{"id":2329,"date":"2020-07-06T03:25:49","date_gmt":"2020-07-05T18:25:49","guid":{"rendered":"https:\/\/wp.study3.biz\/?p=2329"},"modified":"2020-07-06T03:26:54","modified_gmt":"2020-07-05T18:26:54","slug":"amd-ryzen-threadripper-3970x-32-core-processor-3-70gh-windows-10-pro-cuda-10-2-titan-rtx-x2-sli-%e3%81%a7simplep2p%e3%82%92%e5%8b%95%e4%bd%9c%e3%81%95%e3%81%9b%e3%81%a6%e3%81%bf%e3%81%9f","status":"publish","type":"post","link":"https:\/\/wp.study3.biz\/?p=2329","title":{"rendered":"AMD Ryzen Threadripper 3970x 32-core Processor 3.70GH windows 10 pro CUDA 10.2 TITAN RTX x2 SLI \u3067simpleP2P\u3092\u52d5\u4f5c\u3055\u305b\u3066\u307f\u305f"},"content":{"rendered":"<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/wp.study3.biz\/wp-content\/uploads\/2020\/05\/nvidia-smi-nvlink-c.jpg\" alt=\"\" width=\"3840\" height=\"2160\" class=\"alignnone size-full wp-image-2336\" \/><br \/>\nC:\\ProgramData\\NVIDIA Corporation\\CUDA Samples\\v10.2\\bin\\win64\\Debug>simpleP2P<br \/>\n[simpleP2P] &#8211; Starting&#8230;<br \/>\nChecking for multiple GPUs&#8230;<br \/>\nCUDA-capable device count: 2<\/p>\n<p>Checking GPU(s) for support of peer to peer memory access&#8230;<br \/>\n> Peer access from TITAN RTX (GPU0) -> TITAN RTX (GPU1) : Yes<br \/>\n> Peer access from TITAN RTX (GPU1) -> TITAN RTX (GPU0) : Yes<br \/>\nEnabling peer access between GPU0 and GPU1&#8230;<br \/>\nAllocating buffers (64MB on GPU0, GPU1 and CPU Host)&#8230;<br \/>\nCreating event handles&#8230;<br \/>\ncudaMemcpyPeer \/ cudaMemcpy between GPU0 and GPU1:<strong> 40.52GB\/s<\/strong><br \/>\nPreparing host buffer and memcpy to GPU0&#8230;<br \/>\nRun kernel on GPU1, taking source data from GPU0 and writing to GPU1&#8230;<br \/>\nRun kernel on GPU0, taking source data from GPU1 and writing to GPU0&#8230;<br \/>\nCopy data back to host from GPU0 and verify results&#8230;<br \/>\nDisabling peer access&#8230;<br \/>\nShutting down&#8230;<br \/>\nTest passed<\/p>\n<p>C:\\ProgramData\\NVIDIA Corporation\\CUDA Samples\\v10.2\\bin\\win64\\Debug>nvidia-smi nvlink -c<br \/>\nGPU 0: TITAN RTX (UUID: GPU-5a71d61e-f130-637a-b33d-4df555b0ed88)<br \/>\n         Link 0, P2P is supported: true<br \/>\n         Link 0, Access to system memory supported: true<br \/>\n         Link 0, P2P atomics supported: true<br \/>\n         Link 0, System memory atomics supported: true<br \/>\n         Link 0, SLI is supported: true<br \/>\n         Link 0, Link is supported: false<br \/>\n         Link 1, P2P is supported: true<br \/>\n         Link 1, Access to system memory supported: true<br \/>\n         Link 1, P2P atomics supported: true<br \/>\n         Link 1, System memory atomics supported: true<br \/>\n         Link 1, SLI is supported: true<br \/>\n         Link 1, Link is supported: false<br \/>\nGPU 1: TITAN RTX (UUID: GPU-7fb51c1d-c1e7-35cc-aad7-66971f05ddb7)<br \/>\n         Link 0, P2P is supported: true<br \/>\n         Link 0, Access to system memory supported: true<br \/>\n         Link 0, P2P atomics supported: true<br \/>\n         Link 0, System memory atomics supported: true<br \/>\n         Link 0, SLI is supported: true<br \/>\n         Link 0, Link is supported: false<br \/>\n         Link 1, P2P is supported: true<br \/>\n         Link 1, Access to system memory supported: true<br \/>\n         Link 1, P2P atomics supported: true<br \/>\n         Link 1, System memory atomics supported: true<br \/>\n         Link 1, SLI is supported: true<br \/>\n         Link 1, Link is supported: false<\/p>\n<p>C:\\ProgramData\\NVIDIA Corporation\\CUDA Samples\\v10.2\\bin\\win64\\Debug><br \/>\n<a href=\"https:\/\/wp.study3.biz\/wp-content\/uploads\/2020\/05\/nvidia-smi.txt\">nvidia-smi<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>C:\\ProgramData\\NVIDIA Corporation\\CUDA Samples\\v10.2\\bin\\win64\\Debug>simpleP2P [simpleP2P] &#8211; Starting&#038;#8 &hellip; <a href=\"https:\/\/wp.study3.biz\/?p=2329\">\u7d9a\u304d\u3092\u8aad\u3080 <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[18,10],"tags":[],"class_list":["post-2329","post","type-post","status-publish","format-standard","hentry","category-nvidia","category-windows"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/posts\/2329","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2329"}],"version-history":[{"count":3,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/posts\/2329\/revisions"}],"predecessor-version":[{"id":2339,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/posts\/2329\/revisions\/2339"}],"wp:attachment":[{"href":"https:\/\/wp.study3.biz\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2329"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2329"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2329"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}