vendor/llvm-project/llvmorg-11-init-20887-g2e10b7a39b9vendor/llvm-project/master

1 files changed, 6 insertions, 4 deletions

diff --git a/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp b/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp
index 51779e97ac620..64fca0b467977 100644
--- a/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp
@@ -88,15 +88,17 @@ bool SIRemoveShortExecBranches::mustRetainExeczBranch(
     for (MachineBasicBlock::const_iterator I = MBB.begin(), E = MBB.end();
          I != E; ++I) {
       // When a uniform loop is inside non-uniform control flow, the branch
-      // leaving the loop might be an S_CBRANCH_VCCNZ, which is never taken
-      // when EXEC = 0. We should skip the loop lest it becomes infinite.
-      if (I->getOpcode() == AMDGPU::S_CBRANCH_VCCNZ ||
-          I->getOpcode() == AMDGPU::S_CBRANCH_VCCZ)
+      // leaving the loop might never be taken when EXEC = 0.
+      // Hence we should retain cbranch out of the loop lest it become infinite.
+      if (I->isConditionalBranch())
         return true;
 
       if (TII->hasUnwantedEffectsWhenEXECEmpty(*I))
         return true;
 
+      if (TII->isKillTerminator(I->getOpcode()))
+        return true;
+
       // These instructions are potentially expensive even if EXEC = 0.
       if (TII->isSMRD(*I) || TII->isVMEM(*I) || TII->isFLAT(*I) ||
           I->getOpcode() == AMDGPU::S_WAITCNT)