[PATCH] D124843: AMDGPU: Add G_AMDGPU_MAD_64_32 instructions

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.
Herald added a subscriber: kosarev.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp:1641
+
+  bool IsUnsigned = MI.getOpcode() == AMDGPU::G_AMDGPU_MAD_U64_U32;
+  LLT S1 = LLT::scalar(1);
----------------
nhaehnle wrote:
> arsenm wrote:
> > Most places invert this and use IsSigned (saves a few characters I guess)
> How strongly do you feel about that? I used `IsUnsigned` because it puts the more common opcode first in ternary ?: operators.
Not very


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124843/new/

https://reviews.llvm.org/D124843