[X86][SSE] Added support for combining target shuffles to (V)PSHUFD/VPERMILPD/VPERMILPS immediate permutes

This patch allows target shuffles to be combined to single input immediate permute instructions - (V)PSHUFD/VPERMILPD/VPERMILPS - allowing more general pattern matching than what we current do and improves the likelihood of memory folding compared to existing patterns which tend to reuse the input in multiple arguments.

Further permute instructions (V)PSHUFLW/(V)PSHUFHW/(V)PERMQ/(V)PERMPD may be added in the future but its proven tricky to create tests cases for them so far. (V)PSHUFLW/(V)PSHUFHW is already handled quite well in combineTargetShuffle so it may be that removing some of that code may allow us to perform more of the combining in one place without duplication.

Differential Revision: http://reviews.llvm.org/D21148

llvm-svn: 273999

22 files changed, 218 insertions, 117 deletions

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index f9ebaea4d12..a5ee5372e99 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -7148,8 +7148,7 @@ static bool isTargetShuffleEquivalent(ArrayRef<int> Mask,
 /// example.
 ///
 /// NB: We rely heavily on "undef" masks preserving the input lane.
-static SDValue getV4X86ShuffleImm8ForMask(ArrayRef<int> Mask, const SDLoc &DL,
-                                          SelectionDAG &DAG) {
+static unsigned getV4X86ShuffleImm(ArrayRef<int> Mask) {
   assert(Mask.size() == 4 && "Only 4-lane shuffle masks");
   assert(Mask[0] >= -1 && Mask[0] < 4 && "Out of bound mask element!");
   assert(Mask[1] >= -1 && Mask[1] < 4 && "Out of bound mask element!");
@@ -7161,7 +7160,12 @@ static SDValue getV4X86ShuffleImm8ForMask(ArrayRef<int> Mask, const SDLoc &DL,
   Imm |= (Mask[1] < 0 ? 1 : Mask[1]) << 2;
   Imm |= (Mask[2] < 0 ? 2 : Mask[2]) << 4;
   Imm |= (Mask[3] < 0 ? 3 : Mask[3]) << 6;
-  return DAG.getConstant(Imm, DL, MVT::i8);
+  return Imm;
+}
+
+static SDValue getV4X86ShuffleImm8ForMask(ArrayRef<int> Mask, SDLoc DL,
+                                          SelectionDAG &DAG) {
+  return DAG.getConstant(getV4X86ShuffleImm(Mask), DL, MVT::i8);
 }
 
 /// \brief Compute whether each element of a shuffle is zeroable.
@@ -24529,7 +24533,8 @@ static SDValue combineShuffle256(SDNode *N, SelectionDAG &DAG,
 static bool matchUnaryVectorShuffle(MVT SrcVT, ArrayRef<int> Mask,
                                     const X86Subtarget &Subtarget,
                                     unsigned &Shuffle, MVT &ShuffleVT) {
-  bool FloatDomain = SrcVT.isFloatingPoint();
+  bool FloatDomain = SrcVT.isFloatingPoint() ||
+                     (!Subtarget.hasAVX2() && SrcVT.is256BitVector());
 
   // Match a 128-bit integer vector against a VZEXT_MOVL (MOVQ) instruction.
   if (!FloatDomain && SrcVT.is128BitVector() &&
@@ -24607,6 +24612,83 @@ static bool matchUnaryVectorShuffle(MVT SrcVT, ArrayRef<int> Mask,
   return false;
 }
 
+// Attempt to match a combined shuffle mask against supported unary immediate
+// permute instructions.
+// TODO: Investigate sharing more of this with shuffle lowering.
+static bool matchPermuteVectorShuffle(MVT SrcVT, ArrayRef<int> Mask,
+                                      const X86Subtarget &Subtarget,
+                                      unsigned &Shuffle, MVT &ShuffleVT,
+                                      unsigned &PermuteImm) {
+  // Ensure we don't contain any zero elements.
+  for (int M : Mask) {
+    if (M == SM_SentinelZero)
+      return false;
+    assert(SM_SentinelUndef <= M && M < (int)Mask.size() &&
+           "Expected unary shuffle");
+  }
+
+  // We only support permutation of 32/64 bit elements.
+  // TODO - support PSHUFLW/PSHUFHW.
+  unsigned MaskScalarSizeInBits = SrcVT.getSizeInBits() / Mask.size();
+  if (MaskScalarSizeInBits != 32 && MaskScalarSizeInBits != 64)
+    return false;
+  MVT MaskEltVT = MVT::getIntegerVT(MaskScalarSizeInBits);
+
+  // AVX introduced the VPERMILPD/VPERMILPS float permutes, before then we
+  // had to use 2-input SHUFPD/SHUFPS shuffles (not handled here).
+  bool FloatDomain = SrcVT.isFloatingPoint();
+  if (FloatDomain && !Subtarget.hasAVX())
+    return false;
+
+  // Pre-AVX2 we must use float shuffles on 256-bit vectors.
+  if (SrcVT.is256BitVector() && !Subtarget.hasAVX2())
+    FloatDomain = true;
+
+  // TODO - support LaneCrossing for AVX2 PERMQ/PERMPD
+  if (is128BitLaneCrossingShuffleMask(MaskEltVT, Mask))
+    return false;
+
+  // VPERMILPD can permute with a non-repeating shuffle.
+  if (FloatDomain && MaskScalarSizeInBits == 64) {
+    Shuffle = X86ISD::VPERMILPI;
+    ShuffleVT = MVT::getVectorVT(MVT::f64, Mask.size());
+    PermuteImm = 0;
+    for (int i = 0, e = Mask.size(); i != e; ++i) {
+      int M = Mask[i];
+      if (M == SM_SentinelUndef)
+        continue;
+      assert(((M / 2) == (i / 2)) && "Out of range shuffle mask index");
+      PermuteImm |= (M & 1) << i;
+    }
+    return true;
+  }
+
+  // We need a repeating shuffle mask for VPERMILPS/PSHUFD.
+  SmallVector<int, 4> RepeatedMask;
+  if (!is128BitLaneRepeatedShuffleMask(MaskEltVT, Mask, RepeatedMask))
+    return false;
+
+  // Narrow the repeated mask for 32-bit element permutes.
+  SmallVector<int, 4> WordMask = RepeatedMask;
+  if (MaskScalarSizeInBits == 64) {
+    WordMask.clear();
+    for (int M : RepeatedMask) {
+      if (M == SM_SentinelUndef) {
+        WordMask.append(2, SM_SentinelUndef);
+        continue;
+      }
+      WordMask.push_back((M * 2) + 0);
+      WordMask.push_back((M * 2) + 1);
+    }
+  }
+
+  Shuffle = (FloatDomain ? X86ISD::VPERMILPI : X86ISD::PSHUFD);
+  ShuffleVT = (FloatDomain ? MVT::f32 : MVT::i32);
+  ShuffleVT = MVT::getVectorVT(ShuffleVT, SrcVT.getSizeInBits() / 32);
+  PermuteImm = getV4X86ShuffleImm(WordMask);
+  return true;
+}
+
 // Attempt to match a combined unary shuffle mask against supported binary
 // shuffle instructions.
 // TODO: Investigate sharing more of this with shuffle lowering.
@@ -24708,7 +24790,7 @@ static bool combineX86ShuffleChain(SDValue Input, SDValue Root,
 
   // Attempt to match the mask against known shuffle patterns.
   MVT ShuffleVT;
-  unsigned Shuffle;
+  unsigned Shuffle, PermuteImm;
 
   if (matchUnaryVectorShuffle(VT, Mask, Subtarget, Shuffle, ShuffleVT)) {
     if (Depth == 1 && Root.getOpcode() == Shuffle)
@@ -24722,6 +24804,20 @@ static bool combineX86ShuffleChain(SDValue Input, SDValue Root,
     return true;
   }
 
+  if (matchPermuteVectorShuffle(VT, Mask, Subtarget, Shuffle, ShuffleVT,
+                                PermuteImm)) {
+    if (Depth == 1 && Root.getOpcode() == Shuffle)
+      return false; // Nothing to do!
+    Res = DAG.getBitcast(ShuffleVT, Input);
+    DCI.AddToWorklist(Res.getNode());
+    Res = DAG.getNode(Shuffle, DL, ShuffleVT, Res,
+                      DAG.getConstant(PermuteImm, DL, MVT::i8));
+    DCI.AddToWorklist(Res.getNode());
+    DCI.CombineTo(Root.getNode(), DAG.getBitcast(RootVT, Res),
+                  /*AddTo*/ true);
+    return true;
+  }
+
   if (matchBinaryVectorShuffle(VT, Mask, Shuffle, ShuffleVT)) {
     if (Depth == 1 && Root.getOpcode() == Shuffle)
       return false; // Nothing to do!
diff --git a/llvm/test/CodeGen/X86/2012-01-12-extract-sv.ll b/llvm/test/CodeGen/X86/2012-01-12-extract-sv.ll
index 68450add580..9bc4b5f55b6 100644
--- a/llvm/test/CodeGen/X86/2012-01-12-extract-sv.ll
+++ b/llvm/test/CodeGen/X86/2012-01-12-extract-sv.ll
@@ -6,7 +6,7 @@ define void @endless_loop() {
 ; CHECK-NEXT:    vmovaps (%eax), %ymm0
 ; CHECK-NEXT:    vextractf128 $1, %ymm0, %xmm0
 ; CHECK-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
-; CHECK-NEXT:    vmovddup {{.*#+}} xmm1 = xmm0[0,0]
+; CHECK-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[0,1,0,1]
 ; CHECK-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
 ; CHECK-NEXT:    vxorps %ymm2, %ymm2, %ymm2
 ; CHECK-NEXT:    vblendps {{.*#+}} ymm1 = ymm2[0,1,2,3,4,5,6],ymm1[7]
diff --git a/llvm/test/CodeGen/X86/2012-04-26-sdglue.ll b/llvm/test/CodeGen/X86/2012-04-26-sdglue.ll
index eaea7e857ea..2a76e1a66b2 100644
--- a/llvm/test/CodeGen/X86/2012-04-26-sdglue.ll
+++ b/llvm/test/CodeGen/X86/2012-04-26-sdglue.ll
@@ -10,9 +10,9 @@ define void @func() nounwind ssp {
 ; CHECK-NEXT:    vmovups 0, %xmm0
 ; CHECK-NEXT:    vxorps %ymm1, %ymm1, %ymm1
 ; CHECK-NEXT:    vblendps {{.*#+}} ymm2 = ymm0[0,1,2,3],ymm1[4,5,6,7]
-; CHECK-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,2,3,3]
-; CHECK-NEXT:    vpbroadcastd 32, %xmm3
-; CHECK-NEXT:    vinserti128 $1, %xmm3, %ymm0, %ymm0
+; CHECK-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[1,2,3,3]
+; CHECK-NEXT:    vbroadcastss 32, %xmm3
+; CHECK-NEXT:    vinsertf128 $1, %xmm3, %ymm0, %ymm0
 ; CHECK-NEXT:    vmulps %ymm0, %ymm2, %ymm2
 ; CHECK-NEXT:    vmulps %ymm0, %ymm0, %ymm0
 ; CHECK-NEXT:    vaddps %ymm0, %ymm2, %ymm0
diff --git a/llvm/test/CodeGen/X86/avx-intrinsics-fast-isel.ll b/llvm/test/CodeGen/X86/avx-intrinsics-fast-isel.ll
index cf90e5220fd..59eb4cdb195 100644
--- a/llvm/test/CodeGen/X86/avx-intrinsics-fast-isel.ll
+++ b/llvm/test/CodeGen/X86/avx-intrinsics-fast-isel.ll
@@ -2385,14 +2385,14 @@ define <4 x i64> @test_mm256_set1_epi32(i32 %a0) nounwind {
 ; X32-LABEL: test_mm256_set1_epi32:
 ; X32:       # BB#0:
 ; X32-NEXT:    vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; X32-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0]
+; X32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
 ; X32-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm256_set1_epi32:
 ; X64:       # BB#0:
 ; X64-NEXT:    vmovd %edi, %xmm0
-; X64-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0]
+; X64-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
 ; X64-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; X64-NEXT:    retq
   %res0 = insertelement <8 x i32> undef, i32 %a0, i32 0
@@ -2422,7 +2422,7 @@ define <4 x i64> @test_mm256_set1_epi64x(i64 %a0) nounwind {
 ; X64-LABEL: test_mm256_set1_epi64x:
 ; X64:       # BB#0:
 ; X64-NEXT:    vmovq %rdi, %xmm0
-; X64-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; X64-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
 ; X64-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; X64-NEXT:    retq
   %res0 = insertelement <4 x i64> undef, i64 %a0, i32 0
diff --git a/llvm/test/CodeGen/X86/avx-intrinsics-x86.ll b/llvm/test/CodeGen/X86/avx-intrinsics-x86.ll
index dc1414990ee..5e83cd0b603 100644
--- a/llvm/test/CodeGen/X86/avx-intrinsics-x86.ll
+++ b/llvm/test/CodeGen/X86/avx-intrinsics-x86.ll
@@ -4036,7 +4036,7 @@ define <4 x double> @test_x86_avx_vpermilvar_pd_256_2(<4 x double> %a0) {
 ;
 ; AVX512VL-LABEL: test_x86_avx_vpermilvar_pd_256_2:
 ; AVX512VL:       ## BB#0:
-; AVX512VL-NEXT:    vpermilpd LCPI227_0, %ymm0, %ymm0
+; AVX512VL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,3]
 ; AVX512VL-NEXT:    retl
   %res = call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %a0, <4 x i64> <i64 2, i64 0, i64 0, i64 2>) ; <<4 x double>> [#uses=1]
   ret <4 x double> %res
diff --git a/llvm/test/CodeGen/X86/avx-splat.ll b/llvm/test/CodeGen/X86/avx-splat.ll
index d3ae5498a2b..1914b5134be 100644
--- a/llvm/test/CodeGen/X86/avx-splat.ll
+++ b/llvm/test/CodeGen/X86/avx-splat.ll
@@ -28,7 +28,7 @@ define <4 x i64> @funcC(i64 %q) nounwind uwtable readnone ssp {
 ; CHECK-LABEL: funcC:
 ; CHECK:       ## BB#0: ## %entry
 ; CHECK-NEXT:    vmovq %rdi, %xmm0
-; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; CHECK-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
 ; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; CHECK-NEXT:    retq
 entry:
diff --git a/llvm/test/CodeGen/X86/avx-vbroadcast.ll b/llvm/test/CodeGen/X86/avx-vbroadcast.ll
index b7030035444..6151e76ab0b 100644
--- a/llvm/test/CodeGen/X86/avx-vbroadcast.ll
+++ b/llvm/test/CodeGen/X86/avx-vbroadcast.ll
@@ -173,13 +173,13 @@ define <8 x i32> @load_splat_8i32_4i32_33333333(<4 x i32>* %ptr) nounwind uwtabl
 ; X32-LABEL: load_splat_8i32_4i32_33333333:
 ; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    vpermilps {{.*#+}} xmm0 = mem[3,3,3,3]
+; X32-NEXT:    vpshufd {{.*#+}} xmm0 = mem[3,3,3,3]
 ; X32-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: load_splat_8i32_4i32_33333333:
 ; X64:       ## BB#0: ## %entry
-; X64-NEXT:    vpermilps {{.*#+}} xmm0 = mem[3,3,3,3]
+; X64-NEXT:    vpshufd {{.*#+}} xmm0 = mem[3,3,3,3]
 ; X64-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; X64-NEXT:    retq
 entry:
@@ -277,15 +277,13 @@ define <4 x i64> @load_splat_4i64_2i64_1111(<2 x i64>* %ptr) nounwind uwtable re
 ; X32-LABEL: load_splat_4i64_2i64_1111:
 ; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    vmovaps (%eax), %xmm0
-; X32-NEXT:    vmovhlps {{.*#+}} xmm0 = xmm0[1,1]
+; X32-NEXT:    vpshufd {{.*#+}} xmm0 = mem[2,3,2,3]
 ; X32-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: load_splat_4i64_2i64_1111:
 ; X64:       ## BB#0: ## %entry
-; X64-NEXT:    vmovaps (%rdi), %xmm0
-; X64-NEXT:    vmovhlps {{.*#+}} xmm0 = xmm0[1,1]
+; X64-NEXT:    vpshufd {{.*#+}} xmm0 = mem[2,3,2,3]
 ; X64-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; X64-NEXT:    retq
 entry:
diff --git a/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll b/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
index 401e6ccc5d8..59b7efdf9bf 100644
--- a/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
+++ b/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
@@ -760,7 +760,7 @@ define <4 x float> @merge_4f32_f32_X0YY(float* %ptr0, float* %ptr1) nounwind uwt
 ; AVX:       # BB#0:
 ; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
 ; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
-; AVX-NEXT:    vunpcklps {{.*#+}} xmm1 = xmm1[0,0,1,1]
+; AVX-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,0,1,1]
 ; AVX-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
 ; AVX-NEXT:    retq
 ;
diff --git a/llvm/test/CodeGen/X86/pshufb-mask-comments.ll b/llvm/test/CodeGen/X86/pshufb-mask-comments.ll
index b6f228c7d48..8364915fa0d 100644
--- a/llvm/test/CodeGen/X86/pshufb-mask-comments.ll
+++ b/llvm/test/CodeGen/X86/pshufb-mask-comments.ll
@@ -39,9 +39,9 @@ define <16 x i8> @test3(<16 x i8> %V) {
 define <16 x i8> @test4(<16 x i8> %V, <2 x i64>* %P) {
 ; CHECK-LABEL: test4:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movdqa {{.*#+}} xmm1 = [1084818905618843912,506097522914230528]
-; CHECK-NEXT:    movdqa %xmm1, (%rdi)
-; CHECK-NEXT:    pshufb %xmm1, %xmm0
+; CHECK-NEXT:    movaps {{.*#+}} xmm1 = [1084818905618843912,506097522914230528]
+; CHECK-NEXT:    movaps %xmm1, (%rdi)
+; CHECK-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
 ; CHECK-NEXT:    retq
   %1 = insertelement <2 x i64> undef, i64 1084818905618843912, i32 0
   %2 = insertelement <2 x i64>    %1, i64  506097522914230528, i32 1
diff --git a/llvm/test/CodeGen/X86/sse3.ll b/llvm/test/CodeGen/X86/sse3.ll
index e028a41b1ec..6d51fb54f8b 100644
--- a/llvm/test/CodeGen/X86/sse3.ll
+++ b/llvm/test/CodeGen/X86/sse3.ll
@@ -207,7 +207,7 @@ define <8 x i16> @t12(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
 ; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
 ; X64-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
-; X64-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,6,7,6,7]
+; X64-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,3,3]
 ; X64-NEXT:    retq
 entry:
 	%tmp9 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 0, i32 1, i32 undef, i32 undef, i32 3, i32 11, i32 undef , i32 undef >
@@ -220,7 +220,7 @@ define <8 x i16> @t13(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
 ; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
 ; X64-NEXT:    pshuflw {{.*#+}} xmm0 = xmm1[0,2,2,3,4,5,6,7]
-; X64-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,6,7,6,7]
+; X64-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,3,3]
 ; X64-NEXT:    retq
 entry:
 	%tmp9 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 8, i32 9, i32 undef, i32 undef, i32 11, i32 3, i32 undef , i32 undef >
diff --git a/llvm/test/CodeGen/X86/vector-compare-results.ll b/llvm/test/CodeGen/X86/vector-compare-results.ll
index bfe1a65eb54..6c93f69ba61 100644
--- a/llvm/test/CodeGen/X86/vector-compare-results.ll
+++ b/llvm/test/CodeGen/X86/vector-compare-results.ll
@@ -1,4 +1,3 @@
-; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE42
@@ -147,7 +146,7 @@ define <4 x i1> @test_cmp_v4f64(<4 x double> %a0, <4 x double> %a1) nounwind {
 ; AVX2-LABEL: test_cmp_v4f64:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vcmpltpd %ymm0, %ymm1, %ymm0
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6]
+; AVX2-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,3,2,3]
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
@@ -684,10 +683,10 @@ define <8 x i1> @test_cmp_v8f64(<8 x double> %a0, <8 x double> %a1) nounwind {
 ; AVX2-LABEL: test_cmp_v8f64:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vcmpltpd %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6]
+; AVX2-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,3,2,3]
 ; AVX2-NEXT:    vcmpltpd %ymm1, %ymm3, %ymm1
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,0,2,4,6,4,6]
+; AVX2-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[0,2,0,2,4,6,4,6]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,3,2,3]
 ; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero,ymm0[16,17,20,21,24,25,28,29],zero,zero,zero,zero,zero,zero,zero,zero
@@ -2143,10 +2142,10 @@ define <16 x i1> @test_cmp_v16f64(<16 x double> %a0, <16 x double> %a1) nounwind
 ; AVX2-LABEL: test_cmp_v16f64:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vcmpltpd %ymm2, %ymm6, %ymm2
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,0,2,4,6,4,6]
+; AVX2-NEXT:    vpermilps {{.*#+}} ymm2 = ymm2[0,2,0,2,4,6,4,6]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,3,2,3]
 ; AVX2-NEXT:    vcmpltpd %ymm3, %ymm7, %ymm3
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,2,0,2,4,6,4,6]
+; AVX2-NEXT:    vpermilps {{.*#+}} ymm3 = ymm3[0,2,0,2,4,6,4,6]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,3,2,3]
 ; AVX2-NEXT:    vinserti128 $1, %xmm3, %ymm2, %ymm2
 ; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,4,5,8,9,12,13,128,128,128,128,128,128,128,128,0,1,4,5,8,9,12,13,128,128,128,128,128,128,128,128]
@@ -2155,10 +2154,10 @@ define <16 x i1> @test_cmp_v16f64(<16 x double> %a0, <16 x double> %a1) nounwind
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm6 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm6, %xmm2, %xmm2
 ; AVX2-NEXT:    vcmpltpd %ymm0, %ymm4, %ymm0
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6]
+; AVX2-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,3,2,3]
 ; AVX2-NEXT:    vcmpltpd %ymm1, %ymm5, %ymm1
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,0,2,4,6,4,6]
+; AVX2-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[0,2,0,2,4,6,4,6]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,3,2,3]
 ; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-128-v16.ll b/llvm/test/CodeGen/X86/vector-shuffle-128-v16.ll
index 47036117e61..2651063379f 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-128-v16.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-128-v16.ll
@@ -925,7 +925,7 @@ define <16 x i8> @shuffle_v16i8_00_uu_uu_uu_uu_uu_uu_uu_01_uu_uu_uu_uu_uu_uu_uu(
 ; SSE2:       # BB#0:
 ; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
 ; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
-; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0,0,1,1]
+; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: shuffle_v16i8_00_uu_uu_uu_uu_uu_uu_uu_01_uu_uu_uu_uu_uu_uu_uu:
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-128-v2.ll b/llvm/test/CodeGen/X86/vector-shuffle-128-v2.ll
index 28947e7b670..0d50205aa4a 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-128-v2.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-128-v2.ll
@@ -159,7 +159,7 @@ define <2 x double> @shuffle_v2f64_11(<2 x double> %a, <2 x double> %b) {
 ;
 ; AVX-LABEL: shuffle_v2f64_11:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vmovhlps {{.*#+}} xmm0 = xmm0[1,1]
+; AVX-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,1]
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <2 x double> %a, <2 x double> %b, <2 x i32> <i32 1, i32 1>
   ret <2 x double> %shuffle
@@ -217,7 +217,7 @@ define <2 x double> @shuffle_v2f64_33(<2 x double> %a, <2 x double> %b) {
 ;
 ; AVX-LABEL: shuffle_v2f64_33:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vmovhlps {{.*#+}} xmm0 = xmm1[1,1]
+; AVX-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm1[1,1]
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <2 x double> %a, <2 x double> %b, <2 x i32> <i32 3, i32 3>
   ret <2 x double> %shuffle
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll b/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll
index 8516e523aa5..76a403ae358 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll
@@ -227,7 +227,7 @@ define <4 x float> @shuffle_v4f32_0011(<4 x float> %a, <4 x float> %b) {
 ;
 ; AVX-LABEL: shuffle_v4f32_0011:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vunpcklps {{.*#+}} xmm0 = xmm0[0,0,1,1]
+; AVX-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,1]
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 0, i32 1, i32 1>
   ret <4 x float> %shuffle
@@ -240,7 +240,7 @@ define <4 x float> @shuffle_v4f32_2233(<4 x float> %a, <4 x float> %b) {
 ;
 ; AVX-LABEL: shuffle_v4f32_2233:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vunpckhps {{.*#+}} xmm0 = xmm0[2,2,3,3]
+; AVX-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,2,3,3]
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 2, i32 2, i32 3, i32 3>
   ret <4 x float> %shuffle
@@ -1952,30 +1952,16 @@ define <4 x i32> @mask_v4i32_0127(<4 x i32> %a, <4 x i32> %b) {
 }
 
 define <4 x float> @broadcast_v4f32_0101_from_v2f32(<2 x float>* %x) {
-; SSE2-LABEL: broadcast_v4f32_0101_from_v2f32:
-; SSE2:       # BB#0:
-; SSE2-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
-; SSE2-NEXT:    shufpd {{.*#+}} xmm0 = xmm0[0,0]
-; SSE2-NEXT:    retq
-;
-; SSE3-LABEL: broadcast_v4f32_0101_from_v2f32:
-; SSE3:       # BB#0:
-; SSE3-NEXT:    movddup {{.*#+}} xmm0 = mem[0,0]
-; SSE3-NEXT:    retq
-;
-; SSSE3-LABEL: broadcast_v4f32_0101_from_v2f32:
-; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = mem[0,0]
-; SSSE3-NEXT:    retq
-;
-; SSE41-LABEL: broadcast_v4f32_0101_from_v2f32:
-; SSE41:       # BB#0:
-; SSE41-NEXT:    movddup {{.*#+}} xmm0 = mem[0,0]
-; SSE41-NEXT:    retq
+; SSE-LABEL: broadcast_v4f32_0101_from_v2f32:
+; SSE:       # BB#0:
+; SSE-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
+; SSE-NEXT:    retq
 ;
 ; AVX-LABEL: broadcast_v4f32_0101_from_v2f32:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
+; AVX-NEXT:    vmovq {{.*#+}} xmm0 = mem[0],zero
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
 ; AVX-NEXT:    retq
   %1 = load <2 x float>, <2 x float>* %x, align 1
   %2 = shufflevector <2 x float> %1, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-256-v16.ll b/llvm/test/CodeGen/X86/vector-shuffle-256-v16.ll
index 23fbba61dab..e838278a227 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-256-v16.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-256-v16.ll
@@ -1443,7 +1443,7 @@ define <16 x i16> @shuffle_v16i16_02_03_zz_zz_06_07_zz_zz_10_11_zz_zz_14_15_zz_z
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vxorps %ymm1, %ymm1, %ymm1
 ; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: shuffle_v16i16_02_03_zz_zz_06_07_zz_zz_10_11_zz_zz_14_15_zz_zz:
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll b/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll
index 9c7ec845450..5bc04ae0770 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll
@@ -488,7 +488,7 @@ define <4 x double> @shuffle_v4f64_15uu(<4 x double> %a, <4 x double> %b) {
 define <4 x double> @shuffle_v4f64_11uu(<4 x double> %a, <4 x double> %b) {
 ; ALL-LABEL: shuffle_v4f64_11uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vmovhlps {{.*#+}} xmm0 = xmm0[1,1]
+; ALL-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,1]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 1, i32 undef, i32 undef>
   ret <4 x double> %shuffle
@@ -557,7 +557,7 @@ define <4 x i64> @shuffle_v4i64_0000(<4 x i64> %a, <4 x i64> %b) {
 define <4 x i64> @shuffle_v4i64_0001(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-LABEL: shuffle_v4i64_0001:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm1 = xmm0[0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -579,7 +579,7 @@ define <4 x i64> @shuffle_v4i64_0020(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0]
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -641,8 +641,8 @@ define <4 x i64> @shuffle_v4i64_0300(<4 x i64> %a, <4 x i64> %b) {
 define <4 x i64> @shuffle_v4i64_1000(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-LABEL: shuffle_v4i64_1000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -800,7 +800,7 @@ define <4 x i64> @shuffle_v4i64_4012(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vshufpd {{.*#+}} xmm2 = xmm0[1],xmm2[0]
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3]
 ; AVX1-NEXT:    retq
@@ -1320,7 +1320,7 @@ define <4 x double> @splat_v4f64(<2 x double> %r) {
 define <4 x i64> @splat_mem_v4i64_from_v2i64(<2 x i64>* %ptr) {
 ; AVX1-LABEL: splat_mem_v4i64_from_v2i64:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = mem[0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -1397,7 +1397,7 @@ define <4 x double> @splat128_mem_v4f64_from_v2f64(<2 x double>* %ptr) {
 define <4 x double> @broadcast_v4f64_0000_from_v2i64(<2 x i64> %a0) {
 ; AVX1-LABEL: broadcast_v4f64_0000_from_v2i64:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll b/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
index ceda13c22ee..f9448d9cf96 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
@@ -152,8 +152,8 @@ define <8 x float> @shuffle_v8f32_01014545(<8 x float> %a, <8 x float> %b) {
 define <8 x float> @shuffle_v8f32_00112233(<8 x float> %a, <8 x float> %b) {
 ; AVX1-LABEL: shuffle_v8f32_00112233:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vunpcklps {{.*#+}} xmm1 = xmm0[0,0,1,1]
-; AVX1-NEXT:    vunpckhps {{.*#+}} xmm0 = xmm0[2,2,3,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,1,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,2,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -196,7 +196,7 @@ define <8 x float> @shuffle_v8f32_08080808(<8 x float> %a, <8 x float> %b) {
 ; AVX1-LABEL: shuffle_v8f32_08080808:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0]
-; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2,1,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,2,1,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -213,7 +213,7 @@ define <8 x float> @shuffle_v8f32_08084c4c(<8 x float> %a, <8 x float> %b) {
 ; ALL-LABEL: shuffle_v8f32_08084c4c:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,0],ymm1[0,0],ymm0[4,4],ymm1[4,4]
-; ALL-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 4, i32 12, i32 4, i32 12>
   ret <8 x float> %shuffle
@@ -907,8 +907,8 @@ define <8 x i32> @shuffle_v8i32_00000000(<8 x i32> %a, <8 x i32> %b) {
 define <8 x i32> @shuffle_v8i32_00000010(<8 x i32> %a, <8 x i32> %b) {
 ; AVX1-LABEL: shuffle_v8i32_00000010:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -924,8 +924,8 @@ define <8 x i32> @shuffle_v8i32_00000010(<8 x i32> %a, <8 x i32> %b) {
 define <8 x i32> @shuffle_v8i32_00000200(<8 x i32> %a, <8 x i32> %b) {
 ; AVX1-LABEL: shuffle_v8i32_00000200:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,2,0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -941,8 +941,8 @@ define <8 x i32> @shuffle_v8i32_00000200(<8 x i32> %a, <8 x i32> %b) {
 define <8 x i32> @shuffle_v8i32_00003000(<8 x i32> %a, <8 x i32> %b) {
 ; AVX1-LABEL: shuffle_v8i32_00003000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,0,0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[3,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -1042,8 +1042,8 @@ define <8 x i32> @shuffle_v8i32_01014545(<8 x i32> %a, <8 x i32> %b) {
 define <8 x i32> @shuffle_v8i32_00112233(<8 x i32> %a, <8 x i32> %b) {
 ; AVX1-LABEL: shuffle_v8i32_00112233:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,1,1]
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,2,3,3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[0,0,1,1]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -1059,8 +1059,8 @@ define <8 x i32> @shuffle_v8i32_00112233(<8 x i32> %a, <8 x i32> %b) {
 define <8 x i32> @shuffle_v8i32_00001111(<8 x i32> %a, <8 x i32> %b) {
 ; AVX1-LABEL: shuffle_v8i32_00001111:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,1,1,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -1091,7 +1091,7 @@ define <8 x i32> @shuffle_v8i32_08080808(<8 x i32> %a, <8 x i32> %b) {
 ; AVX1-LABEL: shuffle_v8i32_08080808:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0]
-; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2,1,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,2,1,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
@@ -1108,7 +1108,7 @@ define <8 x i32> @shuffle_v8i32_08084c4c(<8 x i32> %a, <8 x i32> %b) {
 ; AVX1-LABEL: shuffle_v8i32_08084c4c:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,0],ymm1[0,0],ymm0[4,4],ymm1[4,4]
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: shuffle_v8i32_08084c4c:
@@ -1239,8 +1239,8 @@ define <8 x i32> @shuffle_v8i32_08991abb(<8 x i32> %a, <8 x i32> %b) {
 define <8 x i32> @shuffle_v8i32_091b2d3f(<8 x i32> %a, <8 x i32> %b) {
 ; AVX1-LABEL: shuffle_v8i32_091b2d3f:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[0,1,1,3]
-; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,1,3,3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm0[0,1,1,3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,1,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
 ; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX1-NEXT:    retq
@@ -1257,7 +1257,7 @@ define <8 x i32> @shuffle_v8i32_091b2d3f(<8 x i32> %a, <8 x i32> %b) {
 define <8 x i32> @shuffle_v8i32_09ab1def(<8 x i32> %a, <8 x i32> %b) {
 ; AVX1-LABEL: shuffle_v8i32_09ab1def:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
 ; AVX1-NEXT:    retq
@@ -2050,7 +2050,7 @@ define <8 x i32> @shuffle_v8i32_z0U2zUz6(<8 x i32> %a) {
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vxorps %ymm1, %ymm1, %ymm1
 ; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[2,0,3,1,6,4,7,5]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[2,0,3,1,6,4,7,5]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: shuffle_v8i32_z0U2zUz6:
@@ -2066,7 +2066,7 @@ define <8 x i32> @shuffle_v8i32_1U3z5zUU(<8 x i32> %a) {
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vxorps %ymm1, %ymm1, %ymm1
 ; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: shuffle_v8i32_1U3z5zUU:
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll
index 3ab7d0be530..fea24ab4545 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll
@@ -67,7 +67,7 @@ define <4 x float> @combine_vpermilvar_4f32_movsldup(<4 x float> %a0) {
 define <4 x float> @combine_vpermilvar_4f32_unpckh(<4 x float> %a0) {
 ; ALL-LABEL: combine_vpermilvar_4f32_unpckh:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vunpckhps {{.*#+}} xmm0 = xmm0[2,2,3,3]
+; ALL-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,2,3,3]
 ; ALL-NEXT:    retq
   %1 = tail call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> <i32 2, i32 2, i32 3, i32 3>)
   ret <4 x float> %1
@@ -76,7 +76,7 @@ define <4 x float> @combine_vpermilvar_4f32_unpckh(<4 x float> %a0) {
 define <4 x float> @combine_vpermilvar_4f32_unpckl(<4 x float> %a0) {
 ; ALL-LABEL: combine_vpermilvar_4f32_unpckl:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vunpcklps {{.*#+}} xmm0 = xmm0[0,0,1,1]
+; ALL-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,1]
 ; ALL-NEXT:    retq
   %1 = tail call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> <i32 0, i32 0, i32 1, i32 1>)
   ret <4 x float> %1
@@ -167,7 +167,7 @@ define <4 x double> @combine_vpermilvar_4f64_movddup(<4 x double> %a0) {
 define <4 x float> @combine_vpermilvar_4f32_4stage(<4 x float> %a0) {
 ; ALL-LABEL: combine_vpermilvar_4f32_4stage:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[8,9,10,11,0,1,2,3,12,13,14,15,4,5,6,7]
+; ALL-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,0,3,1]
 ; ALL-NEXT:    retq
   %1 = tail call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> <i32 3, i32 2, i32 1, i32 0>)
   %2 = tail call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float>  %1, <4 x i32> <i32 2, i32 3, i32 0, i32 1>)
@@ -177,24 +177,10 @@ define <4 x float> @combine_vpermilvar_4f32_4stage(<4 x float> %a0) {
 }
 
 define <8 x float> @combine_vpermilvar_8f32_4stage(<8 x float> %a0) {
-; AVX1-LABEL: combine_vpermilvar_8f32_4stage:
-; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovaps {{.*#+}} ymm1 = [3,2,1,0,3,2,1,0]
-; AVX1-NEXT:    vpermilps %ymm1, %ymm0, %ymm0
-; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[2,3,0,1,6,7,4,5]
-; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
-; AVX1-NEXT:    vpermilps %ymm1, %ymm0, %ymm0
-; AVX1-NEXT:    retq
-;
-; AVX2-LABEL: combine_vpermilvar_8f32_4stage:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,0,1,2,3,12,13,14,15,4,5,6,7,24,25,26,27,16,17,18,19,28,29,30,31,20,21,22,23]
-; AVX2-NEXT:    retq
-;
-; AVX512F-LABEL: combine_vpermilvar_8f32_4stage:
-; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,0,1,2,3,12,13,14,15,4,5,6,7,24,25,26,27,16,17,18,19,28,29,30,31,20,21,22,23]
-; AVX512F-NEXT:    retq
+; ALL-LABEL: combine_vpermilvar_8f32_4stage:
+; ALL:       # BB#0:
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[2,0,3,1,6,4,7,5]
+; ALL-NEXT:    retq
   %1 = tail call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %a0, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0>)
   %2 = tail call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float>  %1, <8 x i32> <i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1>)
   %3 = tail call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float>  %2, <8 x i32> <i32 0, i32 2, i32 1, i32 3, i32 0, i32 2, i32 1, i32 3>)
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
index 1f8531a91b4..b6e66c980e9 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
@@ -51,7 +51,7 @@ define <4 x i64> @combine_permq_pshufb(<4 x i64> %a0) {
 ; CHECK-LABEL: combine_permq_pshufb:
 ; CHECK:       # BB#0:
 ; CHECK-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,2,1,0]
-; CHECK-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,12,13,14,15,0,1,2,3,4,5,6,7,24,25,26,27,28,29,30,31,16,17,18,19,20,21,22,23]
+; CHECK-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[2,3,0,1,6,7,4,5]
 ; CHECK-NEXT:    retq
   %1 = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
   %2 = bitcast <4 x i64> %1 to <32 x i8>
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx512bw.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx512bw.ll
index 658aab594f4..f89294c3013 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx512bw.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx512bw.ll
@@ -212,6 +212,43 @@ define <16 x float> @combine_vpermt2var_16f32_vmovsldup_mask_load(<16 x float> *
   ret <16 x float> %res0
 }
 
+define <16 x float> @combine_vpermt2var_16f32_vpermilps(<16 x float> %x0, <16 x float> %x1) {
+; CHECK-LABEL: combine_vpermt2var_16f32_vpermilps:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vpermilps {{.*#+}} zmm0 = zmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
+; CHECK-NEXT:    retq
+  %res0 = call <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>, <16 x float> %x0, <16 x float> %x1, i16 -1)
+  ret <16 x float> %res0
+}
+define <16 x float> @combine_vpermt2var_16f32_vpermilps_load(<16 x float> *%p0, <16 x float> %x1) {
+; CHECK-LABEL: combine_vpermt2var_16f32_vpermilps_load:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vpermilps {{.*#+}} zmm0 = mem[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
+; CHECK-NEXT:    retq
+  %x0 = load <16 x float>, <16 x float> *%p0
+  %res0 = call <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>, <16 x float> %x0, <16 x float> %x1, i16 -1)
+  ret <16 x float> %res0
+}
+define <16 x float> @combine_vpermt2var_16f32_vpermilps_mask(<16 x float> %x0, <16 x float> %x1, i16 %m) {
+; CHECK-LABEL: combine_vpermt2var_16f32_vpermilps_mask:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    kmovw %edi, %k1
+; CHECK-NEXT:    vpermilps {{.*#+}} zmm0 = zmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
+; CHECK-NEXT:    retq
+  %res0 = call <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>, <16 x float> %x0, <16 x float> %x1, i16 %m)
+  ret <16 x float> %res0
+}
+define <16 x float> @combine_vpermt2var_16f32_vpermilps_mask_load(<16 x float> *%p0, <16 x float> %x1, i16 %m) {
+; CHECK-LABEL: combine_vpermt2var_16f32_vpermilps_mask_load:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    kmovw %esi, %k1
+; CHECK-NEXT:    vpermilps {{.*#+}} zmm0 = mem[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
+; CHECK-NEXT:    retq
+  %x0 = load <16 x float>, <16 x float> *%p0
+  %res0 = call <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>, <16 x float> %x0, <16 x float> %x1, i16 %m)
+  ret <16 x float> %res0
+}
+
 define <16 x i32> @combine_vpermt2var_16i32_identity(<16 x i32> %x0, <16 x i32> %x1) {
 ; CHECK-LABEL: combine_vpermt2var_16i32_identity:
 ; CHECK:       # BB#0:
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining-ssse3.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining-ssse3.ll
index e893d9f8262..4667cb45768 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining-ssse3.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining-ssse3.ll
@@ -94,13 +94,12 @@ define <4 x float> @combine_pshufb_movsldup(<4 x float> %a0) {
 define <16 x i8> @combine_pshufb_palignr(<16 x i8> %a0, <16 x i8> %a1) {
 ; SSE-LABEL: combine_pshufb_palignr:
 ; SSE:       # BB#0:
-; SSE-NEXT:    pshufb {{.*#+}} xmm1 = xmm1[8,9,10,11,12,13,14,15,8,9,10,11,12,13,14,15]
-; SSE-NEXT:    movdqa %xmm1, %xmm0
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
 ; SSE-NEXT:    retq
 ;
 ; AVX-LABEL: combine_pshufb_palignr:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm1[8,9,10,11,12,13,14,15,8,9,10,11,12,13,14,15]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
 ; AVX-NEXT:    retq
   %1 = shufflevector <16 x i8> %a0, <16 x i8> %a1, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
   %2 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %1, <16 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7>)
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
index aa7363669a0..266a3658eda 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
@@ -2440,7 +2440,7 @@ define <4 x float> @combine_undef_input_test9(<4 x float> %a) {
 ;
 ; AVX-LABEL: combine_undef_input_test9:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vmovhlps {{.*#+}} xmm0 = xmm0[1,1]
+; AVX-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,1]
 ; AVX-NEXT:    retq
   %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 5, i32 5>
   %2 = shufflevector <4 x float> %1, <4 x float> %a, <4 x i32> <i32 6, i32 7, i32 0, i32 1>
@@ -2631,7 +2631,7 @@ define <4 x float> @combine_undef_input_test19(<4 x float> %a) {
 ;
 ; AVX-LABEL: combine_undef_input_test19:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vmovhlps {{.*#+}} xmm0 = xmm0[1,1]
+; AVX-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,1]
 ; AVX-NEXT:    retq
   %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 5, i32 5>
   %2 = shufflevector <4 x float> %a, <4 x float> %1, <4 x i32> <i32 2, i32 3, i32 4, i32 5>