NASP/cuda-samples
34
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2024-10-06 05:59:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

add and update samples for CUDA 11.6

Browse Source
This commit is contained in:
Rutwik Choughule 2022-01-13 11:35:24 +05:30
parent 11de19f00c
commit 2e41896e1b
4615 changed files with 178150 additions and 181350 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

117
CHANGELOG.md Normal file
View File

@ -0,0 +1,117 @@
## Changelog
### CUDA 11.5
* Added `cuDLAHybridMode`. Demonstrate usage of cuDLA in hybrid mode.
* Added `cuDLAStandaloneMode`. Demonstrate usage of cuDLA in standalone mode.
* Added `cuDLAErrorReporting`. Demonstrate DLA error detection via CUDA.
* Added `graphMemoryNodes`. Demonstrates memory allocations and frees within CUDA graphs using Graph APIs and Stream Capture APIs.
* Added `graphMemoryFootprint`. Demonstrates how graph memory nodes re-use virtual addresses and physical memory.
* All samples from CUDA toolkit are now available on [GitHub](https://github.com/nvidia/cuda-samples).
### CUDA 11.4 update 1
* Added support for VS Code on linux platform.
### CUDA 11.4
* Added `cdpQuadtree`. Demonstrates Quad Trees implementation using CUDA Dynamic Parallelism.
* Updated `simpleVulkan`, `simpleVulkanMMAP` and `vulkanImageCUDA`. Demonstrates use of SPIR-V shaders.
### CUDA 11.3
* Added `streamOrderedAllocationIPC`. Demonstrates Inter Process Communication using one process per GPU for computation.
* Added `simpleCUBLAS_LU`. Demonstrates batched matrix LU decomposition using cuBLAS API `cublas<t>getrfBatched()`
* Updated `simpleVulkan`. Demonstrates use of timeline semaphore.
* Updated multiple samples to use pinned memory using `cudaMallocHost()`.
### CUDA 11.2
* Added `streamOrderedAllocation`. Demonstrates stream ordered memory allocation on a GPU using cudaMallocAsync and cudaMemPool family of APIs.
* Added `streamOrderedAllocationP2P`. Demonstrates peer-to-peer access of stream ordered memory allocated using cudaMallocAsync and cudaMemPool family of APIs.
* Dropped Visual Studio 2015 support from all the windows supported samples.
* FreeImage is no longer distributed with the CUDA Samples. On Windows, see the [Dependencies](./README.md#freeimage) section for more details on how to set up FreeImage. On Linux, it is recommended to install FreeImage with your distribution's package manager.
* All the samples using CUDA Pipeline & Arrive-wait barriers are been updated to use new `cuda::pipeline` and `cuda::barrier` interfaces.
* Updated all the samples to build with parallel build option `--threads` of `nvcc` cuda compiler.
* Added `cudaNvSciNvMedia`. Demonstrates CUDA-NvMedia interop via NvSciBuf/NvSciSync APIs.
* Added `simpleGL`. Demonstrates interoperability between CUDA and OpenGL.
### CUDA 11.1
* Added `watershedSegmentationNPP`. Demonstrates how to use the NPP watershed segmentation function.
* Added `batchedLabelMarkersAndLabelCompressionNPP`. Demonstrates how to use the NPP label markers generation and label compression functions based on a Union Find (UF) algorithm including both single image and batched image versions.
* Dropped Visual Studio 2012, 2013 support from all the windows supported samples.
* Added kernel performing warp aggregated atomic max in multi buckets using cg::labeled_partition & cg::reduce in `warpAggregatedAtomicsCG`.
* Added extended CG shuffle mechanics to `shfl_scan` sample.
* Added `cudaOpenMP`. Demonstrates how to use OpenMP API to write an application for multiple GPUs.
* Added `simpleZeroCopy`. Demonstrates how to use zero copy, kernels can read and write directly to pinned system memory.
### CUDA 11.0
* Added `dmmaTensorCoreGemm`. Demonstrates double precision GEMM computation using the Double precision Warp Matrix Multiply and Accumulate (WMMA) API introduced with CUDA 11 in Ampere chip family tensor cores.
* Added `bf16TensorCoreGemm`. Demonstrates __nv_bfloat16 (e8m7) GEMM computation using the __nv_bfloat16 WMMA API introduced with CUDA 11 in Ampere chip family tensor cores.
* Added `tf32TensorCoreGemm`. Demonstrates tf32 (e8m10) GEMM computation using the tf32 WMMA API introduced with CUDA 11 in Ampere chip family tensor cores.
* Added `globalToShmemAsyncCopy`. Demonstrates async copy of data from global to shared memory when on compute capability 8.0 or higher. Also demonstrates arrive-wait barrier for synchronization.
* Added `simpleAWBarrier`. Demonstrates arrive wait barriers.
* Added `simpleAttributes`. Demonstrates the stream attributes that affect L2 locality.
* Added warp aggregated atomic multi bucket increments kernel using labeled_partition cooperative groups in `warpAggregatedAtomicsCG` which can be used on compute capability 7.0 and above GPU architectures.
* Added `binaryPartitionCG`. Demonstrates binary partition cooperative groups and reduction within the thread block.
* Added two new reduction kernels in `reduction` one which demonstrates reduce_add_sync intrinstic supported on compute capability 8.0 and another which uses cooperative_groups::reduce function which does thread_block_tile level reduction introduced from CUDA 11.0.
* Added `cudaCompressibleMemory`. Demonstrates compressible memory allocation using cuMemMap API.
* Added `simpleVulkanMMAP`. Demonstrates Vulkan CUDA Interop via cuMemMap APIs.
* Added `concurrentKernels`. Demonstrates the use of CUDA streams for concurrent execution of several kernels on a GPU.
* Dropped Mac OSX support from all samples.
### CUDA 10.2
* Added `simpleD3D11`. Demonstrates CUDA-D3D11 External Resource Interoperability APIs for updating D3D11 buffers from CUDA and synchronization between D3D11 and CUDA with Keyed Mutexes.
* Added `simpleDrvRuntime`. Demonstrates CUDA Driver and Runtime APIs working together to load fatbinary of a CUDA kernel.
* Added `vectorAddMMAP`. Demonstrates how cuMemMap API allows the user to specify the physical properties of their memory while retaining the contiguous nature of their access.
* Added `memMapIPCDrv`. Demonstrates Inter Process Communication using cuMemMap APIs.
* Added `cudaNvSci`. Demonstrates CUDA-NvSciBuf/NvSciSync Interop.
* Added `jacobiCudaGraphs`. Demonstrates Instantiated CUDA Graph Update with Jacobi Iterative Method using different approaches.
* Added `cuSolverSp_LinearSolver`. Demonstrates cuSolverSP's LU, QR and Cholesky factorization.
* Added `MersenneTwisterGP11213`. Demonstrates the Mersenne Twister random number generator GP11213 in cuRAND.
### CUDA 10.1 Update 2
* Added `vulkanImageCUDA`. Demonstrates how to perform Vulkan image - CUDA Interop.
* Added `nvJPEG_encoder`. Demonstrates encoding of jpeg images using NVJPEG Library.
* Added Windows OS support to `nvJPEG` sample.
* Added `boxFilterNPP`. Demonstrates how to use NPP FilterBox function to perform a box filter.
* Added `cannyEdgeDetectorNPP`. Demonstrates the nppiFilterCannyBorder_8u_C1R Canny Edge Detection image filter function.
### CUDA 10.1 Update 1
* Added `NV12toBGRandResize`. Demonstrates how to convert and resize NV12 frames to BGR planars frames using CUDA in batch.
* Added `EGLStream_CUDA_Interop`. Demonstrates data exchange between CUDA and EGL Streams.
* Added `cuSolverDn_LinearSolver`. Demonstrates cuSolverDN's LU, QR and Cholesky factorization.
* Added support of Visual Studio 2019 to all samples supported on [Windows](./README.md#windows-1).
### CUDA 10.1
* Added `immaTensorCoreGemm`. Demonstrates integer GEMM computation using the Warp Matrix Multiply and Accumulate (WMMA) API for integers employing the Tensor Cores.
* Added `simpleIPC`. Demonstrates Inter Process Communication with one process per GPU for computation.
* Added `nvJPEG`. Demonstrates single and batched decoding of jpeg images using NVJPEG Library.
* Added `bandwidthTest`. It measures the memcopy bandwidth of the GPU and memcpy bandwidth across PCI-e.
* Added `reduction`. Demonstrates several important optimization strategies for Data-Parallel Algorithms like reduction.
* Update all the samples to support CUDA 10.1.
### CUDA 10.0
* Added `simpleCudaGraphs`. Demonstrates CUDA Graphs creation, instantiation and launch using Graphs APIs and Stream Capture APIs.
* Added `conjugateGradientCudaGraphs`. Demonstrates conjugate gradient solver on GPU using CUBLAS and CUSPARSE library calls captured and called using CUDA Graph APIs.
* Added `simpleVulkan`. Demonstrates Vulkan - CUDA Interop.
* Added `simpleD3D12`. Demonstrates DX12 - CUDA Interop.
* Added `UnifiedMemoryPerf`. Demonstrates performance comparision of various memory types involved in system.
* Added `p2pBandwidthLatencyTest`. Demonstrates Peer-To-Peer (P2P) data transfers between pairs of GPUs and computes latency and bandwidth.
* Added `systemWideAtomics`. Demonstrates system wide atomic instructions.
* Added `simpleCUBLASXT`. Demonstrates CUBLAS-XT library which performs GEMM operations over multiple GPUs.
* Added Windows OS support to `conjugateGradientMultiDeviceCG` sample.
* Removed support of Visual Studio 2010 from all samples.
### CUDA 9.2
This is the first release of CUDA Samples on GitHub:
* Added `vectorAdd_nvrtc`. Demonstrates runtime compilation library using NVRTC of a simple vectorAdd kernel.
* Added `warpAggregatedAtomicsCG`. Demonstrates warp aggregated atomics using Cooperative Groups.
* Added `deviceQuery`. Enumerates the properties of the CUDA devices present in the system.
* Added `matrixMul`. Demonstrates a matrix multiplication using shared memory through tiled approach.
* Added `matrixMulDrv`. Demonstrates a matrix multiplication using shared memory through tiled approach, uses CUDA Driver API.
* Added `cudaTensorCoreGemm`. Demonstrates a GEMM computation using the Warp Matrix Multiply and Accumulate (WMMA) API introduced in CUDA 9, as well as the new Tensor Cores introduced in the Volta chip family.
* Added `simpleVoteIntrinsics` which uses *_sync equivalent of the vote intrinsics _any, _all added since CUDA 9.0.
* Added `shfl_scan` which uses *_sync equivalent of the shfl intrinsics added since CUDA 9.0.
* Added `conjugateGradientMultiBlockCG`. Demonstrates a conjugate gradient solver on GPU using Multi Block Cooperative Groups.
* Added `conjugateGradientMultiDeviceCG`. Demonstrates a conjugate gradient solver on multiple GPUs using Multi Device Cooperative Groups, also uses unified memory prefetching and usage hints APIs.
* Added `simpleCUBLAS`. Demonstrates how perform GEMM operations using CUBLAS library.
* Added `simpleCUFFT`. Demonstrates how perform FFT operations using CUFFT library.

2
Common/UtilNPP/Exceptions.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/Image.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/ImageAllocatorsCPU.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/ImageAllocatorsNPP.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/ImageIO.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/ImagePacked.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/ImagesCPU.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/ImagesNPP.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/Pixel.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/Signal.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/SignalAllocatorsCPU.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/SignalAllocatorsNPP.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/SignalsCPU.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/UtilNPP/SignalsNPP.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

1
Common/data/Lena_512x512_8u_Gray.raw
View File

File diff suppressed because one or more lines are too long

BIN
Common/data/lena_512x512_8u.raw
View File

Binary file not shown.

BIN
Common/data/teapot512.pgm Normal file
View File

Binary file not shown.

BIN
Common/data/teapot_512x512_8u.raw Normal file
View File

Binary file not shown.

BIN
Common/data/teapot_512x512_8u_Gray.raw Normal file
View File

Binary file not shown.

2
Common/drvapi_error_string.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/dynlink_d3d10.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/dynlink_d3d11.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/exception.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

3
Common/helper_cuda.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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
@ -665,6 +665,7 @@ inline int _ConvertSMVer2Cores(int major, int minor) {
{0x75, 64},
{0x80, 64},
{0x86, 128},
{0x87, 128},
{-1, -1}};
int index = 0;

3
Common/helper_cuda_drvapi.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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
@ -113,6 +113,7 @@ inline int _ConvertSMVer2CoresDRV(int major, int minor) {
{0x75, 64},
{0x80, 64},
{0x86, 128},
{0x87, 128},
{-1, -1}};
int index = 0;

2
Common/helper_cusolver.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/helper_functions.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/helper_gl.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/helper_image.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/helper_math.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/helper_multiprocess.cpp
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/helper_multiprocess.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

10
Common/helper_nvJPEG.hxx
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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
@ -399,10 +399,10 @@ int getInputDir(std::string &input_dir, const char *executable_path) {
// Search in default paths for input images.
std::string pathname = "";
const char *searchPath[] = {
"./images", "../../../../Samples/<executable_name>/images",
"../../../Samples/<executable_name>/images",
"../../Samples/<executable_name>/images"};
"./images",
"../../../../Samples/4_CUDA_Libraries/<executable_name>/images",
"../../../Samples/4_CUDA_Libraries/<executable_name>/images",
"../../Samples/4_CUDA_Libraries/<executable_name>/images"};
for (unsigned int i = 0; i < sizeof(searchPath) / sizeof(char *); ++i) {
std::string pathname(searchPath[i]);

65
Common/helper_string.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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
@ -100,7 +100,7 @@ inline int stringRemoveDelimiter(char delimiter, const char *string) {
string_start++;
}
if (string_start >= static_cast<int>(strlen(string))) {
if (string_start >= static_cast<int>(strlen(string) - 1)) {
return 0;
}
@ -285,14 +285,73 @@ inline char *sdkFindFilePath(const char *filename,
// the .exe file, a .bat file launching an .exe, a browser .exe launching the
// .exe or .bat, etc
const char *searchPath[] = {
"./", // same dir
"./", // same dir
"./data/", // same dir
"../../../../Samples/<executable_name>/", // up 4 in tree
"../../../Samples/<executable_name>/", // up 3 in tree
"../../Samples/<executable_name>/", // up 2 in tree
"../../../../Samples/<executable_name>/data/", // up 4 in tree
"../../../Samples/<executable_name>/data/", // up 3 in tree
"../../Samples/<executable_name>/data/", // up 2 in tree
"../../../../Samples/0_Introduction/<executable_name>/", // up 4 in tree
"../../../Samples/0_Introduction/<executable_name>/", // up 3 in tree
"../../Samples/0_Introduction/<executable_name>/", // up 2 in tree
"../../../../Samples/1_Utilities/<executable_name>/", // up 4 in tree
"../../../Samples/1_Utilities/<executable_name>/", // up 3 in tree
"../../Samples/1_Utilities/<executable_name>/", // up 2 in tree
"../../../../Samples/2_Concepts_and_Techniques/<executable_name>/", // up 4 in tree
"../../../Samples/2_Concepts_and_Techniques/<executable_name>/", // up 3 in tree
"../../Samples/2_Concepts_and_Techniques/<executable_name>/", // up 2 in tree
"../../../../Samples/3_CUDA_Features/<executable_name>/", // up 4 in tree
"../../../Samples/3_CUDA_Features/<executable_name>/", // up 3 in tree
"../../Samples/3_CUDA_Features/<executable_name>/", // up 2 in tree
"../../../../Samples/4_CUDA_Libraries/<executable_name>/", // up 4 in tree
"../../../Samples/4_CUDA_Libraries/<executable_name>/", // up 3 in tree
"../../Samples/4_CUDA_Libraries/<executable_name>/", // up 2 in tree
"../../../../Samples/5_Domain_Specific/<executable_name>/", // up 4 in tree
"../../../Samples/5_Domain_Specific/<executable_name>/", // up 3 in tree
"../../Samples/5_Domain_Specific/<executable_name>/", // up 2 in tree
"../../../../Samples/6_Performance/<executable_name>/", // up 4 in tree
"../../../Samples/6_Performance/<executable_name>/", // up 3 in tree
"../../Samples/6_Performance/<executable_name>/", // up 2 in tree
"../../../../Samples/0_Introduction/<executable_name>/data/", // up 4 in tree
"../../../Samples/0_Introduction/<executable_name>/data/", // up 3 in tree
"../../Samples/0_Introduction/<executable_name>/data/", // up 2 in tree
"../../../../Samples/1_Utilities/<executable_name>/data/", // up 4 in tree
"../../../Samples/1_Utilities/<executable_name>/data/", // up 3 in tree
"../../Samples/1_Utilities/<executable_name>/data/", // up 2 in tree
"../../../../Samples/2_Concepts_and_Techniques/<executable_name>/data/", // up 4 in tree
"../../../Samples/2_Concepts_and_Techniques/<executable_name>/data/", // up 3 in tree
"../../Samples/2_Concepts_and_Techniques/<executable_name>/data/", // up 2 in tree
"../../../../Samples/3_CUDA_Features/<executable_name>/data/", // up 4 in tree
"../../../Samples/3_CUDA_Features/<executable_name>/data/", // up 3 in tree
"../../Samples/3_CUDA_Features/<executable_name>/data/", // up 2 in tree
"../../../../Samples/4_CUDA_Libraries/<executable_name>/data/", // up 4 in tree
"../../../Samples/4_CUDA_Libraries/<executable_name>/data/", // up 3 in tree
"../../Samples/4_CUDA_Libraries/<executable_name>/data/", // up 2 in tree
"../../../../Samples/5_Domain_Specific/<executable_name>/data/", // up 4 in tree
"../../../Samples/5_Domain_Specific/<executable_name>/data/", // up 3 in tree
"../../Samples/5_Domain_Specific/<executable_name>/data/", // up 2 in tree
"../../../../Samples/6_Performance/<executable_name>/data/", // up 4 in tree
"../../../Samples/6_Performance/<executable_name>/data/", // up 3 in tree
"../../Samples/6_Performance/<executable_name>/data/", // up 2 in tree
"../../../../Common/data/", // up 4 in tree
"../../../Common/data/", // up 3 in tree
"../../Common/data/" // up 2 in tree

2
Common/helper_timer.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/multithreading.cpp
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/multithreading.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/nvMath.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/nvMatrix.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/nvQuaternion.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/nvShaderUtils.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/nvVector.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/nvrtc_helper.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/param.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/paramgl.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/rendercheck_d3d10.cpp
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/rendercheck_d3d10.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/rendercheck_d3d11.cpp
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/rendercheck_d3d11.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/rendercheck_d3d9.cpp
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/rendercheck_d3d9.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

2
Common/rendercheck_gl.h
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

1312
Common/rendercheck_gles.h Normal file
View File

File diff suppressed because it is too large Load Diff

2
LICENSE
View File

@ -1,4 +1,4 @@
Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
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

12
Makefile
View File

@ -1,6 +1,6 @@
###############################################################################
#
# Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
# 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
@ -44,20 +44,22 @@ PROJECTS := $(filter-out $(FILTER_OUT),$(PROJECTS))
%.ph_build :
+@$(MAKE) -C $(dir $*) $(MAKECMDGOALS)
%.ph_test :
+@$(MAKE) -C $(dir $*) testrun
%.ph_clean :
+@$(MAKE) -C $(dir $*) clean $(USE_DEVICE)
%.ph_clobber :
+@$(MAKE) -C $(dir $*) clobber $(USE_DEVICE)
%.ph_run :
+@$(MAKE) -C $(dir $*) run
all: $(addsuffix .ph_build,$(PROJECTS))
@echo "Finished building CUDA samples"
build: $(addsuffix .ph_build,$(PROJECTS))
test : $(addsuffix .ph_test,$(PROJECTS))
tidy:
@find * | egrep "#" | xargs rm -f
@find * | egrep "\~" | xargs rm -f
@ -65,5 +67,3 @@ tidy:
clean: tidy $(addsuffix .ph_clean,$(PROJECTS))
clobber: clean $(addsuffix .ph_clobber,$(PROJECTS))
run: $(addsuffix .ph_run,$(PROJECTS))

243
README.md
View File

@ -1,130 +1,23 @@
# CUDA Samples
Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 11.5](https://developer.nvidia.com/cuda-downloads).
Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 11.6](https://developer.nvidia.com/cuda-downloads).
## Release Notes
This section describes the release notes for the CUDA Samples on GitHub only.
### CUDA 11.5
* Added `cuDLAHybridMode`. Demonstrate usage of cuDLA in hybrid mode.
* Added `cuDLAStandaloneMode`. Demonstrate usage of cuDLA in standalone mode.
* Added `cuDLAErrorReporting`. Demonstrate DLA error detection via CUDA.
* Added `graphMemoryNodes`. Demonstrates memory allocations and frees within CUDA graphs using Graph APIs and Stream Capture APIs.
* Added `graphMemoryFootprint`. Demonstrates how graph memory nodes re-use virtual addresses and physical memory.
* All samples from CUDA toolkit are now available on [GitHub](https://github.com/nvidia/cuda-samples).
### CUDA 11.6
* Added new folder structure for samples
* Added support of Visual Studio 2022 to all samples supported on [Windows](#windows-1).
* All CUDA samples are now only available on [GitHub](https://github.com/nvidia/cuda-samples). They are no longer available via CUDA toolkit.
### CUDA 11.4 update 1
* Added support for VS Code on linux platform.
### CUDA 11.4
* Added `cdpQuadtree`. Demonstrates Quad Trees implementation using CUDA Dynamic Parallelism.
* Updated `simpleVulkan`, `simpleVulkanMMAP` and `vulkanImageCUDA`. Demonstrates use of SPIR-V shaders.
### CUDA 11.3
* Added `streamOrderedAllocationIPC`. Demonstrates Inter Process Communication using one process per GPU for computation.
* Added `simpleCUBLAS_LU`. Demonstrates batched matrix LU decomposition using cuBLAS API `cublas<t>getrfBatched()`
* Updated `simpleVulkan`. Demonstrates use of timeline semaphore.
* Updated multiple samples to use pinned memory using `cudaMallocHost()`.
### CUDA 11.2
* Added `streamOrderedAllocation`. Demonstrates stream ordered memory allocation on a GPU using cudaMallocAsync and cudaMemPool family of APIs.
* Added `streamOrderedAllocationP2P`. Demonstrates peer-to-peer access of stream ordered memory allocated using cudaMallocAsync and cudaMemPool family of APIs.
* Dropped Visual Studio 2015 support from all the windows supported samples.
* FreeImage is no longer distributed with the CUDA Samples. On Windows, see the [Dependencies](#freeimage) section for more details on how to set up FreeImage. On Linux, it is recommended to install FreeImage with your distribution's package manager.
* All the samples using CUDA Pipeline & Arrive-wait barriers are been updated to use new `cuda::pipeline` and `cuda::barrier` interfaces.
* Updated all the samples to build with parallel build option `--threads` of `nvcc` cuda compiler.
* Added `cudaNvSciNvMedia`. Demonstrates CUDA-NvMedia interop via NvSciBuf/NvSciSync APIs.
* Added `simpleGL`. Demonstrates interoperability between CUDA and OpenGL.
### CUDA 11.1
* Added `watershedSegmentationNPP`. Demonstrates how to use the NPP watershed segmentation function.
* Added `batchedLabelMarkersAndLabelCompressionNPP`. Demonstrates how to use the NPP label markers generation and label compression functions based on a Union Find (UF) algorithm including both single image and batched image versions.
* Dropped Visual Studio 2012, 2013 support from all the windows supported samples.
* Added kernel performing warp aggregated atomic max in multi buckets using cg::labeled_partition & cg::reduce in `warpAggregatedAtomicsCG`.
* Added extended CG shuffle mechanics to `shfl_scan` sample.
* Added `cudaOpenMP`. Demonstrates how to use OpenMP API to write an application for multiple GPUs.
* Added `simpleZeroCopy`. Demonstrates how to use zero copy, kernels can read and write directly to pinned system memory.
### CUDA 11.0
* Added `dmmaTensorCoreGemm`. Demonstrates double precision GEMM computation using the Double precision Warp Matrix Multiply and Accumulate (WMMA) API introduced with CUDA 11 in Ampere chip family tensor cores.
* Added `bf16TensorCoreGemm`. Demonstrates __nv_bfloat16 (e8m7) GEMM computation using the __nv_bfloat16 WMMA API introduced with CUDA 11 in Ampere chip family tensor cores.
* Added `tf32TensorCoreGemm`. Demonstrates tf32 (e8m10) GEMM computation using the tf32 WMMA API introduced with CUDA 11 in Ampere chip family tensor cores.
* Added `globalToShmemAsyncCopy`. Demonstrates async copy of data from global to shared memory when on compute capability 8.0 or higher. Also demonstrates arrive-wait barrier for synchronization.
* Added `simpleAWBarrier`. Demonstrates arrive wait barriers.
* Added `simpleAttributes`. Demonstrates the stream attributes that affect L2 locality.
* Added warp aggregated atomic multi bucket increments kernel using labeled_partition cooperative groups in `warpAggregatedAtomicsCG` which can be used on compute capability 7.0 and above GPU architectures.
* Added `binaryPartitionCG`. Demonstrates binary partition cooperative groups and reduction within the thread block.
* Added two new reduction kernels in `reduction` one which demonstrates reduce_add_sync intrinstic supported on compute capability 8.0 and another which uses cooperative_groups::reduce function which does thread_block_tile level reduction introduced from CUDA 11.0.
* Added `cudaCompressibleMemory`. Demonstrates compressible memory allocation using cuMemMap API.
* Added `simpleVulkanMMAP`. Demonstrates Vulkan CUDA Interop via cuMemMap APIs.
* Added `concurrentKernels`. Demonstrates the use of CUDA streams for concurrent execution of several kernels on a GPU.
* Dropped Mac OSX support from all samples.
### CUDA 10.2
* Added `simpleD3D11`. Demonstrates CUDA-D3D11 External Resource Interoperability APIs for updating D3D11 buffers from CUDA and synchronization between D3D11 and CUDA with Keyed Mutexes.
* Added `simpleDrvRuntime`. Demonstrates CUDA Driver and Runtime APIs working together to load fatbinary of a CUDA kernel.
* Added `vectorAddMMAP`. Demonstrates how cuMemMap API allows the user to specify the physical properties of their memory while retaining the contiguous nature of their access.
* Added `memMapIPCDrv`. Demonstrates Inter Process Communication using cuMemMap APIs.
* Added `cudaNvSci`. Demonstrates CUDA-NvSciBuf/NvSciSync Interop.
* Added `jacobiCudaGraphs`. Demonstrates Instantiated CUDA Graph Update with Jacobi Iterative Method using different approaches.
* Added `cuSolverSp_LinearSolver`. Demonstrates cuSolverSP's LU, QR and Cholesky factorization.
* Added `MersenneTwisterGP11213`. Demonstrates the Mersenne Twister random number generator GP11213 in cuRAND.
### CUDA 10.1 Update 2
* Added `vulkanImageCUDA`. Demonstrates how to perform Vulkan image - CUDA Interop.
* Added `nvJPEG_encoder`. Demonstrates encoding of jpeg images using NVJPEG Library.
* Added Windows OS support to `nvJPEG` sample.
* Added `boxFilterNPP`. Demonstrates how to use NPP FilterBox function to perform a box filter.
* Added `cannyEdgeDetectorNPP`. Demonstrates the nppiFilterCannyBorder_8u_C1R Canny Edge Detection image filter function.
### CUDA 10.1 Update 1
* Added `NV12toBGRandResize`. Demonstrates how to convert and resize NV12 frames to BGR planars frames using CUDA in batch.
* Added `EGLStream_CUDA_Interop`. Demonstrates data exchange between CUDA and EGL Streams.
* Added `cuSolverDn_LinearSolver`. Demonstrates cuSolverDN's LU, QR and Cholesky factorization.
* Added support of Visual Studio 2019 to all samples supported on [Windows](#windows-1).
### CUDA 10.1
* Added `immaTensorCoreGemm`. Demonstrates integer GEMM computation using the Warp Matrix Multiply and Accumulate (WMMA) API for integers employing the Tensor Cores.
* Added `simpleIPC`. Demonstrates Inter Process Communication with one process per GPU for computation.
* Added `nvJPEG`. Demonstrates single and batched decoding of jpeg images using NVJPEG Library.
* Added `bandwidthTest`. It measures the memcopy bandwidth of the GPU and memcpy bandwidth across PCI-e.
* Added `reduction`. Demonstrates several important optimization strategies for Data-Parallel Algorithms like reduction.
* Update all the samples to support CUDA 10.1.
### CUDA 10.0
* Added `simpleCudaGraphs`. Demonstrates CUDA Graphs creation, instantiation and launch using Graphs APIs and Stream Capture APIs.
* Added `conjugateGradientCudaGraphs`. Demonstrates conjugate gradient solver on GPU using CUBLAS and CUSPARSE library calls captured and called using CUDA Graph APIs.
* Added `simpleVulkan`. Demonstrates Vulkan - CUDA Interop.
* Added `simpleD3D12`. Demonstrates DX12 - CUDA Interop.
* Added `UnifiedMemoryPerf`. Demonstrates performance comparision of various memory types involved in system.
* Added `p2pBandwidthLatencyTest`. Demonstrates Peer-To-Peer (P2P) data transfers between pairs of GPUs and computes latency and bandwidth.
* Added `systemWideAtomics`. Demonstrates system wide atomic instructions.
* Added `simpleCUBLASXT`. Demonstrates CUBLAS-XT library which performs GEMM operations over multiple GPUs.
* Added Windows OS support to `conjugateGradientMultiDeviceCG` sample.
* Removed support of Visual Studio 2010 from all samples.
### CUDA 9.2
This is the first release of CUDA Samples on GitHub:
* Added `vectorAdd_nvrtc`. Demonstrates runtime compilation library using NVRTC of a simple vectorAdd kernel.
* Added `warpAggregatedAtomicsCG`. Demonstrates warp aggregated atomics using Cooperative Groups.
* Added `deviceQuery`. Enumerates the properties of the CUDA devices present in the system.
* Added `matrixMul`. Demonstrates a matrix multiplication using shared memory through tiled approach.
* Added `matrixMulDrv`. Demonstrates a matrix multiplication using shared memory through tiled approach, uses CUDA Driver API.
* Added `cudaTensorCoreGemm`. Demonstrates a GEMM computation using the Warp Matrix Multiply and Accumulate (WMMA) API introduced in CUDA 9, as well as the new Tensor Cores introduced in the Volta chip family.
* Added `simpleVoteIntrinsics` which uses *_sync equivalent of the vote intrinsics _any, _all added since CUDA 9.0.
* Added `shfl_scan` which uses *_sync equivalent of the shfl intrinsics added since CUDA 9.0.
* Added `conjugateGradientMultiBlockCG`. Demonstrates a conjugate gradient solver on GPU using Multi Block Cooperative Groups.
* Added `conjugateGradientMultiDeviceCG`. Demonstrates a conjugate gradient solver on multiple GPUs using Multi Device Cooperative Groups, also uses unified memory prefetching and usage hints APIs.
* Added `simpleCUBLAS`. Demonstrates how perform GEMM operations using CUBLAS library.
* Added `simpleCUFFT`. Demonstrates how perform FFT operations using CUFFT library.
### [older versions...](./CHANGELOG.md)
## Getting Started
### Prerequisites
Download and install the [CUDA Toolkit 11.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.6](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
@ -178,107 +71,26 @@ The samples makefiles can take advantage of certain options:
## Samples list
### Samples by OS
### [0. Introduction](./Samples/0_Introduction/README.md)
Basic CUDA samples for beginners that illustrate key concepts with using CUDA and CUDA runtime APIs.
#### Linux
**[simpleAssert_nvrtc](./Samples/simpleAssert_nvrtc)** | **[vectorAdd_nvrtc](./Samples/vectorAdd_nvrtc)** | **[graphMemoryFootprint](./Samples/graphMemoryFootprint)** | **[MC_EstimatePiQ](./Samples/MC_EstimatePiQ)** |
---|---|---|---|
**[reductionMultiBlockCG](./Samples/reductionMultiBlockCG)** | **[cuDLAStandaloneMode](./Samples/cuDLAStandaloneMode)** | **[conjugateGradientPrecond](./Samples/conjugateGradientPrecond)** | **[ptxjit](./Samples/ptxjit)** |
**[threadMigration](./Samples/threadMigration)** | **[EGLStream_CUDA_CrossGPU](./Samples/EGLStream_CUDA_CrossGPU)** | **[threadFenceReduction](./Samples/threadFenceReduction)** | **[simpleAtomicIntrinsics_nvrtc](./Samples/simpleAtomicIntrinsics_nvrtc)** |
**[shfl_scan](./Samples/shfl_scan)** | **[clock](./Samples/clock)** | **[binaryPartitionCG](./Samples/binaryPartitionCG)** | **[MC_EstimatePiP](./Samples/MC_EstimatePiP)** |
**[transpose](./Samples/transpose)** | **[simpleMultiCopy](./Samples/simpleMultiCopy)** | **[cuDLAErrorReporting](./Samples/cuDLAErrorReporting)** | **[concurrentKernels](./Samples/concurrentKernels)** |
**[streamOrderedAllocationIPC](./Samples/streamOrderedAllocationIPC)** | **[UnifiedMemoryPerf](./Samples/UnifiedMemoryPerf)** | **[cppIntegration](./Samples/cppIntegration)** | **[bf16TensorCoreGemm](./Samples/bf16TensorCoreGemm)** |
**[cuSolverSp_LinearSolver](./Samples/cuSolverSp_LinearSolver)** | **[nvJPEG](./Samples/nvJPEG)** | **[watershedSegmentationNPP](./Samples/watershedSegmentationNPP)** | **[MC_EstimatePiInlineP](./Samples/MC_EstimatePiInlineP)** |
**[vulkanImageCUDA](./Samples/vulkanImageCUDA)** | **[boxFilterNPP](./Samples/boxFilterNPP)** | **[simpleAssert](./Samples/simpleAssert)** | **[simpleTemplates](./Samples/simpleTemplates)** |
**[cuHook](./Samples/cuHook)** | **[simpleCUDA2GL](./Samples/simpleCUDA2GL)** | **[matrixMul](./Samples/matrixMul)** | **[quasirandomGenerator_nvrtc](./Samples/quasirandomGenerator_nvrtc)** |
**[nvJPEG_encoder](./Samples/nvJPEG_encoder)** | **[simpleCudaGraphs](./Samples/simpleCudaGraphs)** | **[simpleTextureDrv](./Samples/simpleTextureDrv)** | **[simpleCUFFT](./Samples/simpleCUFFT)** |
**[simpleCallback](./Samples/simpleCallback)** | **[batchCUBLAS](./Samples/batchCUBLAS)** | **[cudaTensorCoreGemm](./Samples/cudaTensorCoreGemm)** | **[simpleAtomicIntrinsics](./Samples/simpleAtomicIntrinsics)** |
**[newdelete](./Samples/newdelete)** | **[bicubicTexture](./Samples/bicubicTexture)** | **[dxtc](./Samples/dxtc)** | **[cudaOpenMP](./Samples/cudaOpenMP)** |
**[cdpBezierTessellation](./Samples/cdpBezierTessellation)** | **[randomFog](./Samples/randomFog)** | **[bilateralFilter](./Samples/bilateralFilter)** | **[conjugateGradient](./Samples/conjugateGradient)** |
**[particles](./Samples/particles)** | **[NV12toBGRandResize](./Samples/NV12toBGRandResize)** | **[Mandelbrot](./Samples/Mandelbrot)** | **[binomialOptions_nvrtc](./Samples/binomialOptions_nvrtc)** |
**[cudaNvSci](./Samples/cudaNvSci)** | **[mergeSort](./Samples/mergeSort)** | **[HSOpticalFlow](./Samples/HSOpticalFlow)** | **[immaTensorCoreGemm](./Samples/immaTensorCoreGemm)** |
**[convolutionTexture](./Samples/convolutionTexture)** | **[simpleVulkan](./Samples/simpleVulkan)** | **[simpleCUBLAS](./Samples/simpleCUBLAS)** | **[jacobiCudaGraphs](./Samples/jacobiCudaGraphs)** |
**[eigenvalues](./Samples/eigenvalues)** | **[streamOrderedAllocationP2P](./Samples/streamOrderedAllocationP2P)** | **[cuSolverSp_LowlevelCholesky](./Samples/cuSolverSp_LowlevelCholesky)** | **[topologyQuery](./Samples/topologyQuery)** |
**[dmmaTensorCoreGemm](./Samples/dmmaTensorCoreGemm)** | **[volumeRender](./Samples/volumeRender)** | **[stereoDisparity](./Samples/stereoDisparity)** | **[simpleTexture](./Samples/simpleTexture)** |
**[simpleStreams](./Samples/simpleStreams)** | **[smokeParticles](./Samples/smokeParticles)** | **[simpleMultiGPU](./Samples/simpleMultiGPU)** | **[deviceQueryDrv](./Samples/deviceQueryDrv)** |
**[fastWalshTransform](./Samples/fastWalshTransform)** | **[quasirandomGenerator](./Samples/quasirandomGenerator)** | **[vectorAddMMAP](./Samples/vectorAddMMAP)** | **[MersenneTwisterGP11213](./Samples/MersenneTwisterGP11213)** |
**[conjugateGradientUM](./Samples/conjugateGradientUM)** | **[simpleVoteIntrinsics_nvrtc](./Samples/simpleVoteIntrinsics_nvrtc)** | **[simpleLayeredTexture](./Samples/simpleLayeredTexture)** | **[streamOrderedAllocation](./Samples/streamOrderedAllocation)** |
**[cuSolverDn_LinearSolver](./Samples/cuSolverDn_LinearSolver)** | **[cudaCompressibleMemory](./Samples/cudaCompressibleMemory)** | **[matrixMulCUBLAS](./Samples/matrixMulCUBLAS)** | **[histEqualizationNPP](./Samples/histEqualizationNPP)** |
**[simpleAWBarrier](./Samples/simpleAWBarrier)** | **[recursiveGaussian](./Samples/recursiveGaussian)** | **[imageDenoising](./Samples/imageDenoising)** | **[FunctionPointers](./Samples/FunctionPointers)** |
**[simpleGL](./Samples/simpleGL)** | **[segmentationTreeThrust](./Samples/segmentationTreeThrust)** | **[scalarProd](./Samples/scalarProd)** | **[SobolQRNG](./Samples/SobolQRNG)** |
**[p2pBandwidthLatencyTest](./Samples/p2pBandwidthLatencyTest)** | **[conjugateGradientCudaGraphs](./Samples/conjugateGradientCudaGraphs)** | **[simplePitchLinearTexture](./Samples/simplePitchLinearTexture)** | **[freeImageInteropNPP](./Samples/freeImageInteropNPP)** |
**[template](./Samples/template)** | **[dwtHaar1D](./Samples/dwtHaar1D)** | **[postProcessGL](./Samples/postProcessGL)** | **[BlackScholes](./Samples/BlackScholes)** |
**[volumeFiltering](./Samples/volumeFiltering)** | **[simpleCUFFT_callback](./Samples/simpleCUFFT_callback)** | **[UnifiedMemoryStreams](./Samples/UnifiedMemoryStreams)** | **[globalToShmemAsyncCopy](./Samples/globalToShmemAsyncCopy)** |
**[deviceQuery](./Samples/deviceQuery)** | **[simpleHyperQ](./Samples/simpleHyperQ)** | **[systemWideAtomics](./Samples/systemWideAtomics)** | **[cuSolverSp_LowlevelQR](./Samples/cuSolverSp_LowlevelQR)** |
**[inlinePTX](./Samples/inlinePTX)** | **[matrixMulDrv](./Samples/matrixMulDrv)** | **[EGLStream_CUDA_Interop](./Samples/EGLStream_CUDA_Interop)** | **[cuDLAHybridMode](./Samples/cuDLAHybridMode)** |
**[asyncAPI](./Samples/asyncAPI)** | **[MC_EstimatePiInlineQ](./Samples/MC_EstimatePiInlineQ)** | **[scan](./Samples/scan)** | **[simpleCooperativeGroups](./Samples/simpleCooperativeGroups)** |
**[conjugateGradientMultiBlockCG](./Samples/conjugateGradientMultiBlockCG)** | **[simpleTemplates_nvrtc](./Samples/simpleTemplates_nvrtc)** | **[simpleTexture3D](./Samples/simpleTexture3D)** | **[lineOfSight](./Samples/lineOfSight)** |
**[simpleZeroCopy](./Samples/simpleZeroCopy)** | **[binomialOptions](./Samples/binomialOptions)** | **[simpleAttributes](./Samples/simpleAttributes)** | **[bindlessTexture](./Samples/bindlessTexture)** |
**[simpleCUFFT_2d_MGPU](./Samples/simpleCUFFT_2d_MGPU)** | **[simplePrintf](./Samples/simplePrintf)** | **[batchedLabelMarkersAndLabelCompressionNPP](./Samples/batchedLabelMarkersAndLabelCompressionNPP)** | **[histogram](./Samples/histogram)** |
**[matrixMulDynlinkJIT](./Samples/matrixMulDynlinkJIT)** | **[simpleP2P](./Samples/simpleP2P)** | **[conjugateGradientMultiDeviceCG](./Samples/conjugateGradientMultiDeviceCG)** | **[vectorAddDrv](./Samples/vectorAddDrv)** |
**[sortingNetworks](./Samples/sortingNetworks)** | **[alignedTypes](./Samples/alignedTypes)** | **[inlinePTX_nvrtc](./Samples/inlinePTX_nvrtc)** | **[simpleCubemapTexture](./Samples/simpleCubemapTexture)** |
**[simpleIPC](./Samples/simpleIPC)** | **[simpleVulkanMMAP](./Samples/simpleVulkanMMAP)** | **[radixSortThrust](./Samples/radixSortThrust)** | **[MonteCarloMultiGPU](./Samples/MonteCarloMultiGPU)** |
**[cudaNvSciNvMedia](./Samples/cudaNvSciNvMedia)** | **[vectorAdd](./Samples/vectorAdd)** | **[cdpSimplePrint](./Samples/cdpSimplePrint)** | **[FilterBorderControlNPP](./Samples/FilterBorderControlNPP)** |
**[simpleVoteIntrinsics](./Samples/simpleVoteIntrinsics)** | **[convolutionSeparable](./Samples/convolutionSeparable)** | **[nbody](./Samples/nbody)** | **[simpleCUBLAS_LU](./Samples/simpleCUBLAS_LU)** |
**[simpleSeparateCompilation](./Samples/simpleSeparateCompilation)** | **[c++11_cuda](./Samples/c++11_cuda)** | **[fluidsGL](./Samples/fluidsGL)** | **[bandwidthTest](./Samples/bandwidthTest)** |
**[clock_nvrtc](./Samples/clock_nvrtc)** | **[graphMemoryNodes](./Samples/graphMemoryNodes)** | **[cdpQuadtree](./Samples/cdpQuadtree)** | **[interval](./Samples/interval)** |
**[boxFilter](./Samples/boxFilter)** | **[matrixMul_nvrtc](./Samples/matrixMul_nvrtc)** | **[simpleCUBLASXT](./Samples/simpleCUBLASXT)** | **[cppOverload](./Samples/cppOverload)** |
**[marchingCubes](./Samples/marchingCubes)** | **[cuSolverRf](./Samples/cuSolverRf)** | **[BlackScholes_nvrtc](./Samples/BlackScholes_nvrtc)** | **[cdpAdvancedQuicksort](./Samples/cdpAdvancedQuicksort)** |
**[tf32TensorCoreGemm](./Samples/tf32TensorCoreGemm)** | **[cdpSimpleQuicksort](./Samples/cdpSimpleQuicksort)** | **[simpleOccupancy](./Samples/simpleOccupancy)** | **[simpleSurfaceWrite](./Samples/simpleSurfaceWrite)** |
**[simpleCUFFT_MGPU](./Samples/simpleCUFFT_MGPU)** | **[simpleDrvRuntime](./Samples/simpleDrvRuntime)** | **[convolutionFFT2D](./Samples/convolutionFFT2D)** | **[reduction](./Samples/reduction)** |
**[memMapIPCDrv](./Samples/memMapIPCDrv)** | **[SobelFilter](./Samples/SobelFilter)** | **[dct8x8](./Samples/dct8x8)** | **[fp16ScalarProduct](./Samples/fp16ScalarProduct)** |
**[FDTD3d](./Samples/FDTD3d)** | **[oceanFFT](./Samples/oceanFFT)** | **[warpAggregatedAtomicsCG](./Samples/warpAggregatedAtomicsCG)** | **[StreamPriorities](./Samples/StreamPriorities)** |
**[cannyEdgeDetectorNPP](./Samples/cannyEdgeDetectorNPP)** | **[MC_SingleAsianOptionP](./Samples/MC_SingleAsianOptionP)** | **[simpleMPI](./Samples/simpleMPI)** |
### [1. Utilities](./Samples/1_Utilities/README.md)
Utility samples that demonstrate how to query device capabilities and measure GPU/CPU bandwidth.
#### Windows
**[simpleAssert_nvrtc](./Samples/simpleAssert_nvrtc)** | **[vectorAdd_nvrtc](./Samples/vectorAdd_nvrtc)** | **[graphMemoryFootprint](./Samples/graphMemoryFootprint)** | **[MC_EstimatePiQ](./Samples/MC_EstimatePiQ)** |
---|---|---|---|
**[reductionMultiBlockCG](./Samples/reductionMultiBlockCG)** | **[conjugateGradientPrecond](./Samples/conjugateGradientPrecond)** | **[ptxjit](./Samples/ptxjit)** | **[threadMigration](./Samples/threadMigration)** |
**[threadFenceReduction](./Samples/threadFenceReduction)** | **[simpleAtomicIntrinsics_nvrtc](./Samples/simpleAtomicIntrinsics_nvrtc)** | **[shfl_scan](./Samples/shfl_scan)** | **[clock](./Samples/clock)** |
**[binaryPartitionCG](./Samples/binaryPartitionCG)** | **[MC_EstimatePiP](./Samples/MC_EstimatePiP)** | **[transpose](./Samples/transpose)** | **[simpleMultiCopy](./Samples/simpleMultiCopy)** |
**[concurrentKernels](./Samples/concurrentKernels)** | **[UnifiedMemoryPerf](./Samples/UnifiedMemoryPerf)** | **[cppIntegration](./Samples/cppIntegration)** | **[bf16TensorCoreGemm](./Samples/bf16TensorCoreGemm)** |
**[cuSolverSp_LinearSolver](./Samples/cuSolverSp_LinearSolver)** | **[nvJPEG](./Samples/nvJPEG)** | **[watershedSegmentationNPP](./Samples/watershedSegmentationNPP)** | **[MC_EstimatePiInlineP](./Samples/MC_EstimatePiInlineP)** |
**[simpleD3D10](./Samples/simpleD3D10)** | **[vulkanImageCUDA](./Samples/vulkanImageCUDA)** | **[fluidsD3D9](./Samples/fluidsD3D9)** | **[boxFilterNPP](./Samples/boxFilterNPP)** |
**[simpleAssert](./Samples/simpleAssert)** | **[simpleTemplates](./Samples/simpleTemplates)** | **[simpleCUDA2GL](./Samples/simpleCUDA2GL)** | **[matrixMul](./Samples/matrixMul)** |
**[quasirandomGenerator_nvrtc](./Samples/quasirandomGenerator_nvrtc)** | **[nvJPEG_encoder](./Samples/nvJPEG_encoder)** | **[simpleCudaGraphs](./Samples/simpleCudaGraphs)** | **[simpleTextureDrv](./Samples/simpleTextureDrv)** |
**[simpleCUFFT](./Samples/simpleCUFFT)** | **[simpleCallback](./Samples/simpleCallback)** | **[SLID3D10Texture](./Samples/SLID3D10Texture)** | **[batchCUBLAS](./Samples/batchCUBLAS)** |
**[cudaTensorCoreGemm](./Samples/cudaTensorCoreGemm)** | **[simpleAtomicIntrinsics](./Samples/simpleAtomicIntrinsics)** | **[newdelete](./Samples/newdelete)** | **[bicubicTexture](./Samples/bicubicTexture)** |
**[dxtc](./Samples/dxtc)** | **[cudaOpenMP](./Samples/cudaOpenMP)** | **[cdpBezierTessellation](./Samples/cdpBezierTessellation)** | **[randomFog](./Samples/randomFog)** |
**[bilateralFilter](./Samples/bilateralFilter)** | **[conjugateGradient](./Samples/conjugateGradient)** | **[particles](./Samples/particles)** | **[NV12toBGRandResize](./Samples/NV12toBGRandResize)** |
**[Mandelbrot](./Samples/Mandelbrot)** | **[binomialOptions_nvrtc](./Samples/binomialOptions_nvrtc)** | **[simpleD3D10RenderTarget](./Samples/simpleD3D10RenderTarget)** | **[mergeSort](./Samples/mergeSort)** |
**[HSOpticalFlow](./Samples/HSOpticalFlow)** | **[immaTensorCoreGemm](./Samples/immaTensorCoreGemm)** | **[convolutionTexture](./Samples/convolutionTexture)** | **[simpleVulkan](./Samples/simpleVulkan)** |
**[simpleD3D9Texture](./Samples/simpleD3D9Texture)** | **[simpleCUBLAS](./Samples/simpleCUBLAS)** | **[jacobiCudaGraphs](./Samples/jacobiCudaGraphs)** | **[eigenvalues](./Samples/eigenvalues)** |
**[simpleD3D10Texture](./Samples/simpleD3D10Texture)** | **[streamOrderedAllocationP2P](./Samples/streamOrderedAllocationP2P)** | **[cuSolverSp_LowlevelCholesky](./Samples/cuSolverSp_LowlevelCholesky)** | **[topologyQuery](./Samples/topologyQuery)** |
**[dmmaTensorCoreGemm](./Samples/dmmaTensorCoreGemm)** | **[volumeRender](./Samples/volumeRender)** | **[stereoDisparity](./Samples/stereoDisparity)** | **[simpleTexture](./Samples/simpleTexture)** |
**[simpleStreams](./Samples/simpleStreams)** | **[smokeParticles](./Samples/smokeParticles)** | **[simpleMultiGPU](./Samples/simpleMultiGPU)** | **[deviceQueryDrv](./Samples/deviceQueryDrv)** |
**[fastWalshTransform](./Samples/fastWalshTransform)** | **[quasirandomGenerator](./Samples/quasirandomGenerator)** | **[vectorAddMMAP](./Samples/vectorAddMMAP)** | **[MersenneTwisterGP11213](./Samples/MersenneTwisterGP11213)** |
**[conjugateGradientUM](./Samples/conjugateGradientUM)** | **[simpleVoteIntrinsics_nvrtc](./Samples/simpleVoteIntrinsics_nvrtc)** | **[simpleLayeredTexture](./Samples/simpleLayeredTexture)** | **[streamOrderedAllocation](./Samples/streamOrderedAllocation)** |
**[cuSolverDn_LinearSolver](./Samples/cuSolverDn_LinearSolver)** | **[cudaCompressibleMemory](./Samples/cudaCompressibleMemory)** | **[matrixMulCUBLAS](./Samples/matrixMulCUBLAS)** | **[histEqualizationNPP](./Samples/histEqualizationNPP)** |
**[simpleAWBarrier](./Samples/simpleAWBarrier)** | **[recursiveGaussian](./Samples/recursiveGaussian)** | **[imageDenoising](./Samples/imageDenoising)** | **[FunctionPointers](./Samples/FunctionPointers)** |
**[simpleGL](./Samples/simpleGL)** | **[segmentationTreeThrust](./Samples/segmentationTreeThrust)** | **[scalarProd](./Samples/scalarProd)** | **[SobolQRNG](./Samples/SobolQRNG)** |
**[p2pBandwidthLatencyTest](./Samples/p2pBandwidthLatencyTest)** | **[conjugateGradientCudaGraphs](./Samples/conjugateGradientCudaGraphs)** | **[simplePitchLinearTexture](./Samples/simplePitchLinearTexture)** | **[freeImageInteropNPP](./Samples/freeImageInteropNPP)** |
**[template](./Samples/template)** | **[dwtHaar1D](./Samples/dwtHaar1D)** | **[simpleD3D11Texture](./Samples/simpleD3D11Texture)** | **[postProcessGL](./Samples/postProcessGL)** |
**[BlackScholes](./Samples/BlackScholes)** | **[simpleD3D11](./Samples/simpleD3D11)** | **[volumeFiltering](./Samples/volumeFiltering)** | **[UnifiedMemoryStreams](./Samples/UnifiedMemoryStreams)** |
**[globalToShmemAsyncCopy](./Samples/globalToShmemAsyncCopy)** | **[deviceQuery](./Samples/deviceQuery)** | **[simpleHyperQ](./Samples/simpleHyperQ)** | **[cuSolverSp_LowlevelQR](./Samples/cuSolverSp_LowlevelQR)** |
**[inlinePTX](./Samples/inlinePTX)** | **[matrixMulDrv](./Samples/matrixMulDrv)** | **[asyncAPI](./Samples/asyncAPI)** | **[MC_EstimatePiInlineQ](./Samples/MC_EstimatePiInlineQ)** |
**[scan](./Samples/scan)** | **[simpleCooperativeGroups](./Samples/simpleCooperativeGroups)** | **[conjugateGradientMultiBlockCG](./Samples/conjugateGradientMultiBlockCG)** | **[simpleTemplates_nvrtc](./Samples/simpleTemplates_nvrtc)** |
**[simpleTexture3D](./Samples/simpleTexture3D)** | **[lineOfSight](./Samples/lineOfSight)** | **[simpleZeroCopy](./Samples/simpleZeroCopy)** | **[binomialOptions](./Samples/binomialOptions)** |
**[simpleAttributes](./Samples/simpleAttributes)** | **[bindlessTexture](./Samples/bindlessTexture)** | **[simpleD3D12](./Samples/simpleD3D12)** | **[simpleCUFFT_2d_MGPU](./Samples/simpleCUFFT_2d_MGPU)** |
**[simplePrintf](./Samples/simplePrintf)** | **[batchedLabelMarkersAndLabelCompressionNPP](./Samples/batchedLabelMarkersAndLabelCompressionNPP)** | **[histogram](./Samples/histogram)** | **[matrixMulDynlinkJIT](./Samples/matrixMulDynlinkJIT)** |
**[simpleP2P](./Samples/simpleP2P)** | **[conjugateGradientMultiDeviceCG](./Samples/conjugateGradientMultiDeviceCG)** | **[vectorAddDrv](./Samples/vectorAddDrv)** | **[sortingNetworks](./Samples/sortingNetworks)** |
**[alignedTypes](./Samples/alignedTypes)** | **[inlinePTX_nvrtc](./Samples/inlinePTX_nvrtc)** | **[simpleCubemapTexture](./Samples/simpleCubemapTexture)** | **[simpleIPC](./Samples/simpleIPC)** |
**[simpleVulkanMMAP](./Samples/simpleVulkanMMAP)** | **[radixSortThrust](./Samples/radixSortThrust)** | **[MonteCarloMultiGPU](./Samples/MonteCarloMultiGPU)** | **[vectorAdd](./Samples/vectorAdd)** |
**[VFlockingD3D10](./Samples/VFlockingD3D10)** | **[simpleD3D9](./Samples/simpleD3D9)** | **[cdpSimplePrint](./Samples/cdpSimplePrint)** | **[FilterBorderControlNPP](./Samples/FilterBorderControlNPP)** |
**[simpleVoteIntrinsics](./Samples/simpleVoteIntrinsics)** | **[convolutionSeparable](./Samples/convolutionSeparable)** | **[nbody](./Samples/nbody)** | **[simpleCUBLAS_LU](./Samples/simpleCUBLAS_LU)** |
**[simpleSeparateCompilation](./Samples/simpleSeparateCompilation)** | **[c++11_cuda](./Samples/c++11_cuda)** | **[fluidsGL](./Samples/fluidsGL)** | **[bandwidthTest](./Samples/bandwidthTest)** |
**[clock_nvrtc](./Samples/clock_nvrtc)** | **[graphMemoryNodes](./Samples/graphMemoryNodes)** | **[cdpQuadtree](./Samples/cdpQuadtree)** | **[interval](./Samples/interval)** |
**[boxFilter](./Samples/boxFilter)** | **[matrixMul_nvrtc](./Samples/matrixMul_nvrtc)** | **[simpleCUBLASXT](./Samples/simpleCUBLASXT)** | **[cppOverload](./Samples/cppOverload)** |
**[marchingCubes](./Samples/marchingCubes)** | **[cuSolverRf](./Samples/cuSolverRf)** | **[BlackScholes_nvrtc](./Samples/BlackScholes_nvrtc)** | **[cdpAdvancedQuicksort](./Samples/cdpAdvancedQuicksort)** |
**[tf32TensorCoreGemm](./Samples/tf32TensorCoreGemm)** | **[cdpSimpleQuicksort](./Samples/cdpSimpleQuicksort)** | **[simpleOccupancy](./Samples/simpleOccupancy)** | **[simpleSurfaceWrite](./Samples/simpleSurfaceWrite)** |
**[simpleCUFFT_MGPU](./Samples/simpleCUFFT_MGPU)** | **[simpleDrvRuntime](./Samples/simpleDrvRuntime)** | **[convolutionFFT2D](./Samples/convolutionFFT2D)** | **[reduction](./Samples/reduction)** |
**[memMapIPCDrv](./Samples/memMapIPCDrv)** | **[SobelFilter](./Samples/SobelFilter)** | **[dct8x8](./Samples/dct8x8)** | **[fp16ScalarProduct](./Samples/fp16ScalarProduct)** |
**[FDTD3d](./Samples/FDTD3d)** | **[oceanFFT](./Samples/oceanFFT)** | **[warpAggregatedAtomicsCG](./Samples/warpAggregatedAtomicsCG)** | **[cannyEdgeDetectorNPP](./Samples/cannyEdgeDetectorNPP)** |
**[MC_SingleAsianOptionP](./Samples/MC_SingleAsianOptionP)** | **[simpleMPI](./Samples/simpleMPI)** |
### [2. Concepts and Techniques](./Samples/2_Concepts_and_Techniques/README.md)
Samples that demonstrate CUDA related concepts and common problem solving techniques.
### [3. CUDA Features](./Samples/3_CUDA_Features/README.md)
Samples that demonstrate CUDA Features (Cooperative Groups, CUDA Dynamic Parallelism, CUDA Graphs etc).
### [4. CUDA Libraries](./Samples/4_CUDA_Libraries/README.md)
Samples that demonstrate how to use CUDA platform libraries (NPP, NVJPEG, NVGRAPH cuBLAS, cuFFT, cuSPARSE, cuSOLVER and cuRAND).
### [5. Domain Specific](./Samples/5_Domain_Specific/README.md)
Samples that are specific to domain (Graphics, Finance, Image Processing).
### [6. Performance](./Samples/6_Performance/README.md)
Samples that demonstrate performance optimization.
## Dependencies
@ -296,7 +108,7 @@ These third-party dependencies are required by some CUDA samples. If available,
FreeImage is an open source imaging library. FreeImage can usually be installed on Linux using your distribution's package manager system. FreeImage can also be downloaded from the FreeImage website.
To set up FreeImage on a Windows system, extract the FreeImage DLL distribution into the folder `../../Common/FreeImage/Dist/x64` such that it contains the .h, .dll, and .lib files.
To set up FreeImage on a Windows system, extract the FreeImage DLL distribution into the folder `../../../Common/FreeImage/Dist/x64` such that it contains the .h and .lib files. Copy the .dll file to root level `bin/win64/Debug` and `bin/win64/Release` folder.
#### Message Passing Interface
@ -449,3 +261,6 @@ Answers to frequently asked questions about CUDA can be found at http://develope
* [CUDA Programming Guide](http://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html)
* [Accelerated Computing Blog](https://developer.nvidia.com/blog/?tags=accelerated-computing)
## Attributions
* Teapot image is obtained from [Wikimedia](https://en.wikipedia.org/wiki/File:Original_Utah_Teapot.jpg) and is licensed under the Creative Commons [Attribution-Share Alike 2.0](https://creativecommons.org/licenses/by-sa/2.0/deed.en) Generic license. The image is modified for samples use cases.

162
Samples/0_Introduction/README.md Normal file
View File

@ -0,0 +1,162 @@
# 0. Introduction
### [asyncAPI](./asyncAPI)
This sample illustrates the usage of CUDA events for both GPU timing and overlapping CPU and GPU execution. Events are inserted into a stream of CUDA calls. Since CUDA stream calls are asynchronous, the CPU can perform computations while GPU is executing (including DMA memcopies between the host and device). CPU can query CUDA events to determine whether GPU has completed tasks.
### [c++11_cuda](./c++11_cuda)
This sample demonstrates C++11 feature support in CUDA. It scans a input text file and prints no. of occurrences of x, y, z, w characters.
### [clock](./clock)
This example shows how to use the clock function to measure the performance of block of threads of a kernel accurately.
### [clock_nvrtc](./clock_nvrtc)
This example shows how to use the clock function using libNVRTC to measure the performance of block of threads of a kernel accurately.
### [concurrentKernels](./concurrentKernels)
This sample demonstrates the use of CUDA streams for concurrent execution of several kernels on GPU device. It also illustrates how to introduce dependencies between CUDA streams with the new cudaStreamWaitEvent function.
### [cppIntegration](./cppIntegration)
This example demonstrates how to integrate CUDA into an existing C++ application, i.e. the CUDA entry point on host side is only a function which is called from C++ code and only the file containing this function is compiled with nvcc. It also demonstrates that vector types can be used from cpp.
### [cppOverload](./cppOverload)
This sample demonstrates how to use C++ function overloading on the GPU.
### [cudaOpenMP](./cudaOpenMP)
This sample demonstrates how to use OpenMP API to write an application for multiple GPUs.
### [fp16ScalarProduct](./fp16ScalarProduct)
Calculates scalar product of two vectors of FP16 numbers.
### [matrixMul](./matrixMul)
This sample implements matrix multiplication and is exactly the same as Chapter 6 of the programming guide. It has been written for clarity of exposition to illustrate various CUDA programming principles, not with the goal of providing the most performant generic kernel for matrix multiplication. To illustrate GPU performance for matrix multiply, this sample also shows how to use the new CUDA 4.0 interface for CUBLAS to demonstrate high-performance performance for matrix multiplication.
### [matrixMul_nvrtc](./matrixMul_nvrtc)
This sample implements matrix multiplication and is exactly the same as Chapter 6 of the programming guide. It has been written for clarity of exposition to illustrate various CUDA programming principles, not with the goal of providing the most performant generic kernel for matrix multiplication. To illustrate GPU performance for matrix multiply, this sample also shows how to use the new CUDA 4.0 interface for CUBLAS to demonstrate high-performance performance for matrix multiplication.
### [matrixMulDrv](./matrixMulDrv)
This sample implements matrix multiplication and uses the new CUDA 4.0 kernel launch Driver API. It has been written for clarity of exposition to illustrate various CUDA programming principles, not with the goal of providing the most performant generic kernel for matrix multiplication. CUBLAS provides high-performance matrix multiplication.
### [matrixMulDynlinkJIT](./matrixMulDynlinkJIT)
This sample revisits matrix multiplication using the CUDA driver API. It demonstrates how to link to CUDA driver at runtime and how to use JIT (just-in-time) compilation from PTX code. It has been written for clarity of exposition to illustrate various CUDA programming principles, not with the goal of providing the most performant generic kernel for matrix multiplication. CUBLAS provides high-performance matrix multiplication.
### [mergeSort](./mergeSort)
This sample implements a merge sort (also known as Batcher's sort), algorithms belonging to the class of sorting networks. While generally subefficient on large sequences compared to algorithms with better asymptotic algorithmic complexity (i.e. merge sort or radix sort), may be the algorithms of choice for sorting batches of short- to mid-sized (key, value) array pairs. Refer to the excellent tutorial by H. W. Lang http://www.iti.fh-flensburg.de/lang/algorithmen/sortieren/networks/indexen.htm
### [simpleAssert](./simpleAssert)
This CUDA Runtime API sample is a very basic sample that implements how to use the assert function in the device code. Requires Compute Capability 2.0 .
### [simpleAssert_nvrtc](./simpleAssert_nvrtc)
This CUDA Runtime API sample is a very basic sample that implements how to use the assert function in the device code. Requires Compute Capability 2.0 .
### [simpleAtomicIntrinsics](./simpleAtomicIntrinsics)
A simple demonstration of global memory atomic instructions.
### [simpleAtomicIntrinsics_nvrtc](./simpleAtomicIntrinsics_nvrtc)
A simple demonstration of global memory atomic instructions.This sample makes use of NVRTC for Runtime Compilation.
### [simpleAttributes](./simpleAttributes)
This CUDA Runtime API sample is a very basic example that implements how to use the stream attributes that affect L2 locality. Performance improvement due to use of L2 access policy window can only be noticed on Compute capability 8.0 or higher.
### [simpleAWBarrier](./simpleAWBarrier)
A simple demonstration of arrive wait barriers.
### [simpleCallback](./simpleCallback)
This sample implements multi-threaded heterogeneous computing workloads with the new CPU callbacks for CUDA streams and events introduced with CUDA 5.0.
### [simpleCooperativeGroups](./simpleCooperativeGroups)
This sample is a simple code that illustrates basic usage of cooperative groups within the thread block.
### [simpleCubemapTexture](./simpleCubemapTexture)
Simple example that demonstrates how to use a new CUDA 4.1 feature to support cubemap Textures in CUDA C.
### [simpleCUDA2GL](./simpleCUDA2GL)
This sample shows how to copy CUDA image back to OpenGL using the most efficient methods.
### [simpleDrvRuntime](./simpleDrvRuntime)
A simple example which demonstrates how CUDA Driver and Runtime APIs can work together to load cuda fatbinary of vector add kernel and performing vector addition.
### [simpleHyperQ](./simpleHyperQ)
This sample demonstrates the use of CUDA streams for concurrent execution of several kernels on devices which provide HyperQ (SM 3.5). Devices without HyperQ (SM 2.0 and SM 3.0) will run a maximum of two kernels concurrently.
### [simpleIPC](./simpleIPC)
This CUDA Runtime API sample is a very basic sample that demonstrates Inter Process Communication with one process per GPU for computation. Requires Compute Capability 3.0 or higher and a Linux Operating System, or a Windows Operating System with TCC enabled GPUs
### [simpleLayeredTexture](./simpleLayeredTexture)
Simple example that demonstrates how to use a new CUDA 4.0 feature to support layered Textures in CUDA C.
### [simpleMPI](./simpleMPI)
Simple example demonstrating how to use MPI in combination with CUDA.
### [simpleMultiCopy](./simpleMultiCopy)
Supported in GPUs with Compute Capability 1.1, overlapping compute with one memcopy is possible from the host system. For Quadro and Tesla GPUs with Compute Capability 2.0, a second overlapped copy operation in either direction at full speed is possible (PCI-e is symmetric). This sample illustrates the usage of CUDA streams to achieve overlapping of kernel execution with data copies to and from the device.
### [simpleMultiGPU](./simpleMultiGPU)
This application demonstrates how to use the new CUDA 4.0 API for CUDA context management and multi-threaded access to run CUDA kernels on multiple-GPUs.
### [simpleOccupancy](./simpleOccupancy)
This sample demonstrates the basic usage of the CUDA occupancy calculator and occupancy-based launch configurator APIs by launching a kernel with the launch configurator, and measures the utilization difference against a manually configured launch.
### [simpleP2P](./simpleP2P)
This application demonstrates CUDA APIs that support Peer-To-Peer (P2P) copies, Peer-To-Peer (P2P) addressing, and Unified Virtual Memory Addressing (UVA) between multiple GPUs. In general, P2P is supported between two same GPUs with some exceptions, such as some Tesla and Quadro GPUs.
### [simplePitchLinearTexture](./simplePitchLinearTexture)
Use of Pitch Linear Textures
### [simplePrintf](./simplePrintf)
This basic CUDA Runtime API sample demonstrates how to use the printf function in the device code.
### [simpleSeparateCompilation](./simpleSeparateCompilation)
This sample demonstrates a CUDA 5.0 feature, the ability to create a GPU device static library and use it within another CUDA kernel. This example demonstrates how to pass in a GPU device function (from the GPU device static library) as a function pointer to be called. This sample requires devices with compute capability 2.0 or higher.
### [simpleStreams](./simpleStreams)
This sample uses CUDA streams to overlap kernel executions with memory copies between the host and a GPU device. This sample uses a new CUDA 4.0 feature that supports pinning of generic host memory. Requires Compute Capability 2.0 or higher.
### [simpleSurfaceWrite](./simpleSurfaceWrite)
Simple example that demonstrates the use of 2D surface references (Write-to-Texture)
### [simpleTemplates](./simpleTemplates)
This sample is a templatized version of the template project. It also shows how to correctly templatize dynamically allocated shared memory arrays.
### [simpleTemplates_nvrtc](./simpleTemplates_nvrtc)
This sample is a templatized version of the template project. It also shows how to correctly templatize dynamically allocated shared memory arrays.
### [simpleTexture](./simpleTexture)
Simple example that demonstrates use of Textures in CUDA.
### [simpleTexture3D](./simpleTexture3D)
Simple example that demonstrates use of 3D Textures in CUDA.
### [simpleTextureDrv](./simpleTextureDrv)
Simple example that demonstrates use of Textures in CUDA. This sample uses the new CUDA 4.0 kernel launch Driver API.
### [simpleVoteIntrinsics](./simpleVoteIntrinsics)
Simple program which demonstrates how to use the Vote (__any_sync, __all_sync) intrinsic instruction in a CUDA kernel.
### [simpleVoteIntrinsics_nvrtc](./simpleVoteIntrinsics_nvrtc)
Simple program which demonstrates how to use the Vote (any, all) intrinsic instruction in a CUDA kernel with runtime compilation using NVRTC APIs. Requires Compute Capability 2.0 or higher.
### [simpleZeroCopy](./simpleZeroCopy)
This sample illustrates how to use Zero MemCopy, kernels can read and write directly to pinned system memory.
### [systemWideAtomics](./systemWideAtomics)
A simple demonstration of system wide atomic instructions.
### [template](./template)
A trivial template project that can be used as a starting point to create new CUDA projects.
### [UnifiedMemoryStreams](./UnifiedMemoryStreams)
This sample demonstrates the use of OpenMP and streams with Unified Memory on a single GPU.
### [vectorAdd](./vectorAdd)
This CUDA Runtime API sample is a very basic sample that implements element by element vector addition. It is the same as the sample illustrating Chapter 3 of the programming guide with some additions like error checking.
### [vectorAdd_nvrtc](./vectorAdd_nvrtc)
This CUDA Driver API sample uses NVRTC for runtime compilation of vector addition kernel. Vector addition kernel demonstrated is the same as the sample illustrating Chapter 3 of the programming guide.
### [vectorAddDrv](./vectorAddDrv)
This Vector Addition sample is a basic sample that is implemented element by element. It is the same as the sample illustrating Chapter 3 of the programming guide with some additions like error checking. This sample also uses the new CUDA 4.0 kernel launch Driver API.
### [vectorAddMMAP](./vectorAddMMAP)
This sample replaces the device allocation in the vectorAddDrv sample with cuMemMap-ed allocations. This sample demonstrates that the cuMemMap api allows the user to specify the physical properties of their memory while retaining the contiguous nature of their access, thus not requiring a change in their program structure.

18
Samples/0_Introduction/UnifiedMemoryStreams/.vscode/c_cpp_properties.json vendored Normal file
View File

@ -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
}

0
Samples/BlackScholes/.vscode/extensions.json → Samples/0_Introduction/UnifiedMemoryStreams/.vscode/extensions.json vendored
View File

0
Samples/UnifiedMemoryStreams/.vscode/launch.json → Samples/0_Introduction/UnifiedMemoryStreams/.vscode/launch.json vendored
View File

0
Samples/BlackScholes/.vscode/tasks.json → Samples/0_Introduction/UnifiedMemoryStreams/.vscode/tasks.json vendored
View File

381
Samples/0_Introduction/UnifiedMemoryStreams/Makefile Normal file
View File

@ -0,0 +1,381 @@
################################################################################
# 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 $(TARGET_OS) for TARGET_OS!)
endif
# host compiler
ifeq ($(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
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))
UBUNTU = $(shell lsb_release -i -s 2>/dev/null | grep -i ubuntu)
SAMPLE_ENABLED := 1
# This sample is not supported on QNX
ifeq ($(TARGET_OS),qnx)
$(info >>> WARNING - UnifiedMemoryStreams is not supported on QNX - 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 :=
################################################################################
# Attempt to compile a minimal OpenMP application. If a.out exists, OpenMP is properly set up.
ifneq (,$(filter $(TARGET_OS),linux android))
ifneq (,$(filter $(TARGET_OS), android))
LIBRARIES += -lomp
else
LIBRARIES += -lgomp
endif
ALL_CCFLAGS += -Xcompiler -fopenmp
$(shell echo "#include <omp.h>" > test.c ; echo "int main() { omp_get_num_threads(); return 0; }" >> test.c ; $(HOST_COMPILER) -fopenmp test.c)
OPENMP ?= $(shell find a.out 2>/dev/null)
ifeq ($(OPENMP),)
$(info -----------------------------------------------------------------------------------------------)
$(info WARNING - OpenMP is unable to compile)
$(info -----------------------------------------------------------------------------------------------)
$(info This CUDA Sample cannot be built if the OpenMP compiler is not set up correctly.)
$(info This will be a dry-run of the Makefile.)
$(info For more information on how to set up your environment to build and run this )
$(info sample, please refer the CUDA Samples documentation and release notes)
$(info -----------------------------------------------------------------------------------------------)
SAMPLE_ENABLED := 0
endif
$(shell rm a.out test.c 2>/dev/null)
else
LIBRARIES += -lpthread
ALL_CCFLAGS += -DUSE_PTHREADS
endif
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
endif
ifeq ($(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 += --threads 0 --std=c++11
LIBRARIES += -lcublas
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"
endif
################################################################################
# Target rules
all: build
build: UnifiedMemoryStreams
check.deps:
ifeq ($(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
UnifiedMemoryStreams.o:UnifiedMemoryStreams.cu
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
UnifiedMemoryStreams: UnifiedMemoryStreams.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
$(EXEC) ./UnifiedMemoryStreams
testrun: build
clean:
rm -f UnifiedMemoryStreams UnifiedMemoryStreams.o
rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/UnifiedMemoryStreams
clobber: clean

101
Samples/0_Introduction/UnifiedMemoryStreams/NsightEclipse.xml Normal file
View File

@ -0,0 +1,101 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
<entry>
<name>UnifiedMemoryStreams</name>
<cuda_api_list>
<toolkit>cudaStreamDestroy</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaMallocManaged</toolkit>
<toolkit>cudaStreamCreate</toolkit>
<toolkit>cudaDeviceSynchronize</toolkit>
<toolkit>cudaStreamAttachMemAsync</toolkit>
<toolkit>cudaSetDevice</toolkit>
<toolkit>cudaStreamSynchronize</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
</cuda_api_list>
<description><![CDATA[This sample demonstrates the use of OpenMP and streams with Unified Memory on a single GPU.]]></description>
<devicecompilation>whole</devicecompilation>
<includepaths>
<path>./</path>
<path>../</path>
<path>../../../Common</path>
</includepaths>
<keyconcepts>
<concept level="basic">CUDA Systems Integration</concept>
<concept level="basic">OpenMP</concept>
<concept level="basic">CUBLAS</concept>
<concept level="basic">Multithreading</concept>
<concept level="basic">Unified Memory</concept>
<concept level="basic">CUDA Streams and Events</concept>
</keyconcepts>
<keywords>
<keyword>CUDA</keyword>
<keyword>CUBLAS</keyword>
<keyword>OpenMP</keyword>
<keyword>cluster</keyword>
<keyword>multi-GPU Support</keyword>
<keyword>Unified Memory</keyword>
<keyword>UVM</keyword>
<keyword>openMP</keyword>
<keyword>Streams</keyword>
<keyword>pthreads</keyword>
</keywords>
<libraries>
<library>cublas</library>
</libraries>
<librarypaths>
</librarypaths>
<nsight_eclipse>true</nsight_eclipse>
<primary_file>UnifiedMemoryStreams.cu</primary_file>
<required_dependencies>
<dependency>OpenMP</dependency>
<dependency>UVM</dependency>
<dependency>CUBLAS</dependency>
</required_dependencies>
<scopes>
<scope>1:CUDA Basic Topics</scope>
<scope>1:CUDA Systems Integration</scope>
<scope>1:Unified Memory</scope>
</scopes>
<sm-arch>sm35</sm-arch>
<sm-arch>sm37</sm-arch>
<sm-arch>sm50</sm-arch>
<sm-arch>sm52</sm-arch>
<sm-arch>sm53</sm-arch>
<sm-arch>sm60</sm-arch>
<sm-arch>sm61</sm-arch>
<sm-arch>sm70</sm-arch>
<sm-arch>sm72</sm-arch>
<sm-arch>sm75</sm-arch>
<sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<sm-arch>sm87</sm-arch>
<supported_envs>
<env>
<arch>x86_64</arch>
<platform>linux</platform>
</env>
<env>
<arch>x86_64</arch>
<platform>macosx</platform>
</env>
<env>
<platform>windows7</platform>
</env>
<env>
<arch>arm</arch>
</env>
<env>
<arch>sbsa</arch>
</env>
<env>
<arch>ppc64le</arch>
<platform>linux</platform>
</env>
</supported_envs>
<supported_sm_architectures>
<from>3.5</from>
</supported_sm_architectures>
<title>Unified Memory Streams</title>
<type>exe</type>
</entry>

74
Samples/0_Introduction/UnifiedMemoryStreams/README.md Normal file
View File

@ -0,0 +1,74 @@
# UnifiedMemoryStreams - Unified Memory Streams
## Description
This sample demonstrates the use of OpenMP and streams with Unified Memory on a single GPU.
## Key Concepts
CUDA Systems Integration, OpenMP, CUBLAS, Multithreading, Unified Memory, CUDA Streams and Events
## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [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)
## Supported OSes
Linux, Windows
## Supported CPU Architecture
x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaStreamDestroy, cudaFree, cudaMallocManaged, cudaStreamCreate, cudaDeviceSynchronize, cudaStreamAttachMemAsync, cudaSetDevice, cudaStreamSynchronize, cudaGetDeviceProperties
## Dependencies needed to build/run
[OpenMP](../../README.md#openmp), [UVM](../../README.md#uvm), [CUBLAS](../../README.md#cublas)
## Prerequisites
Download and install the [CUDA Toolkit 11.6](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## 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<version>.sln - for Visual Studio <version>
```
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 <sample_dir>
$ make
```
The samples makefiles can take advantage of certain options:
* **TARGET_ARCH=<arch>** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le, 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.<br/>
`$ make TARGET_ARCH=x86_64` <br/> `$ make TARGET_ARCH=ppc64le` <br/> `$ make TARGET_ARCH=armv7l` <br/>
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=<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)

2
Samples/UnifiedMemoryStreams/UnifiedMemoryStreams.cu → Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams.cu
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

0
Samples/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.sln → Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.sln
View File

13
Samples/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj → Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2017.vcxproj
View File

@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@ -52,13 +52,13 @@
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
@ -68,10 +68,9 @@
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
<AdditionalCompilerOptions>/openmp</AdditionalCompilerOptions>
</CudaCompile>
</ItemDefinitionGroup>
@ -109,6 +108,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
</ImportGroup>
</Project>

0
Samples/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.sln → Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.sln
View File

13
Samples/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj → Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2019.vcxproj
View File

@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@ -48,13 +48,13 @@
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
@ -64,10 +64,9 @@
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
<AdditionalCompilerOptions>/openmp</AdditionalCompilerOptions>
</CudaCompile>
</ItemDefinitionGroup>
@ -105,6 +104,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
</ImportGroup>
</Project>

20
Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.sln Normal file
View File

@ -0,0 +1,20 @@

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 2022
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "UnifiedMemoryStreams", "UnifiedMemoryStreams_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

109
Samples/0_Introduction/UnifiedMemoryStreams/UnifiedMemoryStreams_vs2022.vcxproj Normal file
View File

@ -0,0 +1,109 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>UnifiedMemoryStreams_vs2022</RootNamespace>
<ProjectName>UnifiedMemoryStreams</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v143</PlatformToolset>
<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cublas.lib;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)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/UnifiedMemoryStreams.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalCompilerOptions>/openmp</AdditionalCompilerOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="UnifiedMemoryStreams.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
</ImportGroup>
</Project>

18
Samples/0_Introduction/asyncAPI/.vscode/c_cpp_properties.json vendored Normal file
View File

@ -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
}

0
Samples/BlackScholes_nvrtc/.vscode/extensions.json → Samples/0_Introduction/asyncAPI/.vscode/extensions.json vendored
View File

0
Samples/asyncAPI/.vscode/launch.json → Samples/0_Introduction/asyncAPI/.vscode/launch.json vendored
View File

0
Samples/BlackScholes_nvrtc/.vscode/tasks.json → Samples/0_Introduction/asyncAPI/.vscode/tasks.json vendored
View File

341
Samples/0_Introduction/asyncAPI/Makefile Normal file
View File

@ -0,0 +1,341 @@
################################################################################
# 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 $(TARGET_OS) for TARGET_OS!)
endif
# host compiler
ifeq ($(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
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
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 $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
endif
ifeq ($(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 += --threads 0 --std=c++11
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"
endif
################################################################################
# Target rules
all: build
build: asyncAPI
check.deps:
ifeq ($(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
asyncAPI.o:asyncAPI.cu
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
asyncAPI: asyncAPI.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) ./asyncAPI
testrun: build
$(EXEC) ./asyncAPI --dummy-test-param
clean:
rm -f asyncAPI asyncAPI.o
rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/asyncAPI
clobber: clean

90
Samples/0_Introduction/asyncAPI/NsightEclipse.xml Normal file
View File

@ -0,0 +1,90 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
<entry>
<name>asyncAPI</name>
<cuda_api_list>
<toolkit>cudaMemset</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaMallocHost</toolkit>
<toolkit>cudaProfilerStart</toolkit>
<toolkit>cudaEventCreate</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaDeviceSynchronize</toolkit>
<toolkit>cudaFreeHost</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaEventQuery</toolkit>
<toolkit>cudaProfilerStop</toolkit>
<toolkit>cudaEventDestroy</toolkit>
<toolkit>cudaMemcpyAsync</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
</cuda_api_list>
<description><![CDATA[This sample illustrates the usage of CUDA events for both GPU timing and overlapping CPU and GPU execution. Events are inserted into a stream of CUDA calls. Since CUDA stream calls are asynchronous, the CPU can perform computations while GPU is executing (including DMA memcopies between the host and device). CPU can query CUDA events to determine whether GPU has completed tasks.]]></description>
<devicecompilation>whole</devicecompilation>
<includepaths>
<path>./</path>
<path>../</path>
<path>../../../Common</path>
</includepaths>
<keyconcepts>
<concept level="basic">Asynchronous Data Transfers</concept>
<concept level="basic">CUDA Streams and Events</concept>
</keyconcepts>
<keywords>
<keyword>GPGPU</keyword>
</keywords>
<libraries>
</libraries>
<librarypaths>
</librarypaths>
<nsight_eclipse>true</nsight_eclipse>
<primary_file>asyncAPI.cu</primary_file>
<qatests>
<qatest>--dummy-test-param</qatest>
</qatests>
<scopes>
<scope>1:CUDA Basic Topics</scope>
<scope>1:Performance Strategies</scope>
</scopes>
<sm-arch>sm35</sm-arch>
<sm-arch>sm37</sm-arch>
<sm-arch>sm50</sm-arch>
<sm-arch>sm52</sm-arch>
<sm-arch>sm53</sm-arch>
<sm-arch>sm60</sm-arch>
<sm-arch>sm61</sm-arch>
<sm-arch>sm70</sm-arch>
<sm-arch>sm72</sm-arch>
<sm-arch>sm75</sm-arch>
<sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<sm-arch>sm87</sm-arch>
<supported_envs>
<env>
<arch>x86_64</arch>
<platform>linux</platform>
</env>
<env>
<platform>windows7</platform>
</env>
<env>
<arch>x86_64</arch>
<platform>macosx</platform>
</env>
<env>
<arch>arm</arch>
</env>
<env>
<arch>sbsa</arch>
</env>
<env>
<arch>ppc64le</arch>
<platform>linux</platform>
</env>
</supported_envs>
<supported_sm_architectures>
<include>all</include>
</supported_sm_architectures>
<title>asyncAPI</title>
<type>exe</type>
</entry>

70
Samples/0_Introduction/asyncAPI/README.md Normal file
View File

@ -0,0 +1,70 @@
# asyncAPI - asyncAPI
## Description
This sample illustrates the usage of CUDA events for both GPU timing and overlapping CPU and GPU execution. Events are inserted into a stream of CUDA calls. Since CUDA stream calls are asynchronous, the CPU can perform computations while GPU is executing (including DMA memcopies between the host and device). CPU can query CUDA events to determine whether GPU has completed tasks.
## Key Concepts
Asynchronous Data Transfers, CUDA Streams and Events
## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [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)
## Supported OSes
Linux, Windows
## Supported CPU Architecture
x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaMemset, cudaFree, cudaEventRecord, cudaMallocHost, cudaProfilerStart, cudaEventCreate, cudaEventElapsedTime, cudaDeviceSynchronize, cudaFreeHost, cudaMalloc, cudaEventQuery, cudaProfilerStop, cudaEventDestroy, cudaMemcpyAsync, cudaGetDeviceProperties
## Prerequisites
Download and install the [CUDA Toolkit 11.6](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<version>.sln - for Visual Studio <version>
```
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 <sample_dir>
$ make
```
The samples makefiles can take advantage of certain options:
* **TARGET_ARCH=<arch>** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le, 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.<br/>
`$ make TARGET_ARCH=x86_64` <br/> `$ make TARGET_ARCH=ppc64le` <br/> `$ make TARGET_ARCH=armv7l` <br/>
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=<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)

5
Samples/asyncAPI/asyncAPI.cu → Samples/0_Introduction/asyncAPI/asyncAPI.cu
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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
@ -39,6 +39,7 @@
// includes CUDA Runtime
#include <cuda_runtime.h>
#include <cuda_profiler_api.h>
// includes, project
#include <helper_cuda.h>
@ -103,6 +104,7 @@ int main(int argc, char *argv[]) {
float gpu_time = 0.0f;
// asynchronously issue work to the GPU (all to stream 0)
checkCudaErrors(cudaProfilerStart());
sdkStartTimer(&timer);
cudaEventRecord(start, 0);
cudaMemcpyAsync(d_a, a, nbytes, cudaMemcpyHostToDevice, 0);
@ -110,6 +112,7 @@ int main(int argc, char *argv[]) {
cudaMemcpyAsync(a, d_a, nbytes, cudaMemcpyDeviceToHost, 0);
cudaEventRecord(stop, 0);
sdkStopTimer(&timer);
checkCudaErrors(cudaProfilerStop());
// have CPU do some work while waiting for stage 1 to finish
unsigned long int counter = 0;

0
Samples/asyncAPI/asyncAPI_vs2017.sln → Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.sln
View File

13
Samples/asyncAPI/asyncAPI_vs2017.vcxproj → Samples/0_Introduction/asyncAPI/asyncAPI_vs2017.vcxproj
View File

@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@ -52,13 +52,13 @@
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
@ -68,10 +68,9 @@
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@ -108,6 +107,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
</ImportGroup>
</Project>

0
Samples/asyncAPI/asyncAPI_vs2019.sln → Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.sln
View File

13
Samples/asyncAPI/asyncAPI_vs2019.vcxproj → Samples/0_Introduction/asyncAPI/asyncAPI_vs2019.vcxproj
View File

@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@ -48,13 +48,13 @@
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
@ -64,10 +64,9 @@
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@ -104,6 +103,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
</ImportGroup>
</Project>

20
Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.sln Normal file
View File

@ -0,0 +1,20 @@

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 2022
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "asyncAPI", "asyncAPI_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

108
Samples/0_Introduction/asyncAPI/asyncAPI_vs2022.vcxproj Normal file
View File

@ -0,0 +1,108 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>asyncAPI_vs2022</RootNamespace>
<ProjectName>asyncAPI</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v143</PlatformToolset>
<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/asyncAPI.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="asyncAPI.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
</ImportGroup>
</Project>

18
Samples/0_Introduction/c++11_cuda/.vscode/c_cpp_properties.json vendored Normal file
View File

@ -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
}

0
Samples/EGLStream_CUDA_CrossGPU/.vscode/extensions.json → Samples/0_Introduction/c++11_cuda/.vscode/extensions.json vendored
View File

0
Samples/c++11_cuda/.vscode/launch.json → Samples/0_Introduction/c++11_cuda/.vscode/launch.json vendored
View File

0
Samples/EGLStream_CUDA_CrossGPU/.vscode/tasks.json → Samples/0_Introduction/c++11_cuda/.vscode/tasks.json vendored
View File

372
Samples/0_Introduction/c++11_cuda/Makefile Normal file
View File

@ -0,0 +1,372 @@
################################################################################
# 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 $(TARGET_OS) for TARGET_OS!)
endif
# host compiler
ifeq ($(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
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 QNX
ifeq ($(TARGET_OS),qnx)
$(info >>> WARNING - c++11_cuda is not supported on QNX - 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 :=
################################################################################
#Detect if installed version of GCC supports required C++11
ifeq ($(TARGET_OS),linux)
empty :=
space := $(empty) $(empty)
GCCVERSIONSTRING := $(shell expr `$(HOST_COMPILER) -dumpversion`)
#Create version number without "."
GCCVERSION := $(shell expr `echo $(GCCVERSIONSTRING)` | cut -f1 -d.)
GCCVERSION += $(shell expr `echo $(GCCVERSIONSTRING)` | cut -f2 -d.)
GCCVERSION += $(shell expr `echo $(GCCVERSIONSTRING)` | cut -f3 -d.)
# Make sure the version number has at least 3 decimals
GCCVERSION += 00
# Remove spaces from the version number
GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION))
#$(warning $(GCCVERSION))
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 47000)
ifeq ($(IS_MIN_VERSION), 1)
$(info >>> GCC Version is greater or equal to 4.7.0 <<<)
else
$(info >>> Waiving build. Minimum GCC version required is 4.7.0<<<)
SAMPLE_ENABLED := 0
endif
endif
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
endif
ifeq ($(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 ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"
endif
################################################################################
# Target rules
all: build
build: c++11_cuda
check.deps:
ifeq ($(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
c++11_cuda.o:c++11_cuda.cu
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
c++11_cuda: c++11_cuda.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) ./c++11_cuda
testrun: build
$(EXEC) ./c++11_cuda --dummy-test-param
clean:
rm -f c++11_cuda c++11_cuda.o
rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/c++11_cuda
clobber: clean

85
Samples/0_Introduction/c++11_cuda/NsightEclipse.xml Normal file
View File

@ -0,0 +1,85 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
<entry>
<name>c++11_cuda</name>
<cflags>
<flag>--std=c++11</flag>
</cflags>
<cuda_api_list>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaMemset</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaMemcpy</toolkit>
</cuda_api_list>
<description><![CDATA[This sample demonstrates C++11 feature support in CUDA. It scans a input text file and prints no. of occurrences of x, y, z, w characters. ]]></description>
<devicecompilation>whole</devicecompilation>
<includepaths>
<path>./</path>
<path>../</path>
<path>../../../Common</path>
</includepaths>
<keyconcepts>
<concept level="advanced">CPP11 CUDA</concept>
</keyconcepts>
<keywords>
<keyword>GPGPU</keyword>
<keyword>CPP11</keyword>
</keywords>
<libraries>
</libraries>
<librarypaths>
</librarypaths>
<nsight_eclipse>true</nsight_eclipse>
<primary_file>c++11_cuda.cu</primary_file>
<qatests>
<qatest>--dummy-test-param</qatest>
</qatests>
<required_dependencies>
<dependency>CPP11</dependency>
</required_dependencies>
<scopes>
<scope>1:CUDA Advanced Topics</scope>
<scope>1:C++11 CUDA</scope>
</scopes>
<sm-arch>sm35</sm-arch>
<sm-arch>sm37</sm-arch>
<sm-arch>sm50</sm-arch>
<sm-arch>sm52</sm-arch>
<sm-arch>sm53</sm-arch>
<sm-arch>sm60</sm-arch>
<sm-arch>sm61</sm-arch>
<sm-arch>sm70</sm-arch>
<sm-arch>sm72</sm-arch>
<sm-arch>sm75</sm-arch>
<sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<sm-arch>sm87</sm-arch>
<supported_envs>
<env>
<arch>x86_64</arch>
<platform>linux</platform>
</env>
<env>
<arch>x86_64</arch>
<platform>macosx</platform>
</env>
<env>
<arch>arm</arch>
</env>
<env>
<arch>sbsa</arch>
</env>
<env>
<arch>ppc64le</arch>
<platform>linux</platform>
</env>
<env>
<platform>windows7</platform>
</env>
</supported_envs>
<supported_sm_architectures>
<include>all</include>
</supported_sm_architectures>
<title>C++11 CUDA</title>
<type>exe</type>
</entry>

74
Samples/0_Introduction/c++11_cuda/README.md Normal file
View File

@ -0,0 +1,74 @@
# c++11_cuda - C++11 CUDA
## Description
This sample demonstrates C++11 feature support in CUDA. It scans a input text file and prints no. of occurrences of x, y, z, w characters.
## Key Concepts
CPP11 CUDA
## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [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)
## Supported OSes
Linux, Windows
## Supported CPU Architecture
x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaMalloc, cudaMemset, cudaFree, cudaMemcpy
## Dependencies needed to build/run
[CPP11](../../README.md#cpp11)
## Prerequisites
Download and install the [CUDA Toolkit 11.6](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## 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<version>.sln - for Visual Studio <version>
```
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 <sample_dir>
$ make
```
The samples makefiles can take advantage of certain options:
* **TARGET_ARCH=<arch>** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le, 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.<br/>
`$ make TARGET_ARCH=x86_64` <br/> `$ make TARGET_ARCH=ppc64le` <br/> `$ make TARGET_ARCH=armv7l` <br/>
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=<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)

2
Samples/c++11_cuda/c++11_cuda.cu → Samples/0_Introduction/c++11_cuda/c++11_cuda.cu
View File

@ -1,4 +1,4 @@
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
/* 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

0
Samples/c++11_cuda/c++11_cuda_vs2017.sln → Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.sln
View File

13
Samples/c++11_cuda/c++11_cuda_vs2017.vcxproj → Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2017.vcxproj
View File

@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@ -52,13 +52,13 @@
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
@ -68,10 +68,9 @@
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@ -108,6 +107,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
</ImportGroup>
</Project>

0
Samples/c++11_cuda/c++11_cuda_vs2019.sln → Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.sln
View File

13
Samples/c++11_cuda/c++11_cuda_vs2019.vcxproj → Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2019.vcxproj
View File

@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@ -48,13 +48,13 @@
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
@ -64,10 +64,9 @@
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;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;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@ -104,6 +103,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
</ImportGroup>
</Project>

20
Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.sln Normal file
View File

@ -0,0 +1,20 @@

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 2022
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "c++11_cuda", "c++11_cuda_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

108
Samples/0_Introduction/c++11_cuda/c++11_cuda_vs2022.vcxproj Normal file
View File

@ -0,0 +1,108 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>c++11_cuda_vs2022</RootNamespace>
<ProjectName>c++11_cuda</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v143</PlatformToolset>
<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/c++11_cuda.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="c++11_cuda.cu" />
<ClInclude Include="range.hpp" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
</ImportGroup>
</Project>

Some files were not shown because too many files have changed in this diff Show More