Index: lib/Transforms/InstCombine/InstCombineAndOrXor.cpp =================================================================== --- lib/Transforms/InstCombine/InstCombineAndOrXor.cpp +++ lib/Transforms/InstCombine/InstCombineAndOrXor.cpp @@ -2923,15 +2923,19 @@ Value *LHS, *RHS; SelectPatternFlavor SPF = matchSelectPattern(Op0, LHS, RHS).Flavor; if (SelectPatternResult::isMinOrMax(SPF)) { - Value *X; - if (match(RHS, m_Not(m_Value(X)))) - std::swap(RHS, LHS); - - if (match(LHS, m_Not(m_Value(X)))) { + if (match(LHS, m_Not(m_Value(X))) && + !IsFreeToInvert(X, X->hasOneUse())) { Value *NotY = Builder.CreateNot(RHS); return SelectInst::Create( Builder.CreateICmp(getInverseMinMaxPred(SPF), X, NotY), X, NotY); } + + if (match(RHS, m_Not(m_Value(Y))) && + !IsFreeToInvert(Y, Y->hasOneUse())) { + Value *NotX = Builder.CreateNot(LHS); + return SelectInst::Create( + Builder.CreateICmp(getInverseMinMaxPred(SPF), NotX, Y), NotX, Y); + } } } Index: lib/Transforms/InstCombine/InstCombineSelect.cpp =================================================================== --- lib/Transforms/InstCombine/InstCombineSelect.cpp +++ lib/Transforms/InstCombine/InstCombineSelect.cpp @@ -1821,14 +1821,27 @@ // MAX(~a, ~b) -> ~MIN(a, b) // MIN(~a, ~b) -> ~MAX(a, b) Value *A, *B; - if (match(LHS, m_Not(m_Value(A))) && match(RHS, m_Not(m_Value(B))) && - (!LHS->hasNUsesOrMore(3) || !RHS->hasNUsesOrMore(3))) { + if (match(LHS, m_Not(m_Value(A))) && !LHS->hasNUsesOrMore(3) && + // Passing false to only consider m_Not and constants. + IsFreeToInvert(RHS, false)) { CmpInst::Predicate InvertedPred = getInverseMinMaxPred(SPF); + B = Builder.CreateNot(RHS); Value *InvertedCmp = Builder.CreateICmp(InvertedPred, A, B); Value *NewSel = Builder.CreateSelect(InvertedCmp, A, B); return BinaryOperator::CreateNot(NewSel); } + if (match(RHS, m_Not(m_Value(B))) && !RHS->hasNUsesOrMore(3) && + // Passing false to only consider m_Not and constants. + IsFreeToInvert(LHS, false)) { + CmpInst::Predicate InvertedPred = getInverseMinMaxPred(SPF); + A = Builder.CreateNot(LHS); + Value *InvertedCmp = Builder.CreateICmp(InvertedPred, A, B); + Value *NewSel = Builder.CreateSelect(InvertedCmp, A, B); + return BinaryOperator::CreateNot(NewSel); + } + + if (Instruction *I = factorizeMinMaxTree(SPF, LHS, RHS, Builder)) return I; } Index: test/Transforms/InstCombine/max-of-nots.ll =================================================================== --- test/Transforms/InstCombine/max-of-nots.ll +++ test/Transforms/InstCombine/max-of-nots.ll @@ -3,7 +3,7 @@ define <2 x i32> @umin_of_nots(<2 x i32> %x, <2 x i32> %y) { ; CHECK-LABEL: @umin_of_nots( -; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt <2 x i32> [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[TMP1:%.*]] = icmp ult <2 x i32> [[Y:%.*]], [[X:%.*]] ; CHECK-NEXT: [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> [[X]], <2 x i32> [[Y]] ; CHECK-NEXT: [[MIN:%.*]] = xor <2 x i32> [[TMP2]], ; CHECK-NEXT: ret <2 x i32> [[MIN]] @@ -17,7 +17,7 @@ define <2 x i32> @smin_of_nots(<2 x i32> %x, <2 x i32> %y) { ; CHECK-LABEL: @smin_of_nots( -; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt <2 x i32> [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[TMP1:%.*]] = icmp slt <2 x i32> [[Y:%.*]], [[X:%.*]] ; CHECK-NEXT: [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> [[X]], <2 x i32> [[Y]] ; CHECK-NEXT: [[MIN:%.*]] = xor <2 x i32> [[TMP2]], ; CHECK-NEXT: ret <2 x i32> [[MIN]] @@ -31,7 +31,7 @@ define i32 @compute_min_2(i32 %x, i32 %y) { ; CHECK-LABEL: @compute_min_2( -; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[Y:%.*]], [[X:%.*]] ; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 [[Y]] ; CHECK-NEXT: ret i32 [[TMP2]] ; @@ -84,7 +84,7 @@ define i8 @umin3_not(i8 %x, i8 %y, i8 %z) { ; CHECK-LABEL: @umin3_not( -; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i8 [[X:%.*]], [[Z:%.*]] +; CHECK-NEXT: [[TMP1:%.*]] = icmp ult i8 [[Z:%.*]], [[X:%.*]] ; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i8 [[X]], i8 [[Z]] ; CHECK-NEXT: [[TMP3:%.*]] = icmp ugt i8 [[TMP2]], [[Y:%.*]] ; CHECK-NEXT: [[R_V:%.*]] = select i1 [[TMP3]], i8 [[TMP2]], i8 [[Y]] @@ -198,7 +198,7 @@ define i32 @compute_min_3(i32 %x, i32 %y, i32 %z) { ; CHECK-LABEL: @compute_min_3( -; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[Y:%.*]], [[X:%.*]] ; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 [[Y]] ; CHECK-NEXT: [[TMP3:%.*]] = icmp slt i32 [[TMP2]], [[Z:%.*]] ; CHECK-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], i32 [[TMP2]], i32 [[Z]] @@ -239,8 +239,8 @@ ; CHECK-NEXT: [[NOT_VALUE:%.*]] = sub i32 3, [[X:%.*]] ; CHECK-NEXT: call void @fake_use(i32 [[NOT_VALUE]]) ; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[X]], -4 -; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt i32 [[TMP1]], [[Y:%.*]] -; CHECK-NEXT: [[MIN:%.*]] = select i1 [[TMP2]], i32 [[Y]], i32 [[TMP1]] +; CHECK-NEXT: [[TMP2:%.*]] = icmp slt i32 [[TMP1]], [[Y:%.*]] +; CHECK-NEXT: [[MIN:%.*]] = select i1 [[TMP2]], i32 [[TMP1]], i32 [[Y]] ; CHECK-NEXT: ret i32 [[MIN]] ; %not_value = sub i32 3, %x Index: test/Transforms/InstCombine/select.ll =================================================================== --- test/Transforms/InstCombine/select.ll +++ test/Transforms/InstCombine/select.ll @@ -1333,9 +1333,9 @@ define i32 @PR27137(i32 %a) { ; CHECK-LABEL: @PR27137( -; CHECK-NEXT: [[NOT_A:%.*]] = xor i32 [[A:%.*]], -1 -; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[NOT_A]], -1 -; CHECK-NEXT: [[S1:%.*]] = select i1 [[TMP1]], i32 [[NOT_A]], i32 -1 +; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 [[A:%.*]], 0 +; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[A]], i32 0 +; CHECK-NEXT: [[S1:%.*]] = xor i32 [[TMP2]], -1 ; CHECK-NEXT: ret i32 [[S1]] ; %not_a = xor i32 %a, -1 Index: test/Transforms/InstCombine/select_meta.ll =================================================================== --- test/Transforms/InstCombine/select_meta.ll +++ test/Transforms/InstCombine/select_meta.ll @@ -194,12 +194,12 @@ ret i32 %retval } -; The compare should change, but the metadata remains the same because the select operands are not swapped. +; FIXME: Should we preserve the metadata here when we push the not through? define i32 @smin1(i32 %x) { ; CHECK-LABEL: @smin1( -; CHECK-NEXT: [[NOT_X:%.*]] = xor i32 %x, -1 -; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[NOT_X]], -1 -; CHECK-NEXT: [[SEL:%.*]] = select i1 [[CMP]], i32 [[NOT_X]], i32 -1, !prof ![[$MD1]] +; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[X:%.*]], 0 +; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 0 +; CHECK-NEXT: [[SEL:%.*]] = xor i32 [[TMP2]], -1 ; CHECK-NEXT: ret i32 [[SEL]] ; %not_x = xor i32 %x, -1 @@ -211,9 +211,9 @@ ; The compare should change, and the metadata is swapped because the select operands are swapped. define i32 @smin2(i32 %x) { ; CHECK-LABEL: @smin2( -; CHECK-NEXT: [[NOT_X:%.*]] = xor i32 %x, -1 -; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[NOT_X]], -1 -; CHECK-NEXT: [[SEL:%.*]] = select i1 [[CMP]], i32 [[NOT_X]], i32 -1, !prof ![[$MD3]] +; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[X:%.*]], 0 +; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 0 +; CHECK-NEXT: [[SEL:%.*]] = xor i32 [[TMP2]], -1 ; CHECK-NEXT: ret i32 [[SEL]] ; %not_x = xor i32 %x, -1 @@ -225,9 +225,9 @@ ; The compare should change, but the metadata remains the same because the select operands are not swapped. define i32 @smax1(i32 %x) { ; CHECK-LABEL: @smax1( -; CHECK-NEXT: [[NOT_X:%.*]] = xor i32 %x, -1 -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i32 [[NOT_X]], -1 -; CHECK-NEXT: [[SEL:%.*]] = select i1 [[CMP]], i32 [[NOT_X]], i32 -1, !prof ![[$MD1]] +; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 [[X:%.*]], 0 +; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 0 +; CHECK-NEXT: [[SEL:%.*]] = xor i32 [[TMP2]], -1 ; CHECK-NEXT: ret i32 [[SEL]] ; %not_x = xor i32 %x, -1 @@ -239,9 +239,9 @@ ; The compare should change, and the metadata is swapped because the select operands are swapped. define i32 @smax2(i32 %x) { ; CHECK-LABEL: @smax2( -; CHECK-NEXT: [[NOT_X:%.*]] = xor i32 %x, -1 -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i32 [[NOT_X]], -1 -; CHECK-NEXT: [[SEL:%.*]] = select i1 [[CMP]], i32 [[NOT_X]], i32 -1, !prof ![[$MD3]] +; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 [[X:%.*]], 0 +; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 0 +; CHECK-NEXT: [[SEL:%.*]] = xor i32 [[TMP2]], -1 ; CHECK-NEXT: ret i32 [[SEL]] ; %not_x = xor i32 %x, -1 Index: test/Transforms/InstCombine/sub.ll =================================================================== --- test/Transforms/InstCombine/sub.ll +++ test/Transforms/InstCombine/sub.ll @@ -1056,3 +1056,90 @@ %D = sub <2 x i32> , %C ret <2 x i32> %D } + +; Tests for (neg (max ~X, C)) -> ((min X, ~C) + 1). Same for min. +define i32 @test64(i32 %x) { +; CHECK-LABEL: @test64( +; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 [[X:%.*]], 255 +; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 255 +; CHECK-NEXT: [[RES:%.*]] = add i32 [[TMP2]], 1 +; CHECK-NEXT: ret i32 [[RES]] +; + %1 = xor i32 %x, -1 + %2 = icmp sgt i32 %1, -256 + %3 = select i1 %2, i32 %1, i32 -256 + %res = sub i32 0, %3 + ret i32 %res +} + +define i32 @test65(i32 %x) { +; CHECK-LABEL: @test65( +; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[X:%.*]], -256 +; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 -256 +; CHECK-NEXT: [[RES:%.*]] = add i32 [[TMP2]], 1 +; CHECK-NEXT: ret i32 [[RES]] +; + %1 = xor i32 %x, -1 + %2 = icmp slt i32 %1, 255 + %3 = select i1 %2, i32 %1, i32 255 + %res = sub i32 0, %3 + ret i32 %res +} + +define i32 @test66(i32 %x) { +; CHECK-LABEL: @test66( +; CHECK-NEXT: [[TMP1:%.*]] = icmp ult i32 [[X:%.*]], -101 +; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 -101 +; CHECK-NEXT: [[RES:%.*]] = add i32 [[TMP2]], 1 +; CHECK-NEXT: ret i32 [[RES]] +; + %1 = xor i32 %x, -1 + %2 = icmp ugt i32 %1, 100 + %3 = select i1 %2, i32 %1, i32 100 + %res = sub i32 0, %3 + ret i32 %res +} + +define i32 @test67(i32 %x) { +; CHECK-LABEL: @test67( +; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[X:%.*]], 100 +; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 100 +; CHECK-NEXT: [[RES:%.*]] = add i32 [[TMP2]], 1 +; CHECK-NEXT: ret i32 [[RES]] +; + %1 = xor i32 %x, -1 + %2 = icmp ult i32 %1, -101 + %3 = select i1 %2, i32 %1, i32 -101 + %res = sub i32 0, %3 + ret i32 %res +} + +; Check splat vectors too +define <2 x i32> @test68(<2 x i32> %x) { +; CHECK-LABEL: @test68( +; CHECK-NEXT: [[TMP1:%.*]] = icmp slt <2 x i32> [[X:%.*]], +; CHECK-NEXT: [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> [[X]], <2 x i32> +; CHECK-NEXT: [[RES:%.*]] = add <2 x i32> [[TMP2]], +; CHECK-NEXT: ret <2 x i32> [[RES]] +; + %1 = xor <2 x i32> %x, + %2 = icmp sgt <2 x i32> %1, + %3 = select <2 x i1> %2, <2 x i32> %1, <2 x i32> + %res = sub <2 x i32> zeroinitializer, %3 + ret <2 x i32> %res +} + +; And non-splat constant vectors. +define <2 x i32> @test69(<2 x i32> %x) { +; CHECK-LABEL: @test69( +; CHECK-NEXT: [[TMP1:%.*]] = icmp slt <2 x i32> [[X:%.*]], +; CHECK-NEXT: [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> [[X]], <2 x i32> +; CHECK-NEXT: [[RES:%.*]] = add <2 x i32> [[TMP2]], +; CHECK-NEXT: ret <2 x i32> [[RES]] +; + %1 = xor <2 x i32> %x, + %2 = icmp sgt <2 x i32> %1, + %3 = select <2 x i1> %2, <2 x i32> %1, <2 x i32> + %res = sub <2 x i32> zeroinitializer, %3 + ret <2 x i32> %res +} Index: test/Transforms/InstCombine/xor.ll =================================================================== --- test/Transforms/InstCombine/xor.ll +++ test/Transforms/InstCombine/xor.ll @@ -649,8 +649,8 @@ define i32 @test44(i32 %x, i32 %y) { ; CHECK-LABEL: @test44( ; CHECK-NEXT: [[TMP1:%.*]] = sub i32 -4, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = icmp ult i32 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[RES:%.*]] = select i1 [[TMP2]], i32 [[X]], i32 [[TMP1]] +; CHECK-NEXT: [[TMP2:%.*]] = icmp ugt i32 [[TMP1]], [[X:%.*]] +; CHECK-NEXT: [[RES:%.*]] = select i1 [[TMP2]], i32 [[TMP1]], i32 [[X]] ; CHECK-NEXT: ret i32 [[RES]] ; %z = add i32 %y, 3 ; thwart complexity-based canonicalization @@ -663,7 +663,7 @@ define i32 @test45(i32 %x, i32 %y) { ; CHECK-LABEL: @test45( -; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[Y:%.*]], [[X:%.*]] +; CHECK-NEXT: [[TMP1:%.*]] = icmp ult i32 [[X:%.*]], [[Y:%.*]] ; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[Y]], i32 [[X]] ; CHECK-NEXT: ret i32 [[TMP2]] ;