<?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 Re: Optimum processor for  MKL / level 3 blass cgemm in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimum-processor-for-MKL-level-3-blass-cgemm/m-p/946108#M14901</link>
    <description>&lt;DIV&gt;The app will most likely be 32 bit for now, Win XP. That said, is there any benifit to using Linux for MKL orfor disk IO?&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;How does a single package dual core pentium compare to two Xenon's on a work station board (same clock, cache, etc .) ?&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Does cache size make much difference for level 3 cgemm blas?&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Thanks.&lt;/DIV&gt;</description>
    <pubDate>Wed, 15 Feb 2006 22:16:57 GMT</pubDate>
    <dc:creator>john_shaeffer</dc:creator>
    <dc:date>2006-02-15T22:16:57Z</dc:date>
    <item>
      <title>Optimum processor for  MKL / level 3 blass cgemm</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimum-processor-for-MKL-level-3-blass-cgemm/m-p/946106#M14899</link>
      <description>&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;What is the optimum cost effective Intel processor / motherboard to get good MKL performance for level III blas cgemm for matrix sizes in the range of 500 x 500?&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Am quite confused as to relative merits of single / dual core, Pentium vs Xenon, 32 vs 64 bit, HT on / off, cache size, etc. for MKL blas 3 performance.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Hardware costs should stay below $4k. The app is LU factoring100,000 unknowns block wise which will also require fast disk IO, thus a MB with SATA II / Raid 0 will be required. &lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;This will be a Fortran 95 (CVF or IVF)code under Win XP.&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Thanks.&lt;/DIV&gt;</description>
      <pubDate>Wed, 15 Feb 2006 03:52:32 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimum-processor-for-MKL-level-3-blass-cgemm/m-p/946106#M14899</guid>
      <dc:creator>john_shaeffer</dc:creator>
      <dc:date>2006-02-15T03:52:32Z</dc:date>
    </item>
    <item>
      <title>Re: Optimum processor for  MKL / level 3 blass cgemm</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimum-processor-for-MKL-level-3-blass-cgemm/m-p/946107#M14900</link>
      <description>Dual core clearly improves performance per dollar of parallel applications; that should not be confusing.&lt;BR /&gt;Pentium:  1 package per motherboard (2 cores max)&lt;BR /&gt;Xeon: &amp;gt; 1 package per motherboard&lt;BR /&gt;64-bit mode mainly gives you more addressing and larger arrays; only a small performance improvement where the same application works either way.  Were you considering a 32-bit only platform?&lt;BR /&gt;HT isn't likely to give a performance improvement in MKL, particularly not in Windows.</description>
      <pubDate>Wed, 15 Feb 2006 04:44:04 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimum-processor-for-MKL-level-3-blass-cgemm/m-p/946107#M14900</guid>
      <dc:creator>TimP</dc:creator>
      <dc:date>2006-02-15T04:44:04Z</dc:date>
    </item>
    <item>
      <title>Re: Optimum processor for  MKL / level 3 blass cgemm</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimum-processor-for-MKL-level-3-blass-cgemm/m-p/946108#M14901</link>
      <description>&lt;DIV&gt;The app will most likely be 32 bit for now, Win XP. That said, is there any benifit to using Linux for MKL orfor disk IO?&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;How does a single package dual core pentium compare to two Xenon's on a work station board (same clock, cache, etc .) ?&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Does cache size make much difference for level 3 cgemm blas?&lt;/DIV&gt;
&lt;DIV&gt;&lt;/DIV&gt;
&lt;DIV&gt;Thanks.&lt;/DIV&gt;</description>
      <pubDate>Wed, 15 Feb 2006 22:16:57 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimum-processor-for-MKL-level-3-blass-cgemm/m-p/946108#M14901</guid>
      <dc:creator>john_shaeffer</dc:creator>
      <dc:date>2006-02-15T22:16:57Z</dc:date>
    </item>
    <item>
      <title>Re: Optimum processor for  MKL / level 3 blass cgemm</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimum-processor-for-MKL-level-3-blass-cgemm/m-p/946109#M14902</link>
      <description>The answer to the disk I/O question depends on several factors.  With Windows supporting RAID disk controllers on fancier Pentium D systems, it should do as well as linux.&lt;BR /&gt;In my experience, single package dual core performs as well as dual single core Xeon, when the CPU and bus clock rates are close.&lt;BR /&gt;I can't answer your specific question about cache.  In general, MKL is well optimized to work with the cache present on any of the targeted Intel CPUs.</description>
      <pubDate>Thu, 16 Feb 2006 01:06:04 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Optimum-processor-for-MKL-level-3-blass-cgemm/m-p/946109#M14902</guid>
      <dc:creator>TimP</dc:creator>
      <dc:date>2006-02-16T01:06:04Z</dc:date>
    </item>
  </channel>
</rss>

