InsertedCast =
CastInst::Create(CI->getOpcode(), CI->getOperand(0), CI->getType(), "",
InsertPt);
- MadeChange = true;
}
// Replace a use of the cast with a use of the new cast.
TheUse = InsertedCast;
+ MadeChange = true;
++NumCastUses;
}
return SinkCast(CI);
}
-/// OptimizeCmpExpression - sink the given CmpInst into user blocks to reduce
+/// CombineUAddWithOverflow - try to combine CI into a call to the
+/// llvm.uadd.with.overflow intrinsic if possible.
+///
+/// Return true if any changes were made.
+static bool CombineUAddWithOverflow(CmpInst *CI) {
+ Value *A, *B;
+ Instruction *AddI;
+ if (!match(CI,
+ m_UAddWithOverflow(m_Value(A), m_Value(B), m_Instruction(AddI))))
+ return false;
+
+ Type *Ty = AddI->getType();
+ if (!isa<IntegerType>(Ty))
+ return false;
+
+ // We don't want to move around uses of condition values this late, so we we
+ // check if it is legal to create the call to the intrinsic in the basic
+ // block containing the icmp:
+
+ if (AddI->getParent() != CI->getParent() && !AddI->hasOneUse())
+ return false;
+
+#ifndef NDEBUG
+ // Someday m_UAddWithOverflow may get smarter, but this is a safe assumption
+ // for now:
+ if (AddI->hasOneUse())
+ assert(*AddI->user_begin() == CI && "expected!");
+#endif
+
+ Module *M = CI->getParent()->getParent()->getParent();
+ Value *F = Intrinsic::getDeclaration(M, Intrinsic::uadd_with_overflow, Ty);
+
+ auto *InsertPt = AddI->hasOneUse() ? CI : AddI;
+
+ auto *UAddWithOverflow =
+ CallInst::Create(F, {A, B}, "uadd.overflow", InsertPt);
+ auto *UAdd = ExtractValueInst::Create(UAddWithOverflow, 0, "uadd", InsertPt);
+ auto *Overflow =
+ ExtractValueInst::Create(UAddWithOverflow, 1, "overflow", InsertPt);
+
+ CI->replaceAllUsesWith(Overflow);
+ AddI->replaceAllUsesWith(UAdd);
+ CI->eraseFromParent();
+ AddI->eraseFromParent();
+ return true;
+}
+
+/// SinkCmpExpression - Sink the given CmpInst into user blocks to reduce
/// the number of virtual registers that must be created and coalesced. This is
/// a clear win except on targets with multiple condition code registers
/// (PowerPC), where it might lose; some adjustment may be wanted there.
///
/// Return true if any changes are made.
-static bool OptimizeCmpExpression(CmpInst *CI) {
+static bool SinkCmpExpression(CmpInst *CI) {
BasicBlock *DefBB = CI->getParent();
/// InsertedCmp - Only insert a cmp in each block once.
CmpInst::Create(CI->getOpcode(),
CI->getPredicate(), CI->getOperand(0),
CI->getOperand(1), "", InsertPt);
- MadeChange = true;
}
// Replace a use of the cmp with a use of the new cmp.
TheUse = InsertedCmp;
+ MadeChange = true;
++NumCmpUses;
}
// If we removed all uses, nuke the cmp.
- if (CI->use_empty())
+ if (CI->use_empty()) {
CI->eraseFromParent();
+ MadeChange = true;
+ }
return MadeChange;
}
+static bool OptimizeCmpExpression(CmpInst *CI) {
+ if (SinkCmpExpression(CI))
+ return true;
+
+ if (CombineUAddWithOverflow(CI))
+ return true;
+
+ return false;
+}
+
/// isExtractBitsCandidateUse - Check if the candidates could
/// be combined with shift instruction, which includes:
/// 1. Truncate instruction
//
CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.load");
Builder.SetInsertPoint(InsertPt);
-
- Value* Gep = Builder.CreateInBoundsGEP(FirstEltPtr, Builder.getInt32(Idx));
+
+ Value *Gep =
+ Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
LoadInst* Load = Builder.CreateLoad(Gep, false);
VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx));
Builder.SetInsertPoint(InsertPt);
Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
- Value* Gep = Builder.CreateInBoundsGEP(FirstEltPtr, Builder.getInt32(Idx));
+ Value *Gep =
+ Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
Builder.CreateStore(OneElt, Gep);
// Create "else" block, fill it in the next iteration
Inst->removeFromParent();
}
- ~InstructionRemover() { delete Replacer; }
+ ~InstructionRemover() override { delete Replacer; }
/// \brief Really remove the instruction.
void commit() override { delete Inst; }
return false;
} else {
Type *I8PtrTy =
- Builder.getInt8PtrTy(Addr->getType()->getPointerAddressSpace());
+ Builder.getInt8PtrTy(Addr->getType()->getPointerAddressSpace());
+ Type *I8Ty = Builder.getInt8Ty();
// Start with the base register. Do this first so that subsequent address
// matching finds it last, which will prevent it from trying to match it
// SDAG consecutive load/store merging.
if (ResultPtr->getType() != I8PtrTy)
ResultPtr = Builder.CreateBitCast(ResultPtr, I8PtrTy);
- ResultPtr = Builder.CreateGEP(ResultPtr, ResultIndex, "sunkaddr");
+ ResultPtr = Builder.CreateGEP(I8Ty, ResultPtr, ResultIndex, "sunkaddr");
}
ResultIndex = V;
} else {
if (ResultPtr->getType() != I8PtrTy)
ResultPtr = Builder.CreateBitCast(ResultPtr, I8PtrTy);
- SunkAddr = Builder.CreateGEP(ResultPtr, ResultIndex, "sunkaddr");
+ SunkAddr = Builder.CreateGEP(I8Ty, ResultPtr, ResultIndex, "sunkaddr");
}
if (SunkAddr->getType() != Addr->getType())