[X86][SSE] Fold movmsk(not(x)) -> not(movmsk)

Helps to improve folding of comparisons with movmsk results.

llvm-svn: 361056

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -41498,6 +41498,8 @@ static SDValue combineMOVMSK(SDNode *N, SelectionDAG &DAG,
   SDValue Src = N->getOperand(0);
   MVT SrcVT = Src.getSimpleValueType();
   MVT VT = N->getSimpleValueType(0);
+  unsigned NumBits = VT.getScalarSizeInBits();
+  unsigned NumElts = SrcVT.getVectorNumElements();
 
   // Perform constant folding.
   if (ISD::isBuildVectorOfConstantSDNodes(Src.getNode())) {
@@ -41517,9 +41519,20 @@ static SDValue combineMOVMSK(SDNode *N, SelectionDAG &DAG,
       Src.getOperand(0).getScalarValueSizeInBits() == EltWidth)
     return DAG.getNode(X86ISD::MOVMSK, SDLoc(N), VT, Src.getOperand(0));
 
+  // Fold movmsk(not(x)) -> not(movmsk) to improve folding of movmsk results
+  // with scalar comparisons.
+  if (SDValue NotSrc = IsNOT(Src, DAG)) {
+    SDLoc DL(N);
+    APInt NotMask = APInt::getLowBitsSet(NumBits, NumElts);
+    NotSrc = DAG.getBitcast(SrcVT, NotSrc);
+    return DAG.getNode(ISD::XOR, DL, VT,
+                       DAG.getNode(X86ISD::MOVMSK, DL, VT, NotSrc),
+                       DAG.getConstant(NotMask, DL, VT));
+  }
+
   // Simplify the inputs.
   const TargetLowering &TLI = DAG.getTargetLoweringInfo();
-  APInt DemandedMask(APInt::getAllOnesValue(VT.getScalarSizeInBits()));
+  APInt DemandedMask(APInt::getAllOnesValue(NumBits));
   if (TLI.SimplifyDemandedBits(SDValue(N, 0), DemandedMask, DCI))
     return SDValue(N, 0);
 

llvm/test/CodeGen/X86/movmsk-cmp.ll

@@ -4485,9 +4485,8 @@ define i1 @movmsk_v2i64(<2 x i64> %x, <2 x i64> %y) {
 ; SSE2-NEXT:    pcmpeqd %xmm1, %xmm0
 ; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,0,3,2]
 ; SSE2-NEXT:    pand %xmm0, %xmm1
-; SSE2-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE2-NEXT:    movmskpd %xmm1, %eax
-; SSE2-NEXT:    pxor %xmm1, %xmm0
+; SSE2-NEXT:    xorl $3, %eax
-; SSE2-NEXT:    movmskpd %xmm0, %eax
 ; SSE2-NEXT:    cmpb $3, %al
 ; SSE2-NEXT:    sete %al
 ; SSE2-NEXT:    retq
@@ -4495,9 +4494,8 @@ define i1 @movmsk_v2i64(<2 x i64> %x, <2 x i64> %y) {
 ; AVX-LABEL: movmsk_v2i64:
 ; AVX:       # %bb.0:
 ; AVX-NEXT:    vpcmpeqq %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vpxor %xmm1, %xmm0, %xmm0
 ; AVX-NEXT:    vmovmskpd %xmm0, %eax
+; AVX-NEXT:    xorl $3, %eax
 ; AVX-NEXT:    cmpb $3, %al
 ; AVX-NEXT:    sete %al
 ; AVX-NEXT:    retq

llvm/test/CodeGen/X86/vector-compare-all_of.ll

@@ -1102,9 +1102,8 @@ define i1 @bool_reduction_v4i32(<4 x i32> %x, <4 x i32> %y) {
 ; SSE-LABEL: bool_reduction_v4i32:
 ; SSE:       # %bb.0:
 ; SSE-NEXT:    pcmpeqd %xmm1, %xmm0
-; SSE-NEXT:    pcmpeqd %xmm1, %xmm1
+; SSE-NEXT:    movmskps %xmm0, %eax
-; SSE-NEXT:    pxor %xmm0, %xmm1
+; SSE-NEXT:    xorl $15, %eax
-; SSE-NEXT:    movmskps %xmm1, %eax
 ; SSE-NEXT:    cmpb $15, %al
 ; SSE-NEXT:    sete %al
 ; SSE-NEXT:    retq
@@ -1112,9 +1111,8 @@ define i1 @bool_reduction_v4i32(<4 x i32> %x, <4 x i32> %y) {
 ; AVX-LABEL: bool_reduction_v4i32:
 ; AVX:       # %bb.0:
 ; AVX-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vpxor %xmm1, %xmm0, %xmm0
 ; AVX-NEXT:    vmovmskps %xmm0, %eax
+; AVX-NEXT:    xorl $15, %eax
 ; AVX-NEXT:    cmpb $15, %al
 ; AVX-NEXT:    sete %al
 ; AVX-NEXT:    retq

llvm/test/CodeGen/X86/vector-compare-any_of.ll

@@ -1018,20 +1018,16 @@ define i1 @bool_reduction_v4i32(<4 x i32> %x, <4 x i32> %y) {
 ; SSE-LABEL: bool_reduction_v4i32:
 ; SSE:       # %bb.0:
 ; SSE-NEXT:    pcmpeqd %xmm1, %xmm0
-; SSE-NEXT:    pcmpeqd %xmm1, %xmm1
+; SSE-NEXT:    movmskps %xmm0, %eax
-; SSE-NEXT:    pxor %xmm0, %xmm1
+; SSE-NEXT:    xorb $15, %al
-; SSE-NEXT:    movmskps %xmm1, %eax
-; SSE-NEXT:    testb %al, %al
 ; SSE-NEXT:    setne %al
 ; SSE-NEXT:    retq
 ;
 ; AVX-LABEL: bool_reduction_v4i32:
 ; AVX:       # %bb.0:
 ; AVX-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vpxor %xmm1, %xmm0, %xmm0
 ; AVX-NEXT:    vmovmskps %xmm0, %eax
-; AVX-NEXT:    testb %al, %al
+; AVX-NEXT:    xorb $15, %al
 ; AVX-NEXT:    setne %al
 ; AVX-NEXT:    retq
 ;