<?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 Requirements for serializing microcode updates in Software Tuning, Performance Optimization &amp; Platform Monitoring</title>
    <link>https://community.intel.com/t5/Software-Tuning-Performance/Requirements-for-serializing-microcode-updates/m-p/1427237#M8125</link>
    <description>&lt;P&gt;Hello.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;As I understand it, the recommendation when applying microcode updates is to put all CPUs in spinloops and then apply the microcode to each in turn.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Does this imply that the boot processor should not receive microcode updates until all the secondary processors are brought up (and put in spinloops)? Or is this only to avoid simultaneous loads of microcode updates on the same core (via hyperthreads)?&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I want to know:&lt;/P&gt;
&lt;P&gt;a) if it is okay to load microcode updates on the boot processor before the secondaries are brought up, and,&lt;/P&gt;
&lt;P&gt;b) if it is okay to detect hyperthreads and only put those in spinloops and have all the processors load microcode updates simultaneously.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Thank you!&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Sarah&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Edit: This is with regards to early operating system loading of microcode.&lt;/P&gt;</description>
    <pubDate>Thu, 03 Nov 2022 00:32:09 GMT</pubDate>
    <dc:creator>smpham</dc:creator>
    <dc:date>2022-11-03T00:32:09Z</dc:date>
    <item>
      <title>Requirements for serializing microcode updates</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/Requirements-for-serializing-microcode-updates/m-p/1427237#M8125</link>
      <description>&lt;P&gt;Hello.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;As I understand it, the recommendation when applying microcode updates is to put all CPUs in spinloops and then apply the microcode to each in turn.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Does this imply that the boot processor should not receive microcode updates until all the secondary processors are brought up (and put in spinloops)? Or is this only to avoid simultaneous loads of microcode updates on the same core (via hyperthreads)?&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I want to know:&lt;/P&gt;
&lt;P&gt;a) if it is okay to load microcode updates on the boot processor before the secondaries are brought up, and,&lt;/P&gt;
&lt;P&gt;b) if it is okay to detect hyperthreads and only put those in spinloops and have all the processors load microcode updates simultaneously.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Thank you!&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Sarah&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Edit: This is with regards to early operating system loading of microcode.&lt;/P&gt;</description>
      <pubDate>Thu, 03 Nov 2022 00:32:09 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/Requirements-for-serializing-microcode-updates/m-p/1427237#M8125</guid>
      <dc:creator>smpham</dc:creator>
      <dc:date>2022-11-03T00:32:09Z</dc:date>
    </item>
  </channel>
</rss>

