[SelectionDAG] We can ignore knownbits from an undef shuffle vector index if we don't actually demand that element

llvm-svn: 288839

2 files changed, 26 insertions, 5 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 297a7c3121a..f8e9fa21636 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -2083,16 +2083,16 @@ void SelectionDAG::computeKnownBits(SDValue Op, APInt &KnownZero,
     const ShuffleVectorSDNode *SVN = cast<ShuffleVectorSDNode>(Op);
     assert(NumElts == SVN->getMask().size() && "Unexpected vector size");
     for (unsigned i = 0; i != NumElts; ++i) {
+      if (!DemandedElts[i])
+        continue;
+
       int M = SVN->getMaskElt(i);
       if (M < 0) {
         // For UNDEF elements, we don't know anything about the common state of
         // the shuffle result.
-        // FIXME: Is this too pessimistic?
         KnownZero = KnownOne = APInt(BitWidth, 0);
         break;
       }
-      if (!DemandedElts[i])
-        continue;
 
       if ((unsigned)M < NumElts)
         DemandedLHS.setBit((unsigned)M % NumElts);
diff --git a/llvm/test/CodeGen/X86/known-bits-vector.ll b/llvm/test/CodeGen/X86/known-bits-vector.ll
index e5e4fcf8338..2a54580c9ad 100644
--- a/llvm/test/CodeGen/X86/known-bits-vector.ll
+++ b/llvm/test/CodeGen/X86/known-bits-vector.ll
@@ -74,18 +74,39 @@ define <4 x i32> @knownbits_mask_shuffle_shuffle_sext(<8 x i16> %a0) nounwind {
 ; X32-LABEL: knownbits_mask_shuffle_shuffle_sext:
 ; X32:       # BB#0:
 ; X32-NEXT:    vpand {{\.LCPI.*}}, %xmm0, %xmm0
+; X32-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; X32-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; X32-NEXT:    retl
+;
+; X64-LABEL: knownbits_mask_shuffle_shuffle_sext:
+; X64:       # BB#0:
+; X64-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
+; X64-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; X64-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; X64-NEXT:    retq
+  %1 = and <8 x i16> %a0, <i16 -1, i16 -1, i16 -1, i16 -1, i16 15, i16 15, i16 15, i16 15>
+  %2 = shufflevector <8 x i16> %1, <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
+  %3 = shufflevector <8 x i16> %2, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %4 = sext <4 x i16> %3 to <4 x i32>
+  ret <4 x i32> %4
+}
+
+define <4 x i32> @knownbits_mask_shuffle_shuffle_undef_sext(<8 x i16> %a0) nounwind {
+; X32-LABEL: knownbits_mask_shuffle_shuffle_undef_sext:
+; X32:       # BB#0:
+; X32-NEXT:    vpand {{\.LCPI.*}}, %xmm0, %xmm0
 ; X32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
 ; X32-NEXT:    vpmovsxwd %xmm0, %xmm0
 ; X32-NEXT:    retl
 ;
-; X64-LABEL: knownbits_mask_shuffle_shuffle_sext:
+; X64-LABEL: knownbits_mask_shuffle_shuffle_undef_sext:
 ; X64:       # BB#0:
 ; X64-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; X64-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
 ; X64-NEXT:    vpmovsxwd %xmm0, %xmm0
 ; X64-NEXT:    retq
   %1 = and <8 x i16> %a0, <i16 -1, i16 -1, i16 -1, i16 -1, i16 15, i16 15, i16 15, i16 15>
-  %2 = shufflevector <8 x i16> %1, <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
+  %2 = shufflevector <8 x i16> %1, <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
   %3 = shufflevector <8 x i16> %2, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
   %4 = sext <4 x i16> %3 to <4 x i32>
   ret <4 x i32> %4