[all-commits] [llvm/llvm-project] 077ec0: [AMDGPU] Avoid errors with 23-bit division and rem...

[LU-JOHN via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 077ec06128e27e3dce2b97563dab703f89024ddf
      https://github.com/llvm/llvm-project/commit/077ec06128e27e3dce2b97563dab703f89024ddf
  Author: LU-JOHN <John.Lu at amd.com>
  Date:   2026-06-10 (Wed, 10 Jun 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
    M llvm/test/CodeGen/AMDGPU/amdgpu-codegenprepare-idiv.ll
    M llvm/test/CodeGen/AMDGPU/sdiv.ll
    M llvm/test/CodeGen/AMDGPU/sdiv64.ll
    M llvm/test/CodeGen/AMDGPU/sdivrem24.ll
    M llvm/test/CodeGen/AMDGPU/srem64.ll
    M llvm/test/CodeGen/AMDGPU/udiv.ll
    M llvm/test/CodeGen/AMDGPU/udiv64.ll
    M llvm/test/CodeGen/AMDGPU/udivrem24.ll
    M llvm/test/CodeGen/AMDGPU/urem64.ll

  Log Message:
  -----------
  [AMDGPU] Avoid errors with 23-bit division and remainder. (#202753)

Extensive testing of expandDivRem24 found an error when calculating Y/X
when Y = (0x7FFFFF/X)*X-1. There are
36 values of X for which this happens. Limit expansion to 23-bit signed
and 22-bit unsigned to avoid this issue.

Testing added in https://github.com/llvm/llvm-test-suite/pull/419.

---------

Signed-off-by: John Lu <John.Lu at amd.com>



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