<?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>T-SeriesのトピックQuestion Regarding Packet Enqueue</title>
    <link>https://community.nxp.com/t5/T-Series/Question-Regarding-Packet-Enqueue/m-p/717532#M2249</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Following the T1040DPAARM&lt;/P&gt;&lt;P&gt;Below is the description to to Enqueue Command&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;4.3.3.1.1 Writing a Command into the CR&lt;BR /&gt;To write a command into the CR, software must perform the following tasks:&lt;BR /&gt;1. dcbz&lt;BR /&gt;2. Write all words of the command other than word 0.&lt;BR /&gt;3. lwsync&lt;BR /&gt;4. Write word 0 (containing the command verb and alternating valid bit).&lt;BR /&gt;5. dcbf to flush the command from cache to the BMan&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;As far as I understand the QMAN has both CE and CI registers area's.&amp;nbsp; From performance point of view should it make sense to use the CI area to enqueue command and therefor omit the dcbz and dcbf commands.&lt;/P&gt;&lt;P&gt;As to the performance that is reached with that mechanism we have much less then in p2020 ETSEC for sending frames. As far as I understand most of this performance issue is due to dcbz and dcbf.&lt;/P&gt;&lt;P&gt;Any idea how can it be improved ?&lt;/P&gt;&lt;P&gt;Is it possible (to reduce the ring size so less cache lines will be used ?&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Regards ,&lt;/P&gt;&lt;P&gt;Micha&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Fri, 17 Nov 2017 12:23:47 GMT</pubDate>
    <dc:creator>michayardeny</dc:creator>
    <dc:date>2017-11-17T12:23:47Z</dc:date>
    <item>
      <title>Question Regarding Packet Enqueue</title>
      <link>https://community.nxp.com/t5/T-Series/Question-Regarding-Packet-Enqueue/m-p/717532#M2249</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Following the T1040DPAARM&lt;/P&gt;&lt;P&gt;Below is the description to to Enqueue Command&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;4.3.3.1.1 Writing a Command into the CR&lt;BR /&gt;To write a command into the CR, software must perform the following tasks:&lt;BR /&gt;1. dcbz&lt;BR /&gt;2. Write all words of the command other than word 0.&lt;BR /&gt;3. lwsync&lt;BR /&gt;4. Write word 0 (containing the command verb and alternating valid bit).&lt;BR /&gt;5. dcbf to flush the command from cache to the BMan&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;As far as I understand the QMAN has both CE and CI registers area's.&amp;nbsp; From performance point of view should it make sense to use the CI area to enqueue command and therefor omit the dcbz and dcbf commands.&lt;/P&gt;&lt;P&gt;As to the performance that is reached with that mechanism we have much less then in p2020 ETSEC for sending frames. As far as I understand most of this performance issue is due to dcbz and dcbf.&lt;/P&gt;&lt;P&gt;Any idea how can it be improved ?&lt;/P&gt;&lt;P&gt;Is it possible (to reduce the ring size so less cache lines will be used ?&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Regards ,&lt;/P&gt;&lt;P&gt;Micha&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Fri, 17 Nov 2017 12:23:47 GMT</pubDate>
      <guid>https://community.nxp.com/t5/T-Series/Question-Regarding-Packet-Enqueue/m-p/717532#M2249</guid>
      <dc:creator>michayardeny</dc:creator>
      <dc:date>2017-11-17T12:23:47Z</dc:date>
    </item>
    <item>
      <title>Re: Question Regarding Packet Enqueue</title>
      <link>https://community.nxp.com/t5/T-Series/Question-Regarding-Packet-Enqueue/m-p/717533#M2250</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Please ignore the request because the correct data is good enough .&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Tue, 21 Nov 2017 10:26:37 GMT</pubDate>
      <guid>https://community.nxp.com/t5/T-Series/Question-Regarding-Packet-Enqueue/m-p/717533#M2250</guid>
      <dc:creator>michayardeny</dc:creator>
      <dc:date>2017-11-21T10:26:37Z</dc:date>
    </item>
  </channel>
</rss>

