Index: llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp =================================================================== --- llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp +++ llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp @@ -1645,12 +1645,24 @@ return nullptr; if (Cmp.isEquality() && C1.isNullValue()) { + // Restrict this fold to single-use 'and' (PR10267). // Replace (and X, (1 << size(X)-1) != 0) with X s< 0 if (C2->isSignMask()) { Constant *Zero = Constant::getNullValue(X->getType()); auto NewPred = isICMP_NE ? ICmpInst::ICMP_SLT : ICmpInst::ICMP_SGE; return new ICmpInst(NewPred, X, Zero); } + + // Restrict this fold to single-use 'and' (PR10267). + // ((%x & C) == 0) --> %x u< (-C) iff (-C) is power of two. + // If X is (BinOp Y, C3), allow other rules to fold C3 with C2. + if (!match(X, m_c_BinOp(m_Value(), m_Constant())) && + (~(*C2) + 1).isPowerOf2()) { + Constant *NegBOC = + ConstantExpr::getNeg(cast(And->getOperand(1))); + auto NewPred = isICMP_NE ? ICmpInst::ICMP_UGE : ICmpInst::ICMP_ULT; + return new ICmpInst(NewPred, X, NegBOC); + } } // If the LHS is an 'and' of a truncate and we can widen the and/compare to @@ -2796,17 +2808,6 @@ if (C == *BOC && C.isPowerOf2()) return new ICmpInst(isICMP_NE ? ICmpInst::ICMP_EQ : ICmpInst::ICMP_NE, BO, Constant::getNullValue(RHS->getType())); - - // Don't perform the following transforms if the AND has multiple uses - if (!BO->hasOneUse()) - break; - - // ((X & ~7) == 0) --> X < 8 - if (C.isNullValue() && (~(*BOC) + 1).isPowerOf2()) { - Constant *NegBOC = ConstantExpr::getNeg(cast(BOp1)); - auto NewPred = isICMP_NE ? ICmpInst::ICMP_UGE : ICmpInst::ICMP_ULT; - return new ICmpInst(NewPred, BOp0, NegBOC); - } } break; } Index: llvm/test/Transforms/InstCombine/lshr-and-negC-icmpeq-zero.ll =================================================================== --- llvm/test/Transforms/InstCombine/lshr-and-negC-icmpeq-zero.ll +++ llvm/test/Transforms/InstCombine/lshr-and-negC-icmpeq-zero.ll @@ -9,9 +9,8 @@ define i1 @scalar_i8_lshr_and_negC_eq(i8 %x, i8 %y) { ; CHECK-LABEL: @scalar_i8_lshr_and_negC_eq( -; CHECK-NEXT: [[TMP1:%.*]] = shl i8 -4, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and i8 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp eq i8 [[TMP2]], 0 +; CHECK-NEXT: [[LSHR:%.*]] = lshr i8 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ult i8 [[LSHR]], 4 ; CHECK-NEXT: ret i1 [[R]] ; %lshr = lshr i8 %x, %y @@ -22,9 +21,8 @@ define i1 @scalar_i16_lshr_and_negC_eq(i16 %x, i16 %y) { ; CHECK-LABEL: @scalar_i16_lshr_and_negC_eq( -; CHECK-NEXT: [[TMP1:%.*]] = shl i16 -128, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and i16 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp eq i16 [[TMP2]], 0 +; CHECK-NEXT: [[LSHR:%.*]] = lshr i16 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ult i16 [[LSHR]], 128 ; CHECK-NEXT: ret i1 [[R]] ; %lshr = lshr i16 %x, %y @@ -35,9 +33,8 @@ define i1 @scalar_i32_lshr_and_negC_eq(i32 %x, i32 %y) { ; CHECK-LABEL: @scalar_i32_lshr_and_negC_eq( -; CHECK-NEXT: [[TMP1:%.*]] = shl i32 -262144, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and i32 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[TMP2]], 0 +; CHECK-NEXT: [[LSHR:%.*]] = lshr i32 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ult i32 [[LSHR]], 262144 ; CHECK-NEXT: ret i1 [[R]] ; %lshr = lshr i32 %x, %y @@ -48,9 +45,8 @@ define i1 @scalar_i64_lshr_and_negC_eq(i64 %x, i64 %y) { ; CHECK-LABEL: @scalar_i64_lshr_and_negC_eq( -; CHECK-NEXT: [[TMP1:%.*]] = shl i64 -8589934592, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and i64 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp eq i64 [[TMP2]], 0 +; CHECK-NEXT: [[LSHR:%.*]] = lshr i64 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ult i64 [[LSHR]], 8589934592 ; CHECK-NEXT: ret i1 [[R]] ; %lshr = lshr i64 %x, %y @@ -61,9 +57,8 @@ define i1 @scalar_i32_lshr_and_negC_ne(i32 %x, i32 %y) { ; CHECK-LABEL: @scalar_i32_lshr_and_negC_ne( -; CHECK-NEXT: [[TMP1:%.*]] = shl i32 -262144, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and i32 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp ne i32 [[TMP2]], 0 +; CHECK-NEXT: [[LSHR:%.*]] = lshr i32 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ugt i32 [[LSHR]], 262143 ; CHECK-NEXT: ret i1 [[R]] ; %lshr = lshr i32 %x, %y @@ -76,9 +71,8 @@ define <4 x i1> @vec_4xi32_lshr_and_negC_eq(<4 x i32> %x, <4 x i32> %y) { ; CHECK-LABEL: @vec_4xi32_lshr_and_negC_eq( -; CHECK-NEXT: [[TMP1:%.*]] = shl <4 x i32> , [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and <4 x i32> [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp eq <4 x i32> [[TMP2]], zeroinitializer +; CHECK-NEXT: [[LSHR:%.*]] = lshr <4 x i32> [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ult <4 x i32> [[LSHR]], ; CHECK-NEXT: ret <4 x i1> [[R]] ; %lshr = lshr <4 x i32> %x, %y @@ -190,7 +184,8 @@ define i1 @scalar_i32_lshr_and_negC_eq_X_is_constant1(i32 %y) { ; CHECK-LABEL: @scalar_i32_lshr_and_negC_eq_X_is_constant1( ; CHECK-NEXT: [[LSHR:%.*]] = lshr i32 12345, [[Y:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp ult i32 [[LSHR]], 8 +; CHECK-NEXT: [[AND:%.*]] = and i32 [[LSHR]], -8 +; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[AND]], 0 ; CHECK-NEXT: ret i1 [[R]] ; %lshr = lshr i32 12345, %y @@ -202,7 +197,8 @@ define i1 @scalar_i32_lshr_and_negC_eq_X_is_constant2(i32 %y) { ; CHECK-LABEL: @scalar_i32_lshr_and_negC_eq_X_is_constant2( ; CHECK-NEXT: [[LSHR:%.*]] = lshr i32 268435456, [[Y:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp ult i32 [[LSHR]], 8 +; CHECK-NEXT: [[AND:%.*]] = and i32 [[LSHR]], -8 +; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[AND]], 0 ; CHECK-NEXT: ret i1 [[R]] ; %lshr = lshr i32 268435456, %y Index: llvm/test/Transforms/InstCombine/shl-and-negC-icmpeq-zero.ll =================================================================== --- llvm/test/Transforms/InstCombine/shl-and-negC-icmpeq-zero.ll +++ llvm/test/Transforms/InstCombine/shl-and-negC-icmpeq-zero.ll @@ -9,9 +9,8 @@ define i1 @scalar_i8_shl_and_negC_eq(i8 %x, i8 %y) { ; CHECK-LABEL: @scalar_i8_shl_and_negC_eq( -; CHECK-NEXT: [[TMP1:%.*]] = lshr i8 -4, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and i8 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp eq i8 [[TMP2]], 0 +; CHECK-NEXT: [[SHL:%.*]] = shl i8 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ult i8 [[SHL]], 4 ; CHECK-NEXT: ret i1 [[R]] ; %shl = shl i8 %x, %y @@ -22,9 +21,8 @@ define i1 @scalar_i16_shl_and_negC_eq(i16 %x, i16 %y) { ; CHECK-LABEL: @scalar_i16_shl_and_negC_eq( -; CHECK-NEXT: [[TMP1:%.*]] = lshr i16 -128, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and i16 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp eq i16 [[TMP2]], 0 +; CHECK-NEXT: [[SHL:%.*]] = shl i16 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ult i16 [[SHL]], 128 ; CHECK-NEXT: ret i1 [[R]] ; %shl = shl i16 %x, %y @@ -35,9 +33,8 @@ define i1 @scalar_i32_shl_and_negC_eq(i32 %x, i32 %y) { ; CHECK-LABEL: @scalar_i32_shl_and_negC_eq( -; CHECK-NEXT: [[TMP1:%.*]] = lshr i32 -262144, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and i32 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[TMP2]], 0 +; CHECK-NEXT: [[SHL:%.*]] = shl i32 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ult i32 [[SHL]], 262144 ; CHECK-NEXT: ret i1 [[R]] ; %shl = shl i32 %x, %y @@ -48,9 +45,8 @@ define i1 @scalar_i64_shl_and_negC_eq(i64 %x, i64 %y) { ; CHECK-LABEL: @scalar_i64_shl_and_negC_eq( -; CHECK-NEXT: [[TMP1:%.*]] = lshr i64 -8589934592, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and i64 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp eq i64 [[TMP2]], 0 +; CHECK-NEXT: [[SHL:%.*]] = shl i64 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ult i64 [[SHL]], 8589934592 ; CHECK-NEXT: ret i1 [[R]] ; %shl = shl i64 %x, %y @@ -61,9 +57,8 @@ define i1 @scalar_i32_shl_and_negC_ne(i32 %x, i32 %y) { ; CHECK-LABEL: @scalar_i32_shl_and_negC_ne( -; CHECK-NEXT: [[TMP1:%.*]] = lshr i32 -262144, [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and i32 [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp ne i32 [[TMP2]], 0 +; CHECK-NEXT: [[SHL:%.*]] = shl i32 [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ugt i32 [[SHL]], 262143 ; CHECK-NEXT: ret i1 [[R]] ; %shl = shl i32 %x, %y @@ -76,9 +71,8 @@ define <4 x i1> @vec_4xi32_shl_and_negC_eq(<4 x i32> %x, <4 x i32> %y) { ; CHECK-LABEL: @vec_4xi32_shl_and_negC_eq( -; CHECK-NEXT: [[TMP1:%.*]] = lshr <4 x i32> , [[Y:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = and <4 x i32> [[TMP1]], [[X:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp eq <4 x i32> [[TMP2]], zeroinitializer +; CHECK-NEXT: [[SHL:%.*]] = shl <4 x i32> [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[R:%.*]] = icmp ult <4 x i32> [[SHL]], ; CHECK-NEXT: ret <4 x i1> [[R]] ; %shl = shl <4 x i32> %x, %y @@ -190,7 +184,8 @@ define i1 @scalar_i32_shl_and_negC_eq_X_is_constant1(i32 %y) { ; CHECK-LABEL: @scalar_i32_shl_and_negC_eq_X_is_constant1( ; CHECK-NEXT: [[SHL:%.*]] = shl i32 12345, [[Y:%.*]] -; CHECK-NEXT: [[R:%.*]] = icmp ult i32 [[SHL]], 8 +; CHECK-NEXT: [[AND:%.*]] = and i32 [[SHL]], -8 +; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[AND]], 0 ; CHECK-NEXT: ret i1 [[R]] ; %shl = shl i32 12345, %y @@ -201,7 +196,9 @@ define i1 @scalar_i32_shl_and_negC_eq_X_is_constant2(i32 %y) { ; CHECK-LABEL: @scalar_i32_shl_and_negC_eq_X_is_constant2( -; CHECK-NEXT: [[R:%.*]] = icmp ult i32 [[Y:%.*]], 3 +; CHECK-NEXT: [[SHL:%.*]] = shl i32 1, [[Y:%.*]] +; CHECK-NEXT: [[AND:%.*]] = and i32 [[SHL]], -8 +; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[AND]], 0 ; CHECK-NEXT: ret i1 [[R]] ; %shl = shl i32 1, %y