<div dir="ltr"><div>FYI: More past conversations. <br></div><div><a href="http://lists.llvm.org/pipermail/openmp-dev/2019-March/002443.html">http://lists.llvm.org/pipermail/openmp-dev/2019-March/002443.html</a></div><div><a href="http://lists.llvm.org/pipermail/cfe-dev/2019-October/063804.html">http://lists.llvm.org/pipermail/cfe-dev/2019-October/063804.html</a></div><div>Ye<br></div><div><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr">===================<br>
Ye Luo, Ph.D.<br>Computational Science Division & Leadership Computing Facility<br>
Argonne National Laboratory</div></div></div></div></div><br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">Jon Chesterfield via Openmp-dev <<a href="mailto:openmp-dev@lists.llvm.org">openmp-dev@lists.llvm.org</a>> 于2019年12月3日周二 下午3:02写道：<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">I don't think this works today. There's some state in <a href="http://omp_data.cu" target="_blank">omp_data.cu</a> which looks like it gets shared by any target offloading invocation, so I think multiple host threads will invoke kernels that step on each other.<div><br></div><div>Further, I think this should work. It seems like a reasonable use case.</div><div><br></div><div>Shall we fix up deviceRTL (and the compiler side of reduction, possibly elsewhere) to support multiple simultaneous invocations of the openmp target runtime?</div><div><br></div><div>Thanks,</div><div><br></div><div>Jon</div></div>
_______________________________________________<br>
Openmp-dev mailing list<br>
<a href="mailto:Openmp-dev@lists.llvm.org" target="_blank">Openmp-dev@lists.llvm.org</a><br>
<a href="https://lists.llvm.org/cgi-bin/mailman/listinfo/openmp-dev" rel="noreferrer" target="_blank">https://lists.llvm.org/cgi-bin/mailman/listinfo/openmp-dev</a><br>
</blockquote></div>