projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 9f8e779) | patch
[AMDGPU] Add 24-bit mulhi intrinsics in INTRINSIC_WO_CHAIN combine.
authorAbinav Puthan Purayil <abinav.puthanpurayil@amd.com>
Thu, 28 Oct 2021 10:38:59 +0000 (16:08 +0530)
committerAbinav Puthan Purayil <abinav.puthanpurayil@amd.com>
Thu, 28 Oct 2021 11:27:48 +0000 (16:57 +0530)
commit2da6ef3664333cc36c449b271c50a72dd7f61940
treeab690eefe72b6184439b4b88808e8be09973b896tree | snapshot
parent9f8e779b42115216f347fbfc6733077b8d6ae1c5commit | diff
[AMDGPU] Add 24-bit mulhi intrinsics in INTRINSIC_WO_CHAIN combine.

mul24 intrinsic's operands are simplified by
AMDGPUTargetLowering::performIntrinsicWOChainCombine(). This change adds
the mul24hi intrinsics in the combine since its operands can be
simplified like that of the mul24 intrinsics.

Differential Revision: https://reviews.llvm.org/D112702
llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/mul_uint24-amdgcn.ll diff | blob | history
Domain: System / Toolchain;