[PATCH] D156100: [AMDGPU] Have a command-line flag to enable true True16 codegen.

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp:174
+bool AMDGPUSubtarget::useTrue16BitInsts() const {
+  return hasTrue16BitInsts() && EnableTrue16Codegen;
+}
----------------
arsenm wrote:
> Can implement this by just clearing the hasTrue16BitInsts feature in the constructor 
Actually just using -mattr=-true16-whatever should work just as well. Do we really need a dedicated flag?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D156100/new/

https://reviews.llvm.org/D156100