mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2024-11-25 03:49:14 +08:00
80 lines
2.4 KiB
XML
80 lines
2.4 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
|
<entry>
|
|
<name>threadFenceReduction</name>
|
|
<cuda_api_list>
|
|
<toolkit>cudaMemcpy</toolkit>
|
|
<toolkit>cudaFree</toolkit>
|
|
<toolkit>cudaDeviceSynchronize</toolkit>
|
|
<toolkit>cudaMalloc</toolkit>
|
|
<toolkit>cudaGetDeviceProperties</toolkit>
|
|
</cuda_api_list>
|
|
<description><![CDATA[This sample shows how to perform a reduction operation on an array of values using the thread Fence intrinsic to produce a single value in a single kernel (as opposed to two or more kernel calls as shown in the "reduction" CUDA Sample). Single-pass reduction requires global atomic instructions (Compute Capability 2.0 or later) and the _threadfence() intrinsic (CUDA 2.2 or later).]]></description>
|
|
<devicecompilation>whole</devicecompilation>
|
|
<includepaths>
|
|
<path>./</path>
|
|
<path>../</path>
|
|
<path>../../../Common</path>
|
|
</includepaths>
|
|
<keyconcepts>
|
|
<concept level="basic">Cooperative Groups</concept>
|
|
<concept level="advanced">Data-Parallel Algorithms</concept>
|
|
<concept level="advanced">Performance Strategies</concept>
|
|
</keyconcepts>
|
|
<keywords>
|
|
<keyword>reduction</keyword>
|
|
</keywords>
|
|
<libraries>
|
|
</libraries>
|
|
<librarypaths>
|
|
</librarypaths>
|
|
<nsight_eclipse>true</nsight_eclipse>
|
|
<primary_file>threadFenceReduction.cu</primary_file>
|
|
<scopes>
|
|
<scope>1:CUDA Advanced Topics</scope>
|
|
<scope>1:Data-Parallel Algorithms</scope>
|
|
<scope>1:Performance Strategies</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>sbsa</arch>
|
|
</env>
|
|
<env>
|
|
<arch>ppc64le</arch>
|
|
<platform>linux</platform>
|
|
</env>
|
|
</supported_envs>
|
|
<supported_sm_architectures>
|
|
<include>all</include>
|
|
</supported_sm_architectures>
|
|
<title>threadFenceReduction</title>
|
|
<type>exe</type>
|
|
</entry>
|