{"id":2138,"date":"2016-09-27T17:58:03","date_gmt":"2016-09-28T00:58:03","guid":{"rendered":"https:\/\/www.www.pogolinux.com\/blog\/?p=2138"},"modified":"2019-10-16T04:15:44","modified_gmt":"2019-10-16T11:15:44","slug":"nvidia-titan-x-pascal","status":"publish","type":"post","link":"https:\/\/www.pogolinux.com\/blog\/nvidia-titan-x-pascal\/","title":{"rendered":"Is the NVIDIA Titan X up to the Challenges of Deep Learning?"},"content":{"rendered":"<p>NVIDIA has recently introduced the new TITAN X&#x2122;, the biggest and most advanced GPU ever built. Blaise Pascal said, &#8220;Imagination decides everything.&#8221; This certainly applies to\u00a0the hardware engineering team at NVIDIA. Not content with the already &#8220;irresponsible amount of performance&#8221; of\u00a0their GTX 1080, they\u00a0imagined breaking the 10 teraflops barrier for computing on a single chip. The decidedly impressive result is the new NVIDIA TITAN X with Pascal&#x2122;.<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_89 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/www.pogolinux.com\/blog\/nvidia-titan-x-pascal\/#NVIDIA_TITAN_X_with_Pascal\" >NVIDIA TITAN X with Pascal<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/www.pogolinux.com\/blog\/nvidia-titan-x-pascal\/#The_Velocity_D58PSC_%E2%80%93_a_Desktop_Supercomputer\" >The Velocity D58PSC &#8211; a Desktop Supercomputer<\/a><\/li><\/ul><\/nav><\/div>\n<h2 style=\"text-align: center;\"><span class=\"ez-toc-section\" id=\"NVIDIA_TITAN_X_with_Pascal\"><\/span>NVIDIA TITAN X with Pascal<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><img loading=\"lazy\" decoding=\"async\" width=\"205\" height=\"300\" class=\"wp-image-2206 size-full alignright\" style=\"width: 205px;\" src=\"https:\/\/www.pogolinux.com\/blog\/wp-content\/uploads\/2016\/09\/nvidia-tesla-architecture-1.jpg\" alt=\"NVIDIA Tesla Architecture\" \/>When tackling\u00a0deep learning challenges, nothing short of\u00a0ultimate performance\u00a0will get the job done. \u00a0The latest\u00a0Titan X is the first\u00a0GPU to consider. The Titan X with Pascal is built atop\u00a0NVIDIA&#8217;s new upsized GP102 architecture. Highlights of the GP102 include:<\/p>\n<ul>\n<li>30 Streaming Multiprocessors<\/li>\n<li>11 TFLOPS FP32<\/li>\n<li>44 TFLOPS INT8<\/li>\n<li>3584 CUDA Cores at 1.53GHz<\/li>\n<li>12 GB GDDR5x memory (480 GB\/s)<\/li>\n<li>12,000,000,000 Transistors<\/li>\n<li>NVLink High-Speed SLI Interconnect<\/li>\n<\/ul>\n<h2 style=\"white-space: nowrap; text-align: center; margin-left: 55px; margin-top: 50px;\"><span class=\"ez-toc-section\" id=\"The_Velocity_D58PSC_%E2%80%93_a_Desktop_Supercomputer\"><\/span>The Velocity D58PSC &#8211; a Desktop Supercomputer<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><img loading=\"lazy\" decoding=\"async\" width=\"240\" height=\"268\" class=\"alignleft wp-image-2224 size-full\" style=\"padding: 10px 2px; width: 240px; height: 268px;\" src=\"https:\/\/www.pogolinux.com\/blog\/wp-content\/uploads\/2016\/09\/velocity-d58psc-cutaway-240.jpg\" alt=\"Velocity D58PSC with Titan X Cutaway\" \/> One might expect that computational learning projects would require racks and racks of dense compute nodes with lightning fast interconnects. However,\u00a0technologies like the new NVIDIA Titan X\u00a0bring\u00a0High Performance Computing (HPC) right to your desktop. Pogo provides many researchers with their own Personal Supercomputers, such as the Pogo Linux Velocity D58PSC Workstation.<\/p>\n<p>We recently\u00a0built one of these high end workstations for an\u00a0uncompromising client researching machine learning. Pushing the boundaries in a\u00a0deep learning project, this researcher is using TensorFlow, one of the products from the Google Brain Team within the Google Machine Intelligence organization. One aspect of TensorFlow is that it works best with GPU computing. However, even with GPUs, performance increases are sublinear. As a result, achieving top performance requires top-of-the-line GPUs. This is the\u00a0ideal use case for the new Titan X.<\/p>\n<p>Our client required no less than four Titan X cards installed in their new system. Fortunately, the Velocity D58PSC\u00a0provided the ideal platform for this application.<\/p>\n<p>With Dual Intel Xeon E5-2600 v4 series processors and up to 1TB of DDR4 memory, the D58PSC will extract\u00a0maximum performance from these new GPUs. Topping off\u00a0the configuration with up to 8x SAS or SATA SSDs will ensure there will be no I\/O bottlenecks throughout the system. In cutting edge research, having the right equipment is key. By combining the raw CPU and I\/O power of the D58PSC with Titan X GPUs, this researcher has a recipe for success.<\/p>\n<p>To find out more about GPU Computing and what it can do for your projects,\u00a0<a href=\"https:\/\/www.pogolinux.com\/about\/contact\" target=\"_blank\" rel=\"noopener noreferrer\">Contact the Pogo Sales Engineering team<\/a>\u00a0team to learn more\u00a0about these extraordinary technologies.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" width=\"500\" height=\"150\" class=\"alignnone wp-image-2161 size-full\" style=\"padding-left: 80px; width: 500px; height: 150px;\" src=\"https:\/\/www.pogolinux.com\/blog\/wp-content\/uploads\/2016\/09\/velocity-d58psc-cta.jpg\" alt=\"Configure your Velocity D58PSC with the NVIDIA TITAN X Pascal\" \/><\/p>\n<hr style=\"border: 0; height: 0; border-top: 1px solid rgba(0, 0, 0, 0.1); border-bottom: 1px solid rgba(255, 255, 255, 0.3);\" \/>\n<p><i>To learn\u00a0about how Pogo can help you tackle\u00a0the technological challenges\u00a0your organization is facing, please call us at 888-828-POGO, or email <a title=\"Sales at PogoLinux.com\" href=\"mailto:sales@www.pogolinux.com\">sales@www.pogolinux.com<\/a>.<\/i><\/p>\n","protected":false},"excerpt":{"rendered":"<p>NVIDIA has recently introduced the new TITAN X&#x2122;, the biggest and most advanced GPU ever built. Blaise Pascal said, &#8220;Imagination decides everything.&#8221; This certainly applies to\u00a0the hardware engineering team at NVIDIA. Not content with the already &#8220;irresponsible amount of performance&#8221; of\u00a0their GTX 1080, they\u00a0imagined breaking the 10 teraflops barrier for computing on a single chip&#8230;.<\/p>\n","protected":false},"author":1,"featured_media":2146,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"content-type":"","footnotes":""},"categories":[1,3],"tags":[153,154,23],"class_list":["post-2138","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-rackmount-servers","category-workstations","tag-gpu","tag-supercomputing","tag-workstation"],"_links":{"self":[{"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/posts\/2138","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/comments?post=2138"}],"version-history":[{"count":77,"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/posts\/2138\/revisions"}],"predecessor-version":[{"id":4647,"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/posts\/2138\/revisions\/4647"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/media\/2146"}],"wp:attachment":[{"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/media?parent=2138"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/categories?post=2138"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.pogolinux.com\/blog\/wp-json\/wp\/v2\/tags?post=2138"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}