<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Thank you. I am able to in Software Tuning, Performance Optimization &amp; Platform Monitoring</title>
    <link>https://community.intel.com/t5/Software-Tuning-Performance/MKL-Library-AVX-vs-SSE/m-p/1094789#M5714</link>
    <description>&lt;P&gt;Thank you. I am able to dispatch code variants with different SIMD extensions by using the following environment variables -&amp;nbsp;MKL_CBWR, MKL_NUM_THREADS.&lt;/P&gt;</description>
    <pubDate>Wed, 20 Apr 2016 15:46:00 GMT</pubDate>
    <dc:creator>Animesh_J_</dc:creator>
    <dc:date>2016-04-20T15:46:00Z</dc:date>
    <item>
      <title>MKL Library: AVX vs SSE</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/MKL-Library-AVX-vs-SSE/m-p/1094787#M5712</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;

&lt;P&gt;I want to measure the performance difference between SSE2 and AVX implementations for a neural network application. I am using Intel MKL to perform the BLAS calculations so that I have the most optimized implementation.&amp;nbsp;&lt;/P&gt;

&lt;P&gt;Is there anyway to instruct the MKL to release only SSE2 code even if machine supports AVX2. I know AVX2 will mostly perform better than SSE2. But I want to quantify that difference.&lt;/P&gt;

&lt;P&gt;Regards,&lt;/P&gt;

&lt;P&gt;Animesh Jain&lt;/P&gt;</description>
      <pubDate>Mon, 18 Apr 2016 21:43:58 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/MKL-Library-AVX-vs-SSE/m-p/1094787#M5712</guid>
      <dc:creator>Animesh_J_</dc:creator>
      <dc:date>2016-04-18T21:43:58Z</dc:date>
    </item>
    <item>
      <title>Mkl conditional numerical</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/MKL-Library-AVX-vs-SSE/m-p/1094788#M5713</link>
      <description>&lt;P&gt;Mkl conditional numerical reproducibility offers options which should take care of this. &amp;nbsp;It has been discussed several times on mkl forum.&lt;/P&gt;</description>
      <pubDate>Wed, 20 Apr 2016 14:43:43 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/MKL-Library-AVX-vs-SSE/m-p/1094788#M5713</guid>
      <dc:creator>TimP</dc:creator>
      <dc:date>2016-04-20T14:43:43Z</dc:date>
    </item>
    <item>
      <title>Thank you. I am able to</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/MKL-Library-AVX-vs-SSE/m-p/1094789#M5714</link>
      <description>&lt;P&gt;Thank you. I am able to dispatch code variants with different SIMD extensions by using the following environment variables -&amp;nbsp;MKL_CBWR, MKL_NUM_THREADS.&lt;/P&gt;</description>
      <pubDate>Wed, 20 Apr 2016 15:46:00 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/MKL-Library-AVX-vs-SSE/m-p/1094789#M5714</guid>
      <dc:creator>Animesh_J_</dc:creator>
      <dc:date>2016-04-20T15:46:00Z</dc:date>
    </item>
  </channel>
</rss>

