[all-commits] [llvm/llvm-project] a5a095: [AMDGPU] Adapt new lowering sequence for `fdiv16`

[Shilei Tian via All-commits]

  Branch: refs/heads/users/shiltian/fp16-correctly-rounded-sequence
  Home:   https://github.com/llvm/llvm-project
  Commit: a5a095c596c97791a6578166c5b8b2ab6d78c5ff
      https://github.com/llvm/llvm-project/commit/a5a095c596c97791a6578166c5b8b2ab6d78c5ff
  Author: Shilei Tian <i at tianshilei.me>
  Date:   2024-10-08 (Tue, 08 Oct 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/fdiv.f16.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/frem.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-fdiv.mir
    M llvm/test/CodeGen/AMDGPU/fdiv.f16.ll
    M llvm/test/CodeGen/AMDGPU/fold-int-pow2-with-fmul-or-fdiv.ll
    M llvm/test/CodeGen/AMDGPU/frem.ll

  Log Message:
  -----------
  [AMDGPU] Adapt new lowering sequence for `fdiv16`

The current lowering of fdiv16 can generate incorrectly rounded result in some
cases.

Fixes SWDEV-47760.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications