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/StreamPriorities/Makefile
View File

@@ -297,9 +297,9 @@ LIBRARIES :=
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 53 61 70 72 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

15
Samples/3_CUDA_Features/StreamPriorities/NsightEclipse.xml
View File

@@ -3,15 +3,15 @@
<entry>
<name>StreamPriorities</name>
<cuda_api_list>
<toolkit>cudaDeviceGetStreamPriorityRange</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaEventCreate</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaEventSynchronize</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaStreamCreateWithPriority</toolkit>
<toolkit>cudaMemcpy</toolkit>
<toolkit>cudaStreamCreateWithPriority</toolkit>
<toolkit>cudaDeviceGetStreamPriorityRange</toolkit>
<toolkit>cudaEventSynchronize</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
<toolkit>cudaEventCreate</toolkit>
</cuda_api_list>
<description><![CDATA[This sample demonstrates basic use of stream priorities.]]></description>
<devicecompilation>whole</devicecompilation>
@@ -54,6 +54,7 @@
<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/StreamPriorities/README.md
View File

@@ -10,7 +10,7 @@ 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)
[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) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, ppc64le
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaDeviceGetStreamPriorityRange, cudaEventRecord, cudaEventCreate, cudaEventElapsedTime, cudaEventSynchronize, cudaMalloc, cudaStreamCreateWithPriority, cudaMemcpy, cudaGetDeviceProperties
cudaMemcpy, cudaStreamCreateWithPriority, cudaDeviceGetStreamPriorityRange, cudaEventSynchronize, cudaEventRecord, cudaMalloc, cudaEventElapsedTime, cudaGetDeviceProperties, cudaEventCreate
## Dependencies needed to build/run
[Stream-Priorities](../../../README.md#stream-priorities)
## 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

4
Samples/3_CUDA_Features/bf16TensorCoreGemm/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/bf16TensorCoreGemm/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[A CUDA sample demonstrating __nv_bfloat16 (e8m7) GEMM computation using the 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.]]></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/bf16TensorCoreGemm/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/bf16TensorCoreGemm/bf16TensorCoreGemm_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)/bf16TensorCoreGemm.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/bf16TensorCoreGemm/bf16TensorCoreGemm_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)/bf16TensorCoreGemm.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/bf16TensorCoreGemm/bf16TensorCoreGemm_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)/bf16TensorCoreGemm.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>

4
Samples/3_CUDA_Features/binaryPartitionCG/Makefile
View File

@@ -310,9 +310,9 @@ endif
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 53 61 70 72 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

9
Samples/3_CUDA_Features/binaryPartitionCG/NsightEclipse.xml
View File

@@ -6,15 +6,15 @@
<flag>--std=c++11</flag>
</cflags>
<cuda_api_list>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaMallocHost</toolkit>
<toolkit>cudaOccupancyMaxPotentialBlockSize</toolkit>
<toolkit>cudaMemsetAsync</toolkit>
<toolkit>cudaFreeHost</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaStreamSynchronize</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaMemsetAsync</toolkit>
<toolkit>cudaMemcpyAsync</toolkit>
<toolkit>cudaOccupancyMaxPotentialBlockSize</toolkit>
</cuda_api_list>
<description><![CDATA[This sample is a simple code that illustrates binary partition cooperative groups and reduce within the thread block.]]></description>
<devicecompilation>whole</devicecompilation>
@@ -54,6 +54,7 @@
<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/binaryPartitionCG/README.md
View File

@@ -10,7 +10,7 @@ Cooperative Groups
## 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)
[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) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaFree, cudaMallocHost, cudaOccupancyMaxPotentialBlockSize, cudaMemsetAsync, cudaFreeHost, cudaMalloc, cudaStreamCreateWithFlags, cudaStreamSynchronize, cudaMemcpyAsync
cudaStreamCreateWithFlags, cudaFree, cudaMallocHost, cudaFreeHost, cudaStreamSynchronize, cudaMalloc, cudaMemsetAsync, cudaMemcpyAsync, cudaOccupancyMaxPotentialBlockSize
## 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.
## Build and Run

6
Samples/3_CUDA_Features/binaryPartitionCG/binaryPartitionCG_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)/binaryPartitionCG.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>
<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;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/binaryPartitionCG/binaryPartitionCG_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)/binaryPartitionCG.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>
<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;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/binaryPartitionCG/binaryPartitionCG_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)/binaryPartitionCG.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>
<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;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>

4
Samples/3_CUDA_Features/bindlessTexture/Makefile
View File

@@ -299,9 +299,9 @@ endif
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 53 61 70 72 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

31
Samples/3_CUDA_Features/bindlessTexture/NsightEclipse.xml
View File

@@ -3,28 +3,28 @@
<entry>
<name>bindlessTexture</name>
<cuda_api_list>
<toolkit>cudaGraphicsMapResources</toolkit>
<toolkit>cudaGetMipmappedArrayLevel</toolkit>
<toolkit>cudaGraphicsResourceGetMappedPointer</toolkit>
<toolkit>cudaArrayGetInfo</toolkit>
<toolkit>cudaMemcpy</toolkit>
<toolkit>cudaFreeMipmappedArray</toolkit>
<toolkit>cudaGetMipmappedArrayLevel</toolkit>
<toolkit>cudaGraphicsMapResources</toolkit>
<toolkit>cudaDestroySurfaceObject</toolkit>
<toolkit>cudaPitchedPtr</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaGraphicsUnregisterResource</toolkit>
<toolkit>cudaDeviceSynchronize</toolkit>
<toolkit>cudaDestroyTextureObject</toolkit>
<toolkit>cudaGetLastError</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaFreeArray</toolkit>
<toolkit>cudaGraphicsGLRegisterBuffer</toolkit>
<toolkit>cudaExtent</toolkit>
<toolkit>cudaDeviceSynchronize</toolkit>
<toolkit>cudaCreateSurfaceObject</toolkit>
<toolkit>cudaMallocMipmappedArray</toolkit>
<toolkit>cudaPitchedPtr</toolkit>
<toolkit>cudaGraphicsResourceGetMappedPointer</toolkit>
<toolkit>cudaCreateTextureObject</toolkit>
<toolkit>cudaMallocArray</toolkit>
<toolkit>cudaGraphicsUnmapResources</toolkit>
<toolkit>cudaMallocArray</toolkit>
<toolkit>cudaFreeArray</toolkit>
<toolkit>cudaArrayGetInfo</toolkit>
<toolkit>cudaGetLastError</toolkit>
<toolkit>cudaDestroyTextureObject</toolkit>
<toolkit>cudaGraphicsGLRegisterBuffer</toolkit>
<toolkit>cudaFreeMipmappedArray</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaGraphicsUnregisterResource</toolkit>
<toolkit>cudaMalloc</toolkit>
</cuda_api_list>
<description><![CDATA[This example demonstrates use of cudaSurfaceObject, cudaTextureObject, and MipMap support in CUDA. A GPU with Compute Capability SM 3.0 is required to run the sample.]]></description>
<devicecompilation>whole</devicecompilation>
@@ -85,6 +85,7 @@
<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/bindlessTexture/README.md
View File

@@ -10,7 +10,7 @@ Graphics Interop, Texture
## 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)
[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) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaGraphicsMapResources, cudaGetMipmappedArrayLevel, cudaGraphicsResourceGetMappedPointer, cudaArrayGetInfo, cudaMemcpy, cudaFreeMipmappedArray, cudaDestroySurfaceObject, cudaPitchedPtr, cudaMalloc, cudaGraphicsUnregisterResource, cudaDeviceSynchronize, cudaDestroyTextureObject, cudaGetLastError, cudaFree, cudaFreeArray, cudaGraphicsGLRegisterBuffer, cudaExtent, cudaCreateSurfaceObject, cudaMallocMipmappedArray, cudaCreateTextureObject, cudaMallocArray, cudaGraphicsUnmapResources
cudaMemcpy, cudaGetMipmappedArrayLevel, cudaGraphicsMapResources, cudaDestroySurfaceObject, cudaExtent, cudaDeviceSynchronize, cudaCreateSurfaceObject, cudaMallocMipmappedArray, cudaPitchedPtr, cudaGraphicsResourceGetMappedPointer, cudaCreateTextureObject, cudaGraphicsUnmapResources, cudaMallocArray, cudaFreeArray, cudaArrayGetInfo, cudaGetLastError, cudaDestroyTextureObject, cudaGraphicsGLRegisterBuffer, cudaFreeMipmappedArray, cudaFree, cudaGraphicsUnregisterResource, cudaMalloc
## Dependencies needed to build/run
[X11](../../../README.md#x11), [GL](../../../README.md#gl)
## 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/bindlessTexture/bindlessTexture_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)/bindlessTexture.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -118,6 +118,6 @@
</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/bindlessTexture/bindlessTexture_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)/bindlessTexture.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -114,6 +114,6 @@
</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/bindlessTexture/bindlessTexture_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)/bindlessTexture.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -114,6 +114,6 @@
</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>

25
Samples/3_CUDA_Features/bindlessTexture/findgllib.mk
View File

@@ -53,11 +53,12 @@ endif
ifeq ("$(TARGET_OS)","linux")
# $(info) >> findgllib.mk -> LINUX path <<<)
# Each set of Linux Distros have different paths for where to find their OpenGL libraries reside
UBUNTU = $(shell echo $(DISTRO) | grep -i ubuntu >/dev/null 2>&1; echo $$?)
FEDORA = $(shell echo $(DISTRO) | grep -i fedora >/dev/null 2>&1; echo $$?)
RHEL = $(shell echo $(DISTRO) | grep -i 'red\|rhel' >/dev/null 2>&1; echo $$?)
CENTOS = $(shell echo $(DISTRO) | grep -i centos >/dev/null 2>&1; echo $$?)
UBUNTU = $(shell echo $(DISTRO) | grep -i ubuntu >/dev/null 2>&1; echo $$?)
FEDORA = $(shell echo $(DISTRO) | grep -i fedora >/dev/null 2>&1; echo $$?)
RHEL = $(shell echo $(DISTRO) | grep -i 'red\|rhel' >/dev/null 2>&1; echo $$?)
CENTOS = $(shell echo $(DISTRO) | grep -i centos >/dev/null 2>&1; echo $$?)
SUSE = $(shell echo $(DISTRO) | grep -i 'suse\|sles' >/dev/null 2>&1; echo $$?)
KYLIN = $(shell echo $(DISTRO) | grep -i kylin >/dev/null 2>&1; echo $$?)
ifeq ("$(UBUNTU)","0")
ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l)
GLPATH := /usr/arm-linux-gnueabihf/lib
@@ -87,27 +88,17 @@ ifeq ("$(TARGET_OS)","linux")
DFLT_PATH ?= /usr/lib
endif
endif
ifeq ("$(SUSE)","0")
GLPATH ?= /usr/X11R6/lib64
GLLINK ?= -L/usr/X11R6/lib64
DFLT_PATH ?= /usr/lib64
endif
ifeq ("$(FEDORA)","0")
else
GLPATH ?= /usr/lib64/nvidia
GLLINK ?= -L/usr/lib64/nvidia
DFLT_PATH ?= /usr/lib64
endif
ifeq ("$(RHEL)","0")
GLPATH ?= /usr/lib64/nvidia
GLLINK ?= -L/usr/lib64/nvidia
DFLT_PATH ?= /usr/lib64
endif
ifeq ("$(CENTOS)","0")
GLPATH ?= /usr/lib64/nvidia
GLLINK ?= -L/usr/lib64/nvidia
DFLT_PATH ?= /usr/lib64
endif
# find libGL, libGLU
GLLIB := $(shell find -L $(GLPATH) $(DFLT_PATH) -name libGL.so -print 2>/dev/null)
GLULIB := $(shell find -L $(GLPATH) $(DFLT_PATH) -name libGLU.so -print 2>/dev/null)

4
Samples/3_CUDA_Features/cdpAdvancedQuicksort/Makefile
View File

@@ -310,9 +310,9 @@ endif
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 61 70 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

21
Samples/3_CUDA_Features/cdpAdvancedQuicksort/NsightEclipse.xml
View File

@@ -8,20 +8,20 @@
<flag>--std=c++14</flag>
</cflags>
<cuda_api_list>
<toolkit>cudaMemset</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaEventCreate</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaDeviceSynchronize</toolkit>
<toolkit>cudaPeekAtLastError</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaGetLastError</toolkit>
<toolkit>cudaMemcpyAsync</toolkit>
<toolkit>cudaMemcpy</toolkit>
<toolkit>cudaMemcpyAsync</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaGetErrorString</toolkit>
<toolkit>cudaGetLastError</toolkit>
<toolkit>cudaPeekAtLastError</toolkit>
<toolkit>cudaDeviceSynchronize</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaMemset</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
<toolkit>cudaEventCreate</toolkit>
</cuda_api_list>
<description><![CDATA[This sample demonstrates an advanced quicksort implemented using CUDA Dynamic Parallelism. This sample requires devices with compute capability 3.5 or higher.]]></description>
<includepaths>
@@ -63,6 +63,7 @@
<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/cdpAdvancedQuicksort/README.md
View File

@@ -10,7 +10,7 @@ Cooperative Groups, CUDA Dynamic Parallelism
## 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)
[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) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaMemset, cudaFree, cudaEventRecord, cudaEventCreate, cudaEventElapsedTime, cudaDeviceSynchronize, cudaPeekAtLastError, cudaMalloc, cudaStreamCreateWithFlags, cudaGetLastError, cudaMemcpyAsync, cudaMemcpy, cudaGetErrorString, cudaGetDeviceProperties
cudaStreamCreateWithFlags, cudaMemcpy, cudaMemcpyAsync, cudaFree, cudaGetErrorString, cudaGetLastError, cudaPeekAtLastError, cudaDeviceSynchronize, cudaEventRecord, cudaMemset, cudaMalloc, cudaEventElapsedTime, cudaGetDeviceProperties, cudaEventCreate
## Dependencies needed to build/run
[CDP](../../../README.md#cdp)
## 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/cdpAdvancedQuicksort/cdpAdvancedQuicksort_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)/cdpAdvancedQuicksort.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -109,6 +109,6 @@
</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/cdpAdvancedQuicksort/cdpAdvancedQuicksort_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)/cdpAdvancedQuicksort.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -105,6 +105,6 @@
</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/cdpAdvancedQuicksort/cdpAdvancedQuicksort_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)/cdpAdvancedQuicksort.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -105,6 +105,6 @@
</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>

4
Samples/3_CUDA_Features/cdpBezierTessellation/Makefile
View File

@@ -285,9 +285,9 @@ LIBRARIES :=
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 61 70 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

3
Samples/3_CUDA_Features/cdpBezierTessellation/NsightEclipse.xml
View File

@@ -6,10 +6,10 @@
<flag>-dc</flag>
</cflags>
<cuda_api_list>
<toolkit>cudaMemcpy</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaGetDeviceCount</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaMemcpy</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
</cuda_api_list>
<description><![CDATA[This sample demonstrates bezier tessellation of lines implemented using CUDA Dynamic Parallelism. This sample requires devices with compute capability 3.5 or higher.]]></description>
@@ -50,6 +50,7 @@
<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/cdpBezierTessellation/README.md
View File

@@ -10,7 +10,7 @@ CUDA Dynamic Parallelism
## 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)
[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) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaFree, cudaGetDeviceCount, cudaMalloc, cudaMemcpy, cudaGetDeviceProperties
cudaMemcpy, cudaFree, cudaGetDeviceCount, cudaMalloc, cudaGetDeviceProperties
## Dependencies needed to build/run
[CDP](../../../README.md#cdp)
## 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/cdpBezierTessellation/cdpBezierTessellation_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)/cdpBezierTessellation.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -108,6 +108,6 @@
</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/cdpBezierTessellation/cdpBezierTessellation_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)/cdpBezierTessellation.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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/cdpBezierTessellation/cdpBezierTessellation_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)/cdpBezierTessellation.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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>

4
Samples/3_CUDA_Features/cdpQuadtree/Makefile
View File

@@ -310,9 +310,9 @@ endif
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 61 70 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

9
Samples/3_CUDA_Features/cdpQuadtree/NsightEclipse.xml
View File

@@ -7,11 +7,11 @@
<flag>--std=c++14</flag>
</cflags>
<cuda_api_list>
<toolkit>cudaDeviceSetLimit</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaGetLastError</toolkit>
<toolkit>cudaMemcpy</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaGetLastError</toolkit>
<toolkit>cudaDeviceSetLimit</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
</cuda_api_list>
<description><![CDATA[This sample demonstrates Quad Trees implemented using CUDA Dynamic Parallelism. This sample requires devices with compute capability 3.5 or higher.]]></description>
@@ -54,6 +54,7 @@
<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/cdpQuadtree/README.md
View File

@@ -10,7 +10,7 @@ Cooperative Groups, CUDA Dynamic Parallelism
## 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)
[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) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaDeviceSetLimit, cudaFree, cudaMalloc, cudaGetLastError, cudaMemcpy, cudaGetDeviceProperties
cudaMemcpy, cudaFree, cudaGetLastError, cudaDeviceSetLimit, cudaMalloc, cudaGetDeviceProperties
## Dependencies needed to build/run
[CDP](../../../README.md#cdp)
## 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/cdpQuadtree/cdpQuadtree_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)/cdpQuadtree.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -108,6 +108,6 @@
</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/cdpQuadtree/cdpQuadtree_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)/cdpQuadtree.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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/cdpQuadtree/cdpQuadtree_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)/cdpQuadtree.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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>

4
Samples/3_CUDA_Features/cdpSimplePrint/Makefile
View File

@@ -285,9 +285,9 @@ LIBRARIES :=
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 61 70 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

5
Samples/3_CUDA_Features/cdpSimplePrint/NsightEclipse.xml
View File

@@ -6,10 +6,10 @@
<flag>-dc</flag>
</cflags>
<cuda_api_list>
<toolkit>cudaDeviceSetLimit</toolkit>
<toolkit>cudaGetLastError</toolkit>
<toolkit>cudaDeviceSynchronize</toolkit>
<toolkit>cudaGetLastError</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
<toolkit>cudaDeviceSetLimit</toolkit>
</cuda_api_list>
<description><![CDATA[This sample demonstrates simple printf implemented using CUDA Dynamic Parallelism. This sample requires devices with compute capability 3.5 or higher.]]></description>
<includepaths>
@@ -51,6 +51,7 @@
<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/cdpSimplePrint/README.md
View File

@@ -10,7 +10,7 @@ CUDA Dynamic Parallelism
## 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)
[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) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaDeviceSetLimit, cudaGetLastError, cudaDeviceSynchronize, cudaGetDeviceProperties
cudaDeviceSynchronize, cudaGetLastError, cudaGetDeviceProperties, cudaDeviceSetLimit
## Dependencies needed to build/run
[CDP](../../../README.md#cdp)
## 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/cdpSimplePrint/cdpSimplePrint_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)/cdpSimplePrint.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -108,6 +108,6 @@
</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/cdpSimplePrint/cdpSimplePrint_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)/cdpSimplePrint.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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/cdpSimplePrint/cdpSimplePrint_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)/cdpSimplePrint.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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>

4
Samples/3_CUDA_Features/cdpSimpleQuicksort/Makefile
View File

@@ -285,9 +285,9 @@ LIBRARIES :=
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 61 70 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

11
Samples/3_CUDA_Features/cdpSimpleQuicksort/NsightEclipse.xml
View File

@@ -6,13 +6,13 @@
<flag>-dc</flag>
</cflags>
<cuda_api_list>
<toolkit>cudaDeviceSetLimit</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaStreamDestroy</toolkit>
<toolkit>cudaDeviceSynchronize</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaMemcpy</toolkit>
<toolkit>cudaStreamDestroy</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaDeviceSynchronize</toolkit>
<toolkit>cudaDeviceSetLimit</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
</cuda_api_list>
<description><![CDATA[This sample demonstrates simple quicksort implemented using CUDA Dynamic Parallelism. This sample requires devices with compute capability 3.5 or higher.]]></description>
@@ -55,6 +55,7 @@
<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/cdpSimpleQuicksort/README.md
View File

@@ -10,7 +10,7 @@ CUDA Dynamic Parallelism
## 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)
[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) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaDeviceSetLimit, cudaFree, cudaStreamDestroy, cudaDeviceSynchronize, cudaMalloc, cudaStreamCreateWithFlags, cudaMemcpy, cudaGetDeviceProperties
cudaStreamCreateWithFlags, cudaMemcpy, cudaStreamDestroy, cudaFree, cudaDeviceSynchronize, cudaDeviceSetLimit, cudaMalloc, cudaGetDeviceProperties
## Dependencies needed to build/run
[CDP](../../../README.md#cdp)
## 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/cdpSimpleQuicksort/cdpSimpleQuicksort_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)/cdpSimpleQuicksort.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -108,6 +108,6 @@
</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/cdpSimpleQuicksort/cdpSimpleQuicksort_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)/cdpSimpleQuicksort.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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/cdpSimpleQuicksort/cdpSimpleQuicksort_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)/cdpSimpleQuicksort.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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>

4
Samples/3_CUDA_Features/cudaCompressibleMemory/Makefile
View File

@@ -293,9 +293,9 @@ LIBRARIES :=
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 53 61 70 72 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

8
Samples/3_CUDA_Features/cudaCompressibleMemory/README.md
View File

@@ -10,7 +10,7 @@ CUDA Driver API, Compressible Memory, MMAP
## 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)
[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) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, ppc64le, aarch64
## CUDA APIs involved
### [CUDA Driver API](http://docs.nvidia.com/cuda/cuda-driver-api/index.html)
cuMemRelease, cuCtxGetDevice, cuMemGetAllocationPropertiesFromHandle, cuMemSetAccess, cuMemMap, cuMemCreate, cuMemAddressFree, cuMemGetAllocationGranularity, cuMemUnmap, cuMemAddressReserve, cuDeviceGetAttribute
cuMemGetAllocationPropertiesFromHandle, cuMemCreate, cuDeviceGetAttribute, cuCtxGetDevice, cuMemGetAllocationGranularity, cuMemAddressFree, cuMemUnmap, cuMemMap, cuMemRelease, cuMemAddressReserve, cuMemSetAccess
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaEventRecord, cudaEventCreate, cudaOccupancyMaxPotentialBlockSize, cudaEventElapsedTime, cudaEventSynchronize, cudaMemcpy
cudaMemcpy, cudaEventSynchronize, cudaEventRecord, cudaEventElapsedTime, cudaOccupancyMaxPotentialBlockSize, cudaEventCreate
## 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.
## Build and Run

6
Samples/3_CUDA_Features/cudaCompressibleMemory/cudaCompressibleMemory_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)/cudaCompressibleMemory.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -108,6 +108,6 @@
</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/cudaCompressibleMemory/cudaCompressibleMemory_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)/cudaCompressibleMemory.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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/cudaCompressibleMemory/cudaCompressibleMemory_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)/cudaCompressibleMemory.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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>

4
Samples/3_CUDA_Features/cudaTensorCoreGemm/Makefile
View File

@@ -291,9 +291,9 @@ LIBRARIES :=
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 70 72 75 80 86 87
SMS ?= 70 72 75 80 86 87 90
else
SMS ?= 70 75 80 86
SMS ?= 70 75 80 86 90
endif
ifeq ($(SMS),)

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

@@ -6,18 +6,18 @@
<flag>-maxrregcount=255</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 demonstrating a GEMM computation using the Warp Matrix Multiply and Accumulate (WMMA) API introduced in CUDA 9.
@@ -52,6 +52,7 @@ In addition to that, it demonstrates the use of the new CUDA function attribute
<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/cudaTensorCoreGemm/README.md
View File

@@ -14,7 +14,7 @@ Matrix Multiply, WMMA, Tensor Cores
## Supported SM Architectures
[SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
[SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -27,11 +27,11 @@ 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
## 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.
## Build and Run

6
Samples/3_CUDA_Features/cudaTensorCoreGemm/cudaTensorCoreGemm_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)/cudaTensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;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/cudaTensorCoreGemm/cudaTensorCoreGemm_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)/cudaTensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;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/cudaTensorCoreGemm/cudaTensorCoreGemm_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)/cudaTensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;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>

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>

4
Samples/3_CUDA_Features/globalToShmemAsyncCopy/Makefile
View File

@@ -310,9 +310,9 @@ endif
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 70 72 75 80 86 87
SMS ?= 70 72 75 80 86 87 90
else
SMS ?= 70 75 80 86
SMS ?= 70 75 80 86 90
endif
ifeq ($(SMS),)

23
Samples/3_CUDA_Features/globalToShmemAsyncCopy/NsightEclipse.xml
View File

@@ -6,20 +6,20 @@
<flag>--std=c++11</flag>
</cflags>
<cuda_api_list>
<toolkit>cudaFree</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaMallocHost</toolkit>
<toolkit>cudaEventCreate</toolkit>
<toolkit>cudaMemsetAsync</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaEventSynchronize</toolkit>
<toolkit>cudaDeviceGetAttribute</toolkit>
<toolkit>cudaFreeHost</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaEventDestroy</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaDeviceGetAttribute</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaMallocHost</toolkit>
<toolkit>cudaEventSynchronize</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaFreeHost</toolkit>
<toolkit>cudaStreamSynchronize</toolkit>
<toolkit>cudaEventDestroy</toolkit>
<toolkit>cudaEventElapsedTime</toolkit>
<toolkit>cudaMemsetAsync</toolkit>
<toolkit>cudaMemcpyAsync</toolkit>
<toolkit>cudaEventCreate</toolkit>
</cuda_api_list>
<description><![CDATA[This sample implements matrix multiplication which uses asynchronous copy of data from global to shared memory when on compute capability 8.0 or higher. Also demonstrates arrive-wait barrier for synchronization.]]></description>
<devicecompilation>whole</devicecompilation>
@@ -59,6 +59,7 @@
<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/globalToShmemAsyncCopy/README.md
View File

@@ -10,7 +10,7 @@ CUDA Runtime API, Linear Algebra, CPP11 CUDA
## Supported SM Architectures
[SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
[SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,14 +23,14 @@ x86_64, ppc64le, armv7l, aarch64
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaFree, cudaEventRecord, cudaMallocHost, cudaEventCreate, cudaMemsetAsync, cudaEventElapsedTime, cudaEventSynchronize, cudaDeviceGetAttribute, cudaFreeHost, cudaMalloc, cudaStreamCreateWithFlags, cudaEventDestroy, cudaStreamSynchronize, cudaMemcpyAsync
cudaStreamCreateWithFlags, cudaMalloc, cudaDeviceGetAttribute, cudaFree, cudaMallocHost, cudaEventSynchronize, cudaEventRecord, cudaFreeHost, cudaStreamSynchronize, cudaEventDestroy, cudaEventElapsedTime, cudaMemsetAsync, cudaMemcpyAsync, 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/globalToShmemAsyncCopy/globalToShmemAsyncCopy_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)/globalToShmemAsyncCopy.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;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/globalToShmemAsyncCopy/globalToShmemAsyncCopy_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)/globalToShmemAsyncCopy.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;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/globalToShmemAsyncCopy/globalToShmemAsyncCopy_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)/globalToShmemAsyncCopy.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_70,sm_70;compute_75,sm_75;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>

4
Samples/3_CUDA_Features/graphMemoryFootprint/Makefile
View File

@@ -285,9 +285,9 @@ LIBRARIES :=
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 53 61 70 72 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

25
Samples/3_CUDA_Features/graphMemoryFootprint/NsightEclipse.xml
View File

@@ -3,23 +3,23 @@
<entry>
<name>graphMemoryFootprint</name>
<cuda_api_list>
<toolkit>cudaGraphAddMemFreeNode</toolkit>
<toolkit>cudaStreamDestroy</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaGraphExecDestroy</toolkit>
<toolkit>cudaGraphInstantiate</toolkit>
<toolkit>cudaDeviceGetAttribute</toolkit>
<toolkit>cudaDriverGetVersion</toolkit>
<toolkit>cudaGraphCreate</toolkit>
<toolkit>cudaGraphAddKernelNode</toolkit>
<toolkit>cudaGraphAddMemAllocNode</toolkit>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaDeviceGraphMemTrim</toolkit>
<toolkit>cudaStreamSynchronize</toolkit>
<toolkit>cudaGraphInstantiate</toolkit>
<toolkit>cudaStreamDestroy</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaDeviceGetAttribute</toolkit>
<toolkit>cudaGraphAddKernelNode</toolkit>
<toolkit>cudaGraphAddMemFreeNode</toolkit>
<toolkit>cudaDeviceGetGraphMemAttribute</toolkit>
<toolkit>cudaGraphCreate</toolkit>
<toolkit>cudaGraphDestroy</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
<toolkit>cudaDriverGetVersion</toolkit>
<toolkit>cudaGraphLaunch</toolkit>
<toolkit>cudaStreamSynchronize</toolkit>
<toolkit>cudaDeviceGraphMemTrim</toolkit>
<toolkit>cudaGetDeviceProperties</toolkit>
<toolkit>cudaGraphExecDestroy</toolkit>
</cuda_api_list>
<description><![CDATA[This sample demonstrates how graph memory nodes re-use virtual addresses and physical memory.]]></description>
<devicecompilation>whole</devicecompilation>
@@ -56,6 +56,7 @@
<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/graphMemoryFootprint/README.md
View File

@@ -10,7 +10,7 @@ CUDA Runtime API, Performance Strategies, CUDA Graphs
## Supported SM Architectures
[SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
[SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaGraphAddMemFreeNode, cudaStreamDestroy, cudaFree, cudaGraphExecDestroy, cudaGraphInstantiate, cudaDeviceGetAttribute, cudaDriverGetVersion, cudaGraphCreate, cudaGraphAddKernelNode, cudaGraphAddMemAllocNode, cudaStreamCreateWithFlags, cudaDeviceGraphMemTrim, cudaStreamSynchronize, cudaDeviceGetGraphMemAttribute, cudaGraphDestroy, cudaGetDeviceProperties, cudaGraphLaunch
cudaGraphAddMemAllocNode, cudaStreamCreateWithFlags, cudaGraphInstantiate, cudaStreamDestroy, cudaFree, cudaDeviceGetAttribute, cudaGraphAddKernelNode, cudaGraphAddMemFreeNode, cudaDeviceGetGraphMemAttribute, cudaGraphCreate, cudaGraphDestroy, cudaDriverGetVersion, cudaGraphLaunch, cudaStreamSynchronize, cudaDeviceGraphMemTrim, cudaGetDeviceProperties, cudaGraphExecDestroy
## 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.
## Build and Run

6
Samples/3_CUDA_Features/graphMemoryFootprint/graphMemoryFootprint_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)/graphMemoryFootprint.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>
<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;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/graphMemoryFootprint/graphMemoryFootprint_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)/graphMemoryFootprint.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>
<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;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/graphMemoryFootprint/graphMemoryFootprint_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)/graphMemoryFootprint.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>
<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;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>

4
Samples/3_CUDA_Features/graphMemoryNodes/Makefile
View File

@@ -285,9 +285,9 @@ LIBRARIES :=
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 53 61 70 72 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

45
Samples/3_CUDA_Features/graphMemoryNodes/NsightEclipse.xml
View File

@@ -3,32 +3,32 @@
<entry>
<name>graphMemoryNodes</name>
<cuda_api_list>
<toolkit>cudaMallocAsync</toolkit>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaMemcpy</toolkit>
<toolkit>cudaMemcpyAsync</toolkit>
<toolkit>cudaStreamDestroy</toolkit>
<toolkit>cudaMallocManaged</toolkit>
<toolkit>cudaEventCreate</toolkit>
<toolkit>cudaDriverGetVersion</toolkit>
<toolkit>cudaGraphCreate</toolkit>
<toolkit>cudaGraphAddMemAllocNode</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaEventDestroy</toolkit>
<toolkit>cudaStreamEndCapture</toolkit>
<toolkit>cudaGraphExecDestroy</toolkit>
<toolkit>cudaStreamBeginCapture</toolkit>
<toolkit>cudaDeviceGetAttribute</toolkit>
<toolkit>cudaStreamSynchronize</toolkit>
<toolkit>cudaGraphDestroy</toolkit>
<toolkit>cudaDriverGetVersion</toolkit>
<toolkit>cudaGraphLaunch</toolkit>
<toolkit>cudaGraphAddMemFreeNode</toolkit>
<toolkit>cudaStreamWaitEvent</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaGraphInstantiate</toolkit>
<toolkit>cudaGraphAddKernelNode</toolkit>
<toolkit>cudaEventDestroy</toolkit>
<toolkit>cudaMallocAsync</toolkit>
<toolkit>cudaStreamEndCapture</toolkit>
<toolkit>cudaMallocManaged</toolkit>
<toolkit>cudaGraphCreate</toolkit>
<toolkit>cudaMemcpyAsync</toolkit>
<toolkit>cudaFreeAsync</toolkit>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaGraphInstantiate</toolkit>
<toolkit>cudaStreamDestroy</toolkit>
<toolkit>cudaStreamBeginCapture</toolkit>
<toolkit>cudaStreamWaitEvent</toolkit>
<toolkit>cudaEventCreate</toolkit>
<toolkit>cudaGraphAddMemAllocNode</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaGraphAddKernelNode</toolkit>
<toolkit>cudaGraphAddMemFreeNode</toolkit>
<toolkit>cudaGraphDestroy</toolkit>
<toolkit>cudaEventRecord</toolkit>
<toolkit>cudaStreamSynchronize</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaGraphExecDestroy</toolkit>
</cuda_api_list>
<description><![CDATA[A demonstration of memory allocations and frees within CUDA graphs using Graph APIs and Stream Capture APIs.]]></description>
<devicecompilation>whole</devicecompilation>
@@ -67,6 +67,7 @@
<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/graphMemoryNodes/README.md
View File

@@ -10,7 +10,7 @@ CUDA Graphs, Stream Capture
## Supported SM Architectures
[SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
[SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaMallocAsync, cudaStreamCreateWithFlags, cudaMemcpy, cudaMemcpyAsync, cudaStreamDestroy, cudaMallocManaged, cudaEventCreate, cudaDriverGetVersion, cudaGraphCreate, cudaGraphAddMemAllocNode, cudaMalloc, cudaEventDestroy, cudaStreamEndCapture, cudaGraphExecDestroy, cudaStreamBeginCapture, cudaDeviceGetAttribute, cudaStreamSynchronize, cudaGraphDestroy, cudaGraphLaunch, cudaGraphAddMemFreeNode, cudaStreamWaitEvent, cudaFree, cudaEventRecord, cudaGraphInstantiate, cudaGraphAddKernelNode, cudaFreeAsync
cudaMemcpy, cudaDeviceGetAttribute, cudaDriverGetVersion, cudaGraphLaunch, cudaEventDestroy, cudaMallocAsync, cudaStreamEndCapture, cudaMallocManaged, cudaGraphCreate, cudaMemcpyAsync, cudaFreeAsync, cudaStreamCreateWithFlags, cudaGraphInstantiate, cudaStreamDestroy, cudaStreamBeginCapture, cudaStreamWaitEvent, cudaEventCreate, cudaGraphAddMemAllocNode, cudaFree, cudaGraphAddKernelNode, cudaGraphAddMemFreeNode, cudaGraphDestroy, cudaEventRecord, cudaStreamSynchronize, cudaMalloc, cudaGraphExecDestroy
## 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.
## Build and Run

6
Samples/3_CUDA_Features/graphMemoryNodes/graphMemoryNodes_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)/graphMemoryNodes.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>
<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;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/graphMemoryNodes/graphMemoryNodes_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)/graphMemoryNodes.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>
<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;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/graphMemoryNodes/graphMemoryNodes_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)/graphMemoryNodes.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>
<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;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>

4
Samples/3_CUDA_Features/immaTensorCoreGemm/Makefile
View File

@@ -291,9 +291,9 @@ LIBRARIES :=
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 72 75 80 86 87
SMS ?= 72 75 80 86 87 90
else
SMS ?= 75 80 86
SMS ?= 75 80 86 90
endif
ifeq ($(SMS),)

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

@@ -6,18 +6,18 @@
<flag>-maxrregcount=255</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 demonstrating a integer GEMM computation using the Warp Matrix Multiply and Accumulate (WMMA) API for integer introduced in CUDA 10. This sample demonstrates the use of the CUDA WMMA API employing the Tensor Cores introduced in the Volta chip family for faster matrix operations. In addition to that, it demonstrates the use of the new CUDA function attribute cudaFuncAttributeMaxDynamicSharedMemorySize that allows the application to reserve an extended amount of shared memory than it is available by default.]]></description>
<devicecompilation>whole</devicecompilation>
@@ -47,6 +47,7 @@
<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/immaTensorCoreGemm/README.md
View File

@@ -10,7 +10,7 @@ Matrix Multiply, WMMA, Tensor Cores
## Supported SM Architectures
[SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
[SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,11 +23,11 @@ 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
## 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.
## Build and Run

6
Samples/3_CUDA_Features/immaTensorCoreGemm/immaTensorCoreGemm_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)/immaTensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_75,sm_75;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/immaTensorCoreGemm/immaTensorCoreGemm_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)/immaTensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_75,sm_75;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/immaTensorCoreGemm/immaTensorCoreGemm_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)/immaTensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<CodeGeneration>compute_75,sm_75;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>

4
Samples/3_CUDA_Features/jacobiCudaGraphs/Makefile
View File

@@ -279,9 +279,9 @@ LIBRARIES :=
# Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
SMS ?= 53 61 70 72 75 80 86 87
SMS ?= 53 61 70 72 75 80 86 87 90
else
SMS ?= 35 37 50 52 60 61 70 75 80 86
SMS ?= 35 37 50 52 60 61 70 75 80 86 90
endif
ifeq ($(SMS),)

35
Samples/3_CUDA_Features/jacobiCudaGraphs/NsightEclipse.xml
View File

@@ -3,28 +3,28 @@
<entry>
<name>jacobiCudaGraphs</name>
<cuda_api_list>
<toolkit>cudaGraphAddMemsetNode</toolkit>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaMemcpyAsync</toolkit>
<toolkit>cudaExtent</toolkit>
<toolkit>cudaGraphLaunch</toolkit>
<toolkit>cudaGraphAddMemcpyNode</toolkit>
<toolkit>cudaMallocHost</toolkit>
<toolkit>cudaPitchedPtr</toolkit>
<toolkit>cudaGraphCreate</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaPos</toolkit>
<toolkit>cudaGraphAddMemcpyNode</toolkit>
<toolkit>cudaStreamEndCapture</toolkit>
<toolkit>cudaGraphExecDestroy</toolkit>
<toolkit>cudaStreamBeginCapture</toolkit>
<toolkit>cudaGraphExecKernelNodeSetParams</toolkit>
<toolkit>cudaStreamSynchronize</toolkit>
<toolkit>cudaGraphLaunch</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaGraphInstantiate</toolkit>
<toolkit>cudaExtent</toolkit>
<toolkit>cudaMemsetAsync</toolkit>
<toolkit>cudaGraphCreate</toolkit>
<toolkit>cudaFreeHost</toolkit>
<toolkit>cudaGraphAddKernelNode</toolkit>
<toolkit>cudaMemsetAsync</toolkit>
<toolkit>cudaMemcpyAsync</toolkit>
<toolkit>cudaGraphExecKernelNodeSetParams</toolkit>
<toolkit>cudaStreamCreateWithFlags</toolkit>
<toolkit>cudaGraphInstantiate</toolkit>
<toolkit>cudaStreamBeginCapture</toolkit>
<toolkit>cudaFree</toolkit>
<toolkit>cudaGraphExecUpdate</toolkit>
<toolkit>cudaGraphAddKernelNode</toolkit>
<toolkit>cudaPos</toolkit>
<toolkit>cudaStreamSynchronize</toolkit>
<toolkit>cudaGraphAddMemsetNode</toolkit>
<toolkit>cudaMalloc</toolkit>
<toolkit>cudaGraphExecDestroy</toolkit>
</cuda_api_list>
<description><![CDATA[Demonstrates Instantiated CUDA Graph Update with Jacobi Iterative Method using cudaGraphExecKernelNodeSetParams() and cudaGraphExecUpdate() approach.]]></description>
<devicecompilation>whole</devicecompilation>
@@ -66,6 +66,7 @@
<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/jacobiCudaGraphs/README.md
View File

@@ -10,7 +10,7 @@ CUDA Graphs, Stream Capture, Instantiated CUDA Graph Update, Cooperative Groups
## 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)
[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) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
@@ -23,11 +23,11 @@ x86_64, ppc64le, armv7l
## CUDA APIs involved
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
cudaGraphAddMemsetNode, cudaStreamCreateWithFlags, cudaMemcpyAsync, cudaMallocHost, cudaPitchedPtr, cudaGraphCreate, cudaMalloc, cudaPos, cudaGraphAddMemcpyNode, cudaStreamEndCapture, cudaGraphExecDestroy, cudaStreamBeginCapture, cudaGraphExecKernelNodeSetParams, cudaStreamSynchronize, cudaGraphLaunch, cudaFree, cudaGraphInstantiate, cudaExtent, cudaMemsetAsync, cudaFreeHost, cudaGraphAddKernelNode, cudaGraphExecUpdate
cudaExtent, cudaGraphLaunch, cudaGraphAddMemcpyNode, cudaMallocHost, cudaPitchedPtr, cudaStreamEndCapture, cudaGraphCreate, cudaFreeHost, cudaMemsetAsync, cudaMemcpyAsync, cudaGraphExecKernelNodeSetParams, cudaStreamCreateWithFlags, cudaGraphInstantiate, cudaStreamBeginCapture, cudaFree, cudaGraphExecUpdate, cudaGraphAddKernelNode, cudaPos, cudaStreamSynchronize, cudaGraphAddMemsetNode, cudaMalloc, cudaGraphExecDestroy
## 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.
## Build and Run

6
Samples/3_CUDA_Features/jacobiCudaGraphs/jacobiCudaGraphs_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)/jacobiCudaGraphs.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -108,6 +108,6 @@
</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/jacobiCudaGraphs/jacobiCudaGraphs_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)/jacobiCudaGraphs.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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/jacobiCudaGraphs/jacobiCudaGraphs_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)/jacobiCudaGraphs.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>
<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;compute_90,sm_90;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
<Include>./;../../../Common</Include>
<Defines>WIN32</Defines>
@@ -104,6 +104,6 @@
</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>

18
Samples/3_CUDA_Features/memMapIPCDrv/Makefile
View File

@@ -274,24 +274,6 @@ ifeq ($(TARGET_OS),darwin)
SAMPLE_ENABLED := 0
endif
# This sample is not supported on ARMv7
ifeq ($(TARGET_ARCH),armv7l)
$(info >>> WARNING - memMapIPCDrv is not supported on ARMv7 - waiving sample <<<)
SAMPLE_ENABLED := 0
endif
# This sample is not supported on aarch64
ifeq ($(TARGET_ARCH),aarch64)
$(info >>> WARNING - memMapIPCDrv is not supported on aarch64 - waiving sample <<<)
SAMPLE_ENABLED := 0
endif
# This sample is not supported on sbsa
ifeq ($(TARGET_ARCH),sbsa)
$(info >>> WARNING - memMapIPCDrv is not supported on sbsa - waiving sample <<<)
SAMPLE_ENABLED := 0
endif
ALL_LDFLAGS :=
ALL_LDFLAGS += $(ALL_CCFLAGS)
ALL_LDFLAGS += $(addprefix -Xlinker ,$(LDFLAGS))

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