https://community.intel.com/t5/Intel-Fortran-Compiler/PURE-and-OpenMP/m-p/832477#M53199 <DIV id="tiny_quote"> <DIV style="margin-left: 2px; margin-right: 2px;">Quoting <A rel="/en-us/services/profile/quick_profile.php?is_paid=&amp;user_id=336549" class="basic" href="https://community.intel.com/en-us/profile/336549/">TimP (Intel)</A></DIV> <DIV style="background-color: #e5e5e5; padding: 5px; border: 1px; border-style: inset; margin-left: 2px; margin-right: 2px;"><I>I haven't been able to demonstrate a significant difference. ifort seems to rely on inter-procedural analysis for such optimizations. What was your conclusion?</I></DIV></DIV><P></P><P class="sectionbodytext">Thanks Tim - I haven't tried for myself and wanted to see whether the program could benefit if I included/restructered procedures as pure procedures. But unless it does not require extra effort I think I will leave it as it is.</P><P></P><P class="sectionbodytext">Cheers</P><P class="sectionbodytext">-Ralf</P> Sun, 11 Sep 2011 11:55:03 GMT Ralf 2011-09-11T11:55:03Z https://community.intel.com/t5/Intel-Fortran-Compiler/PURE-and-OpenMP/m-p/832475#M53197 <SPAN class="sectionbodytext">Hi there,</SPAN><DIV><SPAN style="font-family: Verdana, Arial, Helvetica, sans-serif;"><BR /></SPAN><DIV></DIV><DIV class="sectionbody">does the use of PURE procedures in an OpenMPparallelizedprogram lead toa measurable benefit in runtime with the latest IVF compiler (or any other compiler for that matter)?</DIV><DIV></DIV><DIV></DIV><DIV class="sectionbodytext">cheers</DIV><DIV class="sectionbodytext">-Ralf</DIV></DIV> Sun, 11 Sep 2011 06:29:08 GMT https://community.intel.com/t5/Intel-Fortran-Compiler/PURE-and-OpenMP/m-p/832475#M53197 Ralf 2011-09-11T06:29:08Z https://community.intel.com/t5/Intel-Fortran-Compiler/PURE-and-OpenMP/m-p/832476#M53198 I haven't been able to demonstrate a significant difference. ifort seems to rely on inter-procedural analysis for such optimizations. What was your conclusion? Sun, 11 Sep 2011 10:32:43 GMT https://community.intel.com/t5/Intel-Fortran-Compiler/PURE-and-OpenMP/m-p/832476#M53198 TimP 2011-09-11T10:32:43Z https://community.intel.com/t5/Intel-Fortran-Compiler/PURE-and-OpenMP/m-p/832477#M53199 <DIV id="tiny_quote"> <DIV style="margin-left: 2px; margin-right: 2px;">Quoting <A rel="/en-us/services/profile/quick_profile.php?is_paid=&amp;user_id=336549" class="basic" href="https://community.intel.com/en-us/profile/336549/">TimP (Intel)</A></DIV> <DIV style="background-color: #e5e5e5; padding: 5px; border: 1px; border-style: inset; margin-left: 2px; margin-right: 2px;"><I>I haven't been able to demonstrate a significant difference. ifort seems to rely on inter-procedural analysis for such optimizations. What was your conclusion?</I></DIV></DIV><P></P><P class="sectionbodytext">Thanks Tim - I haven't tried for myself and wanted to see whether the program could benefit if I included/restructered procedures as pure procedures. But unless it does not require extra effort I think I will leave it as it is.</P><P></P><P class="sectionbodytext">Cheers</P><P class="sectionbodytext">-Ralf</P> Sun, 11 Sep 2011 11:55:03 GMT https://community.intel.com/t5/Intel-Fortran-Compiler/PURE-and-OpenMP/m-p/832477#M53199 Ralf 2011-09-11T11:55:03Z