<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
<p><font face="Hack Nerd Font Mono">Hey Ye,</font></p>
<p><font face="Hack Nerd Font Mono"><br>
</font></p>
<p><font face="Hack Nerd Font Mono">will be solved (for most common
cases) with <a class="moz-txt-link-freetext" href="https://reviews.llvm.org/D83271">https://reviews.llvm.org/D83271</a> .<br>
</font></p>
<p><br>
</p>
<p>~ Johannes<br>
</p>
<p><br>
</p>
<div class="moz-cite-prefix">On 6/30/20 2:25 PM, Ye Luo via
Openmp-dev wrote:<br>
</div>
<blockquote type="cite"
cite="mid:CACiEoH=rrR7MCFDWf0ir4UB9oKarDAqvq7tJ=nQ=BuOQ-AYSNw@mail.gmail.com">
<pre class="moz-quote-pre" wrap="">Hi all,
I just found when there are multiple offload regions, all the finally
assembled kernels use equal amount registers corresponding to the kernel
that uses the most registers. This causes all my kernels spilling registers
and thus kills performance. This is surprising and I didn't see this
behavior with IBM XL compiler.
The reproducer is provided at <a class="moz-txt-link-freetext" href="https://bugs.llvm.org/show_bug.cgi?id=46450">https://bugs.llvm.org/show_bug.cgi?id=46450</a>
I also noticed the same issue with AOMP.
So I'm wondering where could potentially be buggy in the compiling/linking
flow.
Any thoughts?
Best,
Ye
===================
Ye Luo, Ph.D.
Computational Science Division & Leadership Computing Facility
Argonne National Laboratory
</pre>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<pre class="moz-quote-pre" wrap="">_______________________________________________
Openmp-dev mailing list
<a class="moz-txt-link-abbreviated" href="mailto:Openmp-dev@lists.llvm.org">Openmp-dev@lists.llvm.org</a>
<a class="moz-txt-link-freetext" href="https://lists.llvm.org/cgi-bin/mailman/listinfo/openmp-dev">https://lists.llvm.org/cgi-bin/mailman/listinfo/openmp-dev</a>
</pre>
</blockquote>
</body>
</html>