[MachineCSE] Prevent CSE of non-local convergent instrs

At the moment, MachineCSE allows CSE-ing convergent instrs which are
non-local to each other. This can cause illegal codegen as convergent
instrs are control flow dependent. The patch prevents non-local CSE of
convergent instrs by adding a check in isProfitableToCSE and rejecting
CSE-ing if we're considering CSE-ing non-local convergent instrs. We
can still CSE convergent instrs which are in the same control flow
scope, so the patch purposely does not make all convergent instrs
non-CSE candidates in isCSECandidate.

https://reviews.llvm.org/D101187

1 files changed, 5 insertions, 1 deletions

diff --git a/llvm/lib/CodeGen/MachineCSE.cpp b/llvm/lib/CodeGen/MachineCSE.cpp
index 199fe2d..de90d0f 100644
--- a/llvm/lib/CodeGen/MachineCSE.cpp
+++ b/llvm/lib/CodeGen/MachineCSE.cpp
@@ -433,6 +433,11 @@ bool MachineCSE::isProfitableToCSE(Register CSReg, Register Reg,
                                    MachineBasicBlock *CSBB, MachineInstr *MI) {
   // FIXME: Heuristics that works around the lack the live range splitting.
 
+  MachineBasicBlock *BB = MI->getParent();
+  // Prevent CSE-ing non-local convergent instructions.
+  if (MI->isConvergent() && CSBB != BB)
+    return false;
+
   // If CSReg is used at all uses of Reg, CSE should not increase register
   // pressure of CSReg.
   bool MayIncreasePressure = true;
@@ -455,7 +460,6 @@ bool MachineCSE::isProfitableToCSE(Register CSReg, Register Reg,
   // an immediate predecessor. We don't want to increase register pressure and
   // end up causing other computation to be spilled.
   if (TII->isAsCheapAsAMove(*MI)) {
-    MachineBasicBlock *BB = MI->getParent();
     if (CSBB != BB && !CSBB->isSuccessor(BB))
       return false;
   }