<?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 Understanding PCIe bandwidth in Software Tuning, Performance Optimization &amp; Platform Monitoring</title>
    <link>https://community.intel.com/t5/Software-Tuning-Performance/Understanding-PCIe-bandwidth/m-p/1130306#M6394</link>
    <description>&lt;P&gt;Hello. &amp;nbsp;I'm trying to understand the results of pcm-pcie. &amp;nbsp;I read the Bytes option will multiply the number of transfers by 64 Bytes. &amp;nbsp;So in this case it would be 11M (PCIeRdCur) times 64B, which would be 704MB. &amp;nbsp;However, the PCIe Rd (B) column shows a much larger number 3323M. &amp;nbsp;How does this math work?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Also, socket 0 shows more transfers in the PCIeRdCur column, but socket 1 shows more data in the Bytes column. &amp;nbsp;I don't understand.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;PRE class="brush:bash; class-name:dark;"&gt;Skt | PCIeRdCur |  RFO  |  CRd  |  DRd  |  ItoM  |  PRd  |  WiL  | PCIe Rd (B) | PCIe Wr (B)
 0      11 M       380 K    18 M    21 M   3110 K    18 K  9336          3323 M         223 M
 1    2443 K        97 K    28 M    39 M   3110 K   216      65 K        4518 M         205 M
----------------------------------------------------------------------------------------------------
 *      14 M       478 K    47 M    60 M   6220 K    18 K    75 K        7841 M         428 M
&lt;/PRE&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Wed, 09 Jan 2019 21:56:24 GMT</pubDate>
    <dc:creator>Balsley__Elliott</dc:creator>
    <dc:date>2019-01-09T21:56:24Z</dc:date>
    <item>
      <title>Understanding PCIe bandwidth</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/Understanding-PCIe-bandwidth/m-p/1130306#M6394</link>
      <description>&lt;P&gt;Hello. &amp;nbsp;I'm trying to understand the results of pcm-pcie. &amp;nbsp;I read the Bytes option will multiply the number of transfers by 64 Bytes. &amp;nbsp;So in this case it would be 11M (PCIeRdCur) times 64B, which would be 704MB. &amp;nbsp;However, the PCIe Rd (B) column shows a much larger number 3323M. &amp;nbsp;How does this math work?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Also, socket 0 shows more transfers in the PCIeRdCur column, but socket 1 shows more data in the Bytes column. &amp;nbsp;I don't understand.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;PRE class="brush:bash; class-name:dark;"&gt;Skt | PCIeRdCur |  RFO  |  CRd  |  DRd  |  ItoM  |  PRd  |  WiL  | PCIe Rd (B) | PCIe Wr (B)
 0      11 M       380 K    18 M    21 M   3110 K    18 K  9336          3323 M         223 M
 1    2443 K        97 K    28 M    39 M   3110 K   216      65 K        4518 M         205 M
----------------------------------------------------------------------------------------------------
 *      14 M       478 K    47 M    60 M   6220 K    18 K    75 K        7841 M         428 M
&lt;/PRE&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Wed, 09 Jan 2019 21:56:24 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/Understanding-PCIe-bandwidth/m-p/1130306#M6394</guid>
      <dc:creator>Balsley__Elliott</dc:creator>
      <dc:date>2019-01-09T21:56:24Z</dc:date>
    </item>
  </channel>
</rss>

