<?xml version="1.0" encoding="UTF-8"?> 
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
<entry>
  <name>matrixMul</name>
  <cuda_api_list>
    <toolkit>cudaEventCreate</toolkit>
    <toolkit>cudaEventRecord</toolkit>
    <toolkit>cudaEventQuery</toolkit>
    <toolkit>cudaEventDestroy</toolkit>
    <toolkit>cudaEventElapsedTime</toolkit>
    <toolkit>cudaEventSynchronize</toolkit>
    <toolkit>cudaMalloc</toolkit>
    <toolkit>cudaFree</toolkit>
    <toolkit>cudaMemcpy</toolkit>
  </cuda_api_list>
  <description><![CDATA[This sample implements matrix multiplication which makes use of shared memory to ensure data reuse, the matrix multiplication is done using tiling approach. 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.]]></description>
  <devicecompilation>whole</devicecompilation>
  <includepaths>
    <path>./</path>
    <path>../</path>
    <path>../../common/inc</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>sm30</sm-arch>
  <sm-arch>sm35</sm-arch>
  <sm-arch>sm37</sm-arch>
  <sm-arch>sm50</sm-arch>
  <sm-arch>sm52</sm-arch>
  <sm-arch>sm60</sm-arch>
  <sm-arch>sm61</sm-arch>
  <sm-arch>sm70</sm-arch>
  <sm-arch>sm75</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>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>
  <type>exe</type>
</entry>
