<div dir="ltr"><div dir="ltr"><br></div><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_quote"><div>It is not. The number of processes is specified independently using 'mpiexec -n <p>' or when using the test system NP=<p>. <br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div lang="EN-GB"><div><p><span style="font-size:10pt"><u></u><u></u></span></p>
<p style="margin-left:54pt">
<u></u><span><span style="font-size:10pt;font-family:Menlo"><span>(i)<span style="font:7pt "Times New Roman"">
</span></span></span></span><u></u><span style="font-size:10pt;font-family:Menlo">Say I start with -cells 1,1,1 -max_conv its</span><span><span style="font-size:10pt;font-family:Menlo"> 7; that would eventually leave
all refinement on level 7 running on 1 MPI process?</span></span></p></div></div></blockquote></div></div></blockquote><div>I don't understand <br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div lang="EN-GB"><div><p style="margin-left:54pt"><span><span style="font-size:10pt;font-family:Menlo"><u></u><u></u></span></span></p>
<p style="margin-left:54pt">
<u></u><span style="font-size:10pt;font-family:Menlo"><span>(ii)<span style="font:7pt "Times New Roman"">
</span></span></span><u></u><span style="font-size:10pt;font-family:Menlo">Say I start with -cells 2,2,1 -max_conv its</span><span><span style="font-size:10pt;font-family:Menlo"> n</span></span><span style="font-size:10pt;font-family:Menlo">;
is it recommended to run on 4 MPI processes?</span></p></div></div></blockquote></div></div></blockquote><div>Yes!</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_quote"><div>No, those options do not influence the number of processes.</div></div></div></blockquote><div><br></div><div>Correct, but you are not answering the question that he asked! </div><div><br></div><div>The coupling of the two is not enforced in the code, but to get good load balancing you want i*j*k == NP. (there is more flexibility than this, but this is the place to start.)</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_quote"><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div lang="EN-GB"><div>
<p class="MsoNormal"><span>I am running ex56 on gpu; I am looking at KSPSolve (or any other event) but no gpu flops are recorded in the -log_view?</span></p></div></div></blockquote><div><br></div><div>I do not think you are running on the GPU then. Mark can comment, but we usually specify GPU execution using the Vec and Mat types</div><div>through -dm_vec_type and -dm_mat_type.</div></div></div></blockquote><div><br></div><div>This test has a ex56_ prefix.</div><div><br></div><div>Mark</div></div></div>