shiltian wrote: > With early intrinsic feature check it fails gracefully. But in essence it is > same `feature check` ? or am I misunderstanding something.
Actually, if you have access to ROCM-26439, it's a good example of how an instruction's predicate can take effect very late in the pipeline, yet cause a failure much earlier in a way that's quite confusing. https://github.com/llvm/llvm-project/pull/201470 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
