[llvm] [AMDGPU] CodeGen for GFX12 64-bit scalar add/sub (PR #75070)

Jay Foad via llvm-commits llvm-commits at lists.llvm.org
Tue Dec 12 04:29:04 PST 2023


jayfoad wrote:

> does it need a change in the moveToVALU as well?

I think the way it works is that we always select S_ADD_U64_PSEUDO, which is already handled in moveToVALU, and only convert to S_ADD_NC_U64 later. But I will check...

https://github.com/llvm/llvm-project/pull/75070


More information about the llvm-commits mailing list