[InstCombine] Remove the (not (sext)) case from foldBoolSextMaskToSelect and inline the remaining code to match visitOr

[craig.topper]

Summary

The (not (sext)) case is really (xor (sext), -1) which should have been simplified to (sext (xor, 1)) before we got here. So we shouldn't need to handle it.

With that taken care of we only need to two cases so don't need the swap anymore. This makes us in sync with the equivalent code in visitOr so inline this to match.

[spatel]

LGTM.

lib/Transforms/InstCombine/InstCombineAndOrXor.cpp

if (FCmp0 && FCmp1) {
     if (Res)
       return CastInst::Create(CastOpcode, Res, DestTy);
     return nullptr;
   }
 
   return nullptr;
 }
 
-static Instruction *foldBoolSextMaskToSelect(BinaryOperator &I) {
-  Value *Op0 = I.getOperand(0), *Op1 = I.getOperand(1);
-
-  // Canonicalize SExt or Not to the LHS
-  if (match(Op1, m_SExt(m_Value())) || match(Op1, m_Not(m_Value()))) {
-    std::swap(Op0, Op1);
-  }
-
-  // Fold (and (sext bool to A), B) --> (select bool, B, 0)
-  Value *X = nullptr;
-  if (match(Op0, m_SExt(m_Value(X))) && X->getType()->isIntOrIntVectorTy(1)) {
-    Value *Zero = Constant::getNullValue(Op1->getType());
-    return SelectInst::Create(X, Op1, Zero);
-  }
-
-  // Fold (and ~(sext bool to A), B) --> (select bool, 0, B)
-  if (match(Op0, m_Not(m_SExt(m_Value(X)))) &&
-      X->getType()->isIntOrIntVectorTy(1)) {
-    Value *Zero = Constant::getNullValue(Op0->getType());
-    return SelectInst::Create(X, Zero, Op1);
-  }
-
-  return nullptr;
-}
-
 static Instruction *foldAndToXor(BinaryOperator &I,
                                  InstCombiner::BuilderTy &Builder) {
   assert(I.getOpcode() == Instruction::And);
   Value *Op0 = I.getOperand(0);
   Value *Op1 = I.getOperand(1);
   Value *A, *B;
 
   // Operand complexity canonicalization guarantees that the 'or' is Op0.
Instruction *InstCombiner::visitAnd(BinaryOperator &I) {
   if (FCmpInst *LHS = dyn_cast<FCmpInst>(I.getOperand(0)))
     if (FCmpInst *RHS = dyn_cast<FCmpInst>(I.getOperand(1)))
       if (Value *Res = foldAndOfFCmps(LHS, RHS))
         return replaceInstUsesWith(I, Res);
 
   if (Instruction *CastedAnd = foldCastedBitwiseLogic(I))
     return CastedAnd;
 
-  if (Instruction *Select = foldBoolSextMaskToSelect(I))
-    return Select;
+  // and(sext(A), B) / and(B, sext(A)) --> A ? B : 0, where A is i1 or <N x i1>.
+  Value *A;
+  if (match(Op0, m_OneUse(m_SExt(m_Value(A)))) &&
+      A->getType()->isIntOrIntVectorTy(1))
+    return SelectInst::Create(A, Op1, Constant::getNullValue(I.getType()));
+  if (match(Op1, m_OneUse(m_SExt(m_Value(A)))) &&
+      A->getType()->isIntOrIntVectorTy(1))
+    return SelectInst::Create(A, Op0, Constant::getNullValue(I.getType()));
 
   return Changed ? &I : nullptr;
 }
 
 /// Given an OR instruction, check to see if this is a bswap idiom. If so,
 /// insert the new intrinsic and return it.
 Instruction *InstCombiner::MatchBSwap(BinaryOperator &I) {
   Value *Op0 = I.getOperand(0), *Op1 = I.getOperand(1);

test/Transforms/InstCombine/vector-casts.ll

;
   ret <2 x i64> %conv
 }
 
 ; rdar://7434900
 define <2 x i64> @test5(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: @test5(
 ; CHECK-NEXT:    [[CMP:%.*]] = fcmp ult <4 x float> %a, zeroinitializer
 ; CHECK-NEXT:    [[CMP4:%.*]] = fcmp ult <4 x float> %b, zeroinitializer
-; CHECK-NEXT:    [[NARROW:%.*]] = and <4 x i1> [[CMP4]], [[CMP]]
+; CHECK-NEXT:    [[NARROW:%.*]] = and <4 x i1> [[CMP]], [[CMP4]]
 ; CHECK-NEXT:    [[AND:%.*]] = sext <4 x i1> [[NARROW]] to <4 x i32>
 ; CHECK-NEXT:    [[CONV:%.*]] = bitcast <4 x i32> [[AND]] to <2 x i64>
 ; CHECK-NEXT:    ret <2 x i64> [[CONV]]
 ;
   %cmp = fcmp ult <4 x float> %a, zeroinitializer
   %sext = sext <4 x i1> %cmp to <4 x i32>
   %cmp4 = fcmp ult <4 x float> %b, zeroinitializer
   %sext5 = sext <4 x i1> %cmp4 to <4 x i32>