NASP/cuda-samples
85
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-10-23 21:28:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update samples for CUDA 11.8 with correct props

Browse Source
This commit is contained in:
Rob Nertney
2022-10-14 17:43:37 -07:00
parent b312abaa07
commit 81992093d2
1146 changed files with 4209 additions and 4272 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Samples/3_CUDA_Features/dmmaTensorCoreGemm/Makefile
View File

@@ -322,9 +322,9 @@ endif
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 80 86 87
SMS ?= 80 86 87 90
else
SMS ?= 80 86
SMS ?= 80 86 90
endif
ifeq ($(SMS),)

19
Samples/3_CUDA_Features/dmmaTensorCoreGemm/NsightEclipse.xml
View File

@@ -6,18 +6,18 @@
<flag>--std=c++11</flag>
</cflags>
<cuda_api_list>
<toolkit>cudaMemset</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaEventCreate</toolkit>
<toolkit>cudaFuncSetAttribute</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaEventSynchronize</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaGetLastError</toolkit>
<toolkit>cudaMemcpy</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaGetErrorString</toolkit>
<toolkit>cudaGetLastError</toolkit>
<toolkit>cudaEventSynchronize</toolkit>
<toolkit>cudaFuncSetAttribute</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaMemset</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
<toolkit>cudaEventCreate</toolkit>
</cuda_api_list>
<description><![CDATA[CUDA sample 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 for faster matrix operations. This sample also uses async copy provided by cuda pipeline interface for gmem to shmem async loads which improves kernel performance and reduces register presssure. Further, this sample also demonstrates how to use cooperative groups async copy interface over a group for performing gmem to shmem async loads.]]></description>
<devicecompilation>whole</devicecompilation>
@@ -52,6 +52,7 @@
<sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<sm-arch>sm87</sm-arch>
<sm-arch>sm90</sm-arch>
<supported_envs>
<env>
<arch>x86_64</arch>

6
Samples/3_CUDA_Features/dmmaTensorCoreGemm/README.md
View File

@@ -10,7 +10,7 @@ Matrix Multiply, WMMA, Tensor Cores
## Supported SM Architectures
[SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
[SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, ppc64le, aarch64
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaMemset, cudaFree, cudaEventRecord, cudaEventCreate, cudaFuncSetAttribute, cudaEventElapsedTime, cudaEventSynchronize, cudaMalloc, cudaGetLastError, cudaMemcpy, cudaGetErrorString, cudaGetDeviceProperties
cudaMemcpy, cudaFree, cudaGetErrorString, cudaGetLastError, cudaEventSynchronize, cudaFuncSetAttribute, cudaEventRecord, cudaMemset, cudaMalloc, cudaEventElapsedTime, cudaGetDeviceProperties, cudaEventCreate
## 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.
Download and install the [CUDA Toolkit 11.8](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run

6
Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,7 +67,7 @@
<OutputFile>$(OutDir)/dmmaTensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -107,6 +107,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
</ImportGroup>
</Project>

6
Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
<OutputFile>$(OutDir)/dmmaTensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
</ImportGroup>
</Project>

6
Samples/3_CUDA_Features/dmmaTensorCoreGemm/dmmaTensorCoreGemm_vs2022.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.8.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,7 +63,7 @@
<OutputFile>$(OutDir)/dmmaTensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_80,sm_80;compute_86,sm_86;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -103,6 +103,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.8.targets" />
</ImportGroup>
</Project>