<?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: Sampling nonsense in Analyzers</title>
    <link>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992455#M11368</link>
    <description>Sorry I misread ;) Where exactly did you get the numbers from?  Could you post or send me a screen shot pointing out where you got the numbers from?&lt;BR /&gt;</description>
    <pubDate>Tue, 28 Jan 2003 07:35:16 GMT</pubDate>
    <dc:creator>bnshah</dc:creator>
    <dc:date>2003-01-28T07:35:16Z</dc:date>
    <item>
      <title>Sampling nonsense</title>
      <link>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992452#M11365</link>
      <description>[platform XP/P3 vtune 6.1]&lt;BR /&gt;&lt;BR /&gt;I have a hard time understanding the math in vtune sampling result, Example:&lt;BR /&gt;&lt;BR /&gt;Instruction retired - 2,920&lt;BR /&gt;ClockTicks - 1574&lt;BR /&gt;Cycle per retired Instruction - 1.214&lt;BR /&gt;&lt;BR /&gt;If 2920 instruction execute and they take 1.214 cycle this add up to 3539 clockTicks, not 1574.&lt;BR /&gt;&lt;BR /&gt;I didn't find in the help file an explaination on this.&lt;BR /&gt;&lt;BR /&gt;Thanks any clarifying,&lt;BR /&gt;&lt;BR /&gt;Stephan&lt;BR /&gt;&lt;BR /&gt;PS: I asked this on the premier site, but wonder if any of you got the same math or understanding problem?</description>
      <pubDate>Sat, 25 Jan 2003 08:19:36 GMT</pubDate>
      <guid>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992452#M11365</guid>
      <dc:creator>stephan-schaem7</dc:creator>
      <dc:date>2003-01-25T08:19:36Z</dc:date>
    </item>
    <item>
      <title>Re: Sampling nonsense</title>
      <link>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992453#M11366</link>
      <description>Stephan the reason your math is not working out is because Pentium processors since the Pentium Pro can execute and retire multiple instructions per clock cycle (superscalar).  The processors are also pipelined so there is overlap in instruction execution.  We calculate cycles per instruction retired by dividing the number of clocktick samples by the number of instruction retired samples.</description>
      <pubDate>Tue, 28 Jan 2003 04:12:09 GMT</pubDate>
      <guid>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992453#M11366</guid>
      <dc:creator>bnshah</dc:creator>
      <dc:date>2003-01-28T04:12:09Z</dc:date>
    </item>
    <item>
      <title>Re: Sampling nonsense</title>
      <link>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992454#M11367</link>
      <description>Lets review:&lt;BR /&gt;&lt;BR /&gt;2920 instructions executed in 1574 cycle.&lt;BR /&gt;1574 / 2920 = .539 CPI&lt;BR /&gt;&lt;BR /&gt;How do you guy get to 1.214 ;)&lt;BR /&gt;&lt;BR /&gt;Stephan&lt;BR /&gt;&lt;BR /&gt;Instruction retired - 2,920&lt;BR /&gt;ClockTicks - 1574&lt;BR /&gt;Cycle per retired Instruction - 1.214&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Tue, 28 Jan 2003 05:06:20 GMT</pubDate>
      <guid>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992454#M11367</guid>
      <dc:creator>stephan-schaem7</dc:creator>
      <dc:date>2003-01-28T05:06:20Z</dc:date>
    </item>
    <item>
      <title>Re: Sampling nonsense</title>
      <link>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992455#M11368</link>
      <description>Sorry I misread ;) Where exactly did you get the numbers from?  Could you post or send me a screen shot pointing out where you got the numbers from?&lt;BR /&gt;</description>
      <pubDate>Tue, 28 Jan 2003 07:35:16 GMT</pubDate>
      <guid>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992455#M11368</guid>
      <dc:creator>bnshah</dc:creator>
      <dc:date>2003-01-28T07:35:16Z</dc:date>
    </item>
    <item>
      <title>Re: Sampling nonsense</title>
      <link>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992456#M11369</link>
      <description>Stephan, the VTune analyzer is calculating the CPI correctly.  The reason your calculation is not working is because you are using the number of samples of instructions retired and clocktick events to do your calculation.  You should actually use the total number of events.  Total events = samples * sample after value&lt;BR /&gt;In your case the sample after values for clockticks and instructions retired are 346189 and 92150 respectively.  So &lt;BR /&gt;Total events for clockticks for the hightlighted region = 346189 * 1184&lt;BR /&gt;Total events for instructions retired for the hightlighted region = 92150  * 4154&lt;BR /&gt;Thus CPI = 1.071&lt;BR /&gt;&lt;BR /&gt;If you want the VTune analyzer to show you the number of events and not samples in the source view then right click anywhere in the source view and select View Events As -&amp;gt; Sample Counts&lt;BR /&gt;&lt;BR /&gt;Birju&lt;BR /&gt;</description>
      <pubDate>Thu, 06 Feb 2003 04:28:16 GMT</pubDate>
      <guid>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992456#M11369</guid>
      <dc:creator>bnshah</dc:creator>
      <dc:date>2003-02-06T04:28:16Z</dc:date>
    </item>
    <item>
      <title>Re: Sampling nonsense</title>
      <link>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992457#M11370</link>
      <description>Also, Stephan,&lt;BR /&gt;Ratios are always computed based on event values i.e. samples * sample after value and not on samples. This is to because VTune lets you configure events so that they have different sample after values. When computing ratios, they need to be normalized to make any sense. So yes, you can choose to see samples collected for an event instead of event values but ratios will always be based on event values.&lt;BR /&gt;&lt;BR /&gt;Susmita</description>
      <pubDate>Tue, 22 Apr 2003 01:00:32 GMT</pubDate>
      <guid>https://community.intel.com/t5/Analyzers/Sampling-nonsense/m-p/992457#M11370</guid>
      <dc:creator>Susmita_Nayak</dc:creator>
      <dc:date>2003-04-22T01:00:32Z</dc:date>
    </item>
  </channel>
</rss>

