<?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 Re: SCMiMX6Q Performance issue compared to iMX6SOLO in i.MX Processors</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/SCMiMX6Q-Performance-issue-compared-to-iMX6SOLO/m-p/743069#M115619</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hi Manoj&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;in general this may be explained by different burst size as described on&lt;/P&gt;&lt;P&gt;&lt;A href="https://community.nxp.com/thread/436694"&gt;LPDDR2 performance vs DDR3L&lt;/A&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;One can try to further analyze it with mmdc profiling described on above link&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Best regards&lt;BR /&gt;igor&lt;BR /&gt;-----------------------------------------------------------------------------------------------------------------------&lt;BR /&gt;Note: If this post answers your question, please click the Correct Answer button. Thank you!&lt;BR /&gt;-----------------------------------------------------------------------------------------------------------------------&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Thu, 29 Mar 2018 06:00:50 GMT</pubDate>
    <dc:creator>igorpadykov</dc:creator>
    <dc:date>2018-03-29T06:00:50Z</dc:date>
    <item>
      <title>SCMiMX6Q Performance issue compared to iMX6SOLO</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/SCMiMX6Q-Performance-issue-compared-to-iMX6SOLO/m-p/743068#M115618</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hi&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I am working on QWKS-SCMiMX6Q board for performance needed project. Right now I am evaluating the SCMiMX6Q using the qwks board with L4.1.15 kernel and krogoth release. For various reasons, we need to move SCMiMX6q against our own iMX6SOLO board. While evaluating the performance of SCMiMX6q we found it &lt;SPAN style="color: #000000;"&gt;drastically&lt;/SPAN&gt; lags in performance compared to our iMX6SOLO board. The test was conducted using the standard benchmark tools to analyze the performance of&amp;nbsp; DDR. SCM is having a RAM of 1GB LPDDR and our iMX6SOLO is also having 1GB DDR3 RAM. Both processors operate on 32-bit mode and same DDR-Frequency of 400MHz.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;BENCHMARK TOOLS used:&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;LMBENCH&lt;/LI&gt;&lt;LI&gt;MBW&lt;/LI&gt;&lt;LI&gt;STREAM&lt;/LI&gt;&lt;/UL&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="color: #0000ff; text-decoration: underline; font-family: terminal, monaco, monospace;"&gt;PERFORMANCE ANALYSIS:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;LMBENCH was used to analyze LATENCY&lt;/P&gt;&lt;P&gt;MBW and STREAM were used to analyze BANDWIDTH&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;TABLE class="j-table jiveBorder" style="border: 1px solid #c6c6c6;" width="100%"&gt;&lt;THEAD&gt;&lt;TR style="background-color: #efefef;"&gt;&lt;TH&gt;&lt;/TH&gt;&lt;TH&gt;LMBENCH&lt;/TH&gt;&lt;TH&gt;STREAM&lt;/TH&gt;&lt;TH&gt;MBW&lt;/TH&gt;&lt;/TR&gt;&lt;/THEAD&gt;&lt;TBODY&gt;&lt;TR&gt;&lt;TD&gt;SCMiMX6Q&lt;/TD&gt;&lt;TD&gt;57.240ns&lt;/TD&gt;&lt;TD&gt;592.77 MB/sec&lt;/TD&gt;&lt;TD&gt;274.556 MiB/s&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;iMX6SOLO&lt;/TD&gt;&lt;TD&gt;&lt;DIV style="margin-top: 0px; margin-bottom: 0px;"&gt;42.639ns&lt;/DIV&gt;&lt;/TD&gt;&lt;TD&gt;&lt;SPAN style="color: black; font-size: 12pt; font-family: Calibri, Helvetica, sans-serif, EmojiFont, Apple\ Color\ Emoji, Segoe\ UI\ Emoji, NotoColorEmoji, Segoe\ UI\ Symbol, Android\ Emoji, EmojiSymbols;"&gt;&lt;SPAN lang="en-IN"&gt;&amp;nbsp;1104.97 MB/sec&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/TD&gt;&lt;TD&gt;&lt;SPAN style="color: black; font-size: 12pt; font-family: Calibri, Helvetica, sans-serif, EmojiFont, Apple\ Color\ Emoji, Segoe\ UI\ Emoji, NotoColorEmoji, Segoe\ UI\ Symbol, Android\ Emoji, EmojiSymbols;"&gt;&lt;SPAN lang="en-IN"&gt;685.166 MiB/s&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/TD&gt;&lt;/TR&gt;&lt;/TBODY&gt;&lt;/TABLE&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;SCMiMX6Q is &lt;SPAN style="color: #ff0000;"&gt;less than half speed&lt;/SPAN&gt; of our iMX6SOLO board.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;the Actual results must be SCMiMx6q&amp;nbsp; should give more performance compared to SOLO.I suspect the performance is due to the mismatch&amp;nbsp; of the clock&amp;nbsp;frequency for mmdc controllers in SCM.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;CLOCK:&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;mmdc_ch1_axi &amp;nbsp;&amp;nbsp; 528000000&lt;/P&gt;&lt;P&gt;mmdc_ch0_axi&amp;nbsp;&amp;nbsp;&amp;nbsp; 396000000&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Actual suggested frequency rate for DDR is 400 MHZ but why there is a difference. What is the reason behind huge performance difference in SCM.It will affect our products also.I am really running out of ideas.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Any Patches or fix for this issue&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Hoping for a faster and better guidance&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 28 Mar 2018 10:59:56 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/SCMiMX6Q-Performance-issue-compared-to-iMX6SOLO/m-p/743068#M115618</guid>
      <dc:creator>manojsampathkum</dc:creator>
      <dc:date>2018-03-28T10:59:56Z</dc:date>
    </item>
    <item>
      <title>Re: SCMiMX6Q Performance issue compared to iMX6SOLO</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/SCMiMX6Q-Performance-issue-compared-to-iMX6SOLO/m-p/743069#M115619</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hi Manoj&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;in general this may be explained by different burst size as described on&lt;/P&gt;&lt;P&gt;&lt;A href="https://community.nxp.com/thread/436694"&gt;LPDDR2 performance vs DDR3L&lt;/A&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;One can try to further analyze it with mmdc profiling described on above link&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Best regards&lt;BR /&gt;igor&lt;BR /&gt;-----------------------------------------------------------------------------------------------------------------------&lt;BR /&gt;Note: If this post answers your question, please click the Correct Answer button. Thank you!&lt;BR /&gt;-----------------------------------------------------------------------------------------------------------------------&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 29 Mar 2018 06:00:50 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/SCMiMX6Q-Performance-issue-compared-to-iMX6SOLO/m-p/743069#M115619</guid>
      <dc:creator>igorpadykov</dc:creator>
      <dc:date>2018-03-29T06:00:50Z</dc:date>
    </item>
  </channel>
</rss>

