mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2024-11-28 17:29:18 +08:00
89 lines
2.6 KiB
XML
89 lines
2.6 KiB
XML
|
<?xml version="1.0" encoding="UTF-8"?>
|
||
|
|
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
||
|
|
<entry>
|
||
|
|
<name>matrixMulCUBLAS</name>
|
||
|
|
<cuda_api_list>
|
||
|
|
<toolkit>cudaEventCreate</toolkit>
|
||
|
|
<toolkit>cudaEventRecord</toolkit>
|
||
|
|
<toolkit>cudaEventQuery</toolkit>
|
||
|
|
<toolkit>cudaEventDestroy</toolkit>
|
||
|
|
<toolkit>cudaEventElapsedTime</toolkit>
|
||
|
|
<toolkit>cudaMalloc</toolkit>
|
||
|
|
<toolkit>cudaFree</toolkit>
|
||
|
|
<toolkit>cudaMemcpy</toolkit>
|
||
|
|
<toolkit>cublasCreate</toolkit>
|
||
|
|
<toolkit>cublasSgemm</toolkit>
|
||
|
|
</cuda_api_list>
|
||
|
|
<description><![CDATA[This sample implements matrix multiplication from Chapter 3 of the programming guide. 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">Performance Strategies</concept>
|
||
|
|
<concept level="basic">Linear Algebra</concept>
|
||
|
|
<concept level="basic">CUBLAS</concept>
|
||
|
|
</keyconcepts>
|
||
|
|
<keywords>
|
||
|
|
<keyword>CUDA</keyword>
|
||
|
|
<keyword>CUBLAS</keyword>
|
||
|
|
<keyword>matrix multiply</keyword>
|
||
|
|
</keywords>
|
||
|
|
<libraries>
|
||
|
|
<library>cublas</library>
|
||
|
|
</libraries>
|
||
|
|
<librarypaths>
|
||
|
|
</librarypaths>
|
||
|
|
<nsight_eclipse>true</nsight_eclipse>
|
||
|
|
<primary_file>matrixMulCUBLAS.cpp</primary_file>
|
||
|
|
<required_dependencies>
|
||
|
|
<dependency>CUBLAS</dependency>
|
||
|
|
</required_dependencies>
|
||
|
|
<scopes>
|
||
|
|
<scope>1:CUDA Basic Topics</scope>
|
||
|
|
<scope>3:Linear Algebra</scope>
|
||
|
|
</scopes>
|
||
|
|
<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>sm72</sm-arch>
|
||
|
|
<sm-arch>sm75</sm-arch>
|
||
|
|
<sm-arch>sm80</sm-arch>
|
||
|
|
<sm-arch>sm86</sm-arch>
|
||
|
|
<sources>
|
||
|
|
<ignore>new/matrixMulCUBLAS.cpp</ignore>
|
||
|
|
</sources>
|
||
|
|
<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 (CUBLAS)</title>
|
||
|
|
<type>exe</type>
|
||
|
|
</entry>
|