<?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 Using PMC to monitor L3 with Intel Skylake in Intel® Moderncode for Parallel Architectures</title>
    <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Using-PMC-to-monitor-L3-with-Intel-Skylake/m-p/1105787#M7368</link>
    <description>&lt;P&gt;Hi,&lt;/P&gt;

&lt;P&gt;The documentation on this is a little difficult to understand. So, from the Intel 64 and ia32 Architecture Developer's Manual (Vol. 3B), there are a number of PMC's that I can use to monitor L3 cache. Two of them are interesting but I wanted to make sure what they were doing. (This is from section 19.2)&lt;/P&gt;

&lt;BLOCKQUOTE&gt;
	&lt;P&gt;B0H 10H OFFCORE_REQUESTS.L3_MISS_ DEMAND_DATA_RD Demand data read requests that missed L3&lt;/P&gt;

	&lt;P&gt;2EH 41H LONGEST_LAT_CACHE.MISS This event counts each cache miss condition for references to the L3 cache.&amp;nbsp;&lt;/P&gt;
&lt;/BLOCKQUOTE&gt;

&lt;P&gt;Is the difference in these two that the 1st counts only offcore (which i guess means other cores than the polling one) and the other gives a cummulative? Or is there something that I'm missing?&amp;nbsp;&lt;/P&gt;

&lt;P&gt;Thanks!&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Fri, 12 May 2017 22:46:27 GMT</pubDate>
    <dc:creator>AAhma10</dc:creator>
    <dc:date>2017-05-12T22:46:27Z</dc:date>
    <item>
      <title>Using PMC to monitor L3 with Intel Skylake</title>
      <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Using-PMC-to-monitor-L3-with-Intel-Skylake/m-p/1105787#M7368</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;

&lt;P&gt;The documentation on this is a little difficult to understand. So, from the Intel 64 and ia32 Architecture Developer's Manual (Vol. 3B), there are a number of PMC's that I can use to monitor L3 cache. Two of them are interesting but I wanted to make sure what they were doing. (This is from section 19.2)&lt;/P&gt;

&lt;BLOCKQUOTE&gt;
	&lt;P&gt;B0H 10H OFFCORE_REQUESTS.L3_MISS_ DEMAND_DATA_RD Demand data read requests that missed L3&lt;/P&gt;

	&lt;P&gt;2EH 41H LONGEST_LAT_CACHE.MISS This event counts each cache miss condition for references to the L3 cache.&amp;nbsp;&lt;/P&gt;
&lt;/BLOCKQUOTE&gt;

&lt;P&gt;Is the difference in these two that the 1st counts only offcore (which i guess means other cores than the polling one) and the other gives a cummulative? Or is there something that I'm missing?&amp;nbsp;&lt;/P&gt;

&lt;P&gt;Thanks!&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 12 May 2017 22:46:27 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Using-PMC-to-monitor-L3-with-Intel-Skylake/m-p/1105787#M7368</guid>
      <dc:creator>AAhma10</dc:creator>
      <dc:date>2017-05-12T22:46:27Z</dc:date>
    </item>
    <item>
      <title>I have not tested these</title>
      <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Using-PMC-to-monitor-L3-with-Intel-Skylake/m-p/1105788#M7369</link>
      <description>&lt;P&gt;I have not tested these events on Skylake, but if the definitions are similar to earlier processors, the LONGEST_LAT_CACHE.MISS event will count demand loads that miss the LLC and demand stores that miss the LLC.&amp;nbsp; The OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD will only count demand loads that miss the LLC.&amp;nbsp;&amp;nbsp; Neither event will count L2 hardware prefetches that miss the LLC, so neither event is useful for determining the actual data traffic.&amp;nbsp; They are intended to help identify accesses that are *not* prefetched, since these are more likely to cause stalls.&lt;/P&gt;</description>
      <pubDate>Tue, 23 May 2017 14:52:00 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Using-PMC-to-monitor-L3-with-Intel-Skylake/m-p/1105788#M7369</guid>
      <dc:creator>McCalpinJohn</dc:creator>
      <dc:date>2017-05-23T14:52:00Z</dc:date>
    </item>
    <item>
      <title>Oh alright. Thank you so much</title>
      <link>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Using-PMC-to-monitor-L3-with-Intel-Skylake/m-p/1105789#M7370</link>
      <description>&lt;P&gt;Oh alright. Thank you so much for the clarification!&lt;/P&gt;

&lt;P&gt;Adil&lt;/P&gt;</description>
      <pubDate>Wed, 24 May 2017 22:40:18 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Using-PMC-to-monitor-L3-with-Intel-Skylake/m-p/1105789#M7370</guid>
      <dc:creator>AAhma10</dc:creator>
      <dc:date>2017-05-24T22:40:18Z</dc:date>
    </item>
  </channel>
</rss>

