<div dir="ltr"><div dir="ltr"><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Jul 29, 2019 at 5:31 PM Smith, Barry F. <<a href="mailto:bsmith@mcs.anl.gov">bsmith@mcs.anl.gov</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br>
I don't understand the notation in the legend on the second page<br>
<br>
12,288 cpus and no GPUs ?<br></blockquote><div><br></div><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">
<br>
24 GPUs? or 6 GPUs<br></blockquote><div><br></div><div>24 virtual, 6 real GPUs per node. The first case is one node, 24 cores/vGPUs</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">
<br>
192 GPUs?<br>
<br>
1536 GPUs?<br>
<br>
12,288 GPUs? or 12288/4 = 3072 GPUs?<br></blockquote><div><br></div><div>All "GPUs" are one core/process/vGPU. So 12288 virtual GPUs and 3072 physical GPUs.</div><div><br></div><div>Maybe I should add 'virtual GPUs' and put (4 processes/SUMMIT GPU)</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">
<br>
So on the largest run using GPUs or not takes pretty much exactly the same <br>
amount of time?<br></blockquote><div><br></div><div>yes. The raw Mat-vec is about 3x faster with ~95K equations/process. I've attached the data.</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">
<br>
What about 6 GPUs vs 24 CPUs ? Same equal amount of time. <br>
<br>
Can you send some log summaries<br><br>
</blockquote></div></div>