robertvirany wrote: Ping @Artem-B @AlexMaclean - this follows the direction discussed in #134244 by lowering CUDA device `sqrtf` through `__builtin_sqrtf` rather than adding new NVVMReflect/libdevice plumbing. Would appreciate your review when you have time.
https://github.com/llvm/llvm-project/pull/205661 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
