[CGP] move overflow intrinsic insertion to common location; NFCI
We need to enhance the uaddo matching to handle special-cases
as seen in PR40486 and PR31754. That means we won't necessarily
have a def-use pattern, so we'll need to check dominance to
determine where to place the intrinsic (as we already do for
usubo). This preliminary patch is just rearranging the code,
so the planned follow-up to improve uaddo will be more clear.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@354689 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/CodeGen/CodeGenPrepare.cpp b/lib/CodeGen/CodeGenPrepare.cpp
index e961139..a6a4ea2 100644
--- a/lib/CodeGen/CodeGenPrepare.cpp
+++ b/lib/CodeGen/CodeGenPrepare.cpp
@@ -1159,19 +1159,33 @@
return SinkCast(CI);
}
-static void replaceMathCmpWithIntrinsic(BinaryOperator *BO, CmpInst *Cmp,
- Instruction *InsertPt,
+static bool replaceMathCmpWithIntrinsic(BinaryOperator *BO, CmpInst *Cmp,
Intrinsic::ID IID) {
+ // We allow matching the canonical IR (add X, C) back to (usubo X, -C).
Value *Arg0 = BO->getOperand(0);
Value *Arg1 = BO->getOperand(1);
-
- // We allow matching the canonical IR (add X, C) back to (usubo X, -C).
if (BO->getOpcode() == Instruction::Add &&
IID == Intrinsic::usub_with_overflow) {
assert(isa<Constant>(Arg1) && "Unexpected input for usubo");
Arg1 = ConstantExpr::getNeg(cast<Constant>(Arg1));
}
+ Instruction *InsertPt;
+ if (BO->hasOneUse() && BO->user_back() == Cmp) {
+ // If the math is only used by the compare, insert at the compare to keep
+ // the condition in the same block as its users. (CGP aggressively sinks
+ // compares to help out SDAG.)
+ InsertPt = Cmp;
+ } else {
+ // The math and compare may be independent instructions. Check dominance to
+ // determine the insertion point for the intrinsic.
+ DominatorTree DT(*BO->getFunction());
+ bool MathDominates = DT.dominates(BO, Cmp);
+ if (!MathDominates && !DT.dominates(Cmp, BO))
+ return false;
+ InsertPt = MathDominates ? cast<Instruction>(BO) : cast<Instruction>(Cmp);
+ }
+
IRBuilder<> Builder(InsertPt);
Value *MathOV = Builder.CreateBinaryIntrinsic(IID, Arg0, Arg1);
Value *Math = Builder.CreateExtractValue(MathOV, 0, "math");
@@ -1180,12 +1194,13 @@
Cmp->replaceAllUsesWith(OV);
BO->eraseFromParent();
Cmp->eraseFromParent();
+ return true;
}
/// Try to combine the compare into a call to the llvm.uadd.with.overflow
/// intrinsic. Return true if any changes were made.
static bool combineToUAddWithOverflow(CmpInst *Cmp, const TargetLowering &TLI,
- const DataLayout &DL) {
+ const DataLayout &DL, bool &ModifiedDT) {
Value *A, *B;
BinaryOperator *Add;
if (!match(Cmp, m_UAddWithOverflow(m_Value(A), m_Value(B), m_BinOp(Add))))
@@ -1208,9 +1223,11 @@
assert(*Add->user_begin() == Cmp && "expected!");
#endif
- Instruction *InPt = Add->hasOneUse() ? cast<Instruction>(Cmp)
- : cast<Instruction>(Add);
- replaceMathCmpWithIntrinsic(Add, Cmp, InPt, Intrinsic::uadd_with_overflow);
+ if (!replaceMathCmpWithIntrinsic(Add, Cmp, Intrinsic::uadd_with_overflow))
+ return false;
+
+ // Reset callers - do not crash by iterating over a dead instruction.
+ ModifiedDT = true;
return true;
}
@@ -1263,15 +1280,9 @@
TLI.getValueType(DL, Sub->getType())))
return false;
- // Pattern matched and profitability checked. Check dominance to determine the
- // insertion point for an intrinsic that replaces the subtract and compare.
- DominatorTree DT(*Sub->getFunction());
- bool SubDominates = DT.dominates(Sub, Cmp);
- if (!SubDominates && !DT.dominates(Cmp, Sub))
+ if (!replaceMathCmpWithIntrinsic(Sub, Cmp, Intrinsic::usub_with_overflow))
return false;
- Instruction *InPt = SubDominates ? cast<Instruction>(Sub)
- : cast<Instruction>(Cmp);
- replaceMathCmpWithIntrinsic(Sub, Cmp, InPt, Intrinsic::usub_with_overflow);
+
// Reset callers - do not crash by iterating over a dead instruction.
ModifiedDT = true;
return true;
@@ -1348,7 +1359,7 @@
if (sinkCmpExpression(Cmp, TLI))
return true;
- if (combineToUAddWithOverflow(Cmp, TLI, DL))
+ if (combineToUAddWithOverflow(Cmp, TLI, DL, ModifiedDT))
return true;
if (combineToUSubWithOverflow(Cmp, TLI, DL, ModifiedDT))
