[llvm] [LV] Add extra check for signed oveflow for SDiv/SRem (PR #170818)

[Luke Lau via llvm-commits]

================
@@ -2878,11 +2878,22 @@ bool LoopVectorizationCostModel::isPredicatedInst(Instruction *I) const {
              TheLoop->isLoopInvariant(cast<StoreInst>(I)->getValueOperand()));
   }
   case Instruction::UDiv:
-  case Instruction::SDiv:
-  case Instruction::SRem:
   case Instruction::URem:
     // If the divisor is loop-invariant no predication is needed.
     return !Legal->isInvariant(I->getOperand(1));
+  case Instruction::SDiv:
+  case Instruction::SRem: {
+    auto *LHS = I->getOperand(0);
+    auto *RHS = I->getOperand(1);
+    // If RHS is loop-invariant, signed-division overflow is possible
+    // when LHS can be INT_MIN.
+    ScalarEvolution &SE = *PSE.getSE();
+    IntegerType *LHSTy = dyn_cast<IntegerType>(LHS->getType());
+    llvm::ConstantRange LHSRange = SE.getSignedRange(SE.getSCEV(LHS));
----------------
lukel97 wrote:

Can this be simplified to `SE.getSignedRangeMin(SE.getSCEV(LHS)).isMinSignedValue()`?

https://github.com/llvm/llvm-project/pull/170818