mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2024-11-28 14:19:15 +08:00
91 lines
2.7 KiB
XML
91 lines
2.7 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
|
<entry>
|
|
<name>asyncAPI</name>
|
|
<cuda_api_list>
|
|
<toolkit>cudaMemset</toolkit>
|
|
<toolkit>cudaFree</toolkit>
|
|
<toolkit>cudaEventRecord</toolkit>
|
|
<toolkit>cudaMallocHost</toolkit>
|
|
<toolkit>cudaProfilerStart</toolkit>
|
|
<toolkit>cudaEventCreate</toolkit>
|
|
<toolkit>cudaEventElapsedTime</toolkit>
|
|
<toolkit>cudaDeviceSynchronize</toolkit>
|
|
<toolkit>cudaFreeHost</toolkit>
|
|
<toolkit>cudaMalloc</toolkit>
|
|
<toolkit>cudaEventQuery</toolkit>
|
|
<toolkit>cudaProfilerStop</toolkit>
|
|
<toolkit>cudaEventDestroy</toolkit>
|
|
<toolkit>cudaMemcpyAsync</toolkit>
|
|
<toolkit>cudaGetDeviceProperties</toolkit>
|
|
</cuda_api_list>
|
|
<description><![CDATA[This sample illustrates the usage of CUDA events for both GPU timing and overlapping CPU and GPU execution. Events are inserted into a stream of CUDA calls. Since CUDA stream calls are asynchronous, the CPU can perform computations while GPU is executing (including DMA memcopies between the host and device). CPU can query CUDA events to determine whether GPU has completed tasks.]]></description>
|
|
<devicecompilation>whole</devicecompilation>
|
|
<includepaths>
|
|
<path>./</path>
|
|
<path>../</path>
|
|
<path>../../../Common</path>
|
|
</includepaths>
|
|
<keyconcepts>
|
|
<concept level="basic">Asynchronous Data Transfers</concept>
|
|
<concept level="basic">CUDA Streams and Events</concept>
|
|
</keyconcepts>
|
|
<keywords>
|
|
<keyword>GPGPU</keyword>
|
|
</keywords>
|
|
<libraries>
|
|
</libraries>
|
|
<librarypaths>
|
|
</librarypaths>
|
|
<nsight_eclipse>true</nsight_eclipse>
|
|
<primary_file>asyncAPI.cu</primary_file>
|
|
<qatests>
|
|
<qatest>--dummy-test-param</qatest>
|
|
</qatests>
|
|
<scopes>
|
|
<scope>1:CUDA Basic Topics</scope>
|
|
<scope>1:Performance Strategies</scope>
|
|
</scopes>
|
|
<sm-arch>sm35</sm-arch>
|
|
<sm-arch>sm37</sm-arch>
|
|
<sm-arch>sm50</sm-arch>
|
|
<sm-arch>sm52</sm-arch>
|
|
<sm-arch>sm53</sm-arch>
|
|
<sm-arch>sm60</sm-arch>
|
|
<sm-arch>sm61</sm-arch>
|
|
<sm-arch>sm70</sm-arch>
|
|
<sm-arch>sm72</sm-arch>
|
|
<sm-arch>sm75</sm-arch>
|
|
<sm-arch>sm80</sm-arch>
|
|
<sm-arch>sm86</sm-arch>
|
|
<sm-arch>sm87</sm-arch>
|
|
<supported_envs>
|
|
<env>
|
|
<arch>x86_64</arch>
|
|
<platform>linux</platform>
|
|
</env>
|
|
<env>
|
|
<platform>windows7</platform>
|
|
</env>
|
|
<env>
|
|
<arch>x86_64</arch>
|
|
<platform>macosx</platform>
|
|
</env>
|
|
<env>
|
|
<arch>arm</arch>
|
|
</env>
|
|
<env>
|
|
<arch>sbsa</arch>
|
|
</env>
|
|
<env>
|
|
<arch>ppc64le</arch>
|
|
<platform>linux</platform>
|
|
</env>
|
|
</supported_envs>
|
|
<supported_sm_architectures>
|
|
<include>all</include>
|
|
</supported_sm_architectures>
|
|
<title>asyncAPI</title>
|
|
<type>exe</type>
|
|
</entry>
|