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

add and update samples with CUDA 11.3 support

Browse Source
This commit is contained in:
Rutwik Choughule
2021-04-16 11:54:26 +05:30
parent 067cb65523
commit 568b39bd5b
214 changed files with 6590 additions and 3856 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Samples/streamOrderedAllocationP2P/README.md
View File

@@ -27,7 +27,7 @@ cudaMallocAsync, cudaFreeAsync, cudaMemPoolSetAccess, cudaDeviceGetDefaultMemPoo
## Prerequisites
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Download and install the [CUDA Toolkit 11.3](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run

35
Samples/streamOrderedAllocationP2P/streamOrderedAllocationP2P.cu
View File

@@ -122,24 +122,23 @@ std::pair<int, int> getP2PCapableGpuPair() {
int deviceId = itr->second;
checkCudaErrors(cudaSetDevice(deviceId));
std::for_each(
itr, bestFit.second,
[&deviceId, &bestFitDeviceIds](decltype(*itr) mapPair) {
if (deviceId != mapPair.second) {
int access = 0;
checkCudaErrors(
cudaDeviceCanAccessPeer(&access, deviceId, mapPair.second));
printf("Device=%d %s Access Peer Device=%d\n", deviceId,
access ? "CAN" : "CANNOT", mapPair.second);
if (access && bestFitDeviceIds.size() < kNumGpusRequired) {
bestFitDeviceIds.emplace(deviceId);
bestFitDeviceIds.emplace(mapPair.second);
} else {
printf("Ignoring device %i (max devices exceeded)\n",
mapPair.second);
}
}
});
std::for_each(itr, bestFit.second, [&deviceId, &bestFitDeviceIds,
&kNumGpusRequired](
decltype(*itr) mapPair) {
if (deviceId != mapPair.second) {
int access = 0;
checkCudaErrors(
cudaDeviceCanAccessPeer(&access, deviceId, mapPair.second));
printf("Device=%d %s Access Peer Device=%d\n", deviceId,
access ? "CAN" : "CANNOT", mapPair.second);
if (access && bestFitDeviceIds.size() < kNumGpusRequired) {
bestFitDeviceIds.emplace(deviceId);
bestFitDeviceIds.emplace(mapPair.second);
} else {
printf("Ignoring device %i (max devices exceeded)\n", mapPair.second);
}
}
});
if (bestFitDeviceIds.size() >= kNumGpusRequired) {
printf("Selected p2p capable devices - ");

4
Samples/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2017.vcxproj
View File

@@ -38,7 +38,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.3.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -108,6 +108,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.3.targets" />
</ImportGroup>
</Project>

4
Samples/streamOrderedAllocationP2P/streamOrderedAllocationP2P_vs2019.vcxproj
View File

@@ -34,7 +34,7 @@
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
<Import Project="$(CUDAPropsPath)\CUDA 11.3.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -104,6 +104,6 @@
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
<Import Project="$(CUDAPropsPath)\CUDA 11.3.targets" />
</ImportGroup>
</Project>