mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2024-12-01 12:39:17 +08:00
88 lines
2.5 KiB
XML
88 lines
2.5 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
|
<entry>
|
|
<name>concurrentKernels</name>
|
|
<cuda_api_list>
|
|
<toolkit>cudaStreamWaitEvent</toolkit>
|
|
<toolkit>cudaStreamDestroy</toolkit>
|
|
<toolkit>cudaFree</toolkit>
|
|
<toolkit>cudaEventRecord</toolkit>
|
|
<toolkit>cudaMallocHost</toolkit>
|
|
<toolkit>cudaStreamCreate</toolkit>
|
|
<toolkit>cudaEventCreate</toolkit>
|
|
<toolkit>cudaEventElapsedTime</toolkit>
|
|
<toolkit>cudaEventSynchronize</toolkit>
|
|
<toolkit>cudaFreeHost</toolkit>
|
|
<toolkit>cudaMalloc</toolkit>
|
|
<toolkit>cudaEventCreateWithFlags</toolkit>
|
|
<toolkit>cudaEventDestroy</toolkit>
|
|
<toolkit>cudaMemcpyAsync</toolkit>
|
|
<toolkit>cudaGetDeviceProperties</toolkit>
|
|
<toolkit>cudaGetDevice</toolkit>
|
|
</cuda_api_list>
|
|
<description><![CDATA[This sample demonstrates the use of CUDA streams for concurrent execution of several kernels on GPU device. It also illustrates how to introduce dependencies between CUDA streams with the new cudaStreamWaitEvent function.]]></description>
|
|
<devicecompilation>whole</devicecompilation>
|
|
<includepaths>
|
|
<path>./</path>
|
|
<path>../</path>
|
|
<path>../../../Common</path>
|
|
</includepaths>
|
|
<keyconcepts>
|
|
<concept level="advanced">Performance Strategies</concept>
|
|
</keyconcepts>
|
|
<keywords>
|
|
<keyword>CUDA</keyword>
|
|
<keyword>Concurrent Kernels</keyword>
|
|
</keywords>
|
|
<libraries>
|
|
</libraries>
|
|
<librarypaths>
|
|
</librarypaths>
|
|
<nsight_eclipse>true</nsight_eclipse>
|
|
<primary_file>concurrentKernels.cu</primary_file>
|
|
<scopes>
|
|
<scope>1:CUDA Advanced Topics</scope>
|
|
<scope>1:Performance Strategies</scope>
|
|
</scopes>
|
|
<sm-arch>sm35</sm-arch>
|
|
<sm-arch>sm37</sm-arch>
|
|
<sm-arch>sm50</sm-arch>
|
|
<sm-arch>sm52</sm-arch>
|
|
<sm-arch>sm53</sm-arch>
|
|
<sm-arch>sm60</sm-arch>
|
|
<sm-arch>sm61</sm-arch>
|
|
<sm-arch>sm70</sm-arch>
|
|
<sm-arch>sm72</sm-arch>
|
|
<sm-arch>sm75</sm-arch>
|
|
<sm-arch>sm80</sm-arch>
|
|
<sm-arch>sm86</sm-arch>
|
|
<sm-arch>sm87</sm-arch>
|
|
<supported_envs>
|
|
<env>
|
|
<arch>x86_64</arch>
|
|
<platform>linux</platform>
|
|
</env>
|
|
<env>
|
|
<platform>windows7</platform>
|
|
</env>
|
|
<env>
|
|
<arch>x86_64</arch>
|
|
<platform>macosx</platform>
|
|
</env>
|
|
<env>
|
|
<arch>arm</arch>
|
|
</env>
|
|
<env>
|
|
<arch>sbsa</arch>
|
|
</env>
|
|
<env>
|
|
<arch>ppc64le</arch>
|
|
<platform>linux</platform>
|
|
</env>
|
|
</supported_envs>
|
|
<supported_sm_architectures>
|
|
<include>all</include>
|
|
</supported_sm_architectures>
|
|
<title>Concurrent Kernels</title>
|
|
</entry>
|