/Samples/2_Concepts_and_Techniques/interval/README.md index 65498b663..9eafdaba5 100644 --- a/Samples/2_Concepts_and_Techniques/interval/README.md +++ b/Samples/2_Concepts_and_Techniques/interval/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFuncSetCacheConfig, cudaMalloc, cudaFree, cudaGetLastError, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/interval/interval_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/interval/interval_vs2017.vcxproj index cabde8893..a351db755 100644 --- a/Samples/2_Concepts_and_Techniques/interval/interval_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/interval/interval_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -213,6 +213,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/interval/interval_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/interval/interval_vs2019.vcxproj index 2cb000aae..40bc8ee0a 100644 --- a/Samples/2_Concepts_and_Techniques/interval/interval_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/interval/interval_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -209,6 +209,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/interval/interval_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/interval/interval_vs2022.vcxproj index 2d37616b7..e84d40172 100644 --- a/Samples/2_Concepts_and_Techniques/interval/interval_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/interval/interval_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -209,6 +209,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/particles/Makefile b/Samples/2_Concepts_and_Techniques/particles/Makefile index 5da2007aa..f45b05881 100644 --- a/Samples/2_Concepts_and_Techniques/particles/Makefile +++ b/Samples/2_Concepts_and_Techniques/particles/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/particles/README.md b/Samples/2_Concepts_and_Techniques/particles/README.md index da3453b63..f86cac020 100644 --- a/Samples/2_Concepts_and_Techniques/particles/README.md +++ b/Samples/2_Concepts_and_Techniques/particles/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/particles/particles_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/particles/particles_vs2017.vcxproj index f9bb1f46c..d3ae2effe 100644 --- a/Samples/2_Concepts_and_Techniques/particles/particles_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/particles/particles_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -129,6 +129,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/particles/particles_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/particles/particles_vs2019.vcxproj index 97d4bc7d8..f96d4a309 100644 --- a/Samples/2_Concepts_and_Techniques/particles/particles_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/particles/particles_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -125,6 +125,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/particles/particles_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/particles/particles_vs2022.vcxproj index 00f0b6de7..49b56ad1f 100644 --- a/Samples/2_Concepts_and_Techniques/particles/particles_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/particles/particles_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -125,6 +125,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/radixSortThrust/Makefile b/Samples/2_Concepts_and_Techniques/radixSortThrust/Makefile index 92be51abe..503eecc74 100644 --- a/Samples/2_Concepts_and_Techniques/radixSortThrust/Makefile +++ b/Samples/2_Concepts_and_Techniques/radixSortThrust/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/radixSortThrust/README.md b/Samples/2_Concepts_and_Techniques/radixSortThrust/README.md index f4b01c262..2ffa76f20 100644 --- a/Samples/2_Concepts_and_Techniques/radixSortThrust/README.md +++ b/Samples/2_Concepts_and_Techniques/radixSortThrust/README.md @@ -27,7 +27,7 @@ cudaEventSynchronize, cudaEventRecord, cudaGetDevice, cudaEventDestroy, cudaEven ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2017.vcxproj index 53fee37cd..07d1e44b7 100644 --- a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2019.vcxproj index 8812d1f7e..abee20c72 100644 --- a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2022.vcxproj index a9fd806ea..a8c87aa1b 100644 --- a/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/radixSortThrust/radixSortThrust_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reduction/Makefile b/Samples/2_Concepts_and_Techniques/reduction/Makefile index 8ec8d6351..297c1e470 100644 --- a/Samples/2_Concepts_and_Techniques/reduction/Makefile +++ b/Samples/2_Concepts_and_Techniques/reduction/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/reduction/README.md b/Samples/2_Concepts_and_Techniques/reduction/README.md index 5bb81f5b7..ac9167040 100644 --- a/Samples/2_Concepts_and_Techniques/reduction/README.md +++ b/Samples/2_Concepts_and_Techniques/reduction/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaSetDevice, cudaDeviceSynchronize, cudaGetDevice, cudaM ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2017.vcxproj index 972b6588c..fc77c7ce2 100644 --- a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2019.vcxproj index a35184ce5..265821a82 100644 --- a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2022.vcxproj index 6cd327dc2..a9ed5d63d 100644 --- a/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reduction/reduction_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/Makefile b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/Makefile index eaaf0c2f8..d86bffa02 100644 --- a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/Makefile +++ b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/README.md b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/README.md index 0383fdded..706766aa7 100644 --- a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/README.md +++ b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaSetDevice, cudaDeviceSynchronize, cudaLaunchCooperativ ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2017.vcxproj index 1ecfd78d7..7ae7db260 100644 --- a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2019.vcxproj index 0368b5545..b14e94abd 100644 --- a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2022.vcxproj index 186cecd9a..6880c059a 100644 --- a/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/reductionMultiBlockCG/reductionMultiBlockCG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scalarProd/Makefile b/Samples/2_Concepts_and_Techniques/scalarProd/Makefile index 316337e7d..7ed7d15af 100644 --- a/Samples/2_Concepts_and_Techniques/scalarProd/Makefile +++ b/Samples/2_Concepts_and_Techniques/scalarProd/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/scalarProd/README.md b/Samples/2_Concepts_and_Techniques/scalarProd/README.md index 28761f4bd..139d1ca0b 100644 --- a/Samples/2_Concepts_and_Techniques/scalarProd/README.md +++ b/Samples/2_Concepts_and_Techniques/scalarProd/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2017.vcxproj index e543b834c..21a49a06a 100644 --- a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2019.vcxproj index 8f6013640..11eafdeb1 100644 --- a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2022.vcxproj index 3fb523af4..684470fb2 100644 --- a/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scalarProd/scalarProd_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scan/Makefile b/Samples/2_Concepts_and_Techniques/scan/Makefile index 20a849917..5a98f27c8 100644 --- a/Samples/2_Concepts_and_Techniques/scan/Makefile +++ b/Samples/2_Concepts_and_Techniques/scan/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/scan/README.md b/Samples/2_Concepts_and_Techniques/scan/README.md index f238733ce..5db006d31 100644 --- a/Samples/2_Concepts_and_Techniques/scan/README.md +++ b/Samples/2_Concepts_and_Techniques/scan/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/scan/scan_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/scan/scan_vs2017.vcxproj index 929897003..8bb47bade 100644 --- a/Samples/2_Concepts_and_Techniques/scan/scan_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scan/scan_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scan/scan_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/scan/scan_vs2019.vcxproj index b7dc43234..e5b883a7b 100644 --- a/Samples/2_Concepts_and_Techniques/scan/scan_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scan/scan_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/scan/scan_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/scan/scan_vs2022.vcxproj index eeb05f2ef..f2d6c8b8b 100644 --- a/Samples/2_Concepts_and_Techniques/scan/scan_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/scan/scan_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/Makefile b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/Makefile index 8befa5f52..d4f259a4d 100644 --- a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/Makefile +++ b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/README.md b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/README.md index 84093d065..1959b9a8f 100644 --- a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/README.md +++ b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaMemGetInfo, cudaEventSynchronize, cudaEventRecord, cudaMemset, c ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2017.vcxproj index e1ae6ca8e..574587fe8 100644 --- a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2019.vcxproj index 258447647..9e2b52104 100644 --- a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2022.vcxproj index 142373275..5e4c219fc 100644 --- a/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/segmentationTreeThrust/segmentationTreeThrust_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/shfl_scan/Makefile b/Samples/2_Concepts_and_Techniques/shfl_scan/Makefile index 627a2bc4f..df10b6729 100644 --- a/Samples/2_Concepts_and_Techniques/shfl_scan/Makefile +++ b/Samples/2_Concepts_and_Techniques/shfl_scan/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/shfl_scan/README.md b/Samples/2_Concepts_and_Techniques/shfl_scan/README.md index 12cb7c588..8d04c940b 100644 --- a/Samples/2_Concepts_and_Techniques/shfl_scan/README.md +++ b/Samples/2_Concepts_and_Techniques/shfl_scan/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaFree, cudaMallocHost, cudaEventSynchronize, cudaEventRecord, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2017.vcxproj index 7df3fe375..219eb2eb8 100644 --- a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2019.vcxproj index 37df0fe3c..7c2821846 100644 --- a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2022.vcxproj index 9464b3806..bc5157794 100644 --- a/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/shfl_scan/shfl_scan_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/sortingNetworks/Makefile b/Samples/2_Concepts_and_Techniques/sortingNetworks/Makefile index 9e8e0b571..8b88373ec 100644 --- a/Samples/2_Concepts_and_Techniques/sortingNetworks/Makefile +++ b/Samples/2_Concepts_and_Techniques/sortingNetworks/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/sortingNetworks/README.md b/Samples/2_Concepts_and_Techniques/sortingNetworks/README.md index c23943cdd..1b1001317 100644 --- a/Samples/2_Concepts_and_Techniques/sortingNetworks/README.md +++ b/Samples/2_Concepts_and_Techniques/sortingNetworks/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2017.vcxproj index 5d05456f3..8d625e4fa 100644 --- a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2019.vcxproj index 961caf425..65834bc53 100644 --- a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2022.vcxproj index dfa17e1e2..901917378 100644 --- a/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/sortingNetworks/sortingNetworks_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/Makefile b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/Makefile index b551270ff..9611c8f24 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/Makefile +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/README.md b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/README.md index 05d3b3c8b..a93e11215 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/README.md +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/README.md @@ -27,7 +27,7 @@ cudaDeviceGetDefaultMemPool, cudaFreeAsync, cudaStreamCreateWithFlags, cudaStrea ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2017.vcxproj index ab20053e4..31f3d7d49 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2019.vcxproj index 91e4c4d43..343b5af4d 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2022.vcxproj index 270217016..d3a4fdafc 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocation/streamOrderedAllocation_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/Makefile b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/Makefile index 37d08561f..dfe391048 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/Makefile +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/README.md b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/README.md index 625d637b0..e66338801 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/README.md +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationIPC/README.md @@ -30,7 +30,7 @@ cudaDeviceGetAttribute, cudaMemPoolImportFromShareableHandle, cudaSetDevice, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/Makefile b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/Makefile index 532ef73f5..9115e9536 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/Makefile +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/README.md b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/README.md index 9736488ae..775bc09b5 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/README.md +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/README.md @@ -27,7 +27,7 @@ cudaDeviceGetDefaultMemPool, cudaFreeAsync, cudaStreamCreateWithFlags, cudaMemPo ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2017.vcxproj index a1e205273..701b8efa7 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2019.vcxproj index e7d305016..a662490b9 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2022.vcxproj index 12e5fa5a0..bb9274fed 100644 --- a/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadFenceReduction/Makefile b/Samples/2_Concepts_and_Techniques/threadFenceReduction/Makefile index 5f4646b13..58a1f6766 100644 --- a/Samples/2_Concepts_and_Techniques/threadFenceReduction/Makefile +++ b/Samples/2_Concepts_and_Techniques/threadFenceReduction/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/threadFenceReduction/README.md b/Samples/2_Concepts_and_Techniques/threadFenceReduction/README.md index 36af664d8..15c1f3e71 100644 --- a/Samples/2_Concepts_and_Techniques/threadFenceReduction/README.md +++ b/Samples/2_Concepts_and_Techniques/threadFenceReduction/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2017.vcxproj index 116b3f08f..c554d1520 100644 --- a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2019.vcxproj index 40f1241be..5a2236537 100644 --- a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2022.vcxproj index 88b7d1b77..40dbf185e 100644 --- a/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadFenceReduction/threadFenceReduction_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadMigration/Makefile b/Samples/2_Concepts_and_Techniques/threadMigration/Makefile index d7e735bc8..f3d42a2a5 100644 --- a/Samples/2_Concepts_and_Techniques/threadMigration/Makefile +++ b/Samples/2_Concepts_and_Techniques/threadMigration/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/2_Concepts_and_Techniques/threadMigration/README.md b/Samples/2_Concepts_and_Techniques/threadMigration/README.md index 00562b436..893574237 100644 --- a/Samples/2_Concepts_and_Techniques/threadMigration/README.md +++ b/Samples/2_Concepts_and_Techniques/threadMigration/README.md @@ -27,7 +27,7 @@ cuMemcpyDtoH, cuLaunchKernel, cuModuleLoadData, cuDeviceGetName, cuDeviceGet, cu ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2017.vcxproj b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2017.vcxproj index ec306a40b..9268bf34b 100644 --- a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2017.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2019.vcxproj b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2019.vcxproj index d569019f2..7a0f24a9c 100644 --- a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2019.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2022.vcxproj b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2022.vcxproj index 265cfeafe..5de98212b 100644 --- a/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2022.vcxproj +++ b/Samples/2_Concepts_and_Techniques/threadMigration/threadMigration_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/StreamPriorities/Makefile b/Samples/3_CUDA_Features/StreamPriorities/Makefile index 5083641e9..36fdbc14b 100644 --- a/Samples/3_CUDA_Features/StreamPriorities/Makefile +++ b/Samples/3_CUDA_Features/StreamPriorities/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/StreamPriorities/README.md b/Samples/3_CUDA_Features/StreamPriorities/README.md index 6e634cc1d..1657bddf8 100644 --- a/Samples/3_CUDA_Features/StreamPriorities/README.md +++ b/Samples/3_CUDA_Features/StreamPriorities/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaStreamCreateWithPriority, cudaDeviceGetStreamPriorityRange, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/bf16TensorCoreGemm/Makefile b/Samples/3_CUDA_Features/bf16TensorCoreGemm/Makefile index 6fa432f32..bd3bd57da 100644 --- a/Samples/3_CUDA_Features/bf16TensorCoreGemm/Makefile +++ b/Samples/3_CUDA_Features/bf16TensorCoreGemm/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/bf16TensorCoreGemm/README.md b/Samples/3_CUDA_Features/bf16TensorCoreGemm/README.md index 08f90795a..9f72eebe5 100644 --- a/Samples/3_CUDA_Features/bf16TensorCoreGemm/README.md +++ b/Samples/3_CUDA_Features/bf16TensorCoreGemm/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj index 8a417b82a..42c52f3a8 100644 --- a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj index 76f95d031..aed75387e 100644 --- a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2022.vcxproj b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2022.vcxproj index 3ef227812..decbc4da8 100644 --- a/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/binaryPartitionCG/Makefile b/Samples/3_CUDA_Features/binaryPartitionCG/Makefile index 5cbfd13da..076405a83 100644 --- a/Samples/3_CUDA_Features/binaryPartitionCG/Makefile +++ b/Samples/3_CUDA_Features/binaryPartitionCG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/binaryPartitionCG/README.md b/Samples/3_CUDA_Features/binaryPartitionCG/README.md index ff46f83b2..1b26aec54 100644 --- a/Samples/3_CUDA_Features/binaryPartitionCG/README.md +++ b/Samples/3_CUDA_Features/binaryPartitionCG/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaFree, cudaMallocHost, cudaFreeHost, cudaStreamSyn ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj index 284bdda15..de633f563 100644 --- a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj index 218f53855..dd6c16ca9 100644 --- a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2022.vcxproj b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2022.vcxproj index b6971e40d..f8e04a5b7 100644 --- a/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/bindlessTexture/Makefile b/Samples/3_CUDA_Features/bindlessTexture/Makefile index 436726766..5dacf2779 100644 --- a/Samples/3_CUDA_Features/bindlessTexture/Makefile +++ b/Samples/3_CUDA_Features/bindlessTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/bindlessTexture/README.md b/Samples/3_CUDA_Features/bindlessTexture/README.md index 2fe6af3f3..18414d867 100644 --- a/Samples/3_CUDA_Features/bindlessTexture/README.md +++ b/Samples/3_CUDA_Features/bindlessTexture/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaGetMipmappedArrayLevel, cudaGraphicsMapResources, cudaDestroySur ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2017.vcxproj b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2017.vcxproj index 646b9c920..0705c0b8b 100644 --- a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2019.vcxproj b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2019.vcxproj index b602feb76..83ecf3715 100644 --- a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2022.vcxproj b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2022.vcxproj index c6ef32c24..21287f556 100644 --- a/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/bindlessTexture/bindlessTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/Makefile b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/Makefile index 7ad291ba5..ddba40383 100644 --- a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/Makefile +++ b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/README.md b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/README.md index a0c1d2ee1..843cff41f 100644 --- a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/README.md +++ b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/README.md @@ -28,7 +28,7 @@ cudaStreamCreateWithFlags, cudaMemcpy, cudaMemcpyAsync, cudaFree, cudaGetErrorSt ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2017.vcxproj b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2017.vcxproj index 1265858b5..19930bf55 100644 --- a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2019.vcxproj b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2019.vcxproj index 0edcea449..072d1d9f4 100644 --- a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2022.vcxproj b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2022.vcxproj index 4c0a0eed4..2fb87778d 100644 --- a/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cdpAdvancedQuicksort/cdpAdvancedQuicksort_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpBezierTessellation/Makefile b/Samples/3_CUDA_Features/cdpBezierTessellation/Makefile index 470f86223..08b4c3f3c 100644 --- a/Samples/3_CUDA_Features/cdpBezierTessellation/Makefile +++ b/Samples/3_CUDA_Features/cdpBezierTessellation/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cdpBezierTessellation/README.md b/Samples/3_CUDA_Features/cdpBezierTessellation/README.md index aba89c4d2..2b3cc6cbd 100644 --- a/Samples/3_CUDA_Features/cdpBezierTessellation/README.md +++ b/Samples/3_CUDA_Features/cdpBezierTessellation/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaFree, cudaGetDeviceCount, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2017.vcxproj b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2017.vcxproj index 60104969d..be39cd4e6 100644 --- a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2019.vcxproj b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2019.vcxproj index 73583e9ec..52bc6f326 100644 --- a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2022.vcxproj b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2022.vcxproj index 718b47a28..d57888745 100644 --- a/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cdpBezierTessellation/cdpBezierTessellation_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpQuadtree/Makefile b/Samples/3_CUDA_Features/cdpQuadtree/Makefile index 0a08289bf..f3924409b 100644 --- a/Samples/3_CUDA_Features/cdpQuadtree/Makefile +++ b/Samples/3_CUDA_Features/cdpQuadtree/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cdpQuadtree/README.md b/Samples/3_CUDA_Features/cdpQuadtree/README.md index 86c37cedc..13fc0f3f7 100644 --- a/Samples/3_CUDA_Features/cdpQuadtree/README.md +++ b/Samples/3_CUDA_Features/cdpQuadtree/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaFree, cudaGetLastError, cudaDeviceSetLimit, cudaMalloc, cudaGetD ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2017.vcxproj b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2017.vcxproj index f99f787d6..2b3a9765d 100644 --- a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2019.vcxproj b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2019.vcxproj index 7a06bca88..29419939f 100644 --- a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2022.vcxproj b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2022.vcxproj index 6354943a8..72c464820 100644 --- a/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cdpQuadtree/cdpQuadtree_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimplePrint/Makefile b/Samples/3_CUDA_Features/cdpSimplePrint/Makefile index 67f6ebcbb..b3618196a 100644 --- a/Samples/3_CUDA_Features/cdpSimplePrint/Makefile +++ b/Samples/3_CUDA_Features/cdpSimplePrint/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cdpSimplePrint/README.md b/Samples/3_CUDA_Features/cdpSimplePrint/README.md index e0a4b8575..e975d6896 100644 --- a/Samples/3_CUDA_Features/cdpSimplePrint/README.md +++ b/Samples/3_CUDA_Features/cdpSimplePrint/README.md @@ -28,7 +28,7 @@ cudaDeviceSynchronize, cudaGetLastError, cudaGetDeviceProperties, cudaDeviceSetL ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2017.vcxproj b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2017.vcxproj index 49b9beb59..7d5b3cabf 100644 --- a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2019.vcxproj b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2019.vcxproj index 2246a2e04..0cb3dca1b 100644 --- a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2022.vcxproj b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2022.vcxproj index 3cee65424..724c22441 100644 --- a/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimplePrint/cdpSimplePrint_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimpleQuicksort/Makefile b/Samples/3_CUDA_Features/cdpSimpleQuicksort/Makefile index 882d5f4b5..e19010947 100644 --- a/Samples/3_CUDA_Features/cdpSimpleQuicksort/Makefile +++ b/Samples/3_CUDA_Features/cdpSimpleQuicksort/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cdpSimpleQuicksort/README.md b/Samples/3_CUDA_Features/cdpSimpleQuicksort/README.md index a5366db1f..a4aa77614 100644 --- a/Samples/3_CUDA_Features/cdpSimpleQuicksort/README.md +++ b/Samples/3_CUDA_Features/cdpSimpleQuicksort/README.md @@ -28,7 +28,7 @@ cudaStreamCreateWithFlags, cudaMemcpy, cudaStreamDestroy, cudaFree, cudaDeviceSy ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2017.vcxproj b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2017.vcxproj index 492b07b84..bbd3960af 100644 --- a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2019.vcxproj b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2019.vcxproj index 821d377ee..3a327e4c4 100644 --- a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2022.vcxproj b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2022.vcxproj index 9fe6560e2..e6cd2990e 100644 --- a/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cdpSimpleQuicksort/cdpSimpleQuicksort_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaCompressibleMemory/Makefile b/Samples/3_CUDA_Features/cudaCompressibleMemory/Makefile index 6504cea1d..382e7d064 100644 --- a/Samples/3_CUDA_Features/cudaCompressibleMemory/Makefile +++ b/Samples/3_CUDA_Features/cudaCompressibleMemory/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cudaCompressibleMemory/README.md b/Samples/3_CUDA_Features/cudaCompressibleMemory/README.md index 504ddf3a0..a223d3c52 100644 --- a/Samples/3_CUDA_Features/cudaCompressibleMemory/README.md +++ b/Samples/3_CUDA_Features/cudaCompressibleMemory/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaEventSynchronize, cudaEventRecord, cudaEventElapsedTime, cudaOcc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2017.vcxproj b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2017.vcxproj index db1e33a2f..44adc75b5 100644 --- a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2019.vcxproj b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2019.vcxproj index a63f55e6c..f6adc4fe5 100644 --- a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2022.vcxproj b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2022.vcxproj index 9673006c5..0a11b00e8 100644 --- a/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaTensorCoreGemm/Makefile b/Samples/3_CUDA_Features/cudaTensorCoreGemm/Makefile index 9e9f26a7c..fe0d35a56 100644 --- a/Samples/3_CUDA_Features/cudaTensorCoreGemm/Makefile +++ b/Samples/3_CUDA_Features/cudaTensorCoreGemm/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/cudaTensorCoreGemm/README.md b/Samples/3_CUDA_Features/cudaTensorCoreGemm/README.md index 98d6aedc9..e89c6d0ab 100644 --- a/Samples/3_CUDA_Features/cudaTensorCoreGemm/README.md +++ b/Samples/3_CUDA_Features/cudaTensorCoreGemm/README.md @@ -31,7 +31,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2017.vcxproj b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2017.vcxproj index af5073795..511eabfd9 100644 --- a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2019.vcxproj b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2019.vcxproj index 55a737c7b..dfdb635ee 100644 --- a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2022.vcxproj b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2022.vcxproj index 3d7d79ed3..23be7cbe6 100644 --- a/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/Makefile b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/Makefile index 134a0759d..a1fd5b5e5 100644 --- a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/Makefile +++ b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/README.md b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/README.md index cee17b9e5..2320afba2 100644 --- a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/README.md +++ b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2017.vcxproj b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2017.vcxproj index 0a99ba5e3..e8fc315f5 100644 --- a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2019.vcxproj b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2019.vcxproj index 1eab00a42..b514747ac 100644 --- a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2022.vcxproj b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2022.vcxproj index d1ffc909a..7c2d8d635 100644 --- a/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/Makefile b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/Makefile index 3c92e0e89..a7e771284 100644 --- a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/Makefile +++ b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/README.md b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/README.md index 1e771697f..807d0e347 100644 --- a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/README.md +++ b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/README.md @@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaMalloc, cudaDeviceGetAttribute, cudaFree, cudaMal ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2017.vcxproj b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2017.vcxproj index 0da843f61..59465e738 100644 --- a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2019.vcxproj b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2019.vcxproj index 5726eec7d..ab59f6dfc 100644 --- a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2022.vcxproj b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2022.vcxproj index c7a38b13e..961bf1bc5 100644 --- a/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphConditionalNodes/Makefile b/Samples/3_CUDA_Features/graphConditionalNodes/Makefile index d32d3432b..e7b0ae9f0 100644 --- a/Samples/3_CUDA_Features/graphConditionalNodes/Makefile +++ b/Samples/3_CUDA_Features/graphConditionalNodes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/graphConditionalNodes/README.md b/Samples/3_CUDA_Features/graphConditionalNodes/README.md index a67268b65..8fd835cbc 100644 --- a/Samples/3_CUDA_Features/graphConditionalNodes/README.md +++ b/Samples/3_CUDA_Features/graphConditionalNodes/README.md @@ -27,7 +27,7 @@ cudaDeviceSynchronize, cudaDriverGetVersion, cudaFree, cudaGraphAddNode, cudaGra ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2017.vcxproj b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2017.vcxproj index 67ba0b342..09578ddf3 100644 --- a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2019.vcxproj b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2019.vcxproj index 63d2f3548..648745f5e 100644 --- a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2022.vcxproj b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2022.vcxproj index 06c23e440..131394350 100644 --- a/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/graphConditionalNodes/graphConditionalNodes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryFootprint/Makefile b/Samples/3_CUDA_Features/graphMemoryFootprint/Makefile index a65a991c9..bbf756db8 100644 --- a/Samples/3_CUDA_Features/graphMemoryFootprint/Makefile +++ b/Samples/3_CUDA_Features/graphMemoryFootprint/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/graphMemoryFootprint/README.md b/Samples/3_CUDA_Features/graphMemoryFootprint/README.md index 7bdd6fb1a..7e0ffde42 100644 --- a/Samples/3_CUDA_Features/graphMemoryFootprint/README.md +++ b/Samples/3_CUDA_Features/graphMemoryFootprint/README.md @@ -27,7 +27,7 @@ cudaGraphAddMemAllocNode, cudaStreamCreateWithFlags, cudaGraphInstantiate, cudaS ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2017.vcxproj b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2017.vcxproj index 43ba12634..277241cd3 100644 --- a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2019.vcxproj b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2019.vcxproj index 5d808b0b3..314adf821 100644 --- a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2022.vcxproj b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2022.vcxproj index 8014d0736..76a918a7f 100644 --- a/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryNodes/Makefile b/Samples/3_CUDA_Features/graphMemoryNodes/Makefile index 630e29a8c..d90d79cb9 100644 --- a/Samples/3_CUDA_Features/graphMemoryNodes/Makefile +++ b/Samples/3_CUDA_Features/graphMemoryNodes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/graphMemoryNodes/README.md b/Samples/3_CUDA_Features/graphMemoryNodes/README.md index bcde2bdd6..1c993f6a7 100644 --- a/Samples/3_CUDA_Features/graphMemoryNodes/README.md +++ b/Samples/3_CUDA_Features/graphMemoryNodes/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaDeviceGetAttribute, cudaDriverGetVersion, cudaGraphLaunch, cudaE ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2017.vcxproj b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2017.vcxproj index ecc8ed9a0..254388cd6 100644 --- a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2019.vcxproj b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2019.vcxproj index d194794c8..80809dcdc 100644 --- a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2022.vcxproj b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2022.vcxproj index e58656a40..cddca771c 100644 --- a/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/immaTensorCoreGemm/Makefile b/Samples/3_CUDA_Features/immaTensorCoreGemm/Makefile index ca6007245..d8e65764a 100644 --- a/Samples/3_CUDA_Features/immaTensorCoreGemm/Makefile +++ b/Samples/3_CUDA_Features/immaTensorCoreGemm/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/immaTensorCoreGemm/README.md b/Samples/3_CUDA_Features/immaTensorCoreGemm/README.md index df65de28e..88f212014 100644 --- a/Samples/3_CUDA_Features/immaTensorCoreGemm/README.md +++ b/Samples/3_CUDA_Features/immaTensorCoreGemm/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2017.vcxproj b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2017.vcxproj index b97bf3d81..99ef813d0 100644 --- a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2019.vcxproj b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2019.vcxproj index 9aeda6044..7a5efa2e6 100644 --- a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2022.vcxproj b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2022.vcxproj index 8155f810b..71195f50a 100644 --- a/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/jacobiCudaGraphs/Makefile b/Samples/3_CUDA_Features/jacobiCudaGraphs/Makefile index ff0b63b08..b0fded602 100644 --- a/Samples/3_CUDA_Features/jacobiCudaGraphs/Makefile +++ b/Samples/3_CUDA_Features/jacobiCudaGraphs/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/jacobiCudaGraphs/README.md b/Samples/3_CUDA_Features/jacobiCudaGraphs/README.md index 9f0f24ad0..0370d726a 100644 --- a/Samples/3_CUDA_Features/jacobiCudaGraphs/README.md +++ b/Samples/3_CUDA_Features/jacobiCudaGraphs/README.md @@ -25,7 +25,7 @@ cudaExtent, cudaGraphLaunch, cudaGraphAddMemcpyNode, cudaMallocHost, cudaPitched ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2017.vcxproj b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2017.vcxproj index 4f4f19bb8..6e236cb14 100644 --- a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2019.vcxproj b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2019.vcxproj index 5fff35e59..9f78ed561 100644 --- a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2022.vcxproj b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2022.vcxproj index a1dcc71c5..a8982742d 100644 --- a/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/Makefile b/Samples/3_CUDA_Features/memMapIPCDrv/Makefile index 2ed35d4ca..4bbaa7252 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/Makefile +++ b/Samples/3_CUDA_Features/memMapIPCDrv/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/README.md b/Samples/3_CUDA_Features/memMapIPCDrv/README.md index 704c02a29..d15b4c923 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/README.md +++ b/Samples/3_CUDA_Features/memMapIPCDrv/README.md @@ -30,7 +30,7 @@ cuDeviceCanAccessPeer, cuMemImportFromShareableHandle, cuModuleLoadDataEx, cuMod ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj index 6ec4f3e05..aeb0450bd 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj index 65f4dedc2..31acef954 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2022.vcxproj b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2022.vcxproj index ae47cf79d..5a3707293 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIPCDrv_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIpc.cpp b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIpc.cpp index 19d6aa608..73cc62964 100644 --- a/Samples/3_CUDA_Features/memMapIPCDrv/memMapIpc.cpp +++ b/Samples/3_CUDA_Features/memMapIPCDrv/memMapIpc.cpp @@ -80,14 +80,14 @@ bool findModulePath(const char *, string &, char **, string &); // CU_MEM_HANDLE_TYPE_WIN32 meaning that NT HANDLEs will be used. The // ipcHandleTypeFlag variable is a convenience variable and is passed by value // to individual requests. -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) CUmemAllocationHandleType ipcHandleTypeFlag = CU_MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR; #else CUmemAllocationHandleType ipcHandleTypeFlag = CU_MEM_HANDLE_TYPE_WIN32; #endif -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) #define cpu_atomic_add32(a, x) __sync_add_and_fetch(a, x) #elif defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64) #define cpu_atomic_add32(a, x) InterlockedAdd((volatile LONG *)a, x) @@ -121,7 +121,7 @@ static void barrierWait(volatile int *barrier, volatile int *sense, // Windows-specific LPSECURITYATTRIBUTES void getDefaultSecurityDescriptor(CUmemAllocationProp *prop) { -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) return; #elif defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64) static const char sddl[] = "D:P(OA;;GARCSDWDWOCCDCLCSWLODTWPRPCRFA;;;WD)"; @@ -456,7 +456,7 @@ static void parentProcess(char *app) { checkCudaErrors(cuDeviceGetAttribute( &attributeVal, CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED, devices[i])); -#if defined(__linux__) +#if defined(__linux__) || defined(__QNX__) checkCudaErrors(cuDeviceGetAttribute( &deviceSupportsIpcHandle, CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED, diff --git a/Samples/3_CUDA_Features/newdelete/Makefile b/Samples/3_CUDA_Features/newdelete/Makefile index a9284d9ad..62d559bd1 100644 --- a/Samples/3_CUDA_Features/newdelete/Makefile +++ b/Samples/3_CUDA_Features/newdelete/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/newdelete/README.md b/Samples/3_CUDA_Features/newdelete/README.md index b0a78947e..b28d236ad 100644 --- a/Samples/3_CUDA_Features/newdelete/README.md +++ b/Samples/3_CUDA_Features/newdelete/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaDeviceSetLimit, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/newdelete/newdelete_vs2017.vcxproj b/Samples/3_CUDA_Features/newdelete/newdelete_vs2017.vcxproj index c3ec63c72..1f9e4628c 100644 --- a/Samples/3_CUDA_Features/newdelete/newdelete_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/newdelete/newdelete_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/newdelete/newdelete_vs2019.vcxproj b/Samples/3_CUDA_Features/newdelete/newdelete_vs2019.vcxproj index 46e9d9469..7c9e690e8 100644 --- a/Samples/3_CUDA_Features/newdelete/newdelete_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/newdelete/newdelete_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/newdelete/newdelete_vs2022.vcxproj b/Samples/3_CUDA_Features/newdelete/newdelete_vs2022.vcxproj index 502541009..e273c0f46 100644 --- a/Samples/3_CUDA_Features/newdelete/newdelete_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/newdelete/newdelete_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/ptxjit/Makefile b/Samples/3_CUDA_Features/ptxjit/Makefile index 1dbec2771..d527d6312 100644 --- a/Samples/3_CUDA_Features/ptxjit/Makefile +++ b/Samples/3_CUDA_Features/ptxjit/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/ptxjit/README.md b/Samples/3_CUDA_Features/ptxjit/README.md index cc9902376..9f76f1575 100644 --- a/Samples/3_CUDA_Features/ptxjit/README.md +++ b/Samples/3_CUDA_Features/ptxjit/README.md @@ -30,7 +30,7 @@ cudaMalloc, cudaDriverGetVersion, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2017.vcxproj b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2017.vcxproj index a5ea5550d..2fba4834d 100644 --- a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2019.vcxproj b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2019.vcxproj index d8840cabf..cc631e4d0 100644 --- a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2022.vcxproj b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2022.vcxproj index 33554627e..5a4fb1b52 100644 --- a/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/ptxjit/ptxjit_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/simpleCudaGraphs/Makefile b/Samples/3_CUDA_Features/simpleCudaGraphs/Makefile index 4d10e5b1c..93413b8e5 100644 --- a/Samples/3_CUDA_Features/simpleCudaGraphs/Makefile +++ b/Samples/3_CUDA_Features/simpleCudaGraphs/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/simpleCudaGraphs/README.md b/Samples/3_CUDA_Features/simpleCudaGraphs/README.md index 3a531bd89..f0f4c86d2 100644 --- a/Samples/3_CUDA_Features/simpleCudaGraphs/README.md +++ b/Samples/3_CUDA_Features/simpleCudaGraphs/README.md @@ -25,7 +25,7 @@ cudaGraphClone, cudaExtent, cudaGraphLaunch, cudaStreamCreate, cudaLaunchHostFun ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj index 238c47992..389c20f3b 100644 --- a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2019.vcxproj b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2019.vcxproj index 98284f02f..05b80cd1f 100644 --- a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2022.vcxproj b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2022.vcxproj index ddc5a330a..ccda01a51 100644 --- a/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/simpleCudaGraphs/simpleCudaGraphs_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/tf32TensorCoreGemm/Makefile b/Samples/3_CUDA_Features/tf32TensorCoreGemm/Makefile index 90f9badd6..1ac43916c 100644 --- a/Samples/3_CUDA_Features/tf32TensorCoreGemm/Makefile +++ b/Samples/3_CUDA_Features/tf32TensorCoreGemm/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/tf32TensorCoreGemm/README.md b/Samples/3_CUDA_Features/tf32TensorCoreGemm/README.md index d0da41478..d7f389154 100644 --- a/Samples/3_CUDA_Features/tf32TensorCoreGemm/README.md +++ b/Samples/3_CUDA_Features/tf32TensorCoreGemm/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2017.vcxproj b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2017.vcxproj index 5b2ca2ff7..bb73ecde1 100644 --- a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2019.vcxproj b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2019.vcxproj index 4bdb6603d..f4d8adcf4 100644 --- a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2022.vcxproj b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2022.vcxproj index fac250eb4..4c20fef6f 100644 --- a/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/tf32TensorCoreGemm/tf32TensorCoreGemm_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/Makefile b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/Makefile index 2b14baa13..a98389f72 100644 --- a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/Makefile +++ b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/README.md b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/README.md index 58d4cfdc4..c177226db 100644 --- a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/README.md +++ b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/README.md @@ -25,7 +25,7 @@ cudaMemcpy, cudaFree, cudaDeviceGetAttribute, cudaMemset, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2017.vcxproj b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2017.vcxproj index b30b454b3..e6c339a6f 100644 --- a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2017.vcxproj +++ b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2019.vcxproj b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2019.vcxproj index 5fb034abd..ce039e0dc 100644 --- a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2019.vcxproj +++ b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2022.vcxproj b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2022.vcxproj index 7fff8605c..025d764c8 100644 --- a/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2022.vcxproj +++ b/Samples/3_CUDA_Features/warpAggregatedAtomicsCG/warpAggregatedAtomicsCG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2017.vcxproj index d4ea42af4..e210de5ed 100644 --- a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2019.vcxproj index 691d52f15..298b13bc2 100644 --- a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2022.vcxproj index b37f6c566..18ad7155b 100644 --- a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/FilterBorderControlNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/Makefile b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/Makefile index 479027b13..e19cd92ac 100644 --- a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/Makefile +++ b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/README.md b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/README.md index e0aa381d1..3cd4a91b8 100644 --- a/Samples/4_CUDA_Libraries/FilterBorderControlNPP/README.md +++ b/Samples/4_CUDA_Libraries/FilterBorderControlNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaDeviceReset, cudaSetDevice, cudaGetDeviceCount, cudaD ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/Makefile b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/Makefile index 4f3844c19..4f890a80c 100644 --- a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/Makefile +++ b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2017.vcxproj b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2017.vcxproj index af19db634..4034d3a53 100644 --- a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2019.vcxproj b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2019.vcxproj index 6370c38a6..df052e9ba 100644 --- a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2022.vcxproj b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2022.vcxproj index 34e84a85e..c8dbb814d 100644 --- a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/MersenneTwisterGP11213_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/README.md b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/README.md index 8a80dc03e..d64f4f709 100644 --- a/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/README.md +++ b/Samples/4_CUDA_Libraries/MersenneTwisterGP11213/README.md @@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaMallocHost, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/batchCUBLAS/Makefile b/Samples/4_CUDA_Libraries/batchCUBLAS/Makefile index 81b4d51be..1e813cf0d 100644 --- a/Samples/4_CUDA_Libraries/batchCUBLAS/Makefile +++ b/Samples/4_CUDA_Libraries/batchCUBLAS/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/batchCUBLAS/README.md b/Samples/4_CUDA_Libraries/batchCUBLAS/README.md index eedcbbcbc..05325ca73 100644 --- a/Samples/4_CUDA_Libraries/batchCUBLAS/README.md +++ b/Samples/4_CUDA_Libraries/batchCUBLAS/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaGetLastError, cudaDeviceSynchroniz ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2017.vcxproj b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2017.vcxproj index d558f12a9..366337a68 100644 --- a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2019.vcxproj b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2019.vcxproj index ad9dcd1f8..de7cd45ec 100644 --- a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2022.vcxproj b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2022.vcxproj index e375d131a..445f5cb12 100644 --- a/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/batchCUBLAS/batchCUBLAS_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/Makefile b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/Makefile index d984775af..27201be95 100644 --- a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/Makefile +++ b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/README.md b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/README.md index 6324ea355..28b1b3530 100644 --- a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/README.md +++ b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaMallocPitch, cudaFree, cudaDeviceGetAttribute, cudaMa ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj index 16b674926..ac5e1bd4e 100644 --- a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj index f3949f2df..e38256c6a 100644 --- a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2022.vcxproj index 85d8c31c9..4dad43f67 100644 --- a/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/batchedLabelMarkersAndLabelCompressionNPP/batchedLabelMarkersAndLabelCompressionNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/boxFilterNPP/Makefile b/Samples/4_CUDA_Libraries/boxFilterNPP/Makefile index 64fcaacd9..8b531a63b 100644 --- a/Samples/4_CUDA_Libraries/boxFilterNPP/Makefile +++ b/Samples/4_CUDA_Libraries/boxFilterNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/boxFilterNPP/README.md b/Samples/4_CUDA_Libraries/boxFilterNPP/README.md index a157bf865..32133125d 100644 --- a/Samples/4_CUDA_Libraries/boxFilterNPP/README.md +++ b/Samples/4_CUDA_Libraries/boxFilterNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaDriverGetVersion ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2017.vcxproj index 7f5c9e49f..b2f443b32 100644 --- a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2019.vcxproj index d55e4f701..359195e9f 100644 --- a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2022.vcxproj index 4e31516fa..7a908eb88 100644 --- a/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/boxFilterNPP/boxFilterNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/Makefile b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/Makefile index 1b99eafc1..5afef823d 100644 --- a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/Makefile +++ b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/README.md b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/README.md index a8fdeaec3..32f339966 100644 --- a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/README.md +++ b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaFree, cudaSetDevice, cudaGetDeviceCount, cudaDeviceIn ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2017.vcxproj index dbc150a59..e46a9b627 100644 --- a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2019.vcxproj index eec60be23..19a29ad21 100644 --- a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2022.vcxproj index b5b97511b..13c28a9bc 100644 --- a/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cannyEdgeDetectorNPP/cannyEdgeDetectorNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradient/Makefile b/Samples/4_CUDA_Libraries/conjugateGradient/Makefile index adbd1e651..31300fd3e 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradient/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradient/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradient/README.md b/Samples/4_CUDA_Libraries/conjugateGradient/README.md index 0a06a76a4..13fbaa978 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradient/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradient/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2017.vcxproj index 4aa7c82ef..e05f9b9d6 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2019.vcxproj index 8ae8e6e81..7058a1beb 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2022.vcxproj index e9b3e1523..d1dfd7e46 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradient/conjugateGradient_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/Makefile b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/Makefile index 023e27789..54918c627 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/README.md b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/README.md index eecd04ba5..d7dc1bc25 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/README.md @@ -30,7 +30,7 @@ cudaGraphInstantiate, cudaStreamDestroy, cudaStreamBeginCapture, cudaFree, cudaM ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2017.vcxproj index 68c765417..9fbac187a 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2019.vcxproj index 99c1068a2..b67a0cef8 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2022.vcxproj index 8aa21e341..59b4c78bb 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientCudaGraphs/conjugateGradientCudaGraphs_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/Makefile b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/Makefile index 5feec1161..e99a6e5d7 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/README.md b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/README.md index a2d80e737..6667faf07 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/README.md @@ -30,7 +30,7 @@ cudaFree, cudaMallocManaged, cudaDeviceSynchronize, cudaEventRecord, cudaLaunchC ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2017.vcxproj index 896696188..da9eb9e14 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2019.vcxproj index 1d622c34d..e4dcf97d4 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2022.vcxproj index 56341df38..e1487d4c2 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiBlockCG/conjugateGradientMultiBlockCG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/Makefile b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/Makefile index 960c7f81d..ed7a55507 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/README.md b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/README.md index 8935fc08a..5553a7eff 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/README.md @@ -30,7 +30,7 @@ cudaHostAlloc, cudaMemPrefetchAsync, cudaFree, cudaLaunchCooperativeKernel, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2017.vcxproj index bfa5bd7db..d461b8c79 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2019.vcxproj index 6dbc02e30..79967f304 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2022.vcxproj index c20c196df..03a401d1d 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientMultiDeviceCG/conjugateGradientMultiDeviceCG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/Makefile b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/Makefile index a8439da78..cf632f1d2 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/README.md b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/README.md index 94c2d71e6..a7b0f0ab8 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaMemset, cudaMalloc, cudaGetDeviceProperties ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2017.vcxproj index 16fed6ba8..4b27df416 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2019.vcxproj index a06dda35a..b81793137 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2022.vcxproj index 9a3a49cce..b7b5a26f9 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientPrecond/conjugateGradientPrecond_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientUM/Makefile b/Samples/4_CUDA_Libraries/conjugateGradientUM/Makefile index aef6a0d59..f10e14c5a 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientUM/Makefile +++ b/Samples/4_CUDA_Libraries/conjugateGradientUM/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/conjugateGradientUM/README.md b/Samples/4_CUDA_Libraries/conjugateGradientUM/README.md index 2e34c66ab..ac93a42f2 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientUM/README.md +++ b/Samples/4_CUDA_Libraries/conjugateGradientUM/README.md @@ -28,7 +28,7 @@ cudaFree, cudaMallocManaged, cudaDeviceSynchronize, cudaMalloc, cudaGetDevicePro ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2017.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2017.vcxproj index 7f186e699..5c58c38b3 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2019.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2019.vcxproj index ea1ec6f93..2809c19a4 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2022.vcxproj b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2022.vcxproj index 8fe688796..a74a7d0a0 100644 --- a/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/conjugateGradientUM/conjugateGradientUM_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuDLAErrorReporting/Makefile b/Samples/4_CUDA_Libraries/cuDLAErrorReporting/Makefile index 02d79f4a4..25012e427 100644 --- a/Samples/4_CUDA_Libraries/cuDLAErrorReporting/Makefile +++ b/Samples/4_CUDA_Libraries/cuDLAErrorReporting/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuDLAErrorReporting/README.md b/Samples/4_CUDA_Libraries/cuDLAErrorReporting/README.md index f1c59a24a..38db6c24c 100644 --- a/Samples/4_CUDA_Libraries/cuDLAErrorReporting/README.md +++ b/Samples/4_CUDA_Libraries/cuDLAErrorReporting/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaGetErrorName, cudaSe ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuDLAHybridMode/Makefile b/Samples/4_CUDA_Libraries/cuDLAHybridMode/Makefile index 26f3645ed..6e77489b6 100644 --- a/Samples/4_CUDA_Libraries/cuDLAHybridMode/Makefile +++ b/Samples/4_CUDA_Libraries/cuDLAHybridMode/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuDLAHybridMode/README.md b/Samples/4_CUDA_Libraries/cuDLAHybridMode/README.md index 93086b66f..057f79433 100644 --- a/Samples/4_CUDA_Libraries/cuDLAHybridMode/README.md +++ b/Samples/4_CUDA_Libraries/cuDLAHybridMode/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaGetErrorName, cudaSe ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/Makefile b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/Makefile index 8bbd3e20f..5db3f123e 100644 --- a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/Makefile +++ b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/README.md b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/README.md index 4761d7ab6..0a765e8bf 100644 --- a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/README.md +++ b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsHybrid/README.md @@ -27,7 +27,7 @@ cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaGetErrorName, cudaSe ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/Makefile b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/Makefile index aa97778f9..bc6af6696 100644 --- a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/Makefile +++ b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -363,7 +376,7 @@ endif ALL_CCFLAGS += --std=c++11 --threads 0 -LIBRARIES += -lcudla -lnvscibuf -lnvscisync +LIBRARIES += -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia -lcudla -lnvscibuf -lnvscisync ifeq ($(SAMPLE_ENABLED),0) EXEC ?= @echo "[@]" diff --git a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/NsightEclipse.xml b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/NsightEclipse.xml index 341a6c76e..567922435 100644 --- a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/NsightEclipse.xml @@ -27,6 +27,7 @@ nvscisync + $(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia true main.cpp diff --git a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/README.md b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/README.md index bab80837e..fc3e85046 100644 --- a/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/README.md +++ b/Samples/4_CUDA_Libraries/cuDLALayerwiseStatsStandalone/README.md @@ -27,7 +27,7 @@ aarch64 ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/Makefile b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/Makefile index be7d600aa..5b05995dd 100644 --- a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/Makefile +++ b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -363,7 +376,7 @@ endif ALL_CCFLAGS += --std=c++11 --threads 0 -LIBRARIES += -lcudla -lnvscibuf -lnvscisync +LIBRARIES += -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia -lcudla -lnvscibuf -lnvscisync ifeq ($(SAMPLE_ENABLED),0) EXEC ?= @echo "[@]" diff --git a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/NsightEclipse.xml b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/NsightEclipse.xml index 7816fa188..867161752 100644 --- a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/NsightEclipse.xml @@ -27,6 +27,7 @@ nvscisync + $(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia true main.cpp diff --git a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/README.md b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/README.md index 2115512fd..8f7249016 100644 --- a/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/README.md +++ b/Samples/4_CUDA_Libraries/cuDLAStandaloneMode/README.md @@ -27,7 +27,7 @@ aarch64 ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/Makefile b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/Makefile index 6218c90d9..c278c598e 100644 --- a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/Makefile +++ b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/README.md b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/README.md index d1d7995ac..c21dedd4f 100644 --- a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/README.md +++ b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaStreamDestroy, cudaFree, cudaDeviceSynchronize, cudaMemset, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2017.vcxproj index b7aeb9ba3..9c62816b8 100644 --- a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2019.vcxproj index b0ec7cccd..8f13a690a 100644 --- a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2022.vcxproj index 45a2be689..1d866d4d7 100644 --- a/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverDn_LinearSolver/cuSolverDn_LinearSolver_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverRf/Makefile b/Samples/4_CUDA_Libraries/cuSolverRf/Makefile index 647f7558d..1d8e14ca2 100644 --- a/Samples/4_CUDA_Libraries/cuSolverRf/Makefile +++ b/Samples/4_CUDA_Libraries/cuSolverRf/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuSolverRf/README.md b/Samples/4_CUDA_Libraries/cuSolverRf/README.md index 8c2b2a4ab..15dbc1643 100644 --- a/Samples/4_CUDA_Libraries/cuSolverRf/README.md +++ b/Samples/4_CUDA_Libraries/cuSolverRf/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaStreamDestroy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2017.vcxproj index c6daada3e..3708ac5ca 100644 --- a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2019.vcxproj index 17b4a26fe..61e9154f0 100644 --- a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2022.vcxproj index 0d9ab835a..24f187557 100644 --- a/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverRf/cuSolverRf_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/Makefile b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/Makefile index df3ebf358..ba88c0cb7 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/Makefile +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/README.md b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/README.md index 1c1c449f1..5f46bd1fa 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/README.md +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/README.md @@ -33,7 +33,7 @@ cudaStreamDestroy, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaStreamCreate ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2017.vcxproj index 8b8d533ea..12ab6d13e 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2019.vcxproj index 3458a529c..7d68f8ce8 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2022.vcxproj index 45cb23361..3efa6975a 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LinearSolver/cuSolverSp_LinearSolver_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/Makefile b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/Makefile index 652666570..06b740002 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/Makefile +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/README.md b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/README.md index 8fb030a00..7273ac705 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/README.md +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaStreamDestroy, cudaFree, cudaMalloc, cudaStreamCreate ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2017.vcxproj index bb157a2de..474437eec 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2019.vcxproj index af61d7a05..64d5259db 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2022.vcxproj index e760219e1..648827858 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelCholesky/cuSolverSp_LowlevelCholesky_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/Makefile b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/Makefile index 85adca6fd..da213be65 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/Makefile +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/README.md b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/README.md index 543df6caf..a3c2ad5d2 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/README.md +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/README.md @@ -33,7 +33,7 @@ cudaMemcpy, cudaStreamDestroy, cudaFree, cudaMalloc, cudaStreamCreate ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2017.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2017.vcxproj index 393e60bd9..cf8d7ba18 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2019.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2019.vcxproj index c6d2fbecf..1dd545edc 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2022.vcxproj b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2022.vcxproj index 76eb797f9..c28bf3660 100644 --- a/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/cuSolverSp_LowlevelQR/cuSolverSp_LowlevelQR_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/cudaNvSci/Makefile b/Samples/4_CUDA_Libraries/cudaNvSci/Makefile index 9fed51ffb..ac09bb287 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSci/Makefile +++ b/Samples/4_CUDA_Libraries/cudaNvSci/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -415,7 +428,7 @@ endif ALL_CCFLAGS += --std=c++11 --threads 0 -LIBRARIES += -lnvscibuf -lnvscisync +LIBRARIES += -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia -lnvscibuf -lnvscisync ifeq ($(SAMPLE_ENABLED),0) EXEC ?= @echo "[@]" diff --git a/Samples/4_CUDA_Libraries/cudaNvSci/NsightEclipse.xml b/Samples/4_CUDA_Libraries/cudaNvSci/NsightEclipse.xml index 456007c67..704697bab 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSci/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/cudaNvSci/NsightEclipse.xml @@ -62,6 +62,7 @@ nvscisync + $(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia true main.cpp diff --git a/Samples/4_CUDA_Libraries/cudaNvSci/README.md b/Samples/4_CUDA_Libraries/cudaNvSci/README.md index 106fc721a..06dd3e56a 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSci/README.md +++ b/Samples/4_CUDA_Libraries/cudaNvSci/README.md @@ -33,7 +33,7 @@ cudaExternalMemoryGetMappedBuffer, cudaImportExternalSemaphore, cudaDeviceGetAtt ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/Makefile b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/Makefile index 48ccd9de2..05d7a7af7 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/Makefile +++ b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -426,7 +439,7 @@ endif ALL_CCFLAGS += --std=c++11 --threads 0 -LIBRARIES += -lnvscibuf -lnvscisync -lnvmedia +LIBRARIES += -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia -lnvscibuf -lnvscisync -lnvmedia ifeq ($(SAMPLE_ENABLED),0) EXEC ?= @echo "[@]" diff --git a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/NsightEclipse.xml b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/NsightEclipse.xml index fef560b25..55d2d1312 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/NsightEclipse.xml @@ -58,6 +58,7 @@ nvmedia + $(TARGET_FS)/usr/lib/aarch64-linux-gnu/nvidia true main.cpp diff --git a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/README.md b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/README.md index a0053bf44..8106f9c15 100644 --- a/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/README.md +++ b/Samples/4_CUDA_Libraries/cudaNvSciNvMedia/README.md @@ -33,7 +33,7 @@ cudaImportExternalSemaphore, cudaGetMipmappedArrayLevel, cudaSetDevice, cudaDest ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/freeImageInteropNPP/Makefile b/Samples/4_CUDA_Libraries/freeImageInteropNPP/Makefile index b3c105adf..5a42c1888 100644 --- a/Samples/4_CUDA_Libraries/freeImageInteropNPP/Makefile +++ b/Samples/4_CUDA_Libraries/freeImageInteropNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/freeImageInteropNPP/README.md b/Samples/4_CUDA_Libraries/freeImageInteropNPP/README.md index cece4a0b9..1c467a99a 100644 --- a/Samples/4_CUDA_Libraries/freeImageInteropNPP/README.md +++ b/Samples/4_CUDA_Libraries/freeImageInteropNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaSetDevice, cudaGetDeviceCount, cudaDeviceInit, cudaDr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2017.vcxproj index 0d1da49b1..762ea36cf 100644 --- a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2019.vcxproj index 561d8a05a..e598a9f03 100644 --- a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2022.vcxproj index 2c614b09f..a73c199c7 100644 --- a/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/freeImageInteropNPP/freeImageInteropNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/histEqualizationNPP/Makefile b/Samples/4_CUDA_Libraries/histEqualizationNPP/Makefile index a3c4248c8..c2a556d81 100644 --- a/Samples/4_CUDA_Libraries/histEqualizationNPP/Makefile +++ b/Samples/4_CUDA_Libraries/histEqualizationNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/histEqualizationNPP/README.md b/Samples/4_CUDA_Libraries/histEqualizationNPP/README.md index ec761042d..0f19949bf 100644 --- a/Samples/4_CUDA_Libraries/histEqualizationNPP/README.md +++ b/Samples/4_CUDA_Libraries/histEqualizationNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaMemcpy, cudaFree, cudaSetDevice, cudaGetDeviceCount, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2017.vcxproj index d7db4388f..8c156fdf6 100644 --- a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2019.vcxproj index 6e3f50f46..0f9cad5f4 100644 --- a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2022.vcxproj index dd5a22a93..9e594c27c 100644 --- a/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/histEqualizationNPP/histEqualizationNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/jitLto/Makefile b/Samples/4_CUDA_Libraries/jitLto/Makefile index 552eb2e87..9b6cc500f 100644 --- a/Samples/4_CUDA_Libraries/jitLto/Makefile +++ b/Samples/4_CUDA_Libraries/jitLto/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/jitLto/README.md b/Samples/4_CUDA_Libraries/jitLto/README.md index f3a1ff3ca..d1bf0e4e0 100644 --- a/Samples/4_CUDA_Libraries/jitLto/README.md +++ b/Samples/4_CUDA_Libraries/jitLto/README.md @@ -30,7 +30,7 @@ cuModuleLoad, cuModuleLoadDataEx, cuModuleGetFunction, cuMemAlloc, cuMemFree, cu ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2017.vcxproj b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2017.vcxproj index b1e8d29a8..b4f3222d8 100644 --- a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2019.vcxproj b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2019.vcxproj index 76df93e22..af83084aa 100644 --- a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2022.vcxproj b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2022.vcxproj index 1cdec4d5d..6f91b8b3b 100644 --- a/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/jitLto/jitLto_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/lineOfSight/Makefile b/Samples/4_CUDA_Libraries/lineOfSight/Makefile index 54011cbd1..0e1042439 100644 --- a/Samples/4_CUDA_Libraries/lineOfSight/Makefile +++ b/Samples/4_CUDA_Libraries/lineOfSight/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/lineOfSight/README.md b/Samples/4_CUDA_Libraries/lineOfSight/README.md index 8dfb9159b..41215bd86 100644 --- a/Samples/4_CUDA_Libraries/lineOfSight/README.md +++ b/Samples/4_CUDA_Libraries/lineOfSight/README.md @@ -27,7 +27,7 @@ cudaCreateChannelDesc, cudaMallocArray, cudaFreeArray, cudaDeviceSynchronize, cu ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2017.vcxproj b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2017.vcxproj index c4c405e97..8eb4f564c 100644 --- a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2019.vcxproj b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2019.vcxproj index 704c323db..36f2383ba 100644 --- a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2022.vcxproj b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2022.vcxproj index 372958563..e048d20e6 100644 --- a/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/lineOfSight/lineOfSight_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/Makefile b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/Makefile index c781defa6..d23e2b9dc 100644 --- a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/Makefile +++ b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/README.md b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/README.md index 1f04407a6..b21ed988d 100644 --- a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/README.md +++ b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaEventSynchronize, cudaEventRecord, cudaMalloc, cudaEve ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2017.vcxproj b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2017.vcxproj index 61d20323c..53fdc902e 100644 --- a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2019.vcxproj b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2019.vcxproj index 4b5af02b7..d80e4c11d 100644 --- a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2022.vcxproj b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2022.vcxproj index aec61c997..f6b274324 100644 --- a/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/matrixMulCUBLAS/matrixMulCUBLAS_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG/Makefile b/Samples/4_CUDA_Libraries/nvJPEG/Makefile index 473813f53..c4c6e29a1 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/Makefile +++ b/Samples/4_CUDA_Libraries/nvJPEG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -289,11 +302,6 @@ ifeq ($(TARGET_ARCH),aarch64) SAMPLE_ENABLED := 0 endif endif -# This sample is not supported on sbsa -ifeq ($(TARGET_ARCH),sbsa) - $(info >>> WARNING - nvJPEG is not supported on sbsa - waiving sample <<<) - SAMPLE_ENABLED := 0 -endif ALL_LDFLAGS := ALL_LDFLAGS += $(ALL_CCFLAGS) diff --git a/Samples/4_CUDA_Libraries/nvJPEG/NsightEclipse.xml b/Samples/4_CUDA_Libraries/nvJPEG/NsightEclipse.xml index 3875c29c4..8a33531d3 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/nvJPEG/NsightEclipse.xml @@ -60,6 +60,9 @@ qnx + + sbsa + 3.5 diff --git a/Samples/4_CUDA_Libraries/nvJPEG/README.md b/Samples/4_CUDA_Libraries/nvJPEG/README.md index 76acd15a5..08f1be00a 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/README.md +++ b/Samples/4_CUDA_Libraries/nvJPEG/README.md @@ -28,7 +28,7 @@ cudaHostAlloc, cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaEvent ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2017.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2017.vcxproj index 024c2f1dc..7aac56dbd 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2019.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2019.vcxproj index a6d24ea3f..b58eda102 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2022.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2022.vcxproj index cc0634040..cd6ea3c8c 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG/nvJPEG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/Makefile b/Samples/4_CUDA_Libraries/nvJPEG_encoder/Makefile index ed4cfe5ae..cd6e44840 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/Makefile +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) @@ -289,11 +302,6 @@ ifeq ($(TARGET_ARCH),aarch64) SAMPLE_ENABLED := 0 endif endif -# This sample is not supported on sbsa -ifeq ($(TARGET_ARCH),sbsa) - $(info >>> WARNING - nvJPEG_encoder is not supported on sbsa - waiving sample <<<) - SAMPLE_ENABLED := 0 -endif ALL_LDFLAGS := ALL_LDFLAGS += $(ALL_CCFLAGS) diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/NsightEclipse.xml b/Samples/4_CUDA_Libraries/nvJPEG_encoder/NsightEclipse.xml index 6436c0b27..e31c8518e 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/NsightEclipse.xml +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/NsightEclipse.xml @@ -57,6 +57,9 @@ qnx + + sbsa + 3.5 diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/README.md b/Samples/4_CUDA_Libraries/nvJPEG_encoder/README.md index e54657dae..cd3fbb217 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/README.md +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/README.md @@ -28,7 +28,7 @@ cudaFree, cudaGetErrorString, cudaEventSynchronize, cudaDeviceSynchronize, cudaE ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2017.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2017.vcxproj index 6851aac79..019737d4d 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2019.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2019.vcxproj index 57c661099..80dbb3370 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2022.vcxproj b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2022.vcxproj index d89823db0..9255c0ef7 100644 --- a/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/nvJPEG_encoder/nvJPEG_encoder_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/oceanFFT/Makefile b/Samples/4_CUDA_Libraries/oceanFFT/Makefile index 77705a1f3..fc133a356 100644 --- a/Samples/4_CUDA_Libraries/oceanFFT/Makefile +++ b/Samples/4_CUDA_Libraries/oceanFFT/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/oceanFFT/README.md b/Samples/4_CUDA_Libraries/oceanFFT/README.md index 77c929959..fe6f0713b 100644 --- a/Samples/4_CUDA_Libraries/oceanFFT/README.md +++ b/Samples/4_CUDA_Libraries/oceanFFT/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMalloc, cudaFree, cudaGraphicsResour ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2017.vcxproj b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2017.vcxproj index 80653b897..34a53e014 100644 --- a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2019.vcxproj b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2019.vcxproj index 505da9b4e..d1673803a 100644 --- a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2022.vcxproj b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2022.vcxproj index 98375d060..67e4f26cd 100644 --- a/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/oceanFFT/oceanFFT_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/randomFog/Makefile b/Samples/4_CUDA_Libraries/randomFog/Makefile index 8c96318cf..c2e1a6b33 100644 --- a/Samples/4_CUDA_Libraries/randomFog/Makefile +++ b/Samples/4_CUDA_Libraries/randomFog/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/randomFog/README.md b/Samples/4_CUDA_Libraries/randomFog/README.md index d42d5fa76..1181ed59c 100644 --- a/Samples/4_CUDA_Libraries/randomFog/README.md +++ b/Samples/4_CUDA_Libraries/randomFog/README.md @@ -30,7 +30,7 @@ cudaMalloc, cudaGetErrorString, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2017.vcxproj b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2017.vcxproj index 68db16606..5554d6718 100644 --- a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2019.vcxproj b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2019.vcxproj index 9e8ade90d..4846f8b32 100644 --- a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2022.vcxproj b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2022.vcxproj index a45719698..ee943bf9f 100644 --- a/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/randomFog/randomFog_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS/Makefile b/Samples/4_CUDA_Libraries/simpleCUBLAS/Makefile index 63225a72b..70e7d8f42 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS/README.md b/Samples/4_CUDA_Libraries/simpleCUBLAS/README.md index a96b9cfe5..64495d612 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS/README.md @@ -30,7 +30,7 @@ cudaMalloc, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2017.vcxproj index c89f099b2..0d5ff6254 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2019.vcxproj index c84679db4..72033b466 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2022.vcxproj index 43af9e747..525d4fc8d 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLASXT/Makefile b/Samples/4_CUDA_Libraries/simpleCUBLASXT/Makefile index f892667c4..7dad756a6 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLASXT/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUBLASXT/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUBLASXT/README.md b/Samples/4_CUDA_Libraries/simpleCUBLASXT/README.md index 3b4a4e625..443a32189 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLASXT/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUBLASXT/README.md @@ -30,7 +30,7 @@ cudaGetDeviceProperties, cudaGetDeviceCount, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2017.vcxproj index 67143c59b..862f96a30 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2019.vcxproj index 639015518..f92b1d76c 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2022.vcxproj index a4025ea2d..5f3b48aaf 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLASXT/simpleCUBLASXT_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/Makefile b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/Makefile index 461a74cf1..8c3001b96 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/README.md b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/README.md index d01b9a1da..4605545a3 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/README.md @@ -30,7 +30,7 @@ cudaGetErrorEnum, cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2017.vcxproj index d45361522..faf4de306 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2019.vcxproj index dad7fc393..d1104b996 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2022.vcxproj index 65182209d..9e0932942 100644 --- a/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUBLAS_LU/simpleCUBLAS_LU_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT/Makefile b/Samples/4_CUDA_Libraries/simpleCUFFT/Makefile index 4e209436f..5282afcf8 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUFFT/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT/README.md b/Samples/4_CUDA_Libraries/simpleCUFFT/README.md index 2da3f0750..cddeb1d53 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUFFT/README.md @@ -30,7 +30,7 @@ cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2017.vcxproj index 60950cd51..5e73a6515 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2019.vcxproj index 4292937a1..5dc6cc209 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2022.vcxproj index 45bcca7d3..fab046959 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT/simpleCUFFT_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/Makefile b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/Makefile index 15a3c68af..1a5d50d8e 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/README.md b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/README.md index 162193703..bbf62e0e2 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/README.md @@ -30,7 +30,7 @@ cudaXtFree, cudaMemcpy, cudaFree, cudaSetDevice, cudaGetDeviceCount, cudaDeviceS ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2017.vcxproj index 9fc878213..1e7ee2033 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2019.vcxproj index a8d25bb70..5ed650606 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2022.vcxproj index cac438bb8..02ccbb233 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/Makefile b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/Makefile index eb4c0c361..ab4f7c91c 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/README.md b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/README.md index a5b19e6ce..32795573a 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/README.md @@ -30,7 +30,7 @@ cudaXtFree, cudaSetDevice, cudaGetDeviceCount, cudaDeviceSynchronize, cudaGetDev ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2017.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2017.vcxproj index bfe9b8d85..35c0d1714 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2019.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2019.vcxproj index 51b2f7142..05a672144 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2022.vcxproj b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2022.vcxproj index 288c5540a..b4d7f2856 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_MGPU/simpleCUFFT_MGPU_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_callback/Makefile b/Samples/4_CUDA_Libraries/simpleCUFFT_callback/Makefile index 475d93aea..172f79a1c 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_callback/Makefile +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_callback/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/simpleCUFFT_callback/README.md b/Samples/4_CUDA_Libraries/simpleCUFFT_callback/README.md index e9fa27c54..7e3d8a462 100644 --- a/Samples/4_CUDA_Libraries/simpleCUFFT_callback/README.md +++ b/Samples/4_CUDA_Libraries/simpleCUFFT_callback/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaMemcpyFromSymbol, cudaGetDevice, cudaMalloc, cudaGetDe ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/Makefile b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/Makefile index 5379fcf71..dc94c8632 100644 --- a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/Makefile +++ b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/README.md b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/README.md index 5d719f32d..ab548cabe 100644 --- a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/README.md +++ b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaFree, cudaDeviceGetAttribute, cudaDriverGetVersion, c ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2017.vcxproj b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2017.vcxproj index f9012f182..cf2225140 100644 --- a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2017.vcxproj +++ b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2019.vcxproj b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2019.vcxproj index 606317421..a306232eb 100644 --- a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2019.vcxproj +++ b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2022.vcxproj b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2022.vcxproj index 214d48e81..2315351b0 100644 --- a/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2022.vcxproj +++ b/Samples/4_CUDA_Libraries/watershedSegmentationNPP/watershedSegmentationNPP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2017.vcxproj b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2017.vcxproj index 4c9a4fc4b..d3f2a94c4 100644 --- a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2019.vcxproj b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2019.vcxproj index 1a89e223f..646c6af61 100644 --- a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2022.vcxproj b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2022.vcxproj index 63066cebf..ff15d3f51 100644 --- a/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes/BlackScholes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes/Makefile b/Samples/5_Domain_Specific/BlackScholes/Makefile index c5886311e..0665dad99 100644 --- a/Samples/5_Domain_Specific/BlackScholes/Makefile +++ b/Samples/5_Domain_Specific/BlackScholes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/BlackScholes/README.md b/Samples/5_Domain_Specific/BlackScholes/README.md index 6e6f16a5b..3ea0baab8 100644 --- a/Samples/5_Domain_Specific/BlackScholes/README.md +++ b/Samples/5_Domain_Specific/BlackScholes/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaDeviceSynchronize, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2017.vcxproj b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2017.vcxproj index 40d52f990..1269021e0 100644 --- a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2019.vcxproj b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2019.vcxproj index aa7f24196..f98784095 100644 --- a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2022.vcxproj b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2022.vcxproj index e603ba4b8..7ac2934bf 100644 --- a/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/BlackScholes_nvrtc/BlackScholes_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/5_Domain_Specific/BlackScholes_nvrtc/Makefile b/Samples/5_Domain_Specific/BlackScholes_nvrtc/Makefile index c2b6f52b2..75aa63dd1 100644 --- a/Samples/5_Domain_Specific/BlackScholes_nvrtc/Makefile +++ b/Samples/5_Domain_Specific/BlackScholes_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/BlackScholes_nvrtc/README.md b/Samples/5_Domain_Specific/BlackScholes_nvrtc/README.md index 529337e99..d2cb2092b 100644 --- a/Samples/5_Domain_Specific/BlackScholes_nvrtc/README.md +++ b/Samples/5_Domain_Specific/BlackScholes_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2017.vcxproj b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2017.vcxproj index a5a33448a..d15ecc695 100644 --- a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2019.vcxproj b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2019.vcxproj index b75e953be..382028f68 100644 --- a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2022.vcxproj b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2022.vcxproj index d103afe9d..fe1b98ac6 100644 --- a/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/FDTD3d/FDTD3d_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/FDTD3d/Makefile b/Samples/5_Domain_Specific/FDTD3d/Makefile index 588f9bee8..6f78c2996 100644 --- a/Samples/5_Domain_Specific/FDTD3d/Makefile +++ b/Samples/5_Domain_Specific/FDTD3d/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/FDTD3d/README.md b/Samples/5_Domain_Specific/FDTD3d/README.md index 3e35c2ee9..f4cf10374 100644 --- a/Samples/5_Domain_Specific/FDTD3d/README.md +++ b/Samples/5_Domain_Specific/FDTD3d/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaMalloc, cudaFree, cudaFuncGetAttributes, cudaSetDevice, cudaGetD ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2017.vcxproj b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2017.vcxproj index 517090445..c1f102073 100644 --- a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2019.vcxproj b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2019.vcxproj index f550d3899..04a0fae9c 100644 --- a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2022.vcxproj b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2022.vcxproj index 9b721af5f..7d5ce3354 100644 --- a/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/HSOpticalFlow/HSOpticalFlow_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/HSOpticalFlow/Makefile b/Samples/5_Domain_Specific/HSOpticalFlow/Makefile index e532ed874..37cca0155 100644 --- a/Samples/5_Domain_Specific/HSOpticalFlow/Makefile +++ b/Samples/5_Domain_Specific/HSOpticalFlow/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/HSOpticalFlow/README.md b/Samples/5_Domain_Specific/HSOpticalFlow/README.md index 6759bc5a3..c48b998d3 100644 --- a/Samples/5_Domain_Specific/HSOpticalFlow/README.md +++ b/Samples/5_Domain_Specific/HSOpticalFlow/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaMemset, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/Mandelbrot/Makefile b/Samples/5_Domain_Specific/Mandelbrot/Makefile index b03fedeac..634131af4 100644 --- a/Samples/5_Domain_Specific/Mandelbrot/Makefile +++ b/Samples/5_Domain_Specific/Mandelbrot/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2017.vcxproj b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2017.vcxproj index be20b36dd..a65cf809f 100644 --- a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -121,6 +121,6 @@ - + diff --git a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2019.vcxproj b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2019.vcxproj index 8f72c7822..c8dc7a1a7 100644 --- a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2022.vcxproj b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2022.vcxproj index c64d0be51..718dbbb73 100644 --- a/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/Mandelbrot/Mandelbrot_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/Mandelbrot/README.md b/Samples/5_Domain_Specific/Mandelbrot/README.md index b41ab2e07..49605ec38 100644 --- a/Samples/5_Domain_Specific/Mandelbrot/README.md +++ b/Samples/5_Domain_Specific/Mandelbrot/README.md @@ -30,7 +30,7 @@ cudaGLUnmapBufferObject, cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaG ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/MonteCarloMultiGPU/Makefile b/Samples/5_Domain_Specific/MonteCarloMultiGPU/Makefile index f608ae9a4..ca5f212cf 100644 --- a/Samples/5_Domain_Specific/MonteCarloMultiGPU/Makefile +++ b/Samples/5_Domain_Specific/MonteCarloMultiGPU/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2017.vcxproj b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2017.vcxproj index cde141378..46f50fa75 100644 --- a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2019.vcxproj b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2019.vcxproj index 73ec1bb4d..540e7de25 100644 --- a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2022.vcxproj b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2022.vcxproj index b51147fb5..4e9178c46 100644 --- a/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/MonteCarloMultiGPU/README.md b/Samples/5_Domain_Specific/MonteCarloMultiGPU/README.md index 0d3c2a43f..dc1429ae1 100644 --- a/Samples/5_Domain_Specific/MonteCarloMultiGPU/README.md +++ b/Samples/5_Domain_Specific/MonteCarloMultiGPU/README.md @@ -30,7 +30,7 @@ cudaStreamDestroy, cudaMalloc, cudaFree, cudaMallocHost, cudaSetDevice, cudaEven ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/NV12toBGRandResize/Makefile b/Samples/5_Domain_Specific/NV12toBGRandResize/Makefile index 121a70cb1..bf4f3e801 100644 --- a/Samples/5_Domain_Specific/NV12toBGRandResize/Makefile +++ b/Samples/5_Domain_Specific/NV12toBGRandResize/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2017.vcxproj b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2017.vcxproj index ad90dbd35..560f7bc28 100644 --- a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2019.vcxproj b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2019.vcxproj index 7ad22653f..1620f5848 100644 --- a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2022.vcxproj b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2022.vcxproj index 7fca45eb0..dd01a9741 100644 --- a/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/NV12toBGRandResize/NV12toBGRandResize_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/NV12toBGRandResize/README.md b/Samples/5_Domain_Specific/NV12toBGRandResize/README.md index eb153295b..f6c3eee66 100644 --- a/Samples/5_Domain_Specific/NV12toBGRandResize/README.md +++ b/Samples/5_Domain_Specific/NV12toBGRandResize/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaStreamDestroy, cudaMalloc, cudaFree, cudaMallocManaged, cudaStre ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/SLID3D10Texture/README.md b/Samples/5_Domain_Specific/SLID3D10Texture/README.md index 41e5e9599..9ab9405a9 100644 --- a/Samples/5_Domain_Specific/SLID3D10Texture/README.md +++ b/Samples/5_Domain_Specific/SLID3D10Texture/README.md @@ -33,7 +33,7 @@ cudaGraphicsUnmapResources, cudaMalloc, cudaMallocPitch, cudaGetErrorString, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2017.vcxproj b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2017.vcxproj index 5babd8185..ded543b6b 100644 --- a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2019.vcxproj b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2019.vcxproj index 586dd121d..23d324366 100644 --- a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2022.vcxproj b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2022.vcxproj index 77987c275..b56cfdbf6 100644 --- a/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/SLID3D10Texture/SLID3D10Texture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobelFilter/Makefile b/Samples/5_Domain_Specific/SobelFilter/Makefile index 380500b43..47f7ca4ef 100644 --- a/Samples/5_Domain_Specific/SobelFilter/Makefile +++ b/Samples/5_Domain_Specific/SobelFilter/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/SobelFilter/README.md b/Samples/5_Domain_Specific/SobelFilter/README.md index 0b7804d73..7691119eb 100644 --- a/Samples/5_Domain_Specific/SobelFilter/README.md +++ b/Samples/5_Domain_Specific/SobelFilter/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2017.vcxproj b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2017.vcxproj index f7e2cd44f..cebcac4b1 100644 --- a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2019.vcxproj b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2019.vcxproj index 6cefc96ed..f8b6ab984 100644 --- a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2022.vcxproj b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2022.vcxproj index bb3fd0ac0..b2926d1e9 100644 --- a/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/SobelFilter/SobelFilter_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobolQRNG/Makefile b/Samples/5_Domain_Specific/SobolQRNG/Makefile index 3df0f5bc2..c1478305b 100644 --- a/Samples/5_Domain_Specific/SobolQRNG/Makefile +++ b/Samples/5_Domain_Specific/SobolQRNG/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/SobolQRNG/README.md b/Samples/5_Domain_Specific/SobolQRNG/README.md index 1bb837612..5ead5d1b1 100644 --- a/Samples/5_Domain_Specific/SobolQRNG/README.md +++ b/Samples/5_Domain_Specific/SobolQRNG/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaGetErrorString, cudaFree, cudaDeviceSynchronize, cudaGetDevice, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2017.vcxproj b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2017.vcxproj index 6446ca355..32bc67a25 100644 --- a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2019.vcxproj b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2019.vcxproj index c4de241ab..02abfca62 100644 --- a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2022.vcxproj b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2022.vcxproj index 401bbc1a3..e4620fdfd 100644 --- a/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/SobolQRNG/SobolQRNG_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/VFlockingD3D10/README.md b/Samples/5_Domain_Specific/VFlockingD3D10/README.md index 01ead5929..9d6fc0679 100644 --- a/Samples/5_Domain_Specific/VFlockingD3D10/README.md +++ b/Samples/5_Domain_Specific/VFlockingD3D10/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGetErrorString, cudaGraphi ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2017.vcxproj b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2017.vcxproj index 6403b0e5d..cddedfc6c 100644 --- a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2019.vcxproj b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2019.vcxproj index 155b47108..2219cf409 100644 --- a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2022.vcxproj b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2022.vcxproj index 75d5e65e7..f5c7f14e7 100644 --- a/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/VFlockingD3D10/VFlockingD3D10_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/bicubicTexture/Makefile b/Samples/5_Domain_Specific/bicubicTexture/Makefile index 1fa1bae8f..4d8608ad2 100644 --- a/Samples/5_Domain_Specific/bicubicTexture/Makefile +++ b/Samples/5_Domain_Specific/bicubicTexture/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/bicubicTexture/README.md b/Samples/5_Domain_Specific/bicubicTexture/README.md index 860e90654..c3f31ce95 100644 --- a/Samples/5_Domain_Specific/bicubicTexture/README.md +++ b/Samples/5_Domain_Specific/bicubicTexture/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaCreateChannelDesc, cudaMallocArray, cudaFreeArra ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2017.vcxproj b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2017.vcxproj index c0e224ebe..cbb89017a 100644 --- a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2019.vcxproj b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2019.vcxproj index ce7a4a879..2c35d23df 100644 --- a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2022.vcxproj b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2022.vcxproj index 356db7284..6186468b4 100644 --- a/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/bicubicTexture/bicubicTexture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/bilateralFilter/Makefile b/Samples/5_Domain_Specific/bilateralFilter/Makefile index 4410ff339..a8519637a 100644 --- a/Samples/5_Domain_Specific/bilateralFilter/Makefile +++ b/Samples/5_Domain_Specific/bilateralFilter/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/bilateralFilter/README.md b/Samples/5_Domain_Specific/bilateralFilter/README.md index 1a3e5bb32..12aa41b85 100644 --- a/Samples/5_Domain_Specific/bilateralFilter/README.md +++ b/Samples/5_Domain_Specific/bilateralFilter/README.md @@ -30,7 +30,7 @@ cudaRuntimeGetVersion, cudaGraphicsUnmapResources, cudaMallocPitch, cudaFree, cu ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2017.vcxproj b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2017.vcxproj index f8cbcf604..a89ab9a8f 100644 --- a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -120,6 +120,6 @@ - + diff --git a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2019.vcxproj b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2019.vcxproj index 76478a1e5..0b53fffe4 100644 --- a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -116,6 +116,6 @@ - + diff --git a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2022.vcxproj b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2022.vcxproj index 2bbf117c5..dc7e01c4d 100644 --- a/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/bilateralFilter/bilateralFilter_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -116,6 +116,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions/Makefile b/Samples/5_Domain_Specific/binomialOptions/Makefile index 7cd0426fc..485f7f0fb 100644 --- a/Samples/5_Domain_Specific/binomialOptions/Makefile +++ b/Samples/5_Domain_Specific/binomialOptions/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/binomialOptions/README.md b/Samples/5_Domain_Specific/binomialOptions/README.md index 86723a19a..d0da7371e 100644 --- a/Samples/5_Domain_Specific/binomialOptions/README.md +++ b/Samples/5_Domain_Specific/binomialOptions/README.md @@ -27,7 +27,7 @@ cudaDeviceSynchronize, cudaMemcpyToSymbol, cudaMemcpyFromSymbol ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2017.vcxproj b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2017.vcxproj index a52532b98..6e7cf9c3c 100644 --- a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2019.vcxproj b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2019.vcxproj index cf362e90d..3b34983f0 100644 --- a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2022.vcxproj b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2022.vcxproj index 1a00dbbd4..f6d0f3599 100644 --- a/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions/binomialOptions_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions_nvrtc/Makefile b/Samples/5_Domain_Specific/binomialOptions_nvrtc/Makefile index 1a9eca457..0bca70389 100644 --- a/Samples/5_Domain_Specific/binomialOptions_nvrtc/Makefile +++ b/Samples/5_Domain_Specific/binomialOptions_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/binomialOptions_nvrtc/README.md b/Samples/5_Domain_Specific/binomialOptions_nvrtc/README.md index 15e8c5773..6e81d3f47 100644 --- a/Samples/5_Domain_Specific/binomialOptions_nvrtc/README.md +++ b/Samples/5_Domain_Specific/binomialOptions_nvrtc/README.md @@ -33,7 +33,7 @@ cudaBlockSize, cudaGridSize ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2017.vcxproj b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2017.vcxproj index 8c626d62c..de2f66173 100644 --- a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2019.vcxproj b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2019.vcxproj index e8a478a53..89c7d6c00 100644 --- a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2022.vcxproj b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2022.vcxproj index efcbad126..730add2bd 100644 --- a/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/binomialOptions_nvrtc/binomialOptions_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/convolutionFFT2D/Makefile b/Samples/5_Domain_Specific/convolutionFFT2D/Makefile index 4297d56cc..34442f689 100644 --- a/Samples/5_Domain_Specific/convolutionFFT2D/Makefile +++ b/Samples/5_Domain_Specific/convolutionFFT2D/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/convolutionFFT2D/README.md b/Samples/5_Domain_Specific/convolutionFFT2D/README.md index d1fb5bb9b..7a3c37406 100644 --- a/Samples/5_Domain_Specific/convolutionFFT2D/README.md +++ b/Samples/5_Domain_Specific/convolutionFFT2D/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaFree, cudaDestroyTextureObject, cudaDeviceSynchronize, cudaCreat ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2017.vcxproj b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2017.vcxproj index ef5afa1b0..d9286bfab 100644 --- a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2019.vcxproj b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2019.vcxproj index 9d4b8d97a..62fbfacbb 100644 --- a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2022.vcxproj b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2022.vcxproj index 578217612..a74e2da90 100644 --- a/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/convolutionFFT2D/convolutionFFT2D_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/dwtHaar1D/Makefile b/Samples/5_Domain_Specific/dwtHaar1D/Makefile index 0ee7c65f7..f7c8276cc 100644 --- a/Samples/5_Domain_Specific/dwtHaar1D/Makefile +++ b/Samples/5_Domain_Specific/dwtHaar1D/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/dwtHaar1D/README.md b/Samples/5_Domain_Specific/dwtHaar1D/README.md index a4ca4ee71..23a55b776 100644 --- a/Samples/5_Domain_Specific/dwtHaar1D/README.md +++ b/Samples/5_Domain_Specific/dwtHaar1D/README.md @@ -27,7 +27,7 @@ cudaMalloc, cudaMemcpy, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2017.vcxproj b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2017.vcxproj index bd039e30b..e85d18bfe 100644 --- a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2019.vcxproj b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2019.vcxproj index 9bd5ff2ed..0aa77dd08 100644 --- a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2022.vcxproj b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2022.vcxproj index d4e82e001..d67b6431b 100644 --- a/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/dwtHaar1D/dwtHaar1D_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/dxtc/Makefile b/Samples/5_Domain_Specific/dxtc/Makefile index 1b9e06b10..8e5751338 100644 --- a/Samples/5_Domain_Specific/dxtc/Makefile +++ b/Samples/5_Domain_Specific/dxtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/dxtc/README.md b/Samples/5_Domain_Specific/dxtc/README.md index 1023b438c..c3ff39ebb 100644 --- a/Samples/5_Domain_Specific/dxtc/README.md +++ b/Samples/5_Domain_Specific/dxtc/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaGetDevice, cudaMalloc, cudaGetD ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/dxtc/dxtc_vs2017.vcxproj b/Samples/5_Domain_Specific/dxtc/dxtc_vs2017.vcxproj index a59250baa..0a39fd0d6 100644 --- a/Samples/5_Domain_Specific/dxtc/dxtc_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/dxtc/dxtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/dxtc/dxtc_vs2019.vcxproj b/Samples/5_Domain_Specific/dxtc/dxtc_vs2019.vcxproj index db76bb328..269dd0e18 100644 --- a/Samples/5_Domain_Specific/dxtc/dxtc_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/dxtc/dxtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/dxtc/dxtc_vs2022.vcxproj b/Samples/5_Domain_Specific/dxtc/dxtc_vs2022.vcxproj index f08cad42e..f0e656aea 100644 --- a/Samples/5_Domain_Specific/dxtc/dxtc_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/dxtc/dxtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/fastWalshTransform/Makefile b/Samples/5_Domain_Specific/fastWalshTransform/Makefile index ca79a87f9..b0b08d90e 100644 --- a/Samples/5_Domain_Specific/fastWalshTransform/Makefile +++ b/Samples/5_Domain_Specific/fastWalshTransform/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/fastWalshTransform/README.md b/Samples/5_Domain_Specific/fastWalshTransform/README.md index 2e7eb491b..46236c1cc 100644 --- a/Samples/5_Domain_Specific/fastWalshTransform/README.md +++ b/Samples/5_Domain_Specific/fastWalshTransform/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMemset, cudaMalloc ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2017.vcxproj b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2017.vcxproj index 387db453b..81491b260 100644 --- a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2019.vcxproj b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2019.vcxproj index 9173630a2..57900d3d6 100644 --- a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2022.vcxproj b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2022.vcxproj index 14b6b8cba..a13af4569 100644 --- a/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/fastWalshTransform/fastWalshTransform_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -104,6 +104,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsD3D9/README.md b/Samples/5_Domain_Specific/fluidsD3D9/README.md index 7518ae741..84e45b07a 100644 --- a/Samples/5_Domain_Specific/fluidsD3D9/README.md +++ b/Samples/5_Domain_Specific/fluidsD3D9/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2017.vcxproj b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2017.vcxproj index a905deffd..13ddf7033 100644 --- a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2019.vcxproj b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2019.vcxproj index 82a933173..3d59d6c84 100644 --- a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2022.vcxproj b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2022.vcxproj index 373ab5ad3..62924a779 100644 --- a/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/fluidsD3D9/fluidsD3D9_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsGL/Makefile b/Samples/5_Domain_Specific/fluidsGL/Makefile index acccf6a01..f295425a1 100644 --- a/Samples/5_Domain_Specific/fluidsGL/Makefile +++ b/Samples/5_Domain_Specific/fluidsGL/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/fluidsGL/README.md b/Samples/5_Domain_Specific/fluidsGL/README.md index e667c2705..fa66f2f0a 100644 --- a/Samples/5_Domain_Specific/fluidsGL/README.md +++ b/Samples/5_Domain_Specific/fluidsGL/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2017.vcxproj b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2017.vcxproj index 45677537f..6fb0c66ae 100644 --- a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -120,6 +120,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2019.vcxproj b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2019.vcxproj index faadbe595..0c40d0b19 100644 --- a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -116,6 +116,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2022.vcxproj b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2022.vcxproj index beaf36d5d..deee87ab0 100644 --- a/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/fluidsGL/fluidsGL_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -116,6 +116,6 @@ - + diff --git a/Samples/5_Domain_Specific/fluidsGLES/Makefile b/Samples/5_Domain_Specific/fluidsGLES/Makefile index 8fa4ca3a7..b57de511d 100644 --- a/Samples/5_Domain_Specific/fluidsGLES/Makefile +++ b/Samples/5_Domain_Specific/fluidsGLES/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/fluidsGLES/README.md b/Samples/5_Domain_Specific/fluidsGLES/README.md index 866dcda47..1abac27e4 100644 --- a/Samples/5_Domain_Specific/fluidsGLES/README.md +++ b/Samples/5_Domain_Specific/fluidsGLES/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaFreeArray, cudaFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/marchingCubes/Makefile b/Samples/5_Domain_Specific/marchingCubes/Makefile index 30f40e578..f82741656 100644 --- a/Samples/5_Domain_Specific/marchingCubes/Makefile +++ b/Samples/5_Domain_Specific/marchingCubes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/marchingCubes/README.md b/Samples/5_Domain_Specific/marchingCubes/README.md index db8542951..ae1a2f4db 100644 --- a/Samples/5_Domain_Specific/marchingCubes/README.md +++ b/Samples/5_Domain_Specific/marchingCubes/README.md @@ -30,7 +30,7 @@ cudaGLUnmapBufferObject, cudaGraphicsUnmapResources, cudaCreateChannelDesc, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2017.vcxproj b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2017.vcxproj index 599049121..fdf1efa2a 100644 --- a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2019.vcxproj b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2019.vcxproj index fa1654b20..52afc39ee 100644 --- a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -115,6 +115,6 @@ - + diff --git a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2022.vcxproj b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2022.vcxproj index 2d4ddd629..5f823086e 100644 --- a/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/marchingCubes/marchingCubes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -115,6 +115,6 @@ - + diff --git a/Samples/5_Domain_Specific/nbody/Makefile b/Samples/5_Domain_Specific/nbody/Makefile index e218084bd..b6a103767 100644 --- a/Samples/5_Domain_Specific/nbody/Makefile +++ b/Samples/5_Domain_Specific/nbody/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/nbody/README.md b/Samples/5_Domain_Specific/nbody/README.md index eba10a8d1..35a76ed88 100644 --- a/Samples/5_Domain_Specific/nbody/README.md +++ b/Samples/5_Domain_Specific/nbody/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaSetDeviceFlags, cudaGraphicsResourceSetMapFlags, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/nbody/nbody_vs2017.vcxproj b/Samples/5_Domain_Specific/nbody/nbody_vs2017.vcxproj index c20d48082..893f7a237 100644 --- a/Samples/5_Domain_Specific/nbody/nbody_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/nbody/nbody_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -125,6 +125,6 @@ - + diff --git a/Samples/5_Domain_Specific/nbody/nbody_vs2019.vcxproj b/Samples/5_Domain_Specific/nbody/nbody_vs2019.vcxproj index 99874137b..84107c17a 100644 --- a/Samples/5_Domain_Specific/nbody/nbody_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/nbody/nbody_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -121,6 +121,6 @@ - + diff --git a/Samples/5_Domain_Specific/nbody/nbody_vs2022.vcxproj b/Samples/5_Domain_Specific/nbody/nbody_vs2022.vcxproj index fade78127..be9824bb3 100644 --- a/Samples/5_Domain_Specific/nbody/nbody_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/nbody/nbody_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -121,6 +121,6 @@ - + diff --git a/Samples/5_Domain_Specific/nbody_opengles/Makefile b/Samples/5_Domain_Specific/nbody_opengles/Makefile index 1ba63daa5..faad2c501 100644 --- a/Samples/5_Domain_Specific/nbody_opengles/Makefile +++ b/Samples/5_Domain_Specific/nbody_opengles/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/nbody_opengles/README.md b/Samples/5_Domain_Specific/nbody_opengles/README.md index 88f2828aa..f8c93485d 100644 --- a/Samples/5_Domain_Specific/nbody_opengles/README.md +++ b/Samples/5_Domain_Specific/nbody_opengles/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaSetDeviceFlags, cudaGraphicsResourceSetMapFlags, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/nbody_screen/Makefile b/Samples/5_Domain_Specific/nbody_screen/Makefile index c87afabeb..74278b08e 100644 --- a/Samples/5_Domain_Specific/nbody_screen/Makefile +++ b/Samples/5_Domain_Specific/nbody_screen/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/nbody_screen/README.md b/Samples/5_Domain_Specific/nbody_screen/README.md index 292583340..834bdef89 100644 --- a/Samples/5_Domain_Specific/nbody_screen/README.md +++ b/Samples/5_Domain_Specific/nbody_screen/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaSetDeviceFlags, cudaGraphicsResourceSetMapFlags, ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/Makefile b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/Makefile index d48f67ef5..48b92ec5f 100644 --- a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/Makefile +++ b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/README.md b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/README.md index 629fd64f8..d1be7ce91 100644 --- a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/README.md +++ b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/README.md @@ -27,7 +27,7 @@ cudaSetDevice, cudaEventDestroy, cudaOccupancyMaxPotentialBlockSize, cudaCheckEr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2017.vcxproj b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2017.vcxproj index b43284faa..23a18cf0d 100644 --- a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2019.vcxproj b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2019.vcxproj index e644f4df4..227f77eaf 100644 --- a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2022.vcxproj b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2022.vcxproj index 7dec7b3a3..544610977 100644 --- a/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/postProcessGL/Makefile b/Samples/5_Domain_Specific/postProcessGL/Makefile index d346bc75b..2b9ab6e14 100644 --- a/Samples/5_Domain_Specific/postProcessGL/Makefile +++ b/Samples/5_Domain_Specific/postProcessGL/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/postProcessGL/README.md b/Samples/5_Domain_Specific/postProcessGL/README.md index 8639ee806..b89f0349b 100644 --- a/Samples/5_Domain_Specific/postProcessGL/README.md +++ b/Samples/5_Domain_Specific/postProcessGL/README.md @@ -30,7 +30,7 @@ cudaHostAlloc, cudaGraphicsUnmapResources, cudaMalloc, cudaFree, cudaGetChannelD ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2017.vcxproj b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2017.vcxproj index 4281022bf..ac6901e42 100644 --- a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2019.vcxproj b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2019.vcxproj index c24b3099a..2711f5d82 100644 --- a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2022.vcxproj b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2022.vcxproj index 3ce9b99c4..3a0d25bed 100644 --- a/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/postProcessGL/postProcessGL_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator/Makefile b/Samples/5_Domain_Specific/quasirandomGenerator/Makefile index 48cc189e0..a59c32333 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator/Makefile +++ b/Samples/5_Domain_Specific/quasirandomGenerator/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/quasirandomGenerator/README.md b/Samples/5_Domain_Specific/quasirandomGenerator/README.md index 193be5fd5..d2edaea2a 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator/README.md +++ b/Samples/5_Domain_Specific/quasirandomGenerator/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMemset, cudaMemcpyToSymbol, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2017.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2017.vcxproj index b666cb59f..ce61dc736 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2019.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2019.vcxproj index 669b8b3d9..b6339019d 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2022.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2022.vcxproj index 330ca71ce..3a1298710 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator/quasirandomGenerator_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/Makefile b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/Makefile index 620f28f6f..2c0540af7 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/Makefile +++ b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/README.md b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/README.md index e7e9e8c8c..9d1698693 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/README.md +++ b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/README.md @@ -30,7 +30,7 @@ cuMemcpyDtoH, cuMemAlloc, cuMemFree ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2017.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2017.vcxproj index a5e455a52..d3dfefe9a 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2019.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2019.vcxproj index 01ab89e4f..196ed6797 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2022.vcxproj b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2022.vcxproj index 028a4f260..1f5b61c2f 100644 --- a/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/quasirandomGenerator_nvrtc/quasirandomGenerator_nvrtc_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/5_Domain_Specific/recursiveGaussian/Makefile b/Samples/5_Domain_Specific/recursiveGaussian/Makefile index ae114d957..f2d151066 100644 --- a/Samples/5_Domain_Specific/recursiveGaussian/Makefile +++ b/Samples/5_Domain_Specific/recursiveGaussian/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/recursiveGaussian/README.md b/Samples/5_Domain_Specific/recursiveGaussian/README.md index 884b85c15..090f676fa 100644 --- a/Samples/5_Domain_Specific/recursiveGaussian/README.md +++ b/Samples/5_Domain_Specific/recursiveGaussian/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2017.vcxproj b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2017.vcxproj index 621fa9d26..e50cdb892 100644 --- a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2019.vcxproj b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2019.vcxproj index 44420cccf..90818071c 100644 --- a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2022.vcxproj b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2022.vcxproj index 5ed86d806..6cd1d059d 100644 --- a/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/recursiveGaussian/recursiveGaussian_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10/README.md b/Samples/5_Domain_Specific/simpleD3D10/README.md index 00f0e9c8c..b8920771b 100644 --- a/Samples/5_Domain_Specific/simpleD3D10/README.md +++ b/Samples/5_Domain_Specific/simpleD3D10/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaGetErrorString, cudaGraphicsResourceGetMappedPoi ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2017.vcxproj index 127a1f5a7..c0835d3c7 100644 --- a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2019.vcxproj index f32ab0be9..9550b91ba 100644 --- a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2022.vcxproj index 88dd181cf..a2f55214d 100644 --- a/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10/simpleD3D10_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/README.md b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/README.md index 47faa2048..9847a94c5 100644 --- a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/README.md +++ b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaMalloc, cudaUnbindTexture, cudaGetEr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2017.vcxproj index ca9222a0d..bf6351f22 100644 --- a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2019.vcxproj index 7ae056a1e..8e00b3c4d 100644 --- a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2022.vcxproj index 38105d264..fa0b58ae5 100644 --- a/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10RenderTarget/simpleD3D10RenderTarget_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10Texture/README.md b/Samples/5_Domain_Specific/simpleD3D10Texture/README.md index e01758598..243fe3758 100644 --- a/Samples/5_Domain_Specific/simpleD3D10Texture/README.md +++ b/Samples/5_Domain_Specific/simpleD3D10Texture/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMalloc, cudaMallocPitch, cudaGetErrorString, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2017.vcxproj index b07a8b5d3..e0cc4b216 100644 --- a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2019.vcxproj index f26d34781..1396403ad 100644 --- a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2022.vcxproj index 7e0f43c42..393cd14b2 100644 --- a/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D10Texture/simpleD3D10Texture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11/README.md b/Samples/5_Domain_Specific/simpleD3D11/README.md index 15993e1dd..8b9f5e011 100644 --- a/Samples/5_Domain_Specific/simpleD3D11/README.md +++ b/Samples/5_Domain_Specific/simpleD3D11/README.md @@ -30,7 +30,7 @@ cudaImportKeyedMutex, cudaExternalMemoryGetMappedBuffer, cudaStreamCreateWithFla ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2017.vcxproj index bee0e798f..da17569ed 100644 --- a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2019.vcxproj index 1f9ac0dc0..d872e58ae 100644 --- a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2022.vcxproj index 6ff932906..4d5a14994 100644 --- a/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11/simpleD3D11_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11Texture/README.md b/Samples/5_Domain_Specific/simpleD3D11Texture/README.md index db3facdec..19aaf8a5f 100644 --- a/Samples/5_Domain_Specific/simpleD3D11Texture/README.md +++ b/Samples/5_Domain_Specific/simpleD3D11Texture/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMalloc, cudaMallocPitch, cudaGetErrorString, cud ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2017.vcxproj index 6954034d9..cf5f6ba76 100644 --- a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -112,6 +112,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2019.vcxproj index 0ea910a72..17748bff4 100644 --- a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2022.vcxproj index 34972bea4..537885087 100644 --- a/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D11Texture/simpleD3D11Texture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -108,6 +108,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D12/README.md b/Samples/5_Domain_Specific/simpleD3D12/README.md index 1d8a77b72..ad39407f3 100644 --- a/Samples/5_Domain_Specific/simpleD3D12/README.md +++ b/Samples/5_Domain_Specific/simpleD3D12/README.md @@ -30,7 +30,7 @@ cudaWaitExternalSemaphoresAsync, cudaExternalMemoryGetMappedBuffer, cudaImportEx ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2017.vcxproj index 9496182ff..2055ef4c9 100644 --- a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2019.vcxproj index ba258150e..43e423a14 100644 --- a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2019.vcxproj @@ -39,7 +39,7 @@ - + @@ -120,6 +120,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2022.vcxproj index c2484f17f..988cc3188 100644 --- a/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D12/simpleD3D12_vs2022.vcxproj @@ -39,7 +39,7 @@ - + @@ -120,6 +120,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9/README.md b/Samples/5_Domain_Specific/simpleD3D9/README.md index 3e712dd82..c81927c3e 100644 --- a/Samples/5_Domain_Specific/simpleD3D9/README.md +++ b/Samples/5_Domain_Specific/simpleD3D9/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaGraphicsResourceGetMappedPointer, cudaGetLastErr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2017.vcxproj index 53ce5f532..79bd8ec1e 100644 --- a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -109,6 +109,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2019.vcxproj index 4f2b49795..1b452b3dc 100644 --- a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2022.vcxproj index b230029e3..480a63841 100644 --- a/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9/simpleD3D9_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -105,6 +105,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9Texture/README.md b/Samples/5_Domain_Specific/simpleD3D9Texture/README.md index eddc8fc65..70af0508f 100644 --- a/Samples/5_Domain_Specific/simpleD3D9Texture/README.md +++ b/Samples/5_Domain_Specific/simpleD3D9Texture/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMalloc, cudaMallocPitch, cudaFree, cudaGetLastEr ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2017.vcxproj index 8780cd87b..82922ed1f 100644 --- a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -111,6 +111,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2019.vcxproj index 3603498fc..35dbd00e7 100644 --- a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2022.vcxproj index 994a725a9..a80934244 100644 --- a/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleD3D9Texture/simpleD3D9Texture_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleGL/Makefile b/Samples/5_Domain_Specific/simpleGL/Makefile index 17769a6f9..caf7fd38d 100644 --- a/Samples/5_Domain_Specific/simpleGL/Makefile +++ b/Samples/5_Domain_Specific/simpleGL/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleGL/README.md b/Samples/5_Domain_Specific/simpleGL/README.md index 6144bfa63..2419f0433 100644 --- a/Samples/5_Domain_Specific/simpleGL/README.md +++ b/Samples/5_Domain_Specific/simpleGL/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2017.vcxproj index df1ac4438..fc775d758 100644 --- a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2019.vcxproj index 4089f3cb3..e284230de 100644 --- a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2022.vcxproj index d8138a12f..a35bda7ea 100644 --- a/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleGL/simpleGL_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleGLES/Makefile b/Samples/5_Domain_Specific/simpleGLES/Makefile index 05424cd07..06902f2ac 100644 --- a/Samples/5_Domain_Specific/simpleGLES/Makefile +++ b/Samples/5_Domain_Specific/simpleGLES/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleGLES/README.md b/Samples/5_Domain_Specific/simpleGLES/README.md index b640a766a..f22b105fb 100644 --- a/Samples/5_Domain_Specific/simpleGLES/README.md +++ b/Samples/5_Domain_Specific/simpleGLES/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleGLES_EGLOutput/Makefile b/Samples/5_Domain_Specific/simpleGLES_EGLOutput/Makefile index 4fdd337b9..01de12055 100644 --- a/Samples/5_Domain_Specific/simpleGLES_EGLOutput/Makefile +++ b/Samples/5_Domain_Specific/simpleGLES_EGLOutput/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleGLES_EGLOutput/README.md b/Samples/5_Domain_Specific/simpleGLES_EGLOutput/README.md index 06d80d9ec..9af216b4d 100644 --- a/Samples/5_Domain_Specific/simpleGLES_EGLOutput/README.md +++ b/Samples/5_Domain_Specific/simpleGLES_EGLOutput/README.md @@ -35,7 +35,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleGLES_screen/Makefile b/Samples/5_Domain_Specific/simpleGLES_screen/Makefile index 4a764a2ed..f2672bd88 100644 --- a/Samples/5_Domain_Specific/simpleGLES_screen/Makefile +++ b/Samples/5_Domain_Specific/simpleGLES_screen/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleGLES_screen/README.md b/Samples/5_Domain_Specific/simpleGLES_screen/README.md index f4a89cae7..067bdaf40 100644 --- a/Samples/5_Domain_Specific/simpleGLES_screen/README.md +++ b/Samples/5_Domain_Specific/simpleGLES_screen/README.md @@ -30,7 +30,7 @@ cudaGraphicsUnmapResources, cudaMemcpy, cudaFree, cudaGraphicsResourceGetMappedP ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleVulkan/Makefile b/Samples/5_Domain_Specific/simpleVulkan/Makefile index 697cb8673..098a6d9bc 100644 --- a/Samples/5_Domain_Specific/simpleVulkan/Makefile +++ b/Samples/5_Domain_Specific/simpleVulkan/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleVulkan/README.md b/Samples/5_Domain_Specific/simpleVulkan/README.md index baee10f30..6d1a3282d 100644 --- a/Samples/5_Domain_Specific/simpleVulkan/README.md +++ b/Samples/5_Domain_Specific/simpleVulkan/README.md @@ -30,7 +30,7 @@ cudaStreamCreateWithFlags, cudaExternalMemoryGetMappedBuffer, cudaSignalSemaphor ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2017.vcxproj index 11419289c..ec7cfba6c 100644 --- a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -121,6 +121,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2019.vcxproj index 691357fd8..8f3965a3c 100644 --- a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2022.vcxproj index 46ada2774..433f74ccc 100644 --- a/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkan/simpleVulkan_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleVulkanMMAP/Makefile b/Samples/5_Domain_Specific/simpleVulkanMMAP/Makefile index aace0d8be..420d03076 100644 --- a/Samples/5_Domain_Specific/simpleVulkanMMAP/Makefile +++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/simpleVulkanMMAP/README.md b/Samples/5_Domain_Specific/simpleVulkanMMAP/README.md index b1060db7c..ba2bd9183 100644 --- a/Samples/5_Domain_Specific/simpleVulkanMMAP/README.md +++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/README.md @@ -33,7 +33,7 @@ cudaWaitExternalSemaphoresAsync, cudaImportExternalSemaphore, cudaDeviceGetAttri ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2017.vcxproj b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2017.vcxproj index 630d6c46a..d0d825ecb 100644 --- a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -123,6 +123,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2019.vcxproj b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2019.vcxproj index d4e5a06a0..5943395b0 100644 --- a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2022.vcxproj b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2022.vcxproj index b5487d98e..5c47a7d0d 100644 --- a/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/simpleVulkanMMAP/simpleVulkanMMAP_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -119,6 +119,6 @@ - + diff --git a/Samples/5_Domain_Specific/smokeParticles/Makefile b/Samples/5_Domain_Specific/smokeParticles/Makefile index 9e1274362..83977eaac 100644 --- a/Samples/5_Domain_Specific/smokeParticles/Makefile +++ b/Samples/5_Domain_Specific/smokeParticles/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/smokeParticles/README.md b/Samples/5_Domain_Specific/smokeParticles/README.md index 17d500749..366dea3db 100644 --- a/Samples/5_Domain_Specific/smokeParticles/README.md +++ b/Samples/5_Domain_Specific/smokeParticles/README.md @@ -30,7 +30,7 @@ cudaExtent, cudaPitchedPtr, cudaCreateTextureObject, cudaMemcpyToSymbol ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2017.vcxproj b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2017.vcxproj index b22c13e51..ea3b50939 100644 --- a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -137,6 +137,6 @@ - + diff --git a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2019.vcxproj b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2019.vcxproj index 02d81bdf4..11119a14d 100644 --- a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -133,6 +133,6 @@ - + diff --git a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2022.vcxproj b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2022.vcxproj index b315bf2c6..4dec94391 100644 --- a/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/smokeParticles/smokeParticles_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -133,6 +133,6 @@ - + diff --git a/Samples/5_Domain_Specific/stereoDisparity/Makefile b/Samples/5_Domain_Specific/stereoDisparity/Makefile index 87dbd9f1f..920bd2128 100644 --- a/Samples/5_Domain_Specific/stereoDisparity/Makefile +++ b/Samples/5_Domain_Specific/stereoDisparity/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/stereoDisparity/README.md b/Samples/5_Domain_Specific/stereoDisparity/README.md index 62a37a508..182b109c4 100644 --- a/Samples/5_Domain_Specific/stereoDisparity/README.md +++ b/Samples/5_Domain_Specific/stereoDisparity/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaEventSynchronize, cudaDeviceSynchronize, cudaCreateTex ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2017.vcxproj b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2017.vcxproj index baa951901..65f053756 100644 --- a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2019.vcxproj b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2019.vcxproj index 96d8377bd..efdab434a 100644 --- a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2022.vcxproj b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2022.vcxproj index ff27d19b0..8f3d040f1 100644 --- a/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/stereoDisparity/stereoDisparity_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeFiltering/Makefile b/Samples/5_Domain_Specific/volumeFiltering/Makefile index cf8708ca7..67d3cae51 100644 --- a/Samples/5_Domain_Specific/volumeFiltering/Makefile +++ b/Samples/5_Domain_Specific/volumeFiltering/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/volumeFiltering/README.md b/Samples/5_Domain_Specific/volumeFiltering/README.md index 3e88c2649..f07c7b27c 100644 --- a/Samples/5_Domain_Specific/volumeFiltering/README.md +++ b/Samples/5_Domain_Specific/volumeFiltering/README.md @@ -30,7 +30,7 @@ cudaMemcpy, cudaGraphicsMapResources, cudaDestroySurfaceObject, cudaExtent, cuda ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2017.vcxproj b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2017.vcxproj index b72449938..5a1b9424e 100644 --- a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -122,6 +122,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2019.vcxproj b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2019.vcxproj index bc675ab8c..17b3ac6fd 100644 --- a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2022.vcxproj b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2022.vcxproj index f863efdcb..73849d6e9 100644 --- a/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/volumeFiltering/volumeFiltering_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeRender/Makefile b/Samples/5_Domain_Specific/volumeRender/Makefile index 5b5d73a3d..f6bcf9c57 100644 --- a/Samples/5_Domain_Specific/volumeRender/Makefile +++ b/Samples/5_Domain_Specific/volumeRender/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/volumeRender/README.md b/Samples/5_Domain_Specific/volumeRender/README.md index 322973d8c..57e40b0f4 100644 --- a/Samples/5_Domain_Specific/volumeRender/README.md +++ b/Samples/5_Domain_Specific/volumeRender/README.md @@ -30,7 +30,7 @@ cudaProfilerStop, cudaGraphicsUnmapResources, cudaMemcpy, cudaMallocArray, cudaF ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2017.vcxproj b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2017.vcxproj index a7e458a2d..f70cae039 100644 --- a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -118,6 +118,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2019.vcxproj b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2019.vcxproj index ea181dede..4c63b6172 100644 --- a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2022.vcxproj b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2022.vcxproj index 83bba7522..efe37a04f 100644 --- a/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/volumeRender/volumeRender_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -114,6 +114,6 @@ - + diff --git a/Samples/5_Domain_Specific/vulkanImageCUDA/Makefile b/Samples/5_Domain_Specific/vulkanImageCUDA/Makefile index 53c5bc90d..d9750da5f 100644 --- a/Samples/5_Domain_Specific/vulkanImageCUDA/Makefile +++ b/Samples/5_Domain_Specific/vulkanImageCUDA/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/5_Domain_Specific/vulkanImageCUDA/README.md b/Samples/5_Domain_Specific/vulkanImageCUDA/README.md index 76377bda5..c0cfa7f8a 100644 --- a/Samples/5_Domain_Specific/vulkanImageCUDA/README.md +++ b/Samples/5_Domain_Specific/vulkanImageCUDA/README.md @@ -30,7 +30,7 @@ cudaVkSemaphoreSignal, cudaWaitExternalSemaphoresAsync, cudaMemcpy, cudaVkImport ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2017.vcxproj b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2017.vcxproj index 6ef89f261..4e0917268 100644 --- a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2017.vcxproj +++ b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -117,6 +117,6 @@ - + diff --git a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2019.vcxproj b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2019.vcxproj index e6d168a05..c7f2af0c0 100644 --- a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2019.vcxproj +++ b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2022.vcxproj b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2022.vcxproj index eb9713314..5bec4cef0 100644 --- a/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2022.vcxproj +++ b/Samples/5_Domain_Specific/vulkanImageCUDA/vulkanImageCUDA_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -113,6 +113,6 @@ - + diff --git a/Samples/6_Performance/README.md b/Samples/6_Performance/README.md index 64a4b10ae..c44b0ba2c 100644 --- a/Samples/6_Performance/README.md +++ b/Samples/6_Performance/README.md @@ -10,3 +10,5 @@ This sample demonstrates Matrix Transpose. Different performance are shown to a ### [UnifiedMemoryPerf](./UnifiedMemoryPerf) This sample demonstrates the performance comparision using matrix multiplication kernel of Unified Memory with/without hints and other types of memory like zero copy buffers, pageable, pagelocked memory performing synchronous and Asynchronous transfers on a single GPU. +### [cudaGraphsPerfScaling](./cudaGraphsPerfScaling) +This sample demonstrates the performance characteristics of cuda graphs. It is focused on how the apis scale with graph size. diff --git a/Samples/6_Performance/UnifiedMemoryPerf/Makefile b/Samples/6_Performance/UnifiedMemoryPerf/Makefile index a7230f136..dfee2cd4c 100644 --- a/Samples/6_Performance/UnifiedMemoryPerf/Makefile +++ b/Samples/6_Performance/UnifiedMemoryPerf/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/6_Performance/UnifiedMemoryPerf/README.md b/Samples/6_Performance/UnifiedMemoryPerf/README.md index 99b982eca..dd9a92368 100644 --- a/Samples/6_Performance/UnifiedMemoryPerf/README.md +++ b/Samples/6_Performance/UnifiedMemoryPerf/README.md @@ -28,7 +28,7 @@ cudaMemcpy, cudaStreamDestroy, cudaMemPrefetchAsync, cudaFree, cudaMallocHost, c ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Make sure the dependencies mentioned in [Dependencies]() section above are installed. ## Build and Run diff --git a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj index ddcfde4af..439481fe0 100644 --- a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj +++ b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -110,6 +110,6 @@ - + diff --git a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj index 231f8e5a0..fdc41a74f 100644 --- a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj +++ b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2022.vcxproj b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2022.vcxproj index 400137a89..b4e928533 100644 --- a/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2022.vcxproj +++ b/Samples/6_Performance/UnifiedMemoryPerf/UnifiedMemoryPerf_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -106,6 +106,6 @@ - + diff --git a/Samples/6_Performance/alignedTypes/Makefile b/Samples/6_Performance/alignedTypes/Makefile index 191b3e09d..10bcda7e1 100644 --- a/Samples/6_Performance/alignedTypes/Makefile +++ b/Samples/6_Performance/alignedTypes/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/6_Performance/alignedTypes/README.md b/Samples/6_Performance/alignedTypes/README.md index d9bd0e895..8ac983e6b 100644 --- a/Samples/6_Performance/alignedTypes/README.md +++ b/Samples/6_Performance/alignedTypes/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaFree, cudaDeviceSynchronize, cudaMemset, cudaMalloc, cudaGetDevi ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/6_Performance/alignedTypes/alignedTypes_vs2017.vcxproj b/Samples/6_Performance/alignedTypes/alignedTypes_vs2017.vcxproj index 970929f28..f177e1bc2 100644 --- a/Samples/6_Performance/alignedTypes/alignedTypes_vs2017.vcxproj +++ b/Samples/6_Performance/alignedTypes/alignedTypes_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/6_Performance/alignedTypes/alignedTypes_vs2019.vcxproj b/Samples/6_Performance/alignedTypes/alignedTypes_vs2019.vcxproj index c01105081..fcf174ec7 100644 --- a/Samples/6_Performance/alignedTypes/alignedTypes_vs2019.vcxproj +++ b/Samples/6_Performance/alignedTypes/alignedTypes_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/6_Performance/alignedTypes/alignedTypes_vs2022.vcxproj b/Samples/6_Performance/alignedTypes/alignedTypes_vs2022.vcxproj index fcc2c9e7f..bb200e267 100644 --- a/Samples/6_Performance/alignedTypes/alignedTypes_vs2022.vcxproj +++ b/Samples/6_Performance/alignedTypes/alignedTypes_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/c_cpp_properties.json b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/c_cpp_properties.json new file mode 100644 index 000000000..f0066b0f9 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/c_cpp_properties.json @@ -0,0 +1,18 @@ +{ + "configurations": [ + { + "name": "Linux", + "includePath": [ + "${workspaceFolder}/**", + "${workspaceFolder}/../../../Common" + ], + "defines": [], + "compilerPath": "/usr/local/cuda/bin/nvcc", + "cStandard": "gnu17", + "cppStandard": "gnu++14", + "intelliSenseMode": "linux-gcc-x64", + "configurationProvider": "ms-vscode.makefile-tools" + } + ], + "version": 4 +} diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/extensions.json b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/extensions.json new file mode 100644 index 000000000..c7eb54dc0 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/extensions.json @@ -0,0 +1,7 @@ +{ + "recommendations": [ + "nvidia.nsight-vscode-edition", + "ms-vscode.cpptools", + "ms-vscode.makefile-tools" + ] +} diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/launch.json b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/launch.json new file mode 100644 index 000000000..c7dfe643a --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/launch.json @@ -0,0 +1,10 @@ +{ + "configurations": [ + { + "name": "CUDA C++: Launch", + "type": "cuda-gdb", + "request": "launch", + "program": "${workspaceFolder}/cudaGraphsPerfScaling" + } + ] +} diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/tasks.json b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/tasks.json new file mode 100644 index 000000000..4509aeb1c --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/.vscode/tasks.json @@ -0,0 +1,15 @@ +{ + "version": "2.0.0", + "tasks": [ + { + "label": "sample", + "type": "shell", + "command": "make dbg=1", + "problemMatcher": ["$nvcc"], + "group": { + "kind": "build", + "isDefault": true + } + } + ] +} diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/Makefile b/Samples/6_Performance/cudaGraphsPerfScaling/Makefile new file mode 100644 index 000000000..4bc859859 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/Makefile @@ -0,0 +1,363 @@ +################################################################################ +# Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions +# are met: +# * Redistributions of source code must retain the above copyright +# notice, this list of conditions and the following disclaimer. +# * Redistributions in binary form must reproduce the above copyright +# notice, this list of conditions and the following disclaimer in the +# documentation and/or other materials provided with the distribution. +# * Neither the name of NVIDIA CORPORATION nor the names of its +# contributors may be used to endorse or promote products derived +# from this software without specific prior written permission. +# +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY +# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR +# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, +# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, +# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY +# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +# +################################################################################ +# +# Makefile project only supported on Mac OS X and Linux Platforms) +# +################################################################################ + +# Location of the CUDA Toolkit +CUDA_PATH ?= /usr/local/cuda + +############################## +# start deprecated interface # +############################## +ifeq ($(x86_64),1) + $(info WARNING - x86_64 variable has been deprecated) + $(info WARNING - please use TARGET_ARCH=x86_64 instead) + TARGET_ARCH ?= x86_64 +endif +ifeq ($(ARMv7),1) + $(info WARNING - ARMv7 variable has been deprecated) + $(info WARNING - please use TARGET_ARCH=armv7l instead) + TARGET_ARCH ?= armv7l +endif +ifeq ($(aarch64),1) + $(info WARNING - aarch64 variable has been deprecated) + $(info WARNING - please use TARGET_ARCH=aarch64 instead) + TARGET_ARCH ?= aarch64 +endif +ifeq ($(ppc64le),1) + $(info WARNING - ppc64le variable has been deprecated) + $(info WARNING - please use TARGET_ARCH=ppc64le instead) + TARGET_ARCH ?= ppc64le +endif +ifneq ($(GCC),) + $(info WARNING - GCC variable has been deprecated) + $(info WARNING - please use HOST_COMPILER=$(GCC) instead) + HOST_COMPILER ?= $(GCC) +endif +ifneq ($(abi),) + $(error ERROR - abi variable has been removed) +endif +############################ +# end deprecated interface # +############################ + +# architecture +HOST_ARCH := $(shell uname -m) +TARGET_ARCH ?= $(HOST_ARCH) +ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le armv7l)) + ifneq ($(TARGET_ARCH),$(HOST_ARCH)) + ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le)) + TARGET_SIZE := 64 + else ifneq (,$(filter $(TARGET_ARCH),armv7l)) + TARGET_SIZE := 32 + endif + else + TARGET_SIZE := $(shell getconf LONG_BIT) + endif +else + $(error ERROR - unsupported value $(TARGET_ARCH) for TARGET_ARCH!) +endif + +# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now. +ifeq ($(HOST_ARCH),aarch64) + ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null)) + HOST_ARCH := sbsa + TARGET_ARCH := sbsa + endif +endif + +ifneq ($(TARGET_ARCH),$(HOST_ARCH)) + ifeq (,$(filter $(HOST_ARCH)-$(TARGET_ARCH),aarch64-armv7l x86_64-armv7l x86_64-aarch64 x86_64-sbsa x86_64-ppc64le)) + $(error ERROR - cross compiling from $(HOST_ARCH) to $(TARGET_ARCH) is not supported!) + endif +endif + +# When on native aarch64 system with userspace of 32-bit, change TARGET_ARCH to armv7l +ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_SIZE),aarch64-aarch64-32) + TARGET_ARCH = armv7l +endif + +# operating system +HOST_OS := $(shell uname -s 2>/dev/null | tr "[:upper:]" "[:lower:]") +TARGET_OS ?= $(HOST_OS) +ifeq (,$(filter $(TARGET_OS),linux darwin qnx android)) + $(error ERROR - unsupported value $(TARGET_OS) for TARGET_OS!) +endif + +# host compiler +ifdef HOST_COMPILER + CUSTOM_HOST_COMPILER = 1 +endif + +ifeq ($(TARGET_OS),darwin) + ifeq ($(shell expr `xcodebuild -version | grep -i xcode | awk '{print $$2}' | cut -d'.' -f1` \>= 5),1) + HOST_COMPILER ?= clang++ + endif +else ifneq ($(TARGET_ARCH),$(HOST_ARCH)) + ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l) + ifeq ($(TARGET_OS),linux) + HOST_COMPILER ?= arm-linux-gnueabihf-g++ + else ifeq ($(TARGET_OS),qnx) + ifeq ($(QNX_HOST),) + $(error ERROR - QNX_HOST must be passed to the QNX host toolchain) + endif + ifeq ($(QNX_TARGET),) + $(error ERROR - QNX_TARGET must be passed to the QNX target toolchain) + endif + export QNX_HOST + export QNX_TARGET + HOST_COMPILER ?= $(QNX_HOST)/usr/bin/arm-unknown-nto-qnx6.6.0eabi-g++ + else ifeq ($(TARGET_OS),android) + HOST_COMPILER ?= arm-linux-androideabi-g++ + endif + else ifeq ($(TARGET_ARCH),aarch64) + ifeq ($(TARGET_OS), linux) + HOST_COMPILER ?= aarch64-linux-gnu-g++ + else ifeq ($(TARGET_OS),qnx) + ifeq ($(QNX_HOST),) + $(error ERROR - QNX_HOST must be passed to the QNX host toolchain) + endif + ifeq ($(QNX_TARGET),) + $(error ERROR - QNX_TARGET must be passed to the QNX target toolchain) + endif + export QNX_HOST + export QNX_TARGET + HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++ + else ifeq ($(TARGET_OS), android) + HOST_COMPILER ?= aarch64-linux-android-clang++ + endif + else ifeq ($(TARGET_ARCH),sbsa) + HOST_COMPILER ?= aarch64-linux-gnu-g++ + else ifeq ($(TARGET_ARCH),ppc64le) + HOST_COMPILER ?= powerpc64le-linux-gnu-g++ + endif +endif +HOST_COMPILER ?= g++ +NVCC := $(CUDA_PATH)/bin/nvcc -ccbin $(HOST_COMPILER) + +# internal flags +NVCCFLAGS := -m${TARGET_SIZE} +CCFLAGS := +LDFLAGS := + +# build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + +ifeq ($(TARGET_OS),darwin) + LDFLAGS += -rpath $(CUDA_PATH)/lib + CCFLAGS += -arch $(HOST_ARCH) +else ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-armv7l-linux) + LDFLAGS += --dynamic-linker=/lib/ld-linux-armhf.so.3 + CCFLAGS += -mfloat-abi=hard +else ifeq ($(TARGET_OS),android) + LDFLAGS += -pie + CCFLAGS += -fpie -fpic -fexceptions +endif + +ifneq ($(TARGET_ARCH),$(HOST_ARCH)) + ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) + ifneq ($(TARGET_FS),) + GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6) + ifeq ($(GCCVERSIONLTEQ46),1) + CCFLAGS += --sysroot=$(TARGET_FS) + endif + LDFLAGS += --sysroot=$(TARGET_FS) + LDFLAGS += -rpath-link=$(TARGET_FS)/lib + LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib + LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/arm-linux-gnueabihf + endif + endif + ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux) + ifneq ($(TARGET_FS),) + GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6) + ifeq ($(GCCVERSIONLTEQ46),1) + CCFLAGS += --sysroot=$(TARGET_FS) + endif + LDFLAGS += --sysroot=$(TARGET_FS) + LDFLAGS += -rpath-link=$(TARGET_FS)/lib -L$(TARGET_FS)/lib + LDFLAGS += -rpath-link=$(TARGET_FS)/lib/aarch64-linux-gnu -L$(TARGET_FS)/lib/aarch64-linux-gnu + LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib + LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu + LDFLAGS += --unresolved-symbols=ignore-in-shared-libs + CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm + CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu + endif + endif + ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) + NVCCFLAGS += -D_QNX_SOURCE + NVCCFLAGS += --qpp-config 8.3.0,gcc_ntoaarch64le + CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu + LDFLAGS += -lsocket + LDFLAGS += -L/usr/lib/aarch64-qnx-gnu + CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu" + ifdef TARGET_OVERRIDE + LDFLAGS += -lslog2 + endif + + ifneq ($(TARGET_FS),) + LDFLAGS += -L$(TARGET_FS)/usr/lib + CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib" + LDFLAGS += -L$(TARGET_FS)/usr/libnvidia + CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia" + CCFLAGS += -I$(TARGET_FS)/../include + endif + endif +endif + +ifdef TARGET_OVERRIDE # cuda toolkit targets override + NVCCFLAGS += -target-dir $(TARGET_OVERRIDE) +endif + +# Install directory of different arch +CUDA_INSTALL_TARGET_DIR := +ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) + CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-gnueabihf/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux) + CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),sbsa-linux) + CUDA_INSTALL_TARGET_DIR = targets/sbsa-linux/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-android) + CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-androideabi/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-android) + CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux-androideabi/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-qnx) + CUDA_INSTALL_TARGET_DIR = targets/ARMv7-linux-QNX/ +else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) + CUDA_INSTALL_TARGET_DIR = targets/aarch64-qnx/ +else ifeq ($(TARGET_ARCH),ppc64le) + CUDA_INSTALL_TARGET_DIR = targets/ppc64le-linux/ +endif + +# Debug build flags +ifeq ($(dbg),1) + NVCCFLAGS += -g -G + BUILD_TYPE := debug +else + BUILD_TYPE := release +endif + +ALL_CCFLAGS := +ALL_CCFLAGS += $(NVCCFLAGS) +ALL_CCFLAGS += $(EXTRA_NVCCFLAGS) +ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS)) +ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS)) + +SAMPLE_ENABLED := 1 + +# This sample is not supported on Mac OSX +ifeq ($(TARGET_OS),darwin) + $(info >>> WARNING - cudaGraphsPerfScaling is not supported on Mac OSX - waiving sample <<<) + SAMPLE_ENABLED := 0 +endif + +ALL_LDFLAGS := +ALL_LDFLAGS += $(ALL_CCFLAGS) +ALL_LDFLAGS += $(addprefix -Xlinker ,$(LDFLAGS)) +ALL_LDFLAGS += $(addprefix -Xlinker ,$(EXTRA_LDFLAGS)) + +# Common includes and paths for CUDA +INCLUDES := -I../../../Common +LIBRARIES := + +################################################################################ + +# Gencode arguments +ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa)) +SMS ?= 53 61 70 72 75 80 86 87 90 +else +SMS ?= 50 52 60 61 70 75 80 86 89 90 +endif + +ifeq ($(SMS),) +$(info >>> WARNING - no SM architectures have been specified - waiving sample <<<) +SAMPLE_ENABLED := 0 +endif + +ifeq ($(GENCODE_FLAGS),) +# Generate SASS code for each SM architecture listed in $(SMS) +$(foreach sm,$(SMS),$(eval GENCODE_FLAGS += -gencode arch=compute_$(sm),code=sm_$(sm))) + +# Generate PTX code from the highest SM architecture in $(SMS) to guarantee forward-compatibility +HIGHEST_SM := $(lastword $(sort $(SMS))) +ifneq ($(HIGHEST_SM),) +GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM) +endif +endif + +ALL_CCFLAGS += --std=c++11 --threads 0 + +ifeq ($(SAMPLE_ENABLED),0) +EXEC ?= @echo "[@]" +endif + +################################################################################ + +# Target rules +all: build + +build: cudaGraphsPerfScaling + +check.deps: +ifeq ($(SAMPLE_ENABLED),0) + @echo "Sample will be waived due to the above missing dependencies" +else + @echo "Sample is ready - all dependencies have been met" +endif + +cudaGraphPerfScaling.o:cudaGraphPerfScaling.cu + $(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $< + +cudaGraphsPerfScaling: cudaGraphPerfScaling.o + $(EXEC) $(NVCC) $(ALL_LDFLAGS) $(GENCODE_FLAGS) -o $@ $+ $(LIBRARIES) + $(EXEC) mkdir -p ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE) + $(EXEC) cp $@ ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE) + +run: build + $(EXEC) ./cudaGraphsPerfScaling + +testrun: build + +clean: + rm -f cudaGraphsPerfScaling cudaGraphPerfScaling.o + rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/cudaGraphsPerfScaling + +clobber: clean diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/README.md b/Samples/6_Performance/cudaGraphsPerfScaling/README.md new file mode 100644 index 000000000..dce334be8 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/README.md @@ -0,0 +1,70 @@ +# cudaGraphsPerfScaling - Cuda Graphs Perf Scaling + +## Description + +A simple program for characterizing cuda graph api performance with different sized graphs. + +## Key Concepts + +Performance Strategies + +## Supported SM Architectures + +[SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 5.3 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 8.9 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus) + +## Supported OSes + +Linux, Windows + +## Supported CPU Architecture + +x86_64, armv7l + +## CUDA APIs involved + +### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html) +cudaStreamBeginCapture, cudaGraphInstantiate, cudaGraphLaunch, cudaGraphUpload + +## Prerequisites + +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. + +## Build and Run + +### Windows +The Windows samples are built using the Visual Studio IDE. Solution files (.sln) are provided for each supported version of Visual Studio, using the format: +``` +*_vs.sln - for Visual Studio +``` +Each individual sample has its own set of solution files in its directory: + +To build/examine all the samples at once, the complete solution files should be used. To build/examine a single sample, the individual sample solution files should be used. +> **Note:** Some samples require that the Microsoft DirectX SDK (June 2010 or newer) be installed and that the VC++ directory paths are properly set up (**Tools > Options...**). Check DirectX Dependencies section for details." + +### Linux +The Linux samples are built using makefiles. To use the makefiles, change the current directory to the sample directory you wish to build, and run make: +``` +$ cd +$ make +``` +The samples makefiles can take advantage of certain options: +* **TARGET_ARCH=** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, armv7l. + By default, TARGET_ARCH is set to HOST_ARCH. On a x86_64 machine, not setting TARGET_ARCH is the equivalent of setting TARGET_ARCH=x86_64.
+`$ make TARGET_ARCH=x86_64`
`$ make TARGET_ARCH=armv7l`
+ See [here](http://docs.nvidia.com/cuda/cuda-samples/index.html#cross-samples) for more details. +* **dbg=1** - build with debug symbols + ``` + $ make dbg=1 + ``` +* **SMS="A B ..."** - override the SM architectures for which the sample will be built, where `"A B ..."` is a space-delimited list of SM architectures. For example, to generate SASS for SM 50 and SM 60, use `SMS="50 60"`. + ``` + $ make SMS="50 60" + ``` + +* **HOST_COMPILER=** - override the default g++ host compiler. See the [Linux Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#system-requirements) for a list of supported host compilers. +``` + $ make HOST_COMPILER=g++ +``` + +## References (for more details) + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphPerfScaling.cu b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphPerfScaling.cu new file mode 100644 index 000000000..0e811744a --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphPerfScaling.cu @@ -0,0 +1,434 @@ +/* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of NVIDIA CORPORATION nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR + * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, + * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, + * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR + * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY + * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/* + * This is a simple application showing the performance characteristics of cudaGraphs. + */ + +#define USE_NVTX + +#include +#include +#include +#include + +typedef volatile int LatchType; + +std::chrono::time_point getCpuTime() +{ + return std::chrono::high_resolution_clock::now(); +} + +template +float getMicroSecondDuration(T start, T end) +{ + return std::chrono::duration_cast(end-start).count() *.001f; +} + +float getAsyncMicroSecondDuration(cudaEvent_t start, cudaEvent_t end) +{ + float ms; + cudaEventElapsedTime(&ms, start, end); + return ms*1000; +} + +#ifdef USE_NVTX +#include + +class Tracer { +public: + Tracer(const char* name) { + nvtxRangePushA(name); + } + ~Tracer() { + nvtxRangePop(); + } +}; +#define RANGE(name) Tracer uniq_name_using_macros(name); +#define RANGE_PUSH(name) nvtxRangePushA(name) +#define RANGE_POP() nvtxRangePop(); +#else +#define RANGE(name) +#endif + +std::vector stream; +cudaEvent_t event[1]; +cudaEvent_t timingEvent[2]; + +struct hostData { + long long timeElapsed; + bool timeoutDetected; + long long timeElapsed2; + bool timeoutDetected2; + LatchType latch; + LatchType latch2; +}; + +struct hostData *hostData; + +__global__ void empty() +{ +} + +// Function to read the GPU nanosecond timer in a kernel +__device__ __forceinline__ unsigned long long __globaltimer() { + unsigned long long globaltimer; + asm volatile ("mov.u64 %0, %globaltimer;" : "=l"(globaltimer)); + return globaltimer; +} + +__global__ void delay(long long ticks) +{ + long long endTime = clock64() + ticks; + while (clock64() < endTime); +} + +__global__ void waitWithTimeout(long long nanoseconds, bool* timeoutDetected, long long *timeElapsed, LatchType* latch) +{ + long long startTime = __globaltimer(); + long long endTime = startTime + nanoseconds; + long long time = 0; + do { + time = __globaltimer(); + } while (time < endTime && (latch == NULL || *latch == 0)); + if (timeElapsed != NULL) { + *timeElapsed = time - startTime; + } + if (timeoutDetected) { + // report timeout if latch not detected + *timeoutDetected = (latch == NULL || *latch == 0); + } +} + +__global__ void preUploadAnnotation() +{ +} + +__global__ void postUploadAnnotation() +{ +} + +cudaGraph_t createParallelChain(int length, int width, bool singleEntry = false) +{ + RANGE_PUSH(__func__); + RANGE("capture"); + cudaGraph_t graph; + cudaStreamBeginCapture(stream[0], cudaStreamCaptureModeGlobal); + int streamIdx = 0; + if (singleEntry) { + empty<<<1,1,0,stream[streamIdx]>>>(); + } + + cudaEventRecord(event[0], stream[0]); + for (int i = 1; i < width; i++) { + cudaStreamWaitEvent(stream[i], event[0]); + } + + for (int i = 0; i < width; i++) { + streamIdx = i; + for (int j = 0; j < length; j++) { + empty<<<1,1,0,stream[streamIdx]>>>(); + } + } + + for (int i = 1; i < width; i++) { + cudaEventRecord(event[0], stream[i]); + cudaStreamWaitEvent(stream[0], event[0]); + } + + cudaStreamEndCapture(stream[0], &graph); + return graph; +} + +std::vector metricName; +std::vector metricValue; + +int counter2 = 0; +void runDemo(cudaGraph_t graph, int length, int width) +{ + cudaGraphExec_t graphExec; + { + auto start = getCpuTime(); + cudaGraphInstantiateWithFlags(&graphExec, graph, 0); + auto end = getCpuTime(); + metricName.push_back("instantiation"); + metricValue.push_back(getMicroSecondDuration(start, end)); + } + { + RANGE("launch including upload"); + auto start = getCpuTime(); + cudaGraphLaunch(graphExec, stream[0]); + auto apiReturn = getCpuTime(); + cudaStreamSynchronize(stream[0]); + auto streamSync = getCpuTime(); + metricName.push_back("first_launch_api"); + metricValue.push_back(getMicroSecondDuration(start, apiReturn)); + metricName.push_back("first_launch_total"); + metricValue.push_back(getMicroSecondDuration(start, streamSync)); + } + { + RANGE("repeat lauch in empty stream"); + auto start = getCpuTime(); + cudaGraphLaunch(graphExec, stream[0]); + auto apiReturn = getCpuTime(); + cudaStreamSynchronize(stream[0]); + auto streamSync = getCpuTime(); + metricName.push_back("repeat_launch_api"); + metricValue.push_back(getMicroSecondDuration(start, apiReturn)); + metricName.push_back("repeat_launch_total"); + metricValue.push_back(getMicroSecondDuration(start, streamSync)); + } + { + // re-instantiating the exec to simulate first launch into a busy stream. + cudaGraphExecDestroy(graphExec); + cudaGraphInstantiateWithFlags(&graphExec, graph, 0); + + long long maxTimeoutNanoSeconds = 4000 + 500*length*width; + waitWithTimeout<<<1,1,0,stream[0]>>>(maxTimeoutNanoSeconds, &hostData->timeoutDetected, &hostData->timeElapsed, &hostData->latch); + + RANGE("launch including upload in busy stream"); + cudaEventRecord(timingEvent[0], stream[0]); + cudaGraphLaunch(graphExec, stream[0]); + cudaEventRecord(timingEvent[1], stream[0]); + + hostData->latch = 1; + cudaStreamSynchronize(stream[0]); + + metricName.push_back("first_launch_device"); + metricValue.push_back(getAsyncMicroSecondDuration(timingEvent[0], timingEvent[1])); + metricName.push_back("blockingKernelTimeoutDetected"); + metricValue.push_back(hostData->timeoutDetected); + hostData->latch = 0; + hostData->timeoutDetected = 0; + } + { + RANGE("repeat lauch in busy stream"); + long long maxTimeoutNanoSeconds = 4000 + 500*length*width; + waitWithTimeout<<<1,1,0,stream[0]>>>(maxTimeoutNanoSeconds, &hostData->timeoutDetected, &hostData->timeElapsed, &hostData->latch); + cudaEventRecord(timingEvent[0], stream[0]); + cudaGraphLaunch(graphExec, stream[0]); + cudaEventRecord(timingEvent[1], stream[0]); + + hostData->latch = 1; + cudaStreamSynchronize(stream[0]); + + metricName.push_back("repeat_launch_device"); + metricValue.push_back(getAsyncMicroSecondDuration(timingEvent[0], timingEvent[1])); + metricName.push_back("blockingKernelTimeoutDetected"); + metricValue.push_back(hostData->timeoutDetected); + hostData->latch = 0; + hostData->timeoutDetected = 0; + } + { + // re-instantiating the exec to provide upload with work to do. + cudaGraphExecDestroy(graphExec); + cudaGraphInstantiateWithFlags(&graphExec, graph, 0); + long long maxTimeoutNanoSeconds = 4000 + 1000*length*width; + waitWithTimeout<<<1,1,0,stream[0]>>>(maxTimeoutNanoSeconds, &hostData->timeoutDetected2, &hostData->timeElapsed2, &hostData->latch2); + maxTimeoutNanoSeconds = 2000 + 500*length*width; + waitWithTimeout<<<1,1,0,stream[1]>>>(maxTimeoutNanoSeconds, &hostData->timeoutDetected, &hostData->timeElapsed, &hostData->latch); + + RANGE("uploading a graph off of the critical path"); + preUploadAnnotation<<<1,1,0,stream[1]>>>(); + cudaEventRecord(timingEvent[0], stream[0]); + auto start = getCpuTime(); + cudaGraphUpload(graphExec, stream[1]); + auto apiReturn = getCpuTime(); + cudaEventRecord(event[0],stream[1]); + cudaEventRecord(timingEvent[1], stream[0]); + postUploadAnnotation<<<1,1,0,stream[1]>>>(); + + hostData->latch = 1; // release the blocking kernel for the upload + cudaStreamWaitEvent(stream[0],event[0]); + cudaGraphLaunch(graphExec, stream[0]); + cudaEventSynchronize(event[0]); // upload done, similuate critical path being ready for the graph to run by the release of the second latch + + hostData->latch2 = 1; // release the work + cudaStreamSynchronize(stream[0]); + + metricName.push_back("upload_api_time"); + metricValue.push_back(getMicroSecondDuration(start, apiReturn)); + metricName.push_back("updoad_device_time"); + metricValue.push_back(getAsyncMicroSecondDuration(timingEvent[0], timingEvent[1])); + metricName.push_back("blockingKernelTimeoutDetected"); + metricValue.push_back(hostData->timeoutDetected); + + hostData->latch = 0; + hostData->latch2 = 0; + hostData->timeoutDetected = 0; + hostData->timeoutDetected2 = 0; + } + cudaGraphExecDestroy(graphExec); + cudaGraphDestroy(graph); + RANGE_POP(); +} + +void usage() { + printf("programName [outputFmt] [numTrials] [length] [width] [pattern] [stride] [maxLength] \n"); + printf("\toutputFmt - program output, default=3 (see below)\n"); + printf("\tnumTrials (per length)\n"); + printf("\tstarting length of the topology\n"); + printf("\twidth - width of the graph topology\n"); + printf("\tpattern - Structure of graph, default=0 (see below)\n"); + printf("\tstride - how to grow the length between each set of trials \n"); + printf("\tmaxLength - maximum lenght to try \n"); + printf("\n"); + printf("outputFmt can be:\n"); + printf("\t0: this help message\n"); + printf("\t1: csv data headers\n"); + printf("\t2: per trial csv data\n"); + printf("\t3: csv data & headers\n"); + printf("\t4: csv data is printed and trials are averaged for each length\n"); + printf("\t5: csv data is printed and trials are averaged for each length and headers are printed\n"); + printf("\n"); + printf("Pattern can be:\n"); + printf("\t0: No interconnect between branches\n"); + printf("\t1: Adds an extra root node before the initial fork\n"); +} + +int main(int argc, char **argv) +{ + if(argc < 1) { + usage(); + return 0; + } + + int numTrials=1, length=20, width=1, outputFmt=3, pattern=0, stride = 1; + if(argc > 1) outputFmt = atoi(argv[1]); + if(argc > 2) numTrials = atoi(argv[2]); + if(argc > 3) length= atoi(argv[3]); + if(argc > 4) width= atoi(argv[4]); + if(argc > 5) pattern = atoi(argv[5]); + if(argc > 6) stride = atoi(argv[6]); + int maxLength = length; + if(argc > 7) maxLength = atoi(argv[7]); + if (maxLength < length) { + maxLength = length; + } + + if((outputFmt & 4) && (outputFmt & 2)) { + printf("printing average and all samples doesn't make sense\n"); + } + + if(length == 0 || + width == 0 || + outputFmt == 0 || + outputFmt > 5 || + pattern > 1) + { + usage(); + return 0; + } + + bool singleEntry = (pattern == 1); + + cudaGraph_t graph; + + cudaFree(0); + cudaMallocHost(&hostData, sizeof(*hostData)); + stream.resize(width); + for (int i = 0; i < width; i++) + { + cudaStreamCreate(&stream[i]); + } + + cudaEventCreate(&event[0], cudaEventDisableTiming); + cudaEventCreate(&timingEvent[0], 0); + cudaEventCreate(&timingEvent[1], 0); + + { + RANGE("warmup"); + for (int i = 0; i < width; i++) + { + empty<<<1,1,0,stream[i]>>>(); + } + cudaStreamSynchronize(stream[0]); + + auto start = getCpuTime(); + graph = createParallelChain(length, width, singleEntry); + auto end = getCpuTime(); + metricValue.push_back(getMicroSecondDuration(start, end)); + metricName.push_back("capture"); + runDemo(graph, length, width); + } + + if (outputFmt & 1) { + printf("length, width, pattern, "); + for (int i = 0; i < metricName.size(); i++) { + printf("%s, ", metricName[i]); + } + printf("\r\n"); + } + + if (!(outputFmt & 6)) { + printf("skipping trials since no output is expected\n"); + return; + } + + std::vector metricTotal; + metricTotal.resize(metricValue.size()); + + while (length <= maxLength) { + for (int i = 0; i < numTrials; i++) { + metricName.clear(); + metricValue.clear(); + auto start = getCpuTime(); + graph = createParallelChain(length, width, singleEntry); + auto end = getCpuTime(); + metricValue.push_back(getMicroSecondDuration(start, end)); + + runDemo(graph, length, width); + + if (outputFmt & 2) { + printf("%d, %d, %d, ",length, width, pattern); + for (int i = 0; i < metricValue.size(); i++) { + printf("%0.3f, ", metricValue[i]); + } + printf("\r\n"); + } + if (outputFmt & 4) { + for (int i = 0; i < metricTotal.size(); i++) { + metricTotal[i] += metricValue[i]; + } + } + } + + if (outputFmt & 4) { + printf("%d, %d, %d, ",length, width, pattern); + for (int i = 0; i < metricTotal.size(); i++) { + printf("%0.3f, ", metricTotal[i]/numTrials); + metricTotal[i] = 0; + } + printf("\r\n"); + } + + length += stride; + } + + printf("\n"); +} + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.sln b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.sln new file mode 100644 index 000000000..9a8b80cda --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.sln @@ -0,0 +1,20 @@ + +Microsoft Visual Studio Solution File, Format Version 12.00 +# Visual Studio 2017 +Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cudaGraphsPerfScaling", "cudaGraphsPerfScaling_vs2017.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}" +EndProject +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug|x64 = Debug|x64 + Release|x64 = Release|x64 + EndGlobalSection + GlobalSection(ProjectConfigurationPlatforms) = postSolution + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64 + EndGlobalSection + GlobalSection(SolutionProperties) = preSolution + HideSolutionNode = FALSE + EndGlobalSection +EndGlobal diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.vcxproj b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.vcxproj new file mode 100644 index 000000000..88bfe7f13 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2017.vcxproj @@ -0,0 +1,112 @@ + + + + $(VCTargetsPath)\BuildCustomizations + + + + Debug + x64 + + + Release + x64 + + + + {997E0757-EA74-4A4E-A0FC-47D8C8831A15} + cudaGraphsPerfScaling_vs2017 + cudaGraphsPerfScaling + + + + $([Microsoft.Build.Utilities.ToolLocationHelper]::GetLatestSDKTargetPlatformVersion('Windows', '10.0')) + $(LatestTargetPlatformVersion) + $(WindowsTargetPlatformVersion) + + + + Application + MultiByte + v141 + + + true + + + true + + + + + + + + + + + $(Platform)/$(Configuration)/ + $(IncludePath) + AllRules.ruleset + + + + + ../../../bin/win64/$(Configuration)/ + + + + Level3 + WIN32;_MBCS;%(PreprocessorDefinitions) + ./;$(CudaToolkitDir)/include;../../../Common; + + + Console + cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies) + $(CudaToolkitLibDir); + $(OutDir)/cudaGraphsPerfScaling.exe + + + compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_89,sm_89;compute_90,sm_90; + -Xcompiler "/wd 4819" --threads 0 + ./;../../../Common + WIN32 + + + + + Disabled + MultiThreadedDebug + + + true + Default + + + MTd + 64 + + + + + MaxSpeed + MultiThreaded + + + false + UseLinkTimeCodeGeneration + + + MT + 64 + + + + + + + + + + + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.sln b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.sln new file mode 100644 index 000000000..5c4433453 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.sln @@ -0,0 +1,20 @@ + +Microsoft Visual Studio Solution File, Format Version 12.00 +# Visual Studio 2019 +Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cudaGraphsPerfScaling", "cudaGraphsPerfScaling_vs2019.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}" +EndProject +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug|x64 = Debug|x64 + Release|x64 = Release|x64 + EndGlobalSection + GlobalSection(ProjectConfigurationPlatforms) = postSolution + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64 + EndGlobalSection + GlobalSection(SolutionProperties) = preSolution + HideSolutionNode = FALSE + EndGlobalSection +EndGlobal diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.vcxproj b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.vcxproj new file mode 100644 index 000000000..f2d603436 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2019.vcxproj @@ -0,0 +1,108 @@ + + + + $(VCTargetsPath)\BuildCustomizations + + + + Debug + x64 + + + Release + x64 + + + + {997E0757-EA74-4A4E-A0FC-47D8C8831A15} + cudaGraphsPerfScaling_vs2019 + cudaGraphsPerfScaling + + + + + Application + MultiByte + v142 + 10.0 + + + true + + + true + + + + + + + + + + + $(Platform)/$(Configuration)/ + $(IncludePath) + AllRules.ruleset + + + + + ../../../bin/win64/$(Configuration)/ + + + + Level3 + WIN32;_MBCS;%(PreprocessorDefinitions) + ./;$(CudaToolkitDir)/include;../../../Common; + + + Console + cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies) + $(CudaToolkitLibDir); + $(OutDir)/cudaGraphsPerfScaling.exe + + + compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_89,sm_89;compute_90,sm_90; + -Xcompiler "/wd 4819" --threads 0 + ./;../../../Common + WIN32 + + + + + Disabled + MultiThreadedDebug + + + true + Default + + + MTd + 64 + + + + + MaxSpeed + MultiThreaded + + + false + UseLinkTimeCodeGeneration + + + MT + 64 + + + + + + + + + + + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.sln b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.sln new file mode 100644 index 000000000..76280160d --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.sln @@ -0,0 +1,20 @@ + +Microsoft Visual Studio Solution File, Format Version 12.00 +# Visual Studio 2022 +Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cudaGraphsPerfScaling", "cudaGraphsPerfScaling_vs2022.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}" +EndProject +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug|x64 = Debug|x64 + Release|x64 = Release|x64 + EndGlobalSection + GlobalSection(ProjectConfigurationPlatforms) = postSolution + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64 + {997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64 + EndGlobalSection + GlobalSection(SolutionProperties) = preSolution + HideSolutionNode = FALSE + EndGlobalSection +EndGlobal diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.vcxproj b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.vcxproj new file mode 100644 index 000000000..30384f070 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/cudaGraphsPerfScaling_vs2022.vcxproj @@ -0,0 +1,108 @@ + + + + $(VCTargetsPath)\BuildCustomizations + + + + Debug + x64 + + + Release + x64 + + + + {997E0757-EA74-4A4E-A0FC-47D8C8831A15} + cudaGraphsPerfScaling_vs2022 + cudaGraphsPerfScaling + + + + + Application + MultiByte + v143 + 10.0 + + + true + + + true + + + + + + + + + + + $(Platform)/$(Configuration)/ + $(IncludePath) + AllRules.ruleset + + + + + ../../../bin/win64/$(Configuration)/ + + + + Level3 + WIN32;_MBCS;%(PreprocessorDefinitions) + ./;$(CudaToolkitDir)/include;../../../Common; + + + Console + cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies) + $(CudaToolkitLibDir); + $(OutDir)/cudaGraphsPerfScaling.exe + + + compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_89,sm_89;compute_90,sm_90; + -Xcompiler "/wd 4819" --threads 0 + ./;../../../Common + WIN32 + + + + + Disabled + MultiThreadedDebug + + + true + Default + + + MTd + 64 + + + + + MaxSpeed + MultiThreaded + + + false + UseLinkTimeCodeGeneration + + + MT + 64 + + + + + + + + + + + diff --git a/Samples/6_Performance/cudaGraphsPerfScaling/dataCollection.bash b/Samples/6_Performance/cudaGraphsPerfScaling/dataCollection.bash new file mode 100644 index 000000000..a382be108 --- /dev/null +++ b/Samples/6_Performance/cudaGraphsPerfScaling/dataCollection.bash @@ -0,0 +1,17 @@ +GPU=$1 +DRIVER_VERSION=$2 +BINARY=./cudaGraphsPerfScaling +datadir=PERF_DATA + +suffix=$DRIVER_VERSION +prefix=$GPU +mkdir -p $datadir + +trials=600 + +width=1 +nvidia-smi > $datadir/${prefix}_info_${suffix}.txt +$BINARY 5 $trials 1 $width 0 1 256 > $datadir/${prefix}_${width}_small_${suffix}.csv +$BINARY 5 $trials 1 $width 0 32 2048 > $datadir/${prefix}_${width}_large_${suffix}.csv +width=4 +$BINARY 5 $trials 1 $width 0 1 256 > $datadir/${prefix}_${width}_small_${suffix}.csv diff --git a/Samples/6_Performance/transpose/Makefile b/Samples/6_Performance/transpose/Makefile index 1f6d156e2..6885a8d02 100644 --- a/Samples/6_Performance/transpose/Makefile +++ b/Samples/6_Performance/transpose/Makefile @@ -169,6 +169,19 @@ CCFLAGS := LDFLAGS := # build flags + +# Link flag for customized HOST_COMPILER with gcc realpath +GCC_PATH := $(shell which gcc) +ifeq ($(CUSTOM_HOST_COMPILER),1) + ifneq ($(filter /%,$(HOST_COMPILER)),) + ifneq ($(findstring gcc,$(HOST_COMPILER)),) + ifneq ($(GCC_PATH),$(HOST_COMPILER)) + LDFLAGS += -lstdc++ + endif + endif + endif +endif + ifeq ($(TARGET_OS),darwin) LDFLAGS += -rpath $(CUDA_PATH)/lib CCFLAGS += -arch $(HOST_ARCH) diff --git a/Samples/6_Performance/transpose/README.md b/Samples/6_Performance/transpose/README.md index e069e1c66..32c10bb19 100644 --- a/Samples/6_Performance/transpose/README.md +++ b/Samples/6_Performance/transpose/README.md @@ -27,7 +27,7 @@ cudaMemcpy, cudaMalloc, cudaFree, cudaGetLastError, cudaEventSynchronize, cudaEv ## Prerequisites -Download and install the [CUDA Toolkit 12.4](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. +Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. ## Build and Run diff --git a/Samples/6_Performance/transpose/transpose_vs2017.vcxproj b/Samples/6_Performance/transpose/transpose_vs2017.vcxproj index 22e928a7b..195a6ce38 100644 --- a/Samples/6_Performance/transpose/transpose_vs2017.vcxproj +++ b/Samples/6_Performance/transpose/transpose_vs2017.vcxproj @@ -38,7 +38,7 @@ - + @@ -107,6 +107,6 @@ - + diff --git a/Samples/6_Performance/transpose/transpose_vs2019.vcxproj b/Samples/6_Performance/transpose/transpose_vs2019.vcxproj index 6993e8485..7a901a8d3 100644 --- a/Samples/6_Performance/transpose/transpose_vs2019.vcxproj +++ b/Samples/6_Performance/transpose/transpose_vs2019.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - + diff --git a/Samples/6_Performance/transpose/transpose_vs2022.vcxproj b/Samples/6_Performance/transpose/transpose_vs2022.vcxproj index 28938d904..56ce0896e 100644 --- a/Samples/6_Performance/transpose/transpose_vs2022.vcxproj +++ b/Samples/6_Performance/transpose/transpose_vs2022.vcxproj @@ -34,7 +34,7 @@ - + @@ -103,6 +103,6 @@ - +