<?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 problem with profiling in OpenCL* for CPU</title>
    <link>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034731#M3633</link>
    <description>&lt;P&gt;hello !&lt;/P&gt;

&lt;P&gt;I have an issue with an OpenCL application that compute matrix multiplication.&lt;/P&gt;

&lt;P&gt;In particular i think that the problem is related to "clGetEventProfilingInfo" function. If i execute the program by using the CPU (Intel Core i5-4300U) all works fine and by using "clGetEventProfiling" function it calculates the execution time correctly.&lt;/P&gt;

&lt;P&gt;Instead, if i use GPU (Intel HD4400), all works fine if i don't use the "clGetEventProfilingInfo".When i use "clGetEventProfilingInfo" to calculate the execution time and set a local work size in "clEnqueueNDRangeKernel" the program crashes and i don't understand why (instead, if i use "NULL" for local work size parameter in "clEnqueueNDRangeKernel" all seems to work) .Using Visual Studio debugger i think it's a "access violation" problem but i'm not shure.&lt;/P&gt;

&lt;P&gt;This is the code of application :&amp;nbsp;https://www.friendpaste.com/2NIpYvk8R96S01kFD3H3Gl&lt;/P&gt;

&lt;P&gt;Can someone help me?&lt;/P&gt;</description>
    <pubDate>Sat, 19 Sep 2015 15:22:46 GMT</pubDate>
    <dc:creator>Jonny_G_</dc:creator>
    <dc:date>2015-09-19T15:22:46Z</dc:date>
    <item>
      <title>problem with profiling</title>
      <link>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034731#M3633</link>
      <description>&lt;P&gt;hello !&lt;/P&gt;

&lt;P&gt;I have an issue with an OpenCL application that compute matrix multiplication.&lt;/P&gt;

&lt;P&gt;In particular i think that the problem is related to "clGetEventProfilingInfo" function. If i execute the program by using the CPU (Intel Core i5-4300U) all works fine and by using "clGetEventProfiling" function it calculates the execution time correctly.&lt;/P&gt;

&lt;P&gt;Instead, if i use GPU (Intel HD4400), all works fine if i don't use the "clGetEventProfilingInfo".When i use "clGetEventProfilingInfo" to calculate the execution time and set a local work size in "clEnqueueNDRangeKernel" the program crashes and i don't understand why (instead, if i use "NULL" for local work size parameter in "clEnqueueNDRangeKernel" all seems to work) .Using Visual Studio debugger i think it's a "access violation" problem but i'm not shure.&lt;/P&gt;

&lt;P&gt;This is the code of application :&amp;nbsp;https://www.friendpaste.com/2NIpYvk8R96S01kFD3H3Gl&lt;/P&gt;

&lt;P&gt;Can someone help me?&lt;/P&gt;</description>
      <pubDate>Sat, 19 Sep 2015 15:22:46 GMT</pubDate>
      <guid>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034731#M3633</guid>
      <dc:creator>Jonny_G_</dc:creator>
      <dc:date>2015-09-19T15:22:46Z</dc:date>
    </item>
    <item>
      <title>Hi Jonny,</title>
      <link>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034732#M3634</link>
      <description>&lt;P&gt;Hi Jonny,&lt;/P&gt;

&lt;P&gt;It appears that you are trying to set localThreads variable to {512, 512} - this is way too big for a workgroup on a GPU. The size of the workgroup shouldn't exceed 512 elements on your processor and 256 on 5th gen processors and beyond, so the good number to try are {8, 8}, {16, 8} or {32, 8}, etc.&lt;/P&gt;

&lt;P&gt;If that does not solve the issue, please let me know what graphics driver you are using.&lt;/P&gt;</description>
      <pubDate>Mon, 21 Sep 2015 20:32:13 GMT</pubDate>
      <guid>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034732#M3634</guid>
      <dc:creator>Robert_I_Intel</dc:creator>
      <dc:date>2015-09-21T20:32:13Z</dc:date>
    </item>
    <item>
      <title>Yes, it solved the issue .</title>
      <link>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034733#M3635</link>
      <description>&lt;P&gt;Yes, it solved the issue . Thank you.&lt;/P&gt;

&lt;P&gt;I have an other question : when i try to use Intel Code Analyzer on my OpenCL application i have some errors.&amp;nbsp;&lt;/P&gt;

&lt;P&gt;When i lunch the code analysis for kernel side profiling (occupancy) it seems to work but in "Trick per Threads" and "Execution Units" sections i have this message :" Error:unable to retrieve report's data".&amp;nbsp;&lt;/P&gt;

&lt;P&gt;When i lunch the code analysis for kernel side profiling (latency) it doesn't work at all. In "Application Output" section i have this message :"skip source annotation because the source-profile file is empty".&lt;/P&gt;

&lt;P&gt;I'm using a Microsoft Surface Pro 3 with Visual Studio 2013 with the latest &amp;nbsp;Intel Code-Builder. I'm not sure about latest driver for Intel HD4400. If i download the latest driver i can't install it because Surface Pro 3 requires a customize driver that i don't know where to find.&lt;/P&gt;

&lt;P&gt;It could be a drivers problem?&lt;/P&gt;</description>
      <pubDate>Tue, 22 Sep 2015 07:17:11 GMT</pubDate>
      <guid>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034733#M3635</guid>
      <dc:creator>Jonny_G_</dc:creator>
      <dc:date>2015-09-22T07:17:11Z</dc:date>
    </item>
    <item>
      <title>Hi Jonny,</title>
      <link>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034734#M3636</link>
      <description>&lt;P&gt;Hi Jonny,&lt;/P&gt;

&lt;P&gt;Which driver version do you have? Could you provide the kernel/code you are trying to analyze? Did you install the latest Code Builder patch &lt;A href="https://software.intel.com/en-us/forums/opencl/topic/591196"&gt;https://software.intel.com/en-us/forums/opencl/topic/591196&lt;/A&gt; ?&lt;/P&gt;

&lt;P&gt;Thanks!&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 24 Sep 2015 18:55:26 GMT</pubDate>
      <guid>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034734#M3636</guid>
      <dc:creator>Robert_I_Intel</dc:creator>
      <dc:date>2015-09-24T18:55:26Z</dc:date>
    </item>
    <item>
      <title>I've already installed the</title>
      <link>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034735#M3637</link>
      <description>&lt;P&gt;I've already installed the latest Code Builder patch from that link.&lt;/P&gt;

&lt;P&gt;Driver version I have for Intel HD4400 is 10.18.15.4256.&lt;/P&gt;

&lt;P&gt;I downloaded the latest version of driver (Win 10 version) from here :&amp;nbsp;https://downloadcenter.intel.com/download/25308/Intel-Iris-Iris-Pro-and-HD-Graphics-Driver-for-4th-Gen-Windows-10-64bit &amp;nbsp;, but when i try to install it on my Sufrace Pro 3 i have an error that tells me that i need a customized driver for my device and i can't go on with the installation.&lt;/P&gt;

&lt;P&gt;Code that i'm trying to analyze is here :&amp;nbsp;https://www.friendpaste.com/2NIpYvk8R96S01kFD3H3Gl ,obviously&amp;nbsp;&lt;SPAN style="font-size: 1em; line-height: 1.5;"&gt;with valid values in localThreads array.&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 24 Sep 2015 19:48:05 GMT</pubDate>
      <guid>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034735#M3637</guid>
      <dc:creator>Jonny_G_</dc:creator>
      <dc:date>2015-09-24T19:48:05Z</dc:date>
    </item>
    <item>
      <title>I am able to reproduce this</title>
      <link>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034736#M3638</link>
      <description>&lt;P&gt;I am able to reproduce this issue. Will file a bug.&lt;/P&gt;</description>
      <pubDate>Thu, 24 Sep 2015 23:45:02 GMT</pubDate>
      <guid>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034736#M3638</guid>
      <dc:creator>Robert_I_Intel</dc:creator>
      <dc:date>2015-09-24T23:45:02Z</dc:date>
    </item>
    <item>
      <title>is a problem that could be</title>
      <link>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034737#M3639</link>
      <description>&lt;P&gt;is a problem that could be solved ?&lt;/P&gt;</description>
      <pubDate>Sun, 27 Sep 2015 08:40:35 GMT</pubDate>
      <guid>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034737#M3639</guid>
      <dc:creator>Jonny_G_</dc:creator>
      <dc:date>2015-09-27T08:40:35Z</dc:date>
    </item>
    <item>
      <title>Jonny,</title>
      <link>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034738#M3640</link>
      <description>&lt;P&gt;Jonny,&lt;/P&gt;

&lt;P&gt;Yes, the development team told me that they could solve this issue, so the solution should be available in the next release.&lt;/P&gt;</description>
      <pubDate>Mon, 28 Sep 2015 20:49:38 GMT</pubDate>
      <guid>https://community.intel.com/t5/OpenCL-for-CPU/problem-with-profiling/m-p/1034738#M3640</guid>
      <dc:creator>Robert_I_Intel</dc:creator>
      <dc:date>2015-09-28T20:49:38Z</dc:date>
    </item>
  </channel>
</rss>

