mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2024-10-06 14:19:18 +08:00
90 lines
2.8 KiB
XML
90 lines
2.8 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
|
<entry>
|
|
<name>matrixMul</name>
|
|
<cuda_api_list>
|
|
<toolkit>cudaStreamCreateWithFlags</toolkit>
|
|
<toolkit>cudaProfilerStop</toolkit>
|
|
<toolkit>cudaMalloc</toolkit>
|
|
<toolkit>cudaFree</toolkit>
|
|
<toolkit>cudaMallocHost</toolkit>
|
|
<toolkit>cudaProfilerStart</toolkit>
|
|
<toolkit>cudaEventSynchronize</toolkit>
|
|
<toolkit>cudaEventRecord</toolkit>
|
|
<toolkit>cudaFreeHost</toolkit>
|
|
<toolkit>cudaStreamSynchronize</toolkit>
|
|
<toolkit>cudaEventDestroy</toolkit>
|
|
<toolkit>cudaEventElapsedTime</toolkit>
|
|
<toolkit>cudaMemcpyAsync</toolkit>
|
|
<toolkit>cudaEventCreate</toolkit>
|
|
</cuda_api_list>
|
|
<description><![CDATA[This sample implements matrix multiplication and is exactly the same as Chapter 6 of the programming guide. It has been written for clarity of exposition to illustrate various CUDA programming principles, not with the goal of providing the most performant generic kernel for matrix multiplication. To illustrate GPU performance for matrix multiply, this sample also shows how to use the new CUDA 4.0 interface for CUBLAS to demonstrate high-performance performance for matrix multiplication.]]></description>
|
|
<devicecompilation>whole</devicecompilation>
|
|
<includepaths>
|
|
<path>./</path>
|
|
<path>../</path>
|
|
<path>../../../Common</path>
|
|
</includepaths>
|
|
<keyconcepts>
|
|
<concept level="basic">CUDA Runtime API</concept>
|
|
<concept level="basic">Linear Algebra</concept>
|
|
</keyconcepts>
|
|
<keywords>
|
|
<keyword>CUDA</keyword>
|
|
<keyword>matrix multiply</keyword>
|
|
</keywords>
|
|
<libraries>
|
|
</libraries>
|
|
<librarypaths>
|
|
</librarypaths>
|
|
<nsight_eclipse>true</nsight_eclipse>
|
|
<primary_file>matrixMul.cu</primary_file>
|
|
<scopes>
|
|
<scope>1:CUDA Basic Topics</scope>
|
|
<scope>3:Linear Algebra</scope>
|
|
</scopes>
|
|
<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>
|
|
<sm-arch>sm89</sm-arch>
|
|
<sm-arch>sm90</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>aarch64</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>Matrix Multiplication (CUDA Runtime API Version)</title>
|
|
</entry>
|