frasercrmck wrote: The updated version of this patch removes the SPIR-V header workarounds, and optimizes the `upsample` and `mul_hi` implementations for vector types. All the integer functions in this patch now avoid scalarization.
https://github.com/llvm/llvm-project/pull/116786 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
