Artem-B wrote: Looks like there's no objection in principle. @arsenm do you think we need to get someone else on AMD side to take a look, in case this change brings unintended surprises. If there are no objections, then we should let this change land, so we can unblock fixing denormals handling of FP atomics in NVPTX.
https://github.com/llvm/llvm-project/pull/217585 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
