diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp --- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp +++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp @@ -1832,6 +1832,15 @@ auto NewPred = TrueIfNeg ? CmpInst::ICMP_EQ : CmpInst::ICMP_NE; return new ICmpInst(NewPred, X, ConstantInt::getNullValue(X->getType())); } + // (X & X) < 0 --> X == MinSignedC + // (X & X) > -1 --> X != MinSignedC + if (match(And, m_c_And(m_Neg(m_Value(X)), m_Deferred(X)))) { + Constant *MinSignedC = ConstantInt::get( + X->getType(), + APInt::getSignedMinValue(X->getType()->getScalarSizeInBits())); + auto NewPred = TrueIfNeg ? CmpInst::ICMP_EQ : CmpInst::ICMP_NE; + return new ICmpInst(NewPred, X, MinSignedC); + } } // TODO: These all require that Y is constant too, so refactor with the above. diff --git a/llvm/test/Transforms/InstCombine/fold-signbit-test-power2.ll b/llvm/test/Transforms/InstCombine/fold-signbit-test-power2.ll --- a/llvm/test/Transforms/InstCombine/fold-signbit-test-power2.ll +++ b/llvm/test/Transforms/InstCombine/fold-signbit-test-power2.ll @@ -1,56 +1,60 @@ ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt < %s -passes=instcombine -S | FileCheck %s -; icmp slt (and X, -X), 0 --> icmp eq (X, MinSignC) -define i1 @pow2_or_zero1(i8 %x) { -; CHECK-LABEL: @pow2_or_zero1( -; CHECK-NEXT: [[NEG:%.*]] = sub i8 0, [[X:%.*]] -; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and i8 [[NEG]], [[X]] -; CHECK-NEXT: [[CMP:%.*]] = icmp slt i8 [[POW2_OR_ZERO]], 0 +declare void @use(i8) +declare void @use_i1(i1) +declare void @use_i1_vec(<2 x i1>) + +; (X & -X) < 0 --> X == MinSignC +; (X & X) > -1 --> X != MinSignC + +define i1 @pow2_or_zero_is_negative(i8 %x) { +; CHECK-LABEL: @pow2_or_zero_is_negative( +; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8 [[X:%.*]], -128 +; CHECK-NEXT: [[CMP_2:%.*]] = icmp eq i8 [[X]], -128 +; CHECK-NEXT: call void @use_i1(i1 [[CMP_2]]) ; CHECK-NEXT: ret i1 [[CMP]] ; %neg = sub i8 0, %x %pow2_or_zero = and i8 %x, %neg %cmp = icmp slt i8 %pow2_or_zero, 0 + %cmp.2 = icmp ugt i8 %pow2_or_zero, 127 + call void @use_i1(i1 %cmp.2) ret i1 %cmp } -; icmp slt (and -X, X), 0 --> icmp eq (X, MinSignC) -define i1 @pow2_or_zero1_commute(i8 %A) { -; CHECK-LABEL: @pow2_or_zero1_commute( -; CHECK-NEXT: [[X:%.*]] = sdiv i8 42, [[A:%.*]] -; CHECK-NEXT: [[NEG:%.*]] = sub nsw i8 0, [[X]] -; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and i8 [[X]], [[NEG]] -; CHECK-NEXT: [[CMP:%.*]] = icmp slt i8 [[POW2_OR_ZERO]], 0 +define i1 @pow2_or_zero_is_negative_commute(i8 %A) { +; CHECK-LABEL: @pow2_or_zero_is_negative_commute( +; CHECK-NEXT: [[X:%.*]] = mul i8 [[A:%.*]], 42 +; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8 [[X]], -128 ; CHECK-NEXT: ret i1 [[CMP]] ; - %x = sdiv i8 42, %A ; thwart complexity-based canonicalization + %x = mul i8 42, %A ; thwart complexity-based canonicalization %neg = sub i8 0, %x %pow2_or_zero = and i8 %neg, %x %cmp = icmp slt i8 %pow2_or_zero, 0 ret i1 %cmp } -define <2 x i1> @pow2_or_zero1_vec(<2 x i8> %x) { -; CHECK-LABEL: @pow2_or_zero1_vec( -; CHECK-NEXT: [[NEG:%.*]] = sub <2 x i8> zeroinitializer, [[X:%.*]] -; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and <2 x i8> [[NEG]], [[X]] -; CHECK-NEXT: [[CMP:%.*]] = icmp slt <2 x i8> [[POW2_OR_ZERO]], zeroinitializer +define <2 x i1> @pow2_or_zero_is_negative_vec(<2 x i8> %x) { +; CHECK-LABEL: @pow2_or_zero_is_negative_vec( +; CHECK-NEXT: [[CMP:%.*]] = icmp eq <2 x i8> [[X:%.*]], +; CHECK-NEXT: [[CMP_2:%.*]] = icmp eq <2 x i8> [[X]], +; CHECK-NEXT: call void @use_i1_vec(<2 x i1> [[CMP_2]]) ; CHECK-NEXT: ret <2 x i1> [[CMP]] ; %neg = sub <2 x i8> , %x %pow2_or_zero = and <2 x i8> %x, %neg %cmp = icmp slt <2 x i8> %pow2_or_zero, + %cmp.2 = icmp ugt <2 x i8> %pow2_or_zero, + call void @use_i1_vec(<2 x i1> %cmp.2) ret <2 x i1> %cmp } - -define <2 x i1> @pow2_or_zero1_vec_commute(<2 x i8> %A) { -; CHECK-LABEL: @pow2_or_zero1_vec_commute( +define <2 x i1> @pow2_or_zero_is_negative_vec_commute(<2 x i8> %A) { +; CHECK-LABEL: @pow2_or_zero_is_negative_vec_commute( ; CHECK-NEXT: [[X:%.*]] = mul <2 x i8> [[A:%.*]], -; CHECK-NEXT: [[NEG:%.*]] = sub <2 x i8> zeroinitializer, [[X]] -; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and <2 x i8> [[X]], [[NEG]] -; CHECK-NEXT: [[CMP:%.*]] = icmp slt <2 x i8> [[POW2_OR_ZERO]], zeroinitializer +; CHECK-NEXT: [[CMP:%.*]] = icmp eq <2 x i8> [[X]], ; CHECK-NEXT: ret <2 x i1> [[CMP]] ; %x = mul <2 x i8> , %A ; thwart complexity-based canonicalization @@ -60,27 +64,25 @@ ret <2 x i1> %cmp } -; icmp sgt (and X, -X), -1 --> icmp ne (X, MinSignC) -define i1 @pow2_or_zero2(i8 %x) { -; CHECK-LABEL: @pow2_or_zero2( -; CHECK-NEXT: [[NEG:%.*]] = sub i8 0, [[X:%.*]] -; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and i8 [[NEG]], [[X]] -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i8 [[POW2_OR_ZERO]], -1 +define i1 @pow2_or_zero_is_not_negative(i8 %x) { +; CHECK-LABEL: @pow2_or_zero_is_not_negative( +; CHECK-NEXT: [[CMP:%.*]] = icmp ne i8 [[X:%.*]], -128 +; CHECK-NEXT: [[CMP_2:%.*]] = icmp ne i8 [[X]], -128 +; CHECK-NEXT: call void @use_i1(i1 [[CMP_2]]) ; CHECK-NEXT: ret i1 [[CMP]] ; %neg = sub i8 0, %x %pow2_or_zero = and i8 %x, %neg %cmp = icmp sgt i8 %pow2_or_zero, -1 + %cmp.2 = icmp ult i8 %pow2_or_zero, -128 + call void @use_i1(i1 %cmp.2) ret i1 %cmp } -; icmp sgt (and -X, X), -1 --> icmp ne (X, MinSignC) -define i1 @pow2_or_zero2_commute(i8 %A) { -; CHECK-LABEL: @pow2_or_zero2_commute( +define i1 @pow2_or_zero_is_not_negative_commute(i8 %A) { +; CHECK-LABEL: @pow2_or_zero_is_not_negative_commute( ; CHECK-NEXT: [[X:%.*]] = mul i8 [[A:%.*]], 42 -; CHECK-NEXT: [[NEG:%.*]] = sub i8 0, [[X]] -; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and i8 [[X]], [[NEG]] -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i8 [[POW2_OR_ZERO]], -1 +; CHECK-NEXT: [[CMP:%.*]] = icmp ne i8 [[X]], -128 ; CHECK-NEXT: ret i1 [[CMP]] ; %x = mul i8 42, %A ; thwart complexity-based canonicalization @@ -90,25 +92,25 @@ ret i1 %cmp } -define <2 x i1> @pow2_or_zero2_vec(<2 x i8> %x) { -; CHECK-LABEL: @pow2_or_zero2_vec( -; CHECK-NEXT: [[NEG:%.*]] = sub <2 x i8> zeroinitializer, [[X:%.*]] -; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and <2 x i8> [[NEG]], [[X]] -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt <2 x i8> [[POW2_OR_ZERO]], +define <2 x i1> @pow2_or_zero_is_not_negative_vec(<2 x i8> %x) { +; CHECK-LABEL: @pow2_or_zero_is_not_negative_vec( +; CHECK-NEXT: [[CMP:%.*]] = icmp ne <2 x i8> [[X:%.*]], +; CHECK-NEXT: [[CMP_2:%.*]] = icmp ne <2 x i8> [[X]], +; CHECK-NEXT: call void @use_i1_vec(<2 x i1> [[CMP_2]]) ; CHECK-NEXT: ret <2 x i1> [[CMP]] ; %neg = sub <2 x i8> , %x %pow2_or_zero = and <2 x i8> %x, %neg %cmp = icmp sgt <2 x i8> %pow2_or_zero, + %cmp.2 = icmp ult <2 x i8> %pow2_or_zero, + call void @use_i1_vec(<2 x i1> %cmp.2) ret <2 x i1> %cmp } -define <2 x i1> @pow2_or_zero2_vec_commute(<2 x i8> %A) { -; CHECK-LABEL: @pow2_or_zero2_vec_commute( +define <2 x i1> @pow2_or_zero_is_not_negative_vec_commute(<2 x i8> %A) { +; CHECK-LABEL: @pow2_or_zero_is_not_negative_vec_commute( ; CHECK-NEXT: [[X:%.*]] = mul <2 x i8> [[A:%.*]], -; CHECK-NEXT: [[NEG:%.*]] = sub <2 x i8> zeroinitializer, [[X]] -; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and <2 x i8> [[X]], [[NEG]] -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt <2 x i8> [[POW2_OR_ZERO]], +; CHECK-NEXT: [[CMP:%.*]] = icmp ne <2 x i8> [[X]], ; CHECK-NEXT: ret <2 x i1> [[CMP]] ; %x = mul <2 x i8> , %A ; thwart complexity-based canonicalization @@ -117,3 +119,20 @@ %cmp = icmp sgt <2 x i8> %pow2_or_zero, ret <2 x i1> %cmp } + +define i1 @pow2_or_zero_is_negative_extra_use(i8 %x) { +; CHECK-LABEL: @pow2_or_zero_is_negative_extra_use( +; CHECK-NEXT: [[NEG:%.*]] = sub i8 0, [[X:%.*]] +; CHECK-NEXT: call void @use(i8 [[NEG]]) +; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and i8 [[NEG]], [[X]] +; CHECK-NEXT: call void @use(i8 [[POW2_OR_ZERO]]) +; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8 [[X]], -128 +; CHECK-NEXT: ret i1 [[CMP]] +; + %neg = sub i8 0, %x + call void @use(i8 %neg) + %pow2_or_zero = and i8 %x, %neg + call void @use(i8 %pow2_or_zero) + %cmp = icmp slt i8 %pow2_or_zero, 0 + ret i1 %cmp +} diff --git a/llvm/test/Transforms/InstCombine/minmax-of-xor-x.ll b/llvm/test/Transforms/InstCombine/minmax-of-xor-x.ll --- a/llvm/test/Transforms/InstCombine/minmax-of-xor-x.ll +++ b/llvm/test/Transforms/InstCombine/minmax-of-xor-x.ll @@ -134,12 +134,13 @@ define i8 @smax_xor_pow2_neg(i8 %x, i8 %y) { ; CHECK-LABEL: @smax_xor_pow2_neg( -; CHECK-NEXT: [[NY:%.*]] = sub i8 0, [[Y:%.*]] -; CHECK-NEXT: [[YP2:%.*]] = and i8 [[NY]], [[Y]] -; CHECK-NEXT: [[CMP:%.*]] = icmp slt i8 [[YP2]], 0 +; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8 [[Y:%.*]], -128 ; CHECK-NEXT: br i1 [[CMP]], label [[NEG:%.*]], label [[POS:%.*]] ; CHECK: neg: -; CHECK-NEXT: [[R:%.*]] = and i8 [[X:%.*]], 127 +; CHECK-NEXT: [[NY:%.*]] = sub i8 0, [[Y]] +; CHECK-NEXT: [[YP2:%.*]] = and i8 [[NY]], [[Y]] +; CHECK-NEXT: [[X_XOR:%.*]] = xor i8 [[YP2]], [[X:%.*]] +; CHECK-NEXT: [[R:%.*]] = call i8 @llvm.smax.i8(i8 [[X]], i8 [[X_XOR]]) ; CHECK-NEXT: ret i8 [[R]] ; CHECK: pos: ; CHECK-NEXT: call void @barrier()