[InstCombine] Make (X|C1)^C2 -> X^(C1^C2) iff X&~C1 == 0 work for splat vectors

This also corrects the description to match what was actually implemented. The old comment said X^(C1|C2), but it implemented X^((C1|C2)&~(C1&C2)). I believe ((C1|C2)&~(C1&C2)) is equivalent to (C1^C2).

Differential Revision: https://reviews.llvm.org/D36505

llvm-svn: 310658

llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp

@@ -2365,53 +2365,48 @@ Instruction *InstCombiner::visitXor(BinaryOperator &I) {
   {
     const APInt *RHSC;
     if (match(Op1, m_APInt(RHSC))) {
-      Value *V;
+      Value *X;
       const APInt *C;
-      if (match(Op0, m_Sub(m_APInt(C), m_Value(V)))) {
+      if (match(Op0, m_Sub(m_APInt(C), m_Value(X)))) {
         // ~(c-X) == X-c-1 == X+(-c-1)
         if (RHSC->isAllOnesValue()) {
           Constant *NewC = ConstantInt::get(I.getType(), -(*C) - 1);
-          return BinaryOperator::CreateAdd(V, NewC);
+          return BinaryOperator::CreateAdd(X, NewC);
         }
         if (RHSC->isSignMask()) {
           // (C - X) ^ signmask -> (C + signmask - X)
           Constant *NewC = ConstantInt::get(I.getType(), *C + *RHSC);
-          return BinaryOperator::CreateSub(NewC, V);
+          return BinaryOperator::CreateSub(NewC, X);
         }
-      } else if (match(Op0, m_Add(m_Value(V), m_APInt(C)))) {
+      } else if (match(Op0, m_Add(m_Value(X), m_APInt(C)))) {
         // ~(X-c) --> (-c-1)-X
         if (RHSC->isAllOnesValue()) {
           Constant *NewC = ConstantInt::get(I.getType(), -(*C) - 1);
-          return BinaryOperator::CreateSub(NewC, V);
+          return BinaryOperator::CreateSub(NewC, X);
         }
         if (RHSC->isSignMask()) {
           // (X + C) ^ signmask -> (X + C + signmask)
           Constant *NewC = ConstantInt::get(I.getType(), *C + *RHSC);
-          return BinaryOperator::CreateAdd(V, NewC);
+          return BinaryOperator::CreateAdd(X, NewC);
         }
       }
+
+      // (X|C1)^C2 -> X^(C1^C2) iff X&~C1 == 0
+      if (match(Op0, m_Or(m_Value(X), m_APInt(C))) &&
+          MaskedValueIsZero(X, *C, 0, &I)) {
+        Constant *NewC = ConstantInt::get(I.getType(), *C ^ *RHSC);
+        Worklist.Add(cast<Instruction>(Op0));
+        I.setOperand(0, X);
+        I.setOperand(1, NewC);
+        return &I;
+      }
     }
   }
 
   if (ConstantInt *RHSC = dyn_cast<ConstantInt>(Op1)) {
     if (BinaryOperator *Op0I = dyn_cast<BinaryOperator>(Op0)) {
       if (ConstantInt *Op0CI = dyn_cast<ConstantInt>(Op0I->getOperand(1))) {
-        if (Op0I->getOpcode() == Instruction::Or) {
+        if (Op0I->getOpcode() == Instruction::LShr) {
-          // (X|C1)^C2 -> X^(C1|C2) iff X&~C1 == 0
-          if (MaskedValueIsZero(Op0I->getOperand(0), Op0CI->getValue(),
-                                0, &I)) {
-            Constant *NewRHS = ConstantExpr::getOr(Op0CI, RHSC);
-            // Anything in both C1 and C2 is known to be zero, remove it from
-            // NewRHS.
-            Constant *CommonBits = ConstantExpr::getAnd(Op0CI, RHSC);
-            NewRHS = ConstantExpr::getAnd(NewRHS,
-                                       ConstantExpr::getNot(CommonBits));
-            Worklist.Add(Op0I);
-            I.setOperand(0, Op0I->getOperand(0));
-            I.setOperand(1, NewRHS);
-            return &I;
-          }
-        } else if (Op0I->getOpcode() == Instruction::LShr) {
           // ((X^C1) >> C2) ^ C3 -> (X>>C2) ^ ((C1>>C2)^C3)
           // E1 = "X ^ C1"
           BinaryOperator *E1;

llvm/test/Transforms/InstCombine/or.ll

@@ -143,6 +143,19 @@ define i16 @test23(i16 %A) {
   ret i16 %D
 }
 
+define <2 x i16> @test23vec(<2 x i16> %A) {
+; CHECK-LABEL: @test23vec(
+; CHECK-NEXT:    [[B:%.*]] = lshr <2 x i16> [[A:%.*]], <i16 1, i16 1>
+; CHECK-NEXT:    [[D:%.*]] = xor <2 x i16> [[B]], <i16 -24575, i16 -24575>
+; CHECK-NEXT:    ret <2 x i16> [[D]]
+;
+  %B = lshr <2 x i16> %A, <i16 1, i16 1>
+  ;; fold or into xor
+  %C = or <2 x i16> %B, <i16 -32768, i16 -32768>
+  %D = xor <2 x i16> %C, <i16 8193, i16 8193>
+  ret <2 x i16> %D
+}
+
 ; PR1738
 define i1 @test24(double %X, double %Y) {
 ; CHECK-LABEL: @test24(

llvm/test/Transforms/InstCombine/select-with-bitwise-ops.ll

@@ -273,9 +273,8 @@ define <2 x i32> @test65vec(<2 x i64> %x) {
 ; CHECK-NEXT:    [[TMP1:%.*]] = lshr <2 x i64> [[X:%.*]], <i64 3, i64 3>
 ; CHECK-NEXT:    [[TMP2:%.*]] = trunc <2 x i64> [[TMP1]] to <2 x i32>
 ; CHECK-NEXT:    [[TMP3:%.*]] = and <2 x i32> [[TMP2]], <i32 2, i32 2>
-; CHECK-NEXT:    [[TMP4:%.*]] = or <2 x i32> [[TMP3]], <i32 40, i32 40>
+; CHECK-NEXT:    [[TMP4:%.*]] = xor <2 x i32> [[TMP3]], <i32 42, i32 42>
-; CHECK-NEXT:    [[TMP5:%.*]] = xor <2 x i32> [[TMP4]], <i32 2, i32 2>
+; CHECK-NEXT:    ret <2 x i32> [[TMP4]]
-; CHECK-NEXT:    ret <2 x i32> [[TMP5]]
 ;
   %1 = and <2 x i64> %x, <i64 16, i64 16>
   %2 = icmp ne <2 x i64> %1, zeroinitializer
@@ -302,9 +301,8 @@ define <2 x i32> @test66vec(<2 x i64> %x) {
 ; CHECK-NEXT:    [[TMP1:%.*]] = lshr <2 x i64> [[X:%.*]], <i64 31, i64 31>
 ; CHECK-NEXT:    [[TMP2:%.*]] = trunc <2 x i64> [[TMP1]] to <2 x i32>
 ; CHECK-NEXT:    [[TMP3:%.*]] = and <2 x i32> [[TMP2]], <i32 2, i32 2>
-; CHECK-NEXT:    [[TMP4:%.*]] = or <2 x i32> [[TMP3]], <i32 40, i32 40>
+; CHECK-NEXT:    [[TMP4:%.*]] = xor <2 x i32> [[TMP3]], <i32 42, i32 42>
-; CHECK-NEXT:    [[TMP5:%.*]] = xor <2 x i32> [[TMP4]], <i32 2, i32 2>
+; CHECK-NEXT:    ret <2 x i32> [[TMP4]]
-; CHECK-NEXT:    ret <2 x i32> [[TMP5]]
 ;
   %1 = and <2 x i64> %x, <i64 4294967296, i64 4294967296>
   %2 = icmp ne <2 x i64> %1, zeroinitializer
@@ -344,10 +342,9 @@ define <2 x i32> @test67vec(<2 x i16> %x) {
 ; CHECK-LABEL: @test67vec(
 ; CHECK-NEXT:    [[TMP1:%.*]] = lshr <2 x i16> [[X:%.*]], <i16 1, i16 1>
 ; CHECK-NEXT:    [[TMP2:%.*]] = and <2 x i16> [[TMP1]], <i16 2, i16 2>
-; CHECK-NEXT:    [[TMP3:%.*]] = or <2 x i16> [[TMP2]], <i16 40, i16 40>
+; CHECK-NEXT:    [[TMP3:%.*]] = xor <2 x i16> [[TMP2]], <i16 42, i16 42>
-; CHECK-NEXT:    [[TMP4:%.*]] = xor <2 x i16> [[TMP3]], <i16 2, i16 2>
+; CHECK-NEXT:    [[TMP4:%.*]] = zext <2 x i16> [[TMP3]] to <2 x i32>
-; CHECK-NEXT:    [[TMP5:%.*]] = zext <2 x i16> [[TMP4]] to <2 x i32>
+; CHECK-NEXT:    ret <2 x i32> [[TMP4]]
-; CHECK-NEXT:    ret <2 x i32> [[TMP5]]
 ;
   %1 = and <2 x i16> %x, <i16 4, i16 4>
   %2 = icmp ne <2 x i16> %1, zeroinitializer