[llvm] [AMDGPU] Fix checkVALUHazardsHelper distance accounting on branchy CFG (PR #203770)
via llvm-commits
llvm-commits at lists.llvm.org
Sun Jun 14 07:06:32 PDT 2026
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 origin/main HEAD --extensions cpp -- llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp --diff_from_common_commit
``````````
:warning:
The reproduction instructions above might return results for more than one PR
in a stack if you are using a stacked PR workflow. You can limit the results by
changing `origin/main` to the base branch/commit you want to compare against.
:warning:
</details>
<details>
<summary>
View the diff from clang-format here.
</summary>
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp b/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
index 41e6ab837..8af9a86b4 100644
--- a/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
@@ -956,8 +956,7 @@ int GCNHazardRecognizer::checkVALUHazardsHelper(
// Returns 0 when MI is not a hazard producer for Reg.
auto WindowFor = [this, TII, TRI, Reg](const MachineInstr &MI) -> int {
int DataIdx = createsVALUHazard(MI);
- if (DataIdx < 0 ||
- !TRI->regsOverlap(MI.getOperand(DataIdx).getReg(), Reg))
+ if (DataIdx < 0 || !TRI->regsOverlap(MI.getOperand(DataIdx).getReg(), Reg))
return 0;
if (!ST.hasGFX940Insts())
return 1;
@@ -989,8 +988,8 @@ int GCNHazardRecognizer::checkVALUHazardsHelper(
auto IsHazardFn = [&WindowFor, Window](const MachineInstr &MI) {
return WindowFor(MI) >= Window;
};
- WaitStatesNeeded = std::max(WaitStatesNeeded,
- Window - getWaitStatesSince(IsHazardFn, Window));
+ WaitStatesNeeded = std::max(
+ WaitStatesNeeded, Window - getWaitStatesSince(IsHazardFn, Window));
}
return WaitStatesNeeded;
``````````
</details>
https://github.com/llvm/llvm-project/pull/203770
More information about the llvm-commits
mailing list