Skip to content

Commit

Permalink
AMDGPU: Set max supported div/rem size to 64 (llvm#80669)
Browse files Browse the repository at this point in the history
This enables IR expansion for i128 divisions. The vector case is still
broken because ExpandLargeDivRem doesn't try to handle them.

Fixes: SWDEV-426193
  • Loading branch information
arsenm authored Feb 5, 2024
1 parent 4e958ab commit a5d206d
Show file tree
Hide file tree
Showing 3 changed files with 5,469 additions and 6 deletions.
1 change: 1 addition & 0 deletions llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -577,6 +577,7 @@ AMDGPUTargetLowering::AMDGPUTargetLowering(const TargetMachine &TM,
ISD::AssertSext, ISD::INTRINSIC_WO_CHAIN});

setMaxAtomicSizeInBitsSupported(64);
setMaxDivRemBitWidthSupported(64);
}

bool AMDGPUTargetLowering::mayIgnoreSignedZero(SDValue Op) const {
Expand Down
Loading

0 comments on commit a5d206d

Please sign in to comment.