Index: lib/Transforms/InstCombine/InstCombineCalls.cpp =================================================================== --- lib/Transforms/InstCombine/InstCombineCalls.cpp +++ lib/Transforms/InstCombine/InstCombineCalls.cpp @@ -1133,7 +1133,10 @@ return nullptr; } -static Value *foldCttzCtlz(IntrinsicInst &II, InstCombiner &IC) { +static Instruction *foldCttzCtlz(IntrinsicInst &II, InstCombiner &IC) { + assert((II.getIntrinsicID() == Intrinsic::cttz || + II.getIntrinsicID() == Intrinsic::ctlz) && + "Expected cttz or ctlz intrinsic"); Value *Op0 = II.getArgOperand(0); // FIXME: Try to simplify vectors of integers. auto *IT = dyn_cast(Op0->getType()); @@ -1156,8 +1159,20 @@ // zero, this value is constant. // FIXME: This should be in InstSimplify because we're replacing an // instruction with a constant. - if ((Mask & KnownZero) == Mask) - return ConstantInt::get(IT, APInt(BitWidth, NumMaskBits)); + if ((Mask & KnownZero) == Mask) { + auto *C = ConstantInt::get(IT, APInt(BitWidth, NumMaskBits)); + return IC.replaceInstUsesWith(II, C); + } + + // If the input to cttz/ctlz is known to be non-zero, + // then change the 'ZeroIsUndef' parameter to 'true' + // because we know the zero behavior can't affect the result. + if (KnownOne != 0 || isKnownNonZero(Op0, IC.getDataLayout())) { + if (!match(II.getArgOperand(1), m_One())) { + II.setOperand(1, IC.Builder->getTrue()); + return ⅈ + } + } return nullptr; } @@ -1457,8 +1472,8 @@ case Intrinsic::cttz: case Intrinsic::ctlz: - if (Value *V = foldCttzCtlz(*II, *this)) - return replaceInstUsesWith(*II, V); + if (auto *I = foldCttzCtlz(*II, *this)) + return I; break; case Intrinsic::uadd_with_overflow: Index: test/Transforms/InstCombine/intrinsics.ll =================================================================== --- test/Transforms/InstCombine/intrinsics.ll +++ test/Transforms/InstCombine/intrinsics.ll @@ -380,6 +380,16 @@ } +define i32 @ctlz_make_undef(i32 %a) { + %or = or i32 %a, 8 + %ctlz = tail call i32 @llvm.ctlz.i32(i32 %or, i1 false) + ret i32 %ctlz +; CHECK-LABEL: @ctlz_make_undef( +; CHECK-NEXT: %or = or i32 %a, 8 +; CHECK-NEXT: %ctlz = tail call i32 @llvm.ctlz.i32(i32 %or, i1 true) +; CHECK-NEXT: ret i32 %ctlz +} + define i32 @cttz_undef(i32 %Value) nounwind { ; CHECK-LABEL: @cttz_undef( ; CHECK-NEXT: ret i32 undef @@ -389,6 +399,16 @@ } +define i32 @cttz_make_undef(i32 %a) { + %or = or i32 %a, 8 + %cttz = tail call i32 @llvm.cttz.i32(i32 %or, i1 false) + ret i32 %cttz +; CHECK-LABEL: @cttz_make_undef( +; CHECK-NEXT: %or = or i32 %a, 8 +; CHECK-NEXT: %cttz = tail call i32 @llvm.cttz.i32(i32 %or, i1 true) +; CHECK-NEXT: ret i32 %cttz +} + define i32 @ctlz_select(i32 %Value) nounwind { ; CHECK-LABEL: @ctlz_select( ; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.ctlz.i32(i32 %Value, i1 false)