[llvm] [AMDGPU] Simplify and improve codegen for llvm.amdgcn.set.inactive (PR #107889)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Sep 9 09:37:23 PDT 2024
github-actions[bot] wrote:
<!--LLVM CODE FORMAT COMMENT: {clang-format}-->
:warning: C/C++ code formatter, clang-format found issues in your code. :warning:
<details>
<summary>
You can test this locally with the following command:
</summary>
``````````bash
git-clang-format --diff 111932d5cae0199d9c59669b37232a011f8b8757 03605287cb6ae1f7bb4da00afc5c180d184ebf52 --extensions cpp,h -- llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp llvm/lib/Target/AMDGPU/SIISelLowering.cpp llvm/lib/Target/AMDGPU/SIInstrInfo.cpp llvm/lib/Target/AMDGPU/SIInstrInfo.h llvm/lib/Target/AMDGPU/SIPreAllocateWWMRegs.cpp llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp
``````````
</details>
<details>
<summary>
View the diff from clang-format here.
</summary>
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp b/llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp
index 208af0634f..8064c07310 100644
--- a/llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp
+++ b/llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp
@@ -1072,7 +1072,8 @@ void SIWholeQuadMode::lowerBlock(MachineBasicBlock &MBB) {
case AMDGPU::V_SET_INACTIVE_B32:
if (ActiveLanesReg) {
LiveInterval &LI = LIS->getInterval(MI.getOperand(5).getReg());
- MRI->constrainRegClass(ActiveLanesReg, TRI->getRegClass(AMDGPU::SReg_1_XEXECRegClassID));
+ MRI->constrainRegClass(
+ ActiveLanesReg, TRI->getRegClass(AMDGPU::SReg_1_XEXECRegClassID));
MI.getOperand(5).setReg(ActiveLanesReg);
LIS->shrinkToUses(&LI);
} else {
``````````
</details>
https://github.com/llvm/llvm-project/pull/107889
More information about the llvm-commits
mailing list