<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=us-ascii"><meta name=Generator content="Microsoft Word 14 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
        {font-family:Calibri;
        panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
        {font-family:Tahoma;
        panose-1:2 11 6 4 3 5 4 4 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
        {margin:0cm;
        margin-bottom:.0001pt;
        font-size:11.0pt;
        font-family:"Calibri","sans-serif";
        mso-fareast-language:EN-US;}
a:link, span.MsoHyperlink
        {mso-style-priority:99;
        color:blue;
        text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
        {mso-style-priority:99;
        color:purple;
        text-decoration:underline;}
span.EmailStyle17
        {mso-style-type:personal-compose;
        font-family:"Calibri","sans-serif";
        color:windowtext;}
.MsoChpDefault
        {mso-style-type:export-only;
        font-family:"Calibri","sans-serif";
        mso-fareast-language:EN-US;}
@page WordSection1
        {size:612.0pt 792.0pt;
        margin:72.0pt 72.0pt 72.0pt 72.0pt;}
div.WordSection1
        {page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=EN-GB link=blue vlink=purple><div class=WordSection1><p class=MsoNormal>Hi,<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>I’ve been following some instructions from Intel to benchmark WRF on Xeon Phi. I’m doing this for benchmarking purposes only and am not an experienced WRF user:<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal><a href="http://software.intel.com/en-us/articles/how-to-get-wrf-running-on-the-intelr-xeon-phitm-coprocessor?page=1">http://software.intel.com/en-us/articles/how-to-get-wrf-running-on-the-intelr-xeon-phitm-coprocessor?page=1</a><o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>These instructions suggest using the benchmark provided at the following link to test performance and verify correct execution:<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal><a href="http://www.mmm.ucar.edu/WG2bench/conus12km_data_v3/">http://www.mmm.ucar.edu/WG2bench/conus12km_data_v3/</a><o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>To run this benchmark successfully one addition is required to the provided namelist.input file in order for the old benchmark data set to work with the current WRF version (3.5) – namely adding the line “use_baseparam_fr_nml = .t.,” under the &dynamics heading.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>I have run the benchmark as a native application on a single Xeon Phi card and also on a single host Xeon CPU. In both cases I get the message wrf: SUCCESS COMPLETE WRF in the output.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>The problem appears when I try to use diffwrf to compare the output from the benchmark with the wrf_reference data provided as part of the benchmark download at the link above. <o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>It appears that some variables can’t be matched between the experiment result and the reference result and of the variables that can be compared it appears that they are not similar enough to consider it a valid run. I have attached the diffwrf output from both a run on the host Xeon CPU and a run on the Xeon Phi coprocessor. The diffwrf output for both the CPU vs reference and the Phi vs reference are very similar.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>Does this indicate that the execution is erroneous on both the CPU and the Xeon Phi? Or is there some reason why the wrf_reference data included with the benchmark is not a valid comparison against the output data from WRF 3.5?<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>Thanks,<o:p></o:p></p><p class=MsoNormal><br>Paul.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal><span style='font-size:9.0pt;font-family:"Tahoma","sans-serif";color:#00B050;mso-fareast-language:EN-GB'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:9.0pt;font-family:"Tahoma","sans-serif";color:#00B050;mso-fareast-language:EN-GB'>---<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:9.0pt;font-family:"Tahoma","sans-serif";color:#00B050;mso-fareast-language:EN-GB'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:9.0pt;font-family:"Tahoma","sans-serif";color:#00B050;mso-fareast-language:EN-GB'>Paul Caheny<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:9.0pt;font-family:"Tahoma","sans-serif";color:#00B050;mso-fareast-language:EN-GB'>Researcher<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:9.0pt;font-family:"Tahoma","sans-serif";color:#00B050;mso-fareast-language:EN-GB'>Technical Computing Research<br>Fujitsu Laboratories of Europe Ltd (FLE)<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:9.0pt;font-family:"Tahoma","sans-serif";color:#00B050;mso-fareast-language:EN-GB'>phone: +44 (0) 20 8606 4529<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:9.0pt;font-family:"Tahoma","sans-serif";color:#00B050;mso-fareast-language:EN-GB'>e-mail: <a href="mailto:Paul.Caheny@uk.fujitsu.com"><span style='color:#00B050'>Paul.Caheny@uk.fujitsu.com</span></a><o:p></o:p></span></p><p class=MsoNormal><span style='font-size:9.0pt;font-family:"Tahoma","sans-serif";color:#00B050;mso-fareast-language:EN-GB'>web: <a href="http://www.fujitsu.com/emea/about/fle" target="_blank"><span style='color:#00B050'>http://www.fujitsu.com/emea/about/fle/</span></a><o:p></o:p></span></p><p class=MsoNormal><o:p> </o:p></p></div></body></html>
<table><tr><td bgcolor=#ffffff><font color=#000000><pre>______________________________________________________________________
Fujitsu Laboratories of Europe Limited
Hayes Park Central, Hayes End Road, Hayes, Middlesex, UB4 8FE
Registered No. 4153469
This e-mail and any attachments are for the sole use of addressee(s) and
may contain information which is privileged and confidential. Unauthorised
use or copying for disclosure is strictly prohibited. The fact that this
e-mail has been scanned by Trendmicro Interscan does not guarantee that
it has not been intercepted or amended nor that it is virus-free.</pre></font></td></tr></table>