AMDGPU: Set max supported div/rem size to 64 (llvm#80669)

This enables IR expansion for i128 divisions. The vector case is still broken because ExpandLargeDivRem doesn't try to handle them. Fixes: SWDEV-426193 (cherry picked from commit a5d206d)
tstellar · Feb 14, 2024 · fe425eb · fe425eb
1 parent de7db5a
commit fe425eb
Show file tree

Hide file tree

Showing 3 changed files with 5,469 additions and 6 deletions.
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -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 {