Index: llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp =================================================================== --- llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp +++ llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp @@ -1885,6 +1885,42 @@ return new ZExtInst(And, Ty); } } + + const APInt *C1; + const APInt *C2; + Value *X; + if (C->isPowerOf2()) { + if (match(Op0, m_OneUse(m_LShr(m_Shl(m_APInt(C1), m_Value(X)), + m_APInt(C2)))) && + C1->isPowerOf2()) { + unsigned Log2C1 = C1->countTrailingZeros(); + unsigned Log2C = C->countTrailingZeros(); + unsigned LShrEqBits = Log2C + C2->getZExtValue(); + if (LShrEqBits >= Log2C1 && LShrEqBits < Width) { + // iff C,C1 is pow2 and Log2(C1) < Log2(C)+C2 < BitWidth: + // ((C1 << X) >> C2) & C -> X == (Log2(C)+C2-Log2(C1)) ? C : 0 + unsigned CmpC = LShrEqBits - Log2C1; + Value *Cmp = Builder.CreateICmpEQ(X, ConstantInt::get(Ty, CmpC)); + return SelectInst::Create(Cmp, ConstantInt::get(Ty, *C), + ConstantInt::getNullValue(Ty)); + } + } + if (match(Op0, m_OneUse(m_LShr(m_LShr(m_APInt(C1), m_Value(X)), + m_APInt(C2)))) && + C1->isPowerOf2()) { + unsigned Log2C1 = C1->countTrailingZeros(); + unsigned Log2C = C->countTrailingZeros(); + unsigned LShrEqBits = Log2C + C2->getZExtValue(); + if (LShrEqBits < Log2C1) { + // iff C,C1 is pow2 and Log2(C)+C2 < Log2(C1): + // ((C1 >> X) >> C2) & C -> X == (Log2(C1)-Log2(C)-C2) ? C : 0 + unsigned CmpC = Log2C1 - LShrEqBits; + Value *Cmp = Builder.CreateICmpEQ(X, ConstantInt::get(Ty, CmpC)); + return SelectInst::Create(Cmp, ConstantInt::get(Ty, *C), + ConstantInt::getNullValue(Ty)); + } + } + } } if (match(&I, m_And(m_OneUse(m_Shl(m_ZExt(m_Value(X)), m_Value(Y))), Index: llvm/test/Transforms/InstCombine/and.ll =================================================================== --- llvm/test/Transforms/InstCombine/and.ll +++ llvm/test/Transforms/InstCombine/and.ll @@ -1624,9 +1624,8 @@ define i16 @shl_lshr_pow2_const(i16 %x) { ; CHECK-LABEL: @shl_lshr_pow2_const( -; CHECK-NEXT: [[SHL:%.*]] = shl i16 4, [[X:%.*]] -; CHECK-NEXT: [[LSHR:%.*]] = lshr i16 [[SHL]], 6 -; CHECK-NEXT: [[R:%.*]] = and i16 [[LSHR]], 8 +; CHECK-NEXT: [[TMP1:%.*]] = icmp eq i16 [[X:%.*]], 7 +; CHECK-NEXT: [[R:%.*]] = select i1 [[TMP1]], i16 8, i16 0 ; CHECK-NEXT: ret i16 [[R]] ; %shl = shl i16 4, %x @@ -1699,9 +1698,8 @@ define i16 @lshr_lshr_pow2_const(i16 %x) { ; CHECK-LABEL: @lshr_lshr_pow2_const( -; CHECK-NEXT: [[LSHR1:%.*]] = lshr i16 2048, [[X:%.*]] -; CHECK-NEXT: [[LSHR2:%.*]] = lshr i16 [[LSHR1]], 6 -; CHECK-NEXT: [[R:%.*]] = and i16 [[LSHR2]], 4 +; CHECK-NEXT: [[TMP1:%.*]] = icmp eq i16 [[X:%.*]], 3 +; CHECK-NEXT: [[R:%.*]] = select i1 [[TMP1]], i16 4, i16 0 ; CHECK-NEXT: ret i16 [[R]] ; %lshr1 = lshr i16 2048, %x Index: llvm/test/Transforms/InstCombine/icmp-and-shift.ll =================================================================== --- llvm/test/Transforms/InstCombine/icmp-and-shift.ll +++ llvm/test/Transforms/InstCombine/icmp-and-shift.ll @@ -57,11 +57,9 @@ define i32 @icmp_eq_and_pow2_shl_pow2(i32 %0) { ; CHECK-LABEL: @icmp_eq_and_pow2_shl_pow2( -; CHECK-NEXT: [[SHL:%.*]] = shl i32 2, [[TMP0:%.*]] -; CHECK-NEXT: [[AND:%.*]] = lshr i32 [[SHL]], 4 -; CHECK-NEXT: [[AND_LOBIT:%.*]] = and i32 [[AND]], 1 -; CHECK-NEXT: [[TMP2:%.*]] = xor i32 [[AND_LOBIT]], 1 -; CHECK-NEXT: ret i32 [[TMP2]] +; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i32 [[TMP0:%.*]], 3 +; CHECK-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32 +; CHECK-NEXT: ret i32 [[TMP3]] ; %shl = shl i32 2, %0 %and = and i32 %shl, 16 @@ -72,11 +70,9 @@ define <2 x i32> @icmp_eq_and_pow2_shl_pow2_vec(<2 x i32> %0) { ; CHECK-LABEL: @icmp_eq_and_pow2_shl_pow2_vec( -; CHECK-NEXT: [[SHL:%.*]] = shl <2 x i32> , [[TMP0:%.*]] -; CHECK-NEXT: [[AND:%.*]] = lshr <2 x i32> [[SHL]], -; CHECK-NEXT: [[AND_LOBIT:%.*]] = and <2 x i32> [[AND]], -; CHECK-NEXT: [[TMP2:%.*]] = xor <2 x i32> [[AND_LOBIT]], -; CHECK-NEXT: ret <2 x i32> [[TMP2]] +; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <2 x i32> [[TMP0:%.*]], +; CHECK-NEXT: [[TMP3:%.*]] = zext <2 x i1> [[TMP2]] to <2 x i32> +; CHECK-NEXT: ret <2 x i32> [[TMP3]] ; %shl = shl <2 x i32> , %0 %and = and <2 x i32> %shl, @@ -87,9 +83,8 @@ define i32 @icmp_ne_and_pow2_shl_pow2(i32 %0) { ; CHECK-LABEL: @icmp_ne_and_pow2_shl_pow2( -; CHECK-NEXT: [[SHL:%.*]] = shl i32 2, [[TMP0:%.*]] -; CHECK-NEXT: [[AND:%.*]] = lshr i32 [[SHL]], 4 -; CHECK-NEXT: [[AND_LOBIT:%.*]] = and i32 [[AND]], 1 +; CHECK-NEXT: [[TMP2:%.*]] = icmp eq i32 [[TMP0:%.*]], 3 +; CHECK-NEXT: [[AND_LOBIT:%.*]] = zext i1 [[TMP2]] to i32 ; CHECK-NEXT: ret i32 [[AND_LOBIT]] ; %shl = shl i32 2, %0 @@ -101,9 +96,8 @@ define <2 x i32> @icmp_ne_and_pow2_shl_pow2_vec(<2 x i32> %0) { ; CHECK-LABEL: @icmp_ne_and_pow2_shl_pow2_vec( -; CHECK-NEXT: [[SHL:%.*]] = shl <2 x i32> , [[TMP0:%.*]] -; CHECK-NEXT: [[AND:%.*]] = lshr <2 x i32> [[SHL]], -; CHECK-NEXT: [[AND_LOBIT:%.*]] = and <2 x i32> [[AND]], +; CHECK-NEXT: [[TMP2:%.*]] = icmp eq <2 x i32> [[TMP0:%.*]], +; CHECK-NEXT: [[AND_LOBIT:%.*]] = zext <2 x i1> [[TMP2]] to <2 x i32> ; CHECK-NEXT: ret <2 x i32> [[AND_LOBIT]] ; %shl = shl <2 x i32> , %0 @@ -207,6 +201,7 @@ ret <2 x i32> %conv } +; TODO: can be tranform to icmp uge define i32 @icmp_eq_and_pow2_minus1_shl_pow2(i32 %0) { ; CHECK-LABEL: @icmp_eq_and_pow2_minus1_shl_pow2( ; CHECK-NEXT: [[SHL:%.*]] = shl i32 2, [[TMP0:%.*]] @@ -222,6 +217,7 @@ ret i32 %conv } +; TODO: can be tranform to icmp uge define <2 x i32> @icmp_eq_and_pow2_minus1_shl_pow2_vec(<2 x i32> %0) { ; CHECK-LABEL: @icmp_eq_and_pow2_minus1_shl_pow2_vec( ; CHECK-NEXT: [[SHL:%.*]] = shl <2 x i32> , [[TMP0:%.*]] @@ -237,6 +233,7 @@ ret <2 x i32> %conv } +; TODO: can be tranform to icmp ult define i32 @icmp_ne_and_pow2_minus1_shl_pow2(i32 %0) { ; CHECK-LABEL: @icmp_ne_and_pow2_minus1_shl_pow2( ; CHECK-NEXT: [[SHL:%.*]] = shl i32 2, [[TMP0:%.*]] @@ -252,6 +249,7 @@ ret i32 %conv } +; TODO: can be tranform to icmp ult define <2 x i32> @icmp_ne_and_pow2_minus1_shl_pow2_vec(<2 x i32> %0) { ; CHECK-LABEL: @icmp_ne_and_pow2_minus1_shl_pow2_vec( ; CHECK-NEXT: [[SHL:%.*]] = shl <2 x i32> , [[TMP0:%.*]] @@ -335,9 +333,8 @@ define <2 x i32> @icmp_ne_and1_lshr_pow2_vec(<2 x i32> %0) { ; CHECK-LABEL: @icmp_ne_and1_lshr_pow2_vec( -; CHECK-NEXT: [[LSHR:%.*]] = lshr <2 x i32> , [[TMP0:%.*]] -; CHECK-NEXT: [[AND:%.*]] = lshr <2 x i32> [[LSHR]], -; CHECK-NEXT: [[AND_LOBIT:%.*]] = and <2 x i32> [[AND]], +; CHECK-NEXT: [[TMP2:%.*]] = icmp eq <2 x i32> [[TMP0:%.*]], +; CHECK-NEXT: [[AND_LOBIT:%.*]] = zext <2 x i1> [[TMP2]] to <2 x i32> ; CHECK-NEXT: ret <2 x i32> [[AND_LOBIT]] ; %lshr = lshr <2 x i32> , %0 @@ -349,11 +346,9 @@ define i32 @icmp_eq_and_pow2_lshr_pow2(i32 %0) { ; CHECK-LABEL: @icmp_eq_and_pow2_lshr_pow2( -; CHECK-NEXT: [[LSHR:%.*]] = lshr i32 8, [[TMP0:%.*]] -; CHECK-NEXT: [[AND:%.*]] = lshr i32 [[LSHR]], 2 -; CHECK-NEXT: [[AND_LOBIT:%.*]] = and i32 [[AND]], 1 -; CHECK-NEXT: [[TMP2:%.*]] = xor i32 [[AND_LOBIT]], 1 -; CHECK-NEXT: ret i32 [[TMP2]] +; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i32 [[TMP0:%.*]], 1 +; CHECK-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32 +; CHECK-NEXT: ret i32 [[TMP3]] ; %lshr = lshr i32 8, %0 %and = and i32 %lshr, 4 @@ -375,11 +370,9 @@ define <2 x i32> @icmp_eq_and_pow2_lshr_pow2_vec(<2 x i32> %0) { ; CHECK-LABEL: @icmp_eq_and_pow2_lshr_pow2_vec( -; CHECK-NEXT: [[LSHR:%.*]] = lshr <2 x i32> , [[TMP0:%.*]] -; CHECK-NEXT: [[AND:%.*]] = lshr <2 x i32> [[LSHR]], -; CHECK-NEXT: [[AND_LOBIT:%.*]] = and <2 x i32> [[AND]], -; CHECK-NEXT: [[TMP2:%.*]] = xor <2 x i32> [[AND_LOBIT]], -; CHECK-NEXT: ret <2 x i32> [[TMP2]] +; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <2 x i32> [[TMP0:%.*]], +; CHECK-NEXT: [[TMP3:%.*]] = zext <2 x i1> [[TMP2]] to <2 x i32> +; CHECK-NEXT: ret <2 x i32> [[TMP3]] ; %lshr = lshr <2 x i32> , %0 %and = and <2 x i32> %lshr, @@ -390,11 +383,9 @@ define i32 @icmp_ne_and_pow2_lshr_pow2(i32 %0) { ; CHECK-LABEL: @icmp_ne_and_pow2_lshr_pow2( -; CHECK-NEXT: [[LSHR:%.*]] = lshr i32 8, [[TMP0:%.*]] -; CHECK-NEXT: [[AND:%.*]] = lshr i32 [[LSHR]], 2 -; CHECK-NEXT: [[AND_LOBIT:%.*]] = and i32 [[AND]], 1 -; CHECK-NEXT: [[TMP2:%.*]] = xor i32 [[AND_LOBIT]], 1 -; CHECK-NEXT: ret i32 [[TMP2]] +; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i32 [[TMP0:%.*]], 1 +; CHECK-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32 +; CHECK-NEXT: ret i32 [[TMP3]] ; %lshr = lshr i32 8, %0 %and = and i32 %lshr, 4 @@ -416,9 +407,8 @@ define <2 x i32> @icmp_ne_and_pow2_lshr_pow2_vec(<2 x i32> %0) { ; CHECK-LABEL: @icmp_ne_and_pow2_lshr_pow2_vec( -; CHECK-NEXT: [[LSHR:%.*]] = lshr <2 x i32> , [[TMP0:%.*]] -; CHECK-NEXT: [[AND:%.*]] = lshr <2 x i32> [[LSHR]], -; CHECK-NEXT: [[AND_LOBIT:%.*]] = and <2 x i32> [[AND]], +; CHECK-NEXT: [[TMP2:%.*]] = icmp eq <2 x i32> [[TMP0:%.*]], +; CHECK-NEXT: [[AND_LOBIT:%.*]] = zext <2 x i1> [[TMP2]] to <2 x i32> ; CHECK-NEXT: ret <2 x i32> [[AND_LOBIT]] ; %lshr = lshr <2 x i32> , %0