[PATCH] D111523: [AMDGPU] Fix 24 bit mul intrinsic generation for > 32 bit result.

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon Oct 18 09:50:33 PDT 2021

Previous message: [polly] 8568ca7 - Use llvm::erase_if (NFC)
Next message: [PATCH] D111523: [AMDGPU] Fix 24 bit mul intrinsic generation for > 32 bit result.
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

arsenm added a comment.

Do we not emit 24 bit mulhi in the IR pass? Could we just start emitting the full 48 bit computation?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D111523/new/

https://reviews.llvm.org/D111523

Previous message: [polly] 8568ca7 - Use llvm::erase_if (NFC)
Next message: [PATCH] D111523: [AMDGPU] Fix 24 bit mul intrinsic generation for > 32 bit result.
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list