Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -9388,6 +9388,99 @@
   return SDValue();
 }
 
+static bool maskContainsSequenceForVPMOV(ArrayRef<int> Mask, bool SwappedOps,
+                                         int delta)
+{
+  if (SwappedOps) {
+    for (int i = 0; (size_t)i < Mask.size() / delta; ++i) {
+      if ((size_t)Mask[i] != Mask.size() + i * delta)
+        return false;
+    }
+
+    for (int i = Mask.size() / delta; (size_t)i < Mask.size(); ++i) {
+      if ((size_t)Mask[i] >= Mask.size() && (size_t)Mask[i] < Mask.size() * 2)
+        return false;
+    }
+  } else {
+    for (int i = 0; (size_t)i < Mask.size() / delta; ++i) {
+      if (Mask[i] != i * delta)
+        return false;
+    }
+
+    for (int i = Mask.size() / delta; (size_t)i < Mask.size(); ++i) {
+      if (Mask[i] >= 0 && (size_t)Mask[i] < Mask.size())
+        return false;
+    }
+  }
+
+  return true;
+}
+
+// Try to lower trunc+vector_shuffle to a vpmovdb or a vpmovdw instruction.
+//
+// An example is the following:
+//
+// t0: ch = EntryToken
+//           t2: v4i64,ch = CopyFromReg t0, Register:v4i64 %0
+//         t25: v4i32 = truncate t2
+//       t41: v8i16 = bitcast t25
+//       t21: v8i16 = BUILD_VECTOR undef:i16, undef:i16, undef:i16, undef:i16, Constant:i16<0>, Constant:i16<0>, Constant:i16<0>, Constant:i16<0>
+//     t51: v8i16 = vector_shuffle<0,2,4,6,12,13,14,15> t41, t21
+//   t18: v2i64 = bitcast t51
+//
+// Without avx512vl, this is lowered to:
+//
+// vpmovqd %zmm0, %ymm0
+// vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+//
+// But when avx512vl is available, one can just use a single vpmovdw instruction.
+static SDValue lowerVectorShuffleWithVPMOV(const SDLoc &DL, ArrayRef<int> Mask,
+                                           MVT VT, SDValue V1, SDValue V2,
+                                           SelectionDAG &DAG,
+                                           const X86Subtarget &Subtarget) {
+  if (!Subtarget.hasVLX())
+    return SDValue();
+
+  if (VT != MVT::v16i8 && VT != MVT::v8i16)
+    return SDValue();
+
+  bool SwappedOps = false;
+
+  if (!ISD::isBuildVectorAllZeros(V2.getNode())) {
+    if (!ISD::isBuildVectorAllZeros(V1.getNode()))
+      return SDValue();
+
+    std::swap(V1, V2);
+    SwappedOps = true;
+  }
+
+  // Look for:
+  //
+  // bitcast (truncate <8 x i32> %vec to <8 x i16>) to <16 x i8>
+  // bitcast (truncate <4 x i64> %vec to <4 x i32>) to <8 x i16>
+  //
+  // and similar ones.
+  if (V1.getOpcode() != ISD::BITCAST)
+    return SDValue();
+  if (V1.getOperand(0).getOpcode() != ISD::TRUNCATE)
+    return SDValue();
+
+  // Look for a mask that looks like <0, 2, 4, 6, #, #, #, #>
+  // or <0, 4, 8, 12, #, #, #, #>
+  size_t N = VT.getVectorNumElements();
+
+  if (Mask.size() != N)
+    return SDValue();
+
+  // The first half/quarter of the mask should refer to every second/fourth
+  // element of the vector truncated and bitcasted.
+  if (!maskContainsSequenceForVPMOV(Mask, SwappedOps, 2) &&
+      !maskContainsSequenceForVPMOV(Mask, SwappedOps, 4))
+     return SDValue();
+
+  return DAG.getNode(X86ISD::VTRUNC, DL, VT, V1.getOperand(0).getOperand(0));
+}
+
 // X86 has dedicated pack instructions that can handle specific truncation
 // operations: PACKSS and PACKUS.
 static bool matchVectorShuffleWithPACK(MVT VT, MVT &SrcVT, SDValue &V1,
@@ -14923,6 +15016,10 @@
   if (canonicalizeShuffleMaskWithCommute(Mask))
     return DAG.getCommutedVectorShuffle(*SVOp);
 
+  if (SDValue V = lowerVectorShuffleWithVPMOV(DL, Mask, VT, V1, V2, DAG,
+                                              Subtarget))
+    return V;
+
   // For each vector width, delegate to a specialized lowering routine.
   if (VT.is128BitVector())
     return lower128BitVectorShuffle(DL, Mask, VT, V1, V2, Zeroable, Subtarget,
Index: test/CodeGen/X86/shuffle-vs-trunc-256.ll
===================================================================
--- test/CodeGen/X86/shuffle-vs-trunc-256.ll
+++ test/CodeGen/X86/shuffle-vs-trunc-256.ll
@@ -479,6 +479,646 @@
   ret void
 }
 
+define <2 x i64> @trunc_v8i32_to_v8i8_return_v2i64(<8 x i32> %vec) nounwind {
+; IR generated from:
+; return (__m128i) {(long long)__builtin_convertvector((__v8si)__A, __v8qi), 0};
+; AVX1-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
+;
+; AVX512F-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512F-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
+; AVX512VL:       # %bb.0:
+; AVX512VL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512BW-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+;
+; AVX512VBMIVL-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
+; AVX512VBMIVL:       # %bb.0:
+; AVX512VBMIVL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512VBMIVL-NEXT:    vzeroupper
+; AVX512VBMIVL-NEXT:    retq
+  %truncated.vec = trunc <8 x i32> %vec to <8 x i8>
+  %bc = bitcast <8 x i8> %truncated.vec to i64
+  %result = insertelement <2 x i64> zeroinitializer, i64 %bc, i32 0
+  ret <2 x i64> %result
+}
+
+define <16 x i8> @trunc_v8i32_to_v8i8_with_zext_return_v16i8(<8 x i32> %vec) nounwind {
+; AVX1-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
+;
+; AVX512F-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512F-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
+; AVX512VL:       # %bb.0:
+; AVX512VL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512BW-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+;
+; AVX512VBMIVL-LABEL: trunc_v8i32_to_v8i8_with_zext_return_v16i8:
+; AVX512VBMIVL:       # %bb.0:
+; AVX512VBMIVL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512VBMIVL-NEXT:    vzeroupper
+; AVX512VBMIVL-NEXT:    retq
+  %truncated = trunc <8 x i32> %vec to <8 x i8>
+  %truncated.ext = zext <8 x i8> %truncated to <8 x i16>
+  %bc = bitcast <8 x i16> %truncated.ext to <16 x i8>
+  %result = shufflevector <16 x i8> %bc, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+  ret <16 x i8> %result
+}
+
+define <16 x i8> @trunc_v8i32_to_v8i8_via_v8i16_return_v16i8(<8 x i32> %vec) nounwind {
+; AVX1-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
+;
+; AVX512F-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512F-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
+; AVX512VL:       # %bb.0:
+; AVX512VL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512BW-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+;
+; AVX512VBMIVL-LABEL: trunc_v8i32_to_v8i8_via_v8i16_return_v16i8:
+; AVX512VBMIVL:       # %bb.0:
+; AVX512VBMIVL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512VBMIVL-NEXT:    vzeroupper
+; AVX512VBMIVL-NEXT:    retq
+  %truncated = trunc <8 x i32> %vec to <8 x i16>
+  %bc = bitcast <8 x i16> %truncated to <16 x i8>
+  %result = shufflevector <16 x i8> %bc, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 17, i32 20, i32 24, i32 22, i32 31, i32 28, i32 28, i32 29>
+  ret <16 x i8> %result
+}
+
+define <16 x i8> @trunc_v8i32_to_v8i8_return_v16i8(<8 x i32> %vec) nounwind {
+; AVX1-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
+;
+; AVX512F-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512F-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
+; AVX512VL:       # %bb.0:
+; AVX512VL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512BW-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+;
+; AVX512VBMIVL-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
+; AVX512VBMIVL:       # %bb.0:
+; AVX512VBMIVL-NEXT:    vpmovdb %ymm0, %xmm0
+; AVX512VBMIVL-NEXT:    vzeroupper
+; AVX512VBMIVL-NEXT:    retq
+  %truncated = trunc <8 x i32> %vec to <8 x i8>
+  %result = shufflevector <8 x i8> %truncated, <8 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  ret <16 x i8> %result
+}
+
+define <2 x i64> @trunc_v4i64_to_v4i16_return_v2i64(<4 x i64> %vec) nounwind {
+; IR generated from:
+; return (__m128i) {(long long)__builtin_convertvector((__v4di)x, __v4hi), 0};
+; AVX1-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-SLOW-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
+; AVX2-SLOW:       # %bb.0:
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
+; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-SLOW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-SLOW-NEXT:    vzeroupper
+; AVX2-SLOW-NEXT:    retq
+;
+; AVX2-FAST-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
+; AVX2-FAST:       # %bb.0:
+; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
+; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm1, %ymm0
+; AVX2-FAST-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-FAST-NEXT:    vzeroupper
+; AVX2-FAST-NEXT:    retq
+;
+; AVX512F-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
+; AVX512VL:       # %bb.0:
+; AVX512VL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+;
+; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
+; AVX512VBMIVL:       # %bb.0:
+; AVX512VBMIVL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512VBMIVL-NEXT:    vzeroupper
+; AVX512VBMIVL-NEXT:    retq
+  %truncated = trunc <4 x i64> %vec to <4 x i16>
+  %bc = bitcast <4 x i16> %truncated to i64
+  %result = insertelement <2 x i64> zeroinitializer, i64 %bc, i32 0
+  ret <2 x i64> %result
+}
+
+define <8 x i16> @trunc_v4i64_to_v4i16_with_zext_return_v8i16(<4 x i64> %vec) nounwind {
+; AVX1-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-SLOW-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
+; AVX2-SLOW:       # %bb.0:
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
+; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-SLOW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-SLOW-NEXT:    vzeroupper
+; AVX2-SLOW-NEXT:    retq
+;
+; AVX2-FAST-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
+; AVX2-FAST:       # %bb.0:
+; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
+; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm1, %ymm0
+; AVX2-FAST-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-FAST-NEXT:    vzeroupper
+; AVX2-FAST-NEXT:    retq
+;
+; AVX512F-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
+; AVX512VL:       # %bb.0:
+; AVX512VL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+;
+; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i16_with_zext_return_v8i16:
+; AVX512VBMIVL:       # %bb.0:
+; AVX512VBMIVL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512VBMIVL-NEXT:    vzeroupper
+; AVX512VBMIVL-NEXT:    retq
+  %truncated = trunc <4 x i64> %vec to <4 x i16>
+  %truncated.ext = zext <4 x i16> %truncated to <4 x i32>
+  %bc = bitcast <4 x i32> %truncated.ext to <8 x i16>
+  %result = shufflevector <8 x i16> %bc, <8 x i16> zeroinitializer, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>
+  ret <8 x i16> %result
+}
+
+define <8 x i16> @trunc_v4i64_to_v4i16_via_v4i32_return_v8i16(<4 x i64> %vec) nounwind {
+; AVX1-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-SLOW-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
+; AVX2-SLOW:       # %bb.0:
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
+; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-SLOW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-SLOW-NEXT:    vzeroupper
+; AVX2-SLOW-NEXT:    retq
+;
+; AVX2-FAST-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
+; AVX2-FAST:       # %bb.0:
+; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
+; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm1, %ymm0
+; AVX2-FAST-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-FAST-NEXT:    vzeroupper
+; AVX2-FAST-NEXT:    retq
+;
+; AVX512F-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
+; AVX512VL:       # %bb.0:
+; AVX512VL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+;
+; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i16_via_v4i32_return_v8i16:
+; AVX512VBMIVL:       # %bb.0:
+; AVX512VBMIVL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512VBMIVL-NEXT:    vzeroupper
+; AVX512VBMIVL-NEXT:    retq
+  %truncated = trunc <4 x i64> %vec to <4 x i32>
+  %bc = bitcast <4 x i32> %truncated to <8 x i16>
+  %result = shufflevector <8 x i16> %bc, <8 x i16> zeroinitializer, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 8, i32 undef, i32 13>
+  ret <8 x i16> %result
+}
+
+define <8 x i16> @trunc_v4i64_to_v4i16_return_v8i16(<4 x i64> %vec) nounwind {
+; AVX1-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-SLOW-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
+; AVX2-SLOW:       # %bb.0:
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
+; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-SLOW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-SLOW-NEXT:    vzeroupper
+; AVX2-SLOW-NEXT:    retq
+;
+; AVX2-FAST-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
+; AVX2-FAST:       # %bb.0:
+; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
+; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm1, %ymm0
+; AVX2-FAST-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-FAST-NEXT:    vzeroupper
+; AVX2-FAST-NEXT:    retq
+;
+; AVX512F-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
+; AVX512VL:       # %bb.0:
+; AVX512VL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+;
+; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
+; AVX512VBMIVL:       # %bb.0:
+; AVX512VBMIVL-NEXT:    vpmovqw %ymm0, %xmm0
+; AVX512VBMIVL-NEXT:    vzeroupper
+; AVX512VBMIVL-NEXT:    retq
+  %truncated = trunc <4 x i64> %vec to <4 x i16>
+  %result = shufflevector <4 x i16> %truncated, <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  ret <8 x i16> %result
+}
+
+define <16 x i8> @trunc_v4i64_to_v4i8_return_v16i8(<4 x i64> %vec) nounwind {
+; AVX1-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-SLOW-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
+; AVX2-SLOW:       # %bb.0:
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
+; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-SLOW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
+; AVX2-SLOW-NEXT:    vzeroupper
+; AVX2-SLOW-NEXT:    retq
+;
+; AVX2-FAST-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
+; AVX2-FAST:       # %bb.0:
+; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
+; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm1, %ymm0
+; AVX2-FAST-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
+; AVX2-FAST-NEXT:    vzeroupper
+; AVX2-FAST-NEXT:    retq
+;
+; AVX512F-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
+; AVX512VL:       # %bb.0:
+; AVX512VL-NEXT:    vpmovqb %ymm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[u],zero
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpmovqb %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+;
+; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
+; AVX512VBMIVL:       # %bb.0:
+; AVX512VBMIVL-NEXT:    vpmovqb %ymm0, %xmm0
+; AVX512VBMIVL-NEXT:    vzeroupper
+; AVX512VBMIVL-NEXT:    retq
+  %truncated = trunc <4 x i64> %vec to <4 x i8>
+  %result = shufflevector <4 x i8> %truncated, <4 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7, i32 5, i32 5, i32 undef, i32 7>
+  ret <16 x i8> %result
+}
+
+define <16 x i8> @trunc_v8i64_to_v8i8_return_v16i8(<8 x i64> %vec) nounwind {
+; AVX1-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpand %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vpand %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vpand %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vpand %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm0, %xmm0, %xmm0
+; AVX1-NEXT:    vmovq {{.*#+}} xmm0 = xmm0[0],zero
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-SLOW-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
+; AVX2-SLOW:       # %bb.0:
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
+; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
+; AVX2-SLOW-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
+; AVX2-SLOW-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX2-SLOW-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX2-SLOW-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX2-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-SLOW-NEXT:    vmovq {{.*#+}} xmm0 = xmm0[0],zero
+; AVX2-SLOW-NEXT:    vzeroupper
+; AVX2-SLOW-NEXT:    retq
+;
+; AVX2-FAST-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
+; AVX2-FAST:       # %bb.0:
+; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
+; AVX2-FAST-NEXT:    vpermd %ymm0, %ymm2, %ymm0
+; AVX2-FAST-NEXT:    vpermd %ymm1, %ymm2, %ymm1
+; AVX2-FAST-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX2-FAST-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX2-FAST-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX2-FAST-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-FAST-NEXT:    vmovq {{.*#+}} xmm0 = xmm0[0],zero
+; AVX2-FAST-NEXT:    vzeroupper
+; AVX2-FAST-NEXT:    retq
+;
+; AVX512F-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
+; AVX512VL:       # %bb.0:
+; AVX512VL-NEXT:    vpmovqb %zmm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpmovqb %zmm0, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+;
+; AVX512VBMIVL-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
+; AVX512VBMIVL:       # %bb.0:
+; AVX512VBMIVL-NEXT:    vpmovqb %zmm0, %xmm0
+; AVX512VBMIVL-NEXT:    vzeroupper
+; AVX512VBMIVL-NEXT:    retq
+  %truncated = trunc <8 x i64> %vec to <8 x i8>
+  %result = shufflevector <8 x i8> %truncated, <8 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  ret <16 x i8> %result
+}
+
 define void @shuffle_v16i16_to_v4i16(<16 x i16>* %L, <4 x i16>* %S) nounwind {
 ; AVX1-LABEL: shuffle_v16i16_to_v4i16:
 ; AVX1:       # %bb.0: