<?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 Monitoring Different Uncore Events in Software Tuning, Performance Optimization &amp; Platform Monitoring</title>
    <link>https://community.intel.com/t5/Software-Tuning-Performance/Monitoring-Different-Uncore-Events/m-p/967647#M2725</link>
    <description>&lt;P&gt;Hi,&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I've been messing around with the PCM utility and am trying to read a few of the different DRAM metrics on a Jaketown system. I thought I could be really clever and just hack the JKT_Uncore_Pci::program method, and just fill in different DRAM event codes and umasks in MC_CH_PCI_PMON_CTL_EVENT and&amp;nbsp;MC_CH_PCI_PMON_CTL_UMASK, respectively, but when I recompile, there's no change in the metrics I get out. (The test I did was just changing the Event and Umask codes so that counter zero and counter one were counting the same events to see if I get the same values out.) I must be doing something improperly or using the JKT_Uncore_Pci method wrong; anyone have any ideas as to what they might be?&lt;/P&gt;
&lt;P&gt;Best regards,&lt;/P&gt;
&lt;P&gt;Nash Reilly&lt;/P&gt;</description>
    <pubDate>Fri, 07 Dec 2012 17:53:02 GMT</pubDate>
    <dc:creator>Nash_R_</dc:creator>
    <dc:date>2012-12-07T17:53:02Z</dc:date>
    <item>
      <title>Monitoring Different Uncore Events</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/Monitoring-Different-Uncore-Events/m-p/967647#M2725</link>
      <description>&lt;P&gt;Hi,&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I've been messing around with the PCM utility and am trying to read a few of the different DRAM metrics on a Jaketown system. I thought I could be really clever and just hack the JKT_Uncore_Pci::program method, and just fill in different DRAM event codes and umasks in MC_CH_PCI_PMON_CTL_EVENT and&amp;nbsp;MC_CH_PCI_PMON_CTL_UMASK, respectively, but when I recompile, there's no change in the metrics I get out. (The test I did was just changing the Event and Umask codes so that counter zero and counter one were counting the same events to see if I get the same values out.) I must be doing something improperly or using the JKT_Uncore_Pci method wrong; anyone have any ideas as to what they might be?&lt;/P&gt;
&lt;P&gt;Best regards,&lt;/P&gt;
&lt;P&gt;Nash Reilly&lt;/P&gt;</description>
      <pubDate>Fri, 07 Dec 2012 17:53:02 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/Monitoring-Different-Uncore-Events/m-p/967647#M2725</guid>
      <dc:creator>Nash_R_</dc:creator>
      <dc:date>2012-12-07T17:53:02Z</dc:date>
    </item>
    <item>
      <title>Hi Nash,</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/Monitoring-Different-Uncore-Events/m-p/967648#M2726</link>
      <description>Hi Nash,

which event/umask values did you try? What workload did you execute to generate non-zero event counts? Try also do "make clean; make" to rebuild everything from scratch after your changes.

Thanks,
Roman</description>
      <pubDate>Tue, 18 Dec 2012 08:55:10 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/Monitoring-Different-Uncore-Events/m-p/967648#M2726</guid>
      <dc:creator>Roman_D_Intel</dc:creator>
      <dc:date>2012-12-18T08:55:10Z</dc:date>
    </item>
    <item>
      <title>Roman,</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/Monitoring-Different-Uncore-Events/m-p/967649#M2727</link>
      <description>Roman,

Fixed my issue; I was initializing the jkt_uncore_pci class incorrectly (I'm fairly inexperienced at C++). I was able to change event and umask codes properly after that.

Thank you for your response and your continued work on this tool! It's proven a great resource for me. 

Best,
NR</description>
      <pubDate>Tue, 18 Dec 2012 15:00:19 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/Monitoring-Different-Uncore-Events/m-p/967649#M2727</guid>
      <dc:creator>Nash_R_</dc:creator>
      <dc:date>2012-12-18T15:00:19Z</dc:date>
    </item>
    <item>
      <title>I am glad that it worked for</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/Monitoring-Different-Uncore-Events/m-p/967650#M2728</link>
      <description>I am glad that it worked for you.</description>
      <pubDate>Wed, 19 Dec 2012 16:12:42 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/Monitoring-Different-Uncore-Events/m-p/967650#M2728</guid>
      <dc:creator>Roman_D_Intel</dc:creator>
      <dc:date>2012-12-19T16:12:42Z</dc:date>
    </item>
  </channel>
</rss>

