<?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 Hello Dr. Bandwidth, in Software Tuning, Performance Optimization &amp; Platform Monitoring</title>
    <link>https://community.intel.com/t5/Software-Tuning-Performance/Confusing-hardware-counters/m-p/1120455#M6182</link>
    <description>&lt;P&gt;Hello Dr. Bandwidth,&lt;/P&gt;

&lt;P&gt;thank you. I forgot to read their Umask and Event code. Only, their are descriped differently, i thought they are differnt.&lt;/P&gt;

&lt;P&gt;Best,&lt;/P&gt;

&lt;P&gt;Bo&lt;/P&gt;</description>
    <pubDate>Fri, 21 Oct 2016 19:54:55 GMT</pubDate>
    <dc:creator>Bo_W_4</dc:creator>
    <dc:date>2016-10-21T19:54:55Z</dc:date>
    <item>
      <title>Confusing hardware counters</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/Confusing-hardware-counters/m-p/1120453#M6180</link>
      <description>&lt;P&gt;Hello,&lt;/P&gt;

&lt;P&gt;i'm looking at hardware coutners of Broadwell-EP.&amp;nbsp; CYCLE_ACTIVITY_STALLS_L2_MISS and CYCLE_ACTIVITY_STALLS_L2_pending are quite similar: they are described similar (https://download.01.org/perfmon/BDW-DE/BroadwellDE_core_V5.json) and have similar values which are measured with the STREMA benchmark.&lt;/P&gt;

&lt;P&gt;What are differences between them?&lt;/P&gt;

&lt;P&gt;Best,&lt;/P&gt;

&lt;P&gt;Bo&lt;/P&gt;</description>
      <pubDate>Thu, 20 Oct 2016 07:50:49 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/Confusing-hardware-counters/m-p/1120453#M6180</guid>
      <dc:creator>Bo_W_4</dc:creator>
      <dc:date>2016-10-20T07:50:49Z</dc:date>
    </item>
    <item>
      <title>In the file that you</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/Confusing-hardware-counters/m-p/1120454#M6181</link>
      <description>&lt;P&gt;In the file that you reference, these two events have the same Event code and the same Umask, so they are different names for the same event.&lt;/P&gt;

&lt;P&gt;The only difference between the two entries (other than the names and comments) is that the CYCLE_ACTIVITY.STALLS_L2_MISS event says that it can be used on any counter when HT is off, while the CYCLE_ACTIVITY.STALLS_L2_PENDING event says that only counters 0-3 can be used when HT is off.&amp;nbsp; This may or may not be a real difference -- Intel's documentation has traditionally had some inconsistencies in this area.&lt;/P&gt;</description>
      <pubDate>Thu, 20 Oct 2016 14:34:46 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/Confusing-hardware-counters/m-p/1120454#M6181</guid>
      <dc:creator>McCalpinJohn</dc:creator>
      <dc:date>2016-10-20T14:34:46Z</dc:date>
    </item>
    <item>
      <title>Hello Dr. Bandwidth,</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/Confusing-hardware-counters/m-p/1120455#M6182</link>
      <description>&lt;P&gt;Hello Dr. Bandwidth,&lt;/P&gt;

&lt;P&gt;thank you. I forgot to read their Umask and Event code. Only, their are descriped differently, i thought they are differnt.&lt;/P&gt;

&lt;P&gt;Best,&lt;/P&gt;

&lt;P&gt;Bo&lt;/P&gt;</description>
      <pubDate>Fri, 21 Oct 2016 19:54:55 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/Confusing-hardware-counters/m-p/1120455#M6182</guid>
      <dc:creator>Bo_W_4</dc:creator>
      <dc:date>2016-10-21T19:54:55Z</dc:date>
    </item>
  </channel>
</rss>

