<?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 Store Buffer Forwarding Restriction on Size in Intel® Moderncode for Parallel Architectures</title>
    <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Store-Buffer-Forwarding-Restriction-on-Size/m-p/775224#M178</link>
    <description>But that pertains to theIntel NetBurst microarchitecture. I know the document says "Fixing store-forwarding problems for Intel NetBurst microarchitecture generally also avoids problems on Pentium M, Intel Core Duo and Intel Core 2 Duo processors", but I want to induce the "problem" (to avoid using a memory barrier), so I'm asking about the Intel Core microarchitecture (specifically, about the contents ofTable 3-2).</description>
    <pubDate>Sat, 03 Sep 2011 18:08:53 GMT</pubDate>
    <dc:creator>duarten</dc:creator>
    <dc:date>2011-09-03T18:08:53Z</dc:date>
    <item>
      <title>Store Buffer Forwarding Restriction on Size</title>
      <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Store-Buffer-Forwarding-Restriction-on-Size/m-p/775222#M176</link>
      <description>&lt;DIV&gt;
&lt;P&gt;Hi,&lt;/P&gt;

&lt;P&gt;In reading section3.6.5.1 of the most recentIntel 64 and IA-32ArchitecturesOptimization Reference Manual, it seems that for theIntel Core microarchitecture a large load after a small store never stalls (for example, a word aligned 32 bit load after an 8 bit store). Am I interpreting it correctly?&lt;/P&gt;

Thank you,&lt;BR /&gt;
Duarte Nunes
&lt;/DIV&gt;</description>
      <pubDate>Sun, 07 Aug 2011 14:17:26 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Store-Buffer-Forwarding-Restriction-on-Size/m-p/775222#M176</guid>
      <dc:creator>duarten</dc:creator>
      <dc:date>2011-08-07T14:17:26Z</dc:date>
    </item>
    <item>
      <title>Store Buffer Forwarding Restriction on Size</title>
      <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Store-Buffer-Forwarding-Restriction-on-Size/m-p/775223#M177</link>
      <description>&lt;span class="lia-inline-image-display-wrapper"&gt;&lt;img src="https://community.intel.com/skins/images/7B13F55A7CE623EF42E69096FA81A3A1/2021_redesign/images/image_not_found.png" /&gt;&lt;/span&gt;</description>
      <pubDate>Sat, 03 Sep 2011 13:53:31 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Store-Buffer-Forwarding-Restriction-on-Size/m-p/775223#M177</guid>
      <dc:creator>jose-jesus-ambriz-me</dc:creator>
      <dc:date>2011-09-03T13:53:31Z</dc:date>
    </item>
    <item>
      <title>Store Buffer Forwarding Restriction on Size</title>
      <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Store-Buffer-Forwarding-Restriction-on-Size/m-p/775224#M178</link>
      <description>But that pertains to theIntel NetBurst microarchitecture. I know the document says "Fixing store-forwarding problems for Intel NetBurst microarchitecture generally also avoids problems on Pentium M, Intel Core Duo and Intel Core 2 Duo processors", but I want to induce the "problem" (to avoid using a memory barrier), so I'm asking about the Intel Core microarchitecture (specifically, about the contents ofTable 3-2).</description>
      <pubDate>Sat, 03 Sep 2011 18:08:53 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Store-Buffer-Forwarding-Restriction-on-Size/m-p/775224#M178</guid>
      <dc:creator>duarten</dc:creator>
      <dc:date>2011-09-03T18:08:53Z</dc:date>
    </item>
  </channel>
</rss>

