[X86] Attempt to pre-truncate arithmetic operations if useful

[RKSimon]

Summary

In some cases its more efficient to combine TRUNC( BINOP( X, Y ) ) --> BINOP( TRUNC( X ), TRUNC( Y ) ) if the binop is legal for the truncated types.

This is true for vector integer multiplication (especially vXi64), as well ADD/AND/XOR/OR in cases where we only need to truncate one of the inputs at runtime (e.g. a duplicated input or an one use constant we can fold).

Further work could be done here - scalar cases (especially i64) could often benefit (if we avoid partial registers etc.) and other opcodes possibly too.

I have considered implementing this for all targets within the DAGCombiner but wasn't sure we could devise a suitable cost model system that would give us the range we need?

[delena]

One some targets pmulld is significantly slower than pmullw (FeatureSlowPMULLD). I assume that truncating even different (variable) inputs should be profitable in this case.

And your transformation may be profitable for this scenario:

trunc(binop (s/zext(x), s/zext(y)) when x and y are different variables.

lib/Target/X86/X86ISelLowering.cpp

31795

Should you check hasOneUse() here ?

[RKSimon]

Updated based on Elena's feedback

[RKSimon]

In D28219#633779, @delena wrote:

One some targets pmulld is significantly slower than pmullw (FeatureSlowPMULLD). I assume that truncating even different (variable) inputs should be profitable in this case.

And your transformation may be profitable for this scenario:

trunc(binop (s/zext(x), s/zext(y)) when x and y are different variables.

If its alright, I can add support for both of these in followup patches. I've added TODOs to describe possible areas for improvement.

lib/Target/X86/X86ISelLowering.cpp

if (((Subtarget.hasSSE3() && (VT == MVT::v4f32 || VT == MVT::v2f64)) ||
        (Subtarget.hasFp256() && (VT == MVT::v8f32 || VT == MVT::v4f64))) &&
       isHorizontalBinOp(LHS, RHS, IsFadd)) {
     auto NewOpcode = IsFadd ? X86ISD::FHADD : X86ISD::FHSUB;
     return DAG.getNode(NewOpcode, SDLoc(N), VT, LHS, RHS);
   }
   return SDValue();
 }
 
+/// Attempt to pre-truncate inputs to arithmetic ops if it will simplify
+/// the codegen.
+/// e.g. TRUNC( BINOP( X, Y ) ) --> BINOP( TRUNC( X ), TRUNC( Y ) )
+static SDValue combineTruncatedArithmetic(SDValue Src, EVT VT,
+                                          SelectionDAG &DAG,
+                                          const X86Subtarget &Subtarget,
+                                          SDLoc &DL) {
+  const TargetLowering &TLI = DAG.getTargetLoweringInfo();
+  unsigned Opcode = Src.getOpcode();
+  EVT SrcVT = Src.getValueType();
+
+  auto IsRepeatedOpOrOneUseConstant = [](SDValue Op0, SDValue Op1) {
+    if (Op0 == Op1)
+      return true;
+
+    SDValue BC0 = peekThroughOneUseBitcasts(Op0);
+    SDValue BC1 = peekThroughOneUseBitcasts(Op1);
+    return ISD::isBuildVectorOfConstantSDNodes(BC0.getNode()) ||
+           ISD::isBuildVectorOfConstantSDNodes(BC1.getNode());
+  };
+
+  auto TruncateArithmetic = [&](SDValue N0, SDValue N1) {
+    SDValue Trunc0 = DAG.getNode(ISD::TRUNCATE, DL, VT, N0);
+    SDValue Trunc1 = DAG.getNode(ISD::TRUNCATE, DL, VT, N1);
+    return DAG.getNode(Opcode, DL, VT, Trunc0, Trunc1);
+  };
+
+  // Only support vector truncation for now.
+  // TODO: i64 scalar math would benefit as well.
+  if (!VT.isVector())
+    return SDValue();
+
+  // In most cases its only worth pre-truncating if we're only facing the cost
+  // of one truncation.
+  // i.e. if one of the inputs will constant fold or the input is repeated.
+  switch (Opcode) {
+  case ISD::AND:
+  case ISD::XOR:
+  case ISD::OR: {
+    SDValue Op0 = Src.getOperand(0);
+    SDValue Op1 = Src.getOperand(1);
+    if (TLI.isOperationLegalOrPromote(Opcode, VT) &&
+        IsRepeatedOpOrOneUseConstant(Op0, Op1))
+      return TruncateArithmetic(Op0, Op1);
+    break;
+  }
+
+  case ISD::MUL:
+    // X86 is rubbish at scalar and vector i64 multiplies (until AVX512DQ) - its
+    // better to truncate if we have the chance.
+    if (SrcVT.getScalarType() == MVT::i64 && TLI.isOperationLegal(Opcode, VT) &&
+        !TLI.isOperationLegal(Opcode, SrcVT))
+      return TruncateArithmetic(Src.getOperand(0), Src.getOperand(1));
+    LLVM_FALLTHROUGH;
+  case ISD::ADD: {
+    SDValue Op0 = Src.getOperand(0);
+    SDValue Op1 = Src.getOperand(1);
+    if (TLI.isOperationLegal(Opcode, VT) &&
+        IsRepeatedOpOrOneUseConstant(Op0, Op1))
+      return TruncateArithmetic(Op0, Op1);
+    break;
+  }
+  }
+
+  return SDValue();
+}
+
 /// Truncate a group of v4i32 into v16i8/v8i16 using X86ISD::PACKUS.
 static SDValue
 combineVectorTruncationWithPACKUS(SDNode *N, SelectionDAG &DAG,
                                   SmallVector<SDValue, 8> &Regs) {
   assert(Regs.size() > 0 && (Regs[0].getValueType() == MVT::v4i32 ||
                              Regs[0].getValueType() == MVT::v2i64));
   EVT OutVT = N->getValueType(0);
   EVT OutSVT = OutVT.getVectorElementType();

 }
 
 static SDValue combineTruncate(SDNode *N, SelectionDAG &DAG,
                                const X86Subtarget &Subtarget) {
   EVT VT = N->getValueType(0);
   SDValue Src = N->getOperand(0);
   SDLoc DL(N);
 
+  // Attempt to pre-truncate inputs to arithmetic ops instead.
+  if (SDValue V = combineTruncatedArithmetic(Src, VT, DAG, Subtarget, DL))
+    return V;
+
   // Try to detect AVG pattern first.
   if (SDValue Avg = detectAVGPattern(Src, VT, DAG, Subtarget, DL))
     return Avg;
 
   // The bitcast source is a direct mmx result.
   // Detect bitcasts between i32 to x86mmx
   if (Src.getOpcode() == ISD::BITCAST && VT == MVT::i32) {
     SDValue BCSrc = Src.getOperand(0);

test/CodeGen/X86/avx512-any_extend_load.ll

; ALL-NEXT:    retq
   %4 = trunc <8 x i64> %3 to <8 x i8>
   store <8 x i8> %4, <8 x i8>* %ptr, align 1
   ret void
 }
 
 define void @any_extend_load_v8i32(<8 x i8> * %ptr) {
 ; KNL-LABEL: any_extend_load_v8i32:
 ; KNL:       # BB#0:
-; KNL-NEXT:    vpmovzxbd {{.*#+}} ymm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
-; KNL-NEXT:    vpbroadcastd {{.*}}(%rip), %ymm1
-; KNL-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
-; KNL-NEXT:    vpmovdw %zmm0, %ymm0
+; KNL-NEXT:    vpmovzxbw {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
+; KNL-NEXT:    vpaddw {{.*}}(%rip), %xmm0, %xmm0
 ; KNL-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
 ; KNL-NEXT:    vmovq %xmm0, (%rdi)
 ; KNL-NEXT:    retq
 ;
 ; SKX-LABEL: any_extend_load_v8i32:
 ; SKX:       # BB#0:
 ; SKX-NEXT:    vpmovzxbd {{.*#+}} ymm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
 ; SKX-NEXT:    vpaddd {{.*}}(%rip){1to8}, %ymm0, %ymm0

test/CodeGen/X86/i64-to-float.ll

; X64-AVX-NEXT:    retq
   %and = and <2 x i64> %a, <i64 255, i64 65535>
   %cvt = uitofp <2 x i64> %and to <2 x double>
   ret <2 x double> %cvt
 }
 
 define <4 x float> @mask_sitofp_4i64_4f32(<4 x i64> %a) nounwind {
 ; X32-SSE-LABEL: mask_sitofp_4i64_4f32:
 ; X32-SSE:       # BB#0:
-; X32-SSE-NEXT:    andps {{\.LCPI.*}}, %xmm1
-; X32-SSE-NEXT:    andps {{\.LCPI.*}}, %xmm0
 ; X32-SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; X32-SSE-NEXT:    andps {{\.LCPI.*}}, %xmm0
 ; X32-SSE-NEXT:    cvtdq2ps %xmm0, %xmm0
 ; X32-SSE-NEXT:    retl
 ;
 ; X32-AVX-LABEL: mask_sitofp_4i64_4f32:
 ; X32-AVX:       # BB#0:
-; X32-AVX-NEXT:    vandps {{\.LCPI.*}}, %ymm0, %ymm0
 ; X32-AVX-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; X32-AVX-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; X32-AVX-NEXT:    vandps {{\.LCPI.*}}, %xmm0, %xmm0
 ; X32-AVX-NEXT:    vcvtdq2ps %xmm0, %xmm0
 ; X32-AVX-NEXT:    vzeroupper
 ; X32-AVX-NEXT:    retl
 ;
 ; X64-SSE-LABEL: mask_sitofp_4i64_4f32:
 ; X64-SSE:       # BB#0:
-; X64-SSE-NEXT:    andps {{.*}}(%rip), %xmm1
-; X64-SSE-NEXT:    andps {{.*}}(%rip), %xmm0
 ; X64-SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; X64-SSE-NEXT:    andps {{.*}}(%rip), %xmm0
 ; X64-SSE-NEXT:    cvtdq2ps %xmm0, %xmm0
 ; X64-SSE-NEXT:    retq
 ;
 ; X64-AVX-LABEL: mask_sitofp_4i64_4f32:
 ; X64-AVX:       # BB#0:
-; X64-AVX-NEXT:    vandps {{.*}}(%rip), %ymm0, %ymm0
 ; X64-AVX-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; X64-AVX-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; X64-AVX-NEXT:    vandps {{.*}}(%rip), %xmm0, %xmm0
 ; X64-AVX-NEXT:    vcvtdq2ps %xmm0, %xmm0
 ; X64-AVX-NEXT:    vzeroupper
 ; X64-AVX-NEXT:    retq
   %and = and <4 x i64> %a, <i64 127, i64 255, i64 4095, i64 65535>
   %cvt = sitofp <4 x i64> %and to <4 x float>
   ret <4 x float> %cvt
 }
 
 define <4 x float> @mask_uitofp_4i64_4f32(<4 x i64> %a) nounwind {
 ; X32-SSE-LABEL: mask_uitofp_4i64_4f32:
 ; X32-SSE:       # BB#0:
-; X32-SSE-NEXT:    andps {{\.LCPI.*}}, %xmm1
-; X32-SSE-NEXT:    andps {{\.LCPI.*}}, %xmm0
 ; X32-SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; X32-SSE-NEXT:    andps {{\.LCPI.*}}, %xmm0
 ; X32-SSE-NEXT:    cvtdq2ps %xmm0, %xmm0
 ; X32-SSE-NEXT:    retl
 ;
 ; X32-AVX-LABEL: mask_uitofp_4i64_4f32:
 ; X32-AVX:       # BB#0:
-; X32-AVX-NEXT:    vandps {{\.LCPI.*}}, %ymm0, %ymm0
 ; X32-AVX-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; X32-AVX-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; X32-AVX-NEXT:    vandps {{\.LCPI.*}}, %xmm0, %xmm0
 ; X32-AVX-NEXT:    vcvtdq2ps %xmm0, %xmm0
 ; X32-AVX-NEXT:    vzeroupper
 ; X32-AVX-NEXT:    retl
 ;
 ; X64-SSE-LABEL: mask_uitofp_4i64_4f32:
 ; X64-SSE:       # BB#0:
-; X64-SSE-NEXT:    andps {{.*}}(%rip), %xmm1
-; X64-SSE-NEXT:    andps {{.*}}(%rip), %xmm0
 ; X64-SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; X64-SSE-NEXT:    andps {{.*}}(%rip), %xmm0
 ; X64-SSE-NEXT:    cvtdq2ps %xmm0, %xmm0
 ; X64-SSE-NEXT:    retq
 ;
 ; X64-AVX-LABEL: mask_uitofp_4i64_4f32:
 ; X64-AVX:       # BB#0:
-; X64-AVX-NEXT:    vandps {{.*}}(%rip), %ymm0, %ymm0
 ; X64-AVX-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; X64-AVX-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; X64-AVX-NEXT:    vandps {{.*}}(%rip), %xmm0, %xmm0
 ; X64-AVX-NEXT:    vcvtdq2ps %xmm0, %xmm0
 ; X64-AVX-NEXT:    vzeroupper
 ; X64-AVX-NEXT:    retq
   %and = and <4 x i64> %a, <i64 127, i64 255, i64 4095, i64 65535>
   %cvt = uitofp <4 x i64> %and to <4 x float>
   ret <4 x float> %cvt
 }
 

test/CodeGen/X86/vector-trunc-math.ll

 
 ;
 ; add to constant
 ;
 
 define <4 x i32> @trunc_add_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_add_const_v4i64_v4i32:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm2
-; SSE-NEXT:    pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    paddq %xmm2, %xmm0
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; SSE-NEXT:    paddd {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_add_const_v4i64_v4i32:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm1
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpaddq %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm1[0,2],xmm0[0,2]
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_add_const_v4i64_v4i32:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpaddq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_add_const_v4i64_v4i32:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpaddq {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = add <4 x i64> %a0, <i64 0, i64 1, i64 2, i64 3>
   %2 = trunc <4 x i64> %1 to <4 x i32>
   ret <4 x i32> %2
 }
 
 define <8 x i16> @trunc_add_const_v8i64_v8i16(<8 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_add_const_v8i64_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm4
-; SSE-NEXT:    pslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    paddq %xmm0, %xmm4
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm1
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm2
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm3
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm0[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
-; SSE-NEXT:    movsd {{.*#+}} xmm0 = xmm2[0],xmm0[1]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSE-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
+; SSE-NEXT:    paddw {{.*}}(%rip), %xmm2
+; SSE-NEXT:    movdqa %xmm2, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_add_const_v8i64_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm2
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpaddq %xmm2, %xmm0, %xmm2
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm1, %xmm3
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpackusdw %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpackusdw %xmm0, %xmm2, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpaddw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_add_const_v8i64_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpaddq {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vpaddq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; 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
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpaddw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_add_const_v8i64_v8i16:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpaddq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512-NEXT:    vpaddw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = add <8 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
   %2 = trunc <8 x i64> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <8 x i16> @trunc_add_const_v8i32_v8i16(<8 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_add_const_v8i32_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    paddd {{.*}}(%rip), %xmm0
-; SSE-NEXT:    paddd {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    pslld $16, %xmm1
 ; SSE-NEXT:    psrad $16, %xmm1
 ; SSE-NEXT:    pslld $16, %xmm0
 ; SSE-NEXT:    psrad $16, %xmm0
 ; SSE-NEXT:    packssdw %xmm1, %xmm0
+; SSE-NEXT:    paddw {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_add_const_v8i32_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm0
+; 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, %xmm0, %xmm0
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
-; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpaddw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_add_const_v8i32_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpaddd {{.*}}(%rip), %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
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpaddw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_add_const_v8i32_v8i16:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpaddd {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpmovdw %zmm0, %ymm0
-; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512-NEXT:    vpaddw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = add <8 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   %2 = trunc <8 x i32> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <16 x i8> @trunc_add_const_v16i64_v16i8(<16 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_add_const_v16i64_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm8
-; SSE-NEXT:    pslldq {{.*#+}} xmm8 = zero,zero,zero,zero,zero,zero,zero,zero,xmm8[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    paddq %xmm8, %xmm0
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm1
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm2
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm3
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm4
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm5
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm6
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm7
 ; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
 ; SSE-NEXT:    pand %xmm8, %xmm7
 ; SSE-NEXT:    pand %xmm8, %xmm6
 ; SSE-NEXT:    packuswb %xmm7, %xmm6
 ; SSE-NEXT:    pand %xmm8, %xmm5
 ; SSE-NEXT:    pand %xmm8, %xmm4
 ; SSE-NEXT:    packuswb %xmm5, %xmm4
 ; SSE-NEXT:    packuswb %xmm6, %xmm4
 ; SSE-NEXT:    pand %xmm8, %xmm3
 ; SSE-NEXT:    pand %xmm8, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm8, %xmm1
 ; SSE-NEXT:    pand %xmm8, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm4, %xmm0
+; SSE-NEXT:    paddb {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_add_const_v16i64_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm4
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpaddq %xmm4, %xmm0, %xmm8
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm1, %xmm5
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm2, %xmm6
-; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm2
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm2, %xmm2
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm3, %xmm7
-; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm3
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm3, %xmm3
-; AVX1-NEXT:    vmovdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
-; AVX1-NEXT:    vpand %xmm4, %xmm3, %xmm3
-; AVX1-NEXT:    vpand %xmm4, %xmm7, %xmm7
-; AVX1-NEXT:    vpackuswb %xmm3, %xmm7, %xmm3
-; AVX1-NEXT:    vpand %xmm4, %xmm2, %xmm2
-; AVX1-NEXT:    vpand %xmm4, %xmm6, %xmm6
-; AVX1-NEXT:    vpackuswb %xmm2, %xmm6, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm4
+; AVX1-NEXT:    vmovaps {{.*#+}} xmm5 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vandps %xmm5, %xmm4, %xmm4
+; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
+; AVX1-NEXT:    vpackuswb %xmm4, %xmm3, %xmm3
+; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm4
+; AVX1-NEXT:    vandps %xmm5, %xmm4, %xmm4
+; AVX1-NEXT:    vandps %xmm5, %xmm2, %xmm2
+; AVX1-NEXT:    vpackuswb %xmm4, %xmm2, %xmm2
 ; AVX1-NEXT:    vpackuswb %xmm3, %xmm2, %xmm2
-; AVX1-NEXT:    vpand %xmm4, %xmm1, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm5, %xmm3
-; AVX1-NEXT:    vpackuswb %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm0, %xmm0
-; AVX1-NEXT:    vpand %xmm4, %xmm8, %xmm3
-; AVX1-NEXT:    vpackuswb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
+; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
+; AVX1-NEXT:    vandps %xmm5, %xmm1, %xmm1
+; AVX1-NEXT:    vpackuswb %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
+; AVX1-NEXT:    vandps %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_add_const_v16i64_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpaddq {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vpaddq {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpaddq {{.*}}(%rip), %ymm3, %ymm3
-; AVX2-NEXT:    vpaddq {{.*}}(%rip), %ymm2, %ymm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
 ; 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]
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
+; AVX2-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_add_const_v16i64_v16i8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpaddq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512F-NEXT:    vpaddq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512F-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_add_const_v16i64_v16i8:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpaddq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512BW-NEXT:    vpaddq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512BW-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512BW-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512BW-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_add_const_v16i64_v16i8:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpaddq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512DQ-NEXT:    vpaddq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512DQ-NEXT:    vinserti32x8 $1, %ymm1, %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = add <16 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
   %2 = trunc <16 x i64> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_add_const_v16i32_v16i8(<16 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_add_const_v16i32_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    paddd {{.*}}(%rip), %xmm0
-; SSE-NEXT:    paddd {{.*}}(%rip), %xmm1
-; SSE-NEXT:    paddd {{.*}}(%rip), %xmm2
-; SSE-NEXT:    paddd {{.*}}(%rip), %xmm3
 ; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
 ; SSE-NEXT:    pand %xmm4, %xmm3
 ; SSE-NEXT:    pand %xmm4, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm4, %xmm1
 ; SSE-NEXT:    pand %xmm4, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
+; SSE-NEXT:    paddb {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_add_const_v16i32_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm2
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vpaddd {{.*}}(%rip), %xmm1, %xmm3
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpaddd {{.*}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
-; AVX1-NEXT:    vpand %xmm4, %xmm1, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm3, %xmm3
-; AVX1-NEXT:    vpackuswb %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    vpand %xmm4, %xmm0, %xmm0
-; AVX1-NEXT:    vpand %xmm4, %xmm2, %xmm2
-; AVX1-NEXT:    vpackuswb %xmm0, %xmm2, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vmovaps {{.*#+}} xmm3 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
+; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vandps %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vandps %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_add_const_v16i32_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpaddd {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpaddd {{.*}}(%rip), %ymm1, %ymm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [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]
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_add_const_v16i32_v16i8:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpaddd {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = add <16 x i32> %a0, <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>
   %2 = trunc <16 x i32> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_add_const_v16i16_v16i8(<16 x i16> %a0) nounwind {
 ; SSE-LABEL: trunc_add_const_v16i16_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    paddw {{.*}}(%rip), %xmm0
-; SSE-NEXT:    paddw {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
 ; SSE-NEXT:    pand %xmm2, %xmm1
 ; SSE-NEXT:    pand %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
+; SSE-NEXT:    paddb {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_add_const_v16i16_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpaddw {{.*}}(%rip), %xmm0, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpaddw {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
-; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
-; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_add_const_v16i16_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpaddw {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_add_const_v16i16_v16i8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpaddw {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
 ; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_add_const_v16i16_v16i8:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpaddw {{.*}}(%rip), %ymm0, %ymm0
+; AVX512BW-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
-; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512BW-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_add_const_v16i16_v16i8:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpaddw {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovsxwd %ymm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vpaddb {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = add <16 x i16> %a0, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
   %2 = trunc <16 x i16> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 ;
 ; sub

 ; SSE-NEXT:    pmuludq %xmm2, %xmm0
 ; SSE-NEXT:    paddq %xmm4, %xmm0
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_mul_v4i64_v4i32:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
-; AVX1-NEXT:    vpsrlq $32, %xmm3, %xmm4
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm4, %xmm4
-; AVX1-NEXT:    vpsrlq $32, %xmm2, %xmm5
-; AVX1-NEXT:    vpmuludq %xmm5, %xmm3, %xmm5
-; AVX1-NEXT:    vpaddq %xmm4, %xmm5, %xmm4
-; AVX1-NEXT:    vpsllq $32, %xmm4, %xmm4
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm3, %xmm2
-; AVX1-NEXT:    vpaddq %xmm4, %xmm2, %xmm2
-; AVX1-NEXT:    vpsrlq $32, %xmm0, %xmm3
-; AVX1-NEXT:    vpmuludq %xmm1, %xmm3, %xmm3
-; AVX1-NEXT:    vpsrlq $32, %xmm1, %xmm4
-; AVX1-NEXT:    vpmuludq %xmm4, %xmm0, %xmm4
-; AVX1-NEXT:    vpaddq %xmm3, %xmm4, %xmm3
-; AVX1-NEXT:    vpsllq $32, %xmm3, %xmm3
-; AVX1-NEXT:    vpmuludq %xmm1, %xmm0, %xmm0
-; AVX1-NEXT:    vpaddq %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
+; AVX1-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_mul_v4i64_v4i32:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsrlq $32, %ymm0, %ymm2
-; AVX2-NEXT:    vpmuludq %ymm1, %ymm2, %ymm2
-; AVX2-NEXT:    vpsrlq $32, %ymm1, %ymm3
-; AVX2-NEXT:    vpmuludq %ymm3, %ymm0, %ymm3
-; AVX2-NEXT:    vpaddq %ymm2, %ymm3, %ymm2
-; AVX2-NEXT:    vpsllq $32, %ymm2, %ymm2
-; AVX2-NEXT:    vpmuludq %ymm1, %ymm0, %ymm0
-; AVX2-NEXT:    vpaddq %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_mul_v4i64_v4i32:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpsrlq $32, %ymm0, %ymm2
-; AVX512F-NEXT:    vpmuludq %ymm1, %ymm2, %ymm2
-; AVX512F-NEXT:    vpsrlq $32, %ymm1, %ymm3
-; AVX512F-NEXT:    vpmuludq %ymm3, %ymm0, %ymm3
-; AVX512F-NEXT:    vpaddq %ymm2, %ymm3, %ymm2
-; AVX512F-NEXT:    vpsllq $32, %ymm2, %ymm2
-; AVX512F-NEXT:    vpmuludq %ymm1, %ymm0, %ymm0
-; AVX512F-NEXT:    vpaddq %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    # kill: %YMM1<def> %YMM1<kill> %ZMM1<def>
+; AVX512F-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
+; AVX512F-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512F-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512F-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_mul_v4i64_v4i32:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpsrlq $32, %ymm0, %ymm2
-; AVX512BW-NEXT:    vpmuludq %ymm1, %ymm2, %ymm2
-; AVX512BW-NEXT:    vpsrlq $32, %ymm1, %ymm3
-; AVX512BW-NEXT:    vpmuludq %ymm3, %ymm0, %ymm3
-; AVX512BW-NEXT:    vpaddq %ymm2, %ymm3, %ymm2
-; AVX512BW-NEXT:    vpsllq $32, %ymm2, %ymm2
-; AVX512BW-NEXT:    vpmuludq %ymm1, %ymm0, %ymm0
-; AVX512BW-NEXT:    vpaddq %ymm2, %ymm0, %ymm0
+; AVX512BW-NEXT:    # kill: %YMM1<def> %YMM1<kill> %ZMM1<def>
+; AVX512BW-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
+; AVX512BW-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512BW-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_mul_v4i64_v4i32:
 ; AVX512DQ:       # BB#0:
 ; AVX512DQ-NEXT:    # kill: %YMM1<def> %YMM1<kill> %ZMM1<def>
 ; AVX512DQ-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512DQ-NEXT:    vpmullq %zmm1, %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512DQ-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
 ; AVX512DQ-NEXT:    retq
   %1 = mul <4 x i64> %a0, %a1
   %2 = trunc <4 x i64> %1 to <4 x i32>
   ret <4 x i32> %2
 }
 
 define <8 x i16> @trunc_mul_v8i64_v8i16(<8 x i64> %a0, <8 x i64> %a1) nounwind {
 ; SSE-LABEL: trunc_mul_v8i64_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movdqa %xmm0, %xmm8
-; SSE-NEXT:    psrlq $32, %xmm8
-; SSE-NEXT:    pmuludq %xmm4, %xmm8
-; SSE-NEXT:    movdqa %xmm4, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm9
-; SSE-NEXT:    pmuludq %xmm0, %xmm9
-; SSE-NEXT:    paddq %xmm8, %xmm9
-; SSE-NEXT:    psllq $32, %xmm9
-; SSE-NEXT:    pmuludq %xmm4, %xmm0
-; SSE-NEXT:    paddq %xmm9, %xmm0
-; SSE-NEXT:    movdqa %xmm1, %xmm8
-; SSE-NEXT:    psrlq $32, %xmm8
-; SSE-NEXT:    pmuludq %xmm5, %xmm8
-; SSE-NEXT:    movdqa %xmm5, %xmm4
-; SSE-NEXT:    psrlq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm1, %xmm4
-; SSE-NEXT:    paddq %xmm8, %xmm4
-; SSE-NEXT:    psllq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm5, %xmm1
-; SSE-NEXT:    paddq %xmm4, %xmm1
-; SSE-NEXT:    movdqa %xmm2, %xmm4
-; SSE-NEXT:    psrlq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm6, %xmm4
-; SSE-NEXT:    movdqa %xmm6, %xmm5
-; SSE-NEXT:    psrlq $32, %xmm5
-; SSE-NEXT:    pmuludq %xmm2, %xmm5
-; SSE-NEXT:    paddq %xmm4, %xmm5
-; SSE-NEXT:    psllq $32, %xmm5
-; SSE-NEXT:    pmuludq %xmm6, %xmm2
-; SSE-NEXT:    paddq %xmm5, %xmm2
-; SSE-NEXT:    movdqa %xmm3, %xmm4
-; SSE-NEXT:    psrlq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm7, %xmm4
-; SSE-NEXT:    movdqa %xmm7, %xmm5
-; SSE-NEXT:    psrlq $32, %xmm5
-; SSE-NEXT:    pmuludq %xmm3, %xmm5
-; SSE-NEXT:    paddq %xmm4, %xmm5
-; SSE-NEXT:    psllq $32, %xmm5
-; SSE-NEXT:    pmuludq %xmm7, %xmm3
-; SSE-NEXT:    paddq %xmm5, %xmm3
+; SSE-NEXT:    pshufd {{.*#+}} xmm7 = xmm7[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm7 = xmm7[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm6 = xmm6[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm6 = xmm6[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1]
+; SSE-NEXT:    pshufd {{.*#+}} xmm5 = xmm5[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm5 = xmm5[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1]
+; SSE-NEXT:    movsd {{.*#+}} xmm6 = xmm4[0],xmm6[1]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
 ; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
 ; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
 ; SSE-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
-; SSE-NEXT:    movapd %xmm2, %xmm0
+; SSE-NEXT:    pmullw %xmm6, %xmm2
+; SSE-NEXT:    movdqa %xmm2, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_mul_v8i64_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpsrlq $32, %xmm0, %xmm4
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm4, %xmm4
-; AVX1-NEXT:    vpsrlq $32, %xmm2, %xmm5
-; AVX1-NEXT:    vpmuludq %xmm5, %xmm0, %xmm5
-; AVX1-NEXT:    vpaddq %xmm4, %xmm5, %xmm4
-; AVX1-NEXT:    vpsllq $32, %xmm4, %xmm4
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm0, %xmm5
-; AVX1-NEXT:    vpaddq %xmm4, %xmm5, %xmm4
-; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm2
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpsrlq $32, %xmm0, %xmm5
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm5, %xmm5
-; AVX1-NEXT:    vpsrlq $32, %xmm2, %xmm6
-; AVX1-NEXT:    vpmuludq %xmm6, %xmm0, %xmm6
-; AVX1-NEXT:    vpaddq %xmm5, %xmm6, %xmm5
-; AVX1-NEXT:    vpsllq $32, %xmm5, %xmm5
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm0, %xmm0
-; AVX1-NEXT:    vpaddq %xmm5, %xmm0, %xmm0
-; AVX1-NEXT:    vpsrlq $32, %xmm1, %xmm2
-; AVX1-NEXT:    vpmuludq %xmm3, %xmm2, %xmm2
-; AVX1-NEXT:    vpsrlq $32, %xmm3, %xmm5
-; AVX1-NEXT:    vpmuludq %xmm5, %xmm1, %xmm5
-; AVX1-NEXT:    vpaddq %xmm2, %xmm5, %xmm2
-; AVX1-NEXT:    vpsllq $32, %xmm2, %xmm2
-; AVX1-NEXT:    vpmuludq %xmm3, %xmm1, %xmm5
-; AVX1-NEXT:    vpaddq %xmm2, %xmm5, %xmm2
-; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm3
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpsrlq $32, %xmm1, %xmm5
-; AVX1-NEXT:    vpmuludq %xmm3, %xmm5, %xmm5
-; AVX1-NEXT:    vpsrlq $32, %xmm3, %xmm6
-; AVX1-NEXT:    vpmuludq %xmm6, %xmm1, %xmm6
-; AVX1-NEXT:    vpaddq %xmm5, %xmm6, %xmm5
-; AVX1-NEXT:    vpsllq $32, %xmm5, %xmm5
-; AVX1-NEXT:    vpmuludq %xmm3, %xmm1, %xmm1
-; AVX1-NEXT:    vpaddq %xmm5, %xmm1, %xmm1
-; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
-; AVX1-NEXT:    vpackusdw %xmm1, %xmm2, %xmm1
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm4[0],xmm3[1,2,3],xmm4[4],xmm3[5,6,7]
-; AVX1-NEXT:    vpackusdw %xmm0, %xmm2, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm4
+; AVX1-NEXT:    vpxor %xmm5, %xmm5, %xmm5
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm4 = xmm4[0],xmm5[1,2,3],xmm4[4],xmm5[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm3 = xmm3[0],xmm5[1,2,3],xmm3[4],xmm5[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm4, %xmm3, %xmm3
+; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm4
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm4 = xmm4[0],xmm5[1,2,3],xmm4[4],xmm5[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm5[1,2,3],xmm2[4],xmm5[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm4, %xmm2, %xmm2
+; AVX1-NEXT:    vpackusdw %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm3 = xmm3[0],xmm5[1,2,3],xmm3[4],xmm5[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm5[1,2,3],xmm1[4],xmm5[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm3 = xmm3[0],xmm5[1,2,3],xmm3[4],xmm5[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm5[1,2,3],xmm0[4],xmm5[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpmullw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_mul_v8i64_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsrlq $32, %ymm1, %ymm4
-; AVX2-NEXT:    vpmuludq %ymm3, %ymm4, %ymm4
-; AVX2-NEXT:    vpsrlq $32, %ymm3, %ymm5
-; AVX2-NEXT:    vpmuludq %ymm5, %ymm1, %ymm5
-; AVX2-NEXT:    vpaddq %ymm4, %ymm5, %ymm4
-; AVX2-NEXT:    vpsllq $32, %ymm4, %ymm4
-; AVX2-NEXT:    vpmuludq %ymm3, %ymm1, %ymm1
-; AVX2-NEXT:    vpaddq %ymm4, %ymm1, %ymm1
-; AVX2-NEXT:    vpsrlq $32, %ymm0, %ymm3
-; AVX2-NEXT:    vpmuludq %ymm2, %ymm3, %ymm3
-; AVX2-NEXT:    vpsrlq $32, %ymm2, %ymm4
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm0, %ymm4
-; AVX2-NEXT:    vpaddq %ymm3, %ymm4, %ymm3
-; AVX2-NEXT:    vpsllq $32, %ymm3, %ymm3
-; AVX2-NEXT:    vpmuludq %ymm2, %ymm0, %ymm0
-; AVX2-NEXT:    vpaddq %ymm3, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
+; 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]
+; AVX2-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
+; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; 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
+; AVX2-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpmullw %xmm2, %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_mul_v8i64_v8i16:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpsrlq $32, %zmm0, %zmm2
-; AVX512F-NEXT:    vpmuludq %zmm1, %zmm2, %zmm2
-; AVX512F-NEXT:    vpsrlq $32, %zmm1, %zmm3
-; AVX512F-NEXT:    vpmuludq %zmm3, %zmm0, %zmm3
-; AVX512F-NEXT:    vpaddq %zmm2, %zmm3, %zmm2
-; AVX512F-NEXT:    vpsllq $32, %zmm2, %zmm2
-; AVX512F-NEXT:    vpmuludq %zmm1, %zmm0, %zmm0
-; AVX512F-NEXT:    vpaddq %zmm2, %zmm0, %zmm0
+; AVX512F-NEXT:    vpmovqw %zmm1, %xmm1
 ; AVX512F-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512F-NEXT:    vpmullw %xmm1, %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_mul_v8i64_v8i16:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpsrlq $32, %zmm0, %zmm2
-; AVX512BW-NEXT:    vpmuludq %zmm1, %zmm2, %zmm2
-; AVX512BW-NEXT:    vpsrlq $32, %zmm1, %zmm3
-; AVX512BW-NEXT:    vpmuludq %zmm3, %zmm0, %zmm3
-; AVX512BW-NEXT:    vpaddq %zmm2, %zmm3, %zmm2
-; AVX512BW-NEXT:    vpsllq $32, %zmm2, %zmm2
-; AVX512BW-NEXT:    vpmuludq %zmm1, %zmm0, %zmm0
-; AVX512BW-NEXT:    vpaddq %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpmovqw %zmm1, %xmm1
 ; AVX512BW-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512BW-NEXT:    vpmullw %xmm1, %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_mul_v8i64_v8i16:
 ; AVX512DQ:       # BB#0:
 ; AVX512DQ-NEXT:    vpmullq %zmm1, %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovqw %zmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = mul <8 x i64> %a0, %a1

 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm3, %xmm2
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm2, %xmm1
 ; AVX1-NEXT:    vpackuswb %xmm0, %xmm1, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_mul_v16i64_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsrlq $32, %ymm1, %ymm8
-; AVX2-NEXT:    vpmuludq %ymm5, %ymm8, %ymm8
-; AVX2-NEXT:    vpsrlq $32, %ymm5, %ymm9
-; AVX2-NEXT:    vpmuludq %ymm9, %ymm1, %ymm9
-; AVX2-NEXT:    vpaddq %ymm8, %ymm9, %ymm8
-; AVX2-NEXT:    vpsllq $32, %ymm8, %ymm8
-; AVX2-NEXT:    vpmuludq %ymm5, %ymm1, %ymm1
-; AVX2-NEXT:    vpaddq %ymm8, %ymm1, %ymm1
-; AVX2-NEXT:    vpsrlq $32, %ymm0, %ymm5
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm5, %ymm5
-; AVX2-NEXT:    vpsrlq $32, %ymm4, %ymm8
-; AVX2-NEXT:    vpmuludq %ymm8, %ymm0, %ymm8
-; AVX2-NEXT:    vpaddq %ymm5, %ymm8, %ymm5
-; AVX2-NEXT:    vpsllq $32, %ymm5, %ymm5
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm0, %ymm0
-; AVX2-NEXT:    vpaddq %ymm5, %ymm0, %ymm0
-; AVX2-NEXT:    vpsrlq $32, %ymm3, %ymm4
-; AVX2-NEXT:    vpmuludq %ymm7, %ymm4, %ymm4
-; AVX2-NEXT:    vpsrlq $32, %ymm7, %ymm5
-; AVX2-NEXT:    vpmuludq %ymm5, %ymm3, %ymm5
-; AVX2-NEXT:    vpaddq %ymm4, %ymm5, %ymm4
-; AVX2-NEXT:    vpsllq $32, %ymm4, %ymm4
-; AVX2-NEXT:    vpmuludq %ymm7, %ymm3, %ymm3
-; AVX2-NEXT:    vpaddq %ymm4, %ymm3, %ymm3
-; AVX2-NEXT:    vpsrlq $32, %ymm2, %ymm4
-; AVX2-NEXT:    vpmuludq %ymm6, %ymm4, %ymm4
-; AVX2-NEXT:    vpsrlq $32, %ymm6, %ymm5
-; AVX2-NEXT:    vpmuludq %ymm5, %ymm2, %ymm5
-; AVX2-NEXT:    vpaddq %ymm4, %ymm5, %ymm4
-; AVX2-NEXT:    vpsllq $32, %ymm4, %ymm4
-; AVX2-NEXT:    vpmuludq %ymm6, %ymm2, %ymm2
-; AVX2-NEXT:    vpaddq %ymm4, %ymm2, %ymm2
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
-; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm7 = ymm7[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm7 = ymm7[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
+; AVX2-NEXT:    vpmulld %xmm7, %xmm3, %xmm3
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm6 = ymm6[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm6 = ymm6[0,2,2,3]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
+; AVX2-NEXT:    vpmulld %xmm6, %xmm2, %xmm2
 ; 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]
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
-; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
-; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; 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:    vpshufd {{.*#+}} ymm5 = ymm5[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm5 = ymm5[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
+; AVX2-NEXT:    vpmulld %xmm5, %xmm1, %xmm1
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm4 = ymm4[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm4 = ymm4[0,2,2,3]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vpmulld %xmm4, %xmm0, %xmm0
 ; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    vpshufb %xmm4, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm6, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_mul_v16i64_v16i8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpsrlq $32, %zmm1, %zmm4
-; AVX512F-NEXT:    vpmuludq %zmm3, %zmm4, %zmm4
-; AVX512F-NEXT:    vpsrlq $32, %zmm3, %zmm5
-; AVX512F-NEXT:    vpmuludq %zmm5, %zmm1, %zmm5
-; AVX512F-NEXT:    vpaddq %zmm4, %zmm5, %zmm4
-; AVX512F-NEXT:    vpsllq $32, %zmm4, %zmm4
-; AVX512F-NEXT:    vpmuludq %zmm3, %zmm1, %zmm1
-; AVX512F-NEXT:    vpaddq %zmm4, %zmm1, %zmm1
-; AVX512F-NEXT:    vpsrlq $32, %zmm0, %zmm3
-; AVX512F-NEXT:    vpmuludq %zmm2, %zmm3, %zmm3
-; AVX512F-NEXT:    vpsrlq $32, %zmm2, %zmm4
-; AVX512F-NEXT:    vpmuludq %zmm4, %zmm0, %zmm4
-; AVX512F-NEXT:    vpaddq %zmm3, %zmm4, %zmm3
-; AVX512F-NEXT:    vpsllq $32, %zmm3, %zmm3
-; AVX512F-NEXT:    vpmuludq %zmm2, %zmm0, %zmm0
-; AVX512F-NEXT:    vpaddq %zmm3, %zmm0, %zmm0
-; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512F-NEXT:    vpmovqd %zmm3, %ymm3
 ; AVX512F-NEXT:    vpmovqd %zmm1, %ymm1
+; AVX512F-NEXT:    vpmulld %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpmovqd %zmm2, %ymm2
+; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512F-NEXT:    vpmulld %ymm2, %ymm0, %ymm0
 ; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_mul_v16i64_v16i8:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpsrlq $32, %zmm1, %zmm4
-; AVX512BW-NEXT:    vpmuludq %zmm3, %zmm4, %zmm4
-; AVX512BW-NEXT:    vpsrlq $32, %zmm3, %zmm5
-; AVX512BW-NEXT:    vpmuludq %zmm5, %zmm1, %zmm5
-; AVX512BW-NEXT:    vpaddq %zmm4, %zmm5, %zmm4
-; AVX512BW-NEXT:    vpsllq $32, %zmm4, %zmm4
-; AVX512BW-NEXT:    vpmuludq %zmm3, %zmm1, %zmm1
-; AVX512BW-NEXT:    vpaddq %zmm4, %zmm1, %zmm1
-; AVX512BW-NEXT:    vpsrlq $32, %zmm0, %zmm3
-; AVX512BW-NEXT:    vpmuludq %zmm2, %zmm3, %zmm3
-; AVX512BW-NEXT:    vpsrlq $32, %zmm2, %zmm4
-; AVX512BW-NEXT:    vpmuludq %zmm4, %zmm0, %zmm4
-; AVX512BW-NEXT:    vpaddq %zmm3, %zmm4, %zmm3
-; AVX512BW-NEXT:    vpsllq $32, %zmm3, %zmm3
-; AVX512BW-NEXT:    vpmuludq %zmm2, %zmm0, %zmm0
-; AVX512BW-NEXT:    vpaddq %zmm3, %zmm0, %zmm0
-; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512BW-NEXT:    vpmovqd %zmm3, %ymm3
 ; AVX512BW-NEXT:    vpmovqd %zmm1, %ymm1
+; AVX512BW-NEXT:    vpmulld %ymm3, %ymm1, %ymm1
+; AVX512BW-NEXT:    vpmovqd %zmm2, %ymm2
+; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512BW-NEXT:    vpmulld %ymm2, %ymm0, %ymm0
 ; AVX512BW-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpmovdb %zmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_mul_v16i64_v16i8:
 ; AVX512DQ:       # BB#0:
 ; AVX512DQ-NEXT:    vpmullq %zmm3, %zmm1, %zmm1
 ; AVX512DQ-NEXT:    vpmullq %zmm2, %zmm0, %zmm0

 ; SSE-NEXT:    psllq $32, %xmm0
 ; SSE-NEXT:    paddq %xmm3, %xmm0
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_mul_const_v4i64_v4i32:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [2,3]
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm1, %xmm3
-; AVX1-NEXT:    vpsrlq $32, %xmm1, %xmm1
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm1, %xmm1
-; AVX1-NEXT:    vpsllq $32, %xmm1, %xmm1
-; AVX1-NEXT:    vpaddq %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm2
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm0, %xmm3
-; AVX1-NEXT:    vpsrlq $32, %xmm0, %xmm0
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm0, %xmm0
-; AVX1-NEXT:    vpsllq $32, %xmm0, %xmm0
-; AVX1-NEXT:    vpaddq %xmm0, %xmm3, %xmm0
 ; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpmulld {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_mul_const_v4i64_v4i32:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,1,2,3]
-; AVX2-NEXT:    vpmuludq %ymm1, %ymm0, %ymm2
-; AVX2-NEXT:    vpsrlq $32, %ymm0, %ymm0
-; AVX2-NEXT:    vpmuludq %ymm1, %ymm0, %ymm0
-; AVX2-NEXT:    vpsllq $32, %ymm0, %ymm0
-; AVX2-NEXT:    vpaddq %ymm0, %ymm2, %ymm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpmulld {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
-; AVX512F-LABEL: trunc_mul_const_v4i64_v4i32:
-; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,1,2,3]
-; AVX512F-NEXT:    vpmuludq %ymm1, %ymm0, %ymm2
-; AVX512F-NEXT:    vpsrlq $32, %ymm0, %ymm0
-; AVX512F-NEXT:    vpmuludq %ymm1, %ymm0, %ymm0
-; AVX512F-NEXT:    vpsllq $32, %ymm0, %ymm0
-; AVX512F-NEXT:    vpaddq %ymm0, %ymm2, %ymm0
-; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512F-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
-; AVX512F-NEXT:    retq
-;
-; AVX512BW-LABEL: trunc_mul_const_v4i64_v4i32:
-; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,1,2,3]
-; AVX512BW-NEXT:    vpmuludq %ymm1, %ymm0, %ymm2
-; AVX512BW-NEXT:    vpsrlq $32, %ymm0, %ymm0
-; AVX512BW-NEXT:    vpmuludq %ymm1, %ymm0, %ymm0
-; AVX512BW-NEXT:    vpsllq $32, %ymm0, %ymm0
-; AVX512BW-NEXT:    vpaddq %ymm0, %ymm2, %ymm0
-; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
-; AVX512BW-NEXT:    retq
-;
-; AVX512DQ-LABEL: trunc_mul_const_v4i64_v4i32:
-; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
-; AVX512DQ-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,1,2,3]
-; AVX512DQ-NEXT:    vpmullq %zmm1, %zmm0, %zmm0
-; AVX512DQ-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512DQ-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
-; AVX512DQ-NEXT:    retq
+; AVX512-LABEL: trunc_mul_const_v4i64_v4i32:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
+; AVX512-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512-NEXT:    vpmulld {{.*}}(%rip), %xmm0, %xmm0
+; AVX512-NEXT:    retq
   %1 = mul <4 x i64> %a0, <i64 0, i64 1, i64 2, i64 3>
   %2 = trunc <4 x i64> %1 to <4 x i32>
   ret <4 x i32> %2
 }
 
 define <8 x i16> @trunc_mul_const_v8i64_v8i16(<8 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_mul_const_v8i64_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm4
-; SSE-NEXT:    pslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    movdqa %xmm0, %xmm5
-; SSE-NEXT:    pmuludq %xmm4, %xmm5
-; SSE-NEXT:    psrlq $32, %xmm0
-; SSE-NEXT:    pmuludq %xmm4, %xmm0
-; SSE-NEXT:    psllq $32, %xmm0
-; SSE-NEXT:    paddq %xmm5, %xmm0
-; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [2,3]
-; SSE-NEXT:    movdqa %xmm1, %xmm5
-; SSE-NEXT:    pmuludq %xmm4, %xmm5
-; SSE-NEXT:    psrlq $32, %xmm1
-; SSE-NEXT:    pmuludq %xmm4, %xmm1
-; SSE-NEXT:    psllq $32, %xmm1
-; SSE-NEXT:    paddq %xmm5, %xmm1
-; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [4,5]
-; SSE-NEXT:    movdqa %xmm2, %xmm5
-; SSE-NEXT:    pmuludq %xmm4, %xmm5
-; SSE-NEXT:    psrlq $32, %xmm2
-; SSE-NEXT:    pmuludq %xmm4, %xmm2
-; SSE-NEXT:    psllq $32, %xmm2
-; SSE-NEXT:    paddq %xmm5, %xmm2
-; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [6,7]
-; SSE-NEXT:    movdqa %xmm3, %xmm5
-; SSE-NEXT:    pmuludq %xmm4, %xmm5
-; SSE-NEXT:    psrlq $32, %xmm3
-; SSE-NEXT:    pmuludq %xmm4, %xmm3
-; SSE-NEXT:    psllq $32, %xmm3
-; SSE-NEXT:    paddq %xmm5, %xmm3
 ; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
 ; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
 ; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
 ; SSE-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
-; SSE-NEXT:    movapd %xmm2, %xmm0
+; SSE-NEXT:    pmullw {{.*}}(%rip), %xmm2
+; SSE-NEXT:    movdqa %xmm2, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_mul_const_v8i64_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    movl $1, %eax
-; AVX1-NEXT:    vmovq %rax, %xmm2
-; AVX1-NEXT:    vpslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm0, %xmm3
-; AVX1-NEXT:    vpsrlq $32, %xmm0, %xmm4
-; AVX1-NEXT:    vpmuludq %xmm2, %xmm4, %xmm2
-; AVX1-NEXT:    vpsllq $32, %xmm2, %xmm2
-; AVX1-NEXT:    vpaddq %xmm2, %xmm3, %xmm2
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [2,3]
-; AVX1-NEXT:    vpmuludq %xmm3, %xmm0, %xmm4
-; AVX1-NEXT:    vpsrlq $32, %xmm0, %xmm0
-; AVX1-NEXT:    vpmuludq %xmm3, %xmm0, %xmm0
-; AVX1-NEXT:    vpsllq $32, %xmm0, %xmm0
-; AVX1-NEXT:    vpaddq %xmm0, %xmm4, %xmm0
-; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [4,5]
-; AVX1-NEXT:    vpmuludq %xmm3, %xmm1, %xmm4
-; AVX1-NEXT:    vpsrlq $32, %xmm1, %xmm5
-; AVX1-NEXT:    vpmuludq %xmm3, %xmm5, %xmm3
-; AVX1-NEXT:    vpsllq $32, %xmm3, %xmm3
-; AVX1-NEXT:    vpaddq %xmm3, %xmm4, %xmm3
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*#+}} xmm4 = [6,7]
-; AVX1-NEXT:    vpmuludq %xmm4, %xmm1, %xmm5
-; AVX1-NEXT:    vpsrlq $32, %xmm1, %xmm1
-; AVX1-NEXT:    vpmuludq %xmm4, %xmm1, %xmm1
-; AVX1-NEXT:    vpsllq $32, %xmm1, %xmm1
-; AVX1-NEXT:    vpaddq %xmm1, %xmm5, %xmm1
-; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpackusdw %xmm1, %xmm3, %xmm1
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
-; AVX1-NEXT:    vpackusdw %xmm0, %xmm2, %xmm0
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpmullw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_mul_const_v8i64_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [4,5,6,7]
-; AVX2-NEXT:    vpmuludq %ymm2, %ymm1, %ymm3
-; AVX2-NEXT:    vpsrlq $32, %ymm1, %ymm1
-; AVX2-NEXT:    vpmuludq %ymm2, %ymm1, %ymm1
-; AVX2-NEXT:    vpsllq $32, %ymm1, %ymm1
-; AVX2-NEXT:    vpaddq %ymm1, %ymm3, %ymm1
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,1,2,3]
-; AVX2-NEXT:    vpmuludq %ymm2, %ymm0, %ymm3
-; AVX2-NEXT:    vpsrlq $32, %ymm0, %ymm0
-; AVX2-NEXT:    vpmuludq %ymm2, %ymm0, %ymm0
-; AVX2-NEXT:    vpsllq $32, %ymm0, %ymm0
-; AVX2-NEXT:    vpaddq %ymm0, %ymm3, %ymm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; 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
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpmullw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
-; AVX512F-LABEL: trunc_mul_const_v8i64_v8i16:
-; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vmovdqa32 {{.*#+}} zmm1 = [0,1,2,3,4,5,6,7]
-; AVX512F-NEXT:    vpmuludq %zmm1, %zmm0, %zmm2
-; AVX512F-NEXT:    vpsrlq $32, %zmm0, %zmm0
-; AVX512F-NEXT:    vpmuludq %zmm1, %zmm0, %zmm0
-; AVX512F-NEXT:    vpsllq $32, %zmm0, %zmm0
-; AVX512F-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
-; AVX512F-NEXT:    vpmovqw %zmm0, %xmm0
-; AVX512F-NEXT:    retq
-;
-; AVX512BW-LABEL: trunc_mul_const_v8i64_v8i16:
-; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vmovdqa32 {{.*#+}} zmm1 = [0,1,2,3,4,5,6,7]
-; AVX512BW-NEXT:    vpmuludq %zmm1, %zmm0, %zmm2
-; AVX512BW-NEXT:    vpsrlq $32, %zmm0, %zmm0
-; AVX512BW-NEXT:    vpmuludq %zmm1, %zmm0, %zmm0
-; AVX512BW-NEXT:    vpsllq $32, %zmm0, %zmm0
-; AVX512BW-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
-; AVX512BW-NEXT:    vpmovqw %zmm0, %xmm0
-; AVX512BW-NEXT:    retq
-;
-; AVX512DQ-LABEL: trunc_mul_const_v8i64_v8i16:
-; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpmullq {{.*}}(%rip), %zmm0, %zmm0
-; AVX512DQ-NEXT:    vpmovqw %zmm0, %xmm0
-; AVX512DQ-NEXT:    retq
+; AVX512-LABEL: trunc_mul_const_v8i64_v8i16:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512-NEXT:    vpmullw {{.*}}(%rip), %xmm0, %xmm0
+; AVX512-NEXT:    retq
   %1 = mul <8 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
   %2 = trunc <8 x i64> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <8 x i16> @trunc_mul_const_v8i32_v8i16(<8 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_mul_const_v8i32_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [0,1,2,3]
-; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
-; SSE-NEXT:    pmuludq %xmm2, %xmm0
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
-; SSE-NEXT:    pmuludq %xmm3, %xmm2
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
-; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [4,5,6,7]
-; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
-; SSE-NEXT:    pmuludq %xmm2, %xmm1
-; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
-; SSE-NEXT:    pmuludq %xmm3, %xmm2
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSE-NEXT:    pslld $16, %xmm1
 ; SSE-NEXT:    psrad $16, %xmm1
 ; SSE-NEXT:    pslld $16, %xmm0
 ; SSE-NEXT:    psrad $16, %xmm0
 ; SSE-NEXT:    packssdw %xmm1, %xmm0
+; SSE-NEXT:    pmullw {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_mul_const_v8i32_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpmulld {{.*}}(%rip), %xmm0, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpmulld {{.*}}(%rip), %xmm0, %xmm0
+; 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, %xmm0, %xmm0
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
-; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpmullw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_mul_const_v8i32_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpmulld {{.*}}(%rip), %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
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpmullw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_mul_const_v8i32_v8i16:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpmulld {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpmovdw %zmm0, %ymm0
-; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512-NEXT:    vpmullw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = mul <8 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   %2 = trunc <8 x i32> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <16 x i8> @trunc_mul_const_v16i64_v16i8(<16 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_mul_const_v16i64_v16i8:

 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm3, %xmm2
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm2, %xmm1
 ; AVX1-NEXT:    vpackuswb %xmm0, %xmm1, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_mul_const_v16i64_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm4 = [4,5,6,7]
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm1, %ymm5
-; AVX2-NEXT:    vpsrlq $32, %ymm1, %ymm1
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm1, %ymm1
-; AVX2-NEXT:    vpsllq $32, %ymm1, %ymm1
-; AVX2-NEXT:    vpaddq %ymm1, %ymm5, %ymm1
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,1,2,3]
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm0, %ymm5
-; AVX2-NEXT:    vpsrlq $32, %ymm0, %ymm0
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm0, %ymm0
-; AVX2-NEXT:    vpsllq $32, %ymm0, %ymm0
-; AVX2-NEXT:    vpaddq %ymm0, %ymm5, %ymm0
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm4 = [12,13,14,15]
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm3, %ymm5
-; AVX2-NEXT:    vpsrlq $32, %ymm3, %ymm3
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm3, %ymm3
-; AVX2-NEXT:    vpsllq $32, %ymm3, %ymm3
-; AVX2-NEXT:    vpaddq %ymm3, %ymm5, %ymm3
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm4 = [8,9,10,11]
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm2, %ymm5
-; AVX2-NEXT:    vpsrlq $32, %ymm2, %ymm2
-; AVX2-NEXT:    vpmuludq %ymm4, %ymm2, %ymm2
-; AVX2-NEXT:    vpsllq $32, %ymm2, %ymm2
-; AVX2-NEXT:    vpaddq %ymm2, %ymm5, %ymm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
+; AVX2-NEXT:    vpmulld {{.*}}(%rip), %xmm2, %xmm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
+; AVX2-NEXT:    vpmulld {{.*}}(%rip), %xmm3, %xmm3
 ; 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]
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vpmulld {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
+; AVX2-NEXT:    vpmulld {{.*}}(%rip), %xmm1, %xmm1
 ; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_mul_const_v16i64_v16i8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vmovdqa32 {{.*#+}} zmm2 = [8,9,10,11,12,13,14,15]
-; AVX512F-NEXT:    vpmuludq %zmm2, %zmm1, %zmm3
-; AVX512F-NEXT:    vpsrlq $32, %zmm1, %zmm1
-; AVX512F-NEXT:    vpmuludq %zmm2, %zmm1, %zmm1
-; AVX512F-NEXT:    vpsllq $32, %zmm1, %zmm1
-; AVX512F-NEXT:    vpaddq %zmm1, %zmm3, %zmm1
-; AVX512F-NEXT:    vmovdqa32 {{.*#+}} zmm2 = [0,1,2,3,4,5,6,7]
-; AVX512F-NEXT:    vpmuludq %zmm2, %zmm0, %zmm3
-; AVX512F-NEXT:    vpsrlq $32, %zmm0, %zmm0
-; AVX512F-NEXT:    vpmuludq %zmm2, %zmm0, %zmm0
-; AVX512F-NEXT:    vpsllq $32, %zmm0, %zmm0
-; AVX512F-NEXT:    vpaddq %zmm0, %zmm3, %zmm0
 ; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512F-NEXT:    vpmulld {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512F-NEXT:    vpmovqd %zmm1, %ymm1
+; AVX512F-NEXT:    vpmulld {{.*}}(%rip), %ymm1, %ymm1
 ; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_mul_const_v16i64_v16i8:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vmovdqa32 {{.*#+}} zmm2 = [8,9,10,11,12,13,14,15]
-; AVX512BW-NEXT:    vpmuludq %zmm2, %zmm1, %zmm3
-; AVX512BW-NEXT:    vpsrlq $32, %zmm1, %zmm1
-; AVX512BW-NEXT:    vpmuludq %zmm2, %zmm1, %zmm1
-; AVX512BW-NEXT:    vpsllq $32, %zmm1, %zmm1
-; AVX512BW-NEXT:    vpaddq %zmm1, %zmm3, %zmm1
-; AVX512BW-NEXT:    vmovdqa32 {{.*#+}} zmm2 = [0,1,2,3,4,5,6,7]
-; AVX512BW-NEXT:    vpmuludq %zmm2, %zmm0, %zmm3
-; AVX512BW-NEXT:    vpsrlq $32, %zmm0, %zmm0
-; AVX512BW-NEXT:    vpmuludq %zmm2, %zmm0, %zmm0
-; AVX512BW-NEXT:    vpsllq $32, %zmm0, %zmm0
-; AVX512BW-NEXT:    vpaddq %zmm0, %zmm3, %zmm0
 ; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512BW-NEXT:    vpmulld {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512BW-NEXT:    vpmovqd %zmm1, %ymm1
+; AVX512BW-NEXT:    vpmulld {{.*}}(%rip), %ymm1, %ymm1
 ; AVX512BW-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpmovdb %zmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_mul_const_v16i64_v16i8:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpmullq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512DQ-NEXT:    vpmullq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm0, %ymm0
+; AVX512DQ-NEXT:    vpmulld {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm1, %ymm1
+; AVX512DQ-NEXT:    vpmulld {{.*}}(%rip), %ymm1, %ymm1
 ; AVX512DQ-NEXT:    vinserti32x8 $1, %ymm1, %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = mul <16 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
   %2 = trunc <16 x i64> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 

 ; AVX1-NEXT:    vpand %xmm4, %xmm2, %xmm2
 ; AVX1-NEXT:    vpackuswb %xmm0, %xmm2, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_mul_const_v16i32_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpmulld {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpmulld {{.*}}(%rip), %ymm1, %ymm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [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]
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
+; AVX2-NEXT:    vpmullw {{.*}}(%rip), %xmm1, %xmm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vpmullw {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_mul_const_v16i32_v16i8:
 ; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpmulld {{.*}}(%rip), %zmm0, %zmm0

 
 ;
 ; and to constant
 ;
 
 define <4 x i32> @trunc_and_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_and_const_v4i64_v4i32:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm2
-; SSE-NEXT:    pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    pand %xmm2, %xmm0
-; SSE-NEXT:    andps {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; SSE-NEXT:    andps {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_and_const_v4i64_v4i32:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm0, %ymm0
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vandps {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_and_const_v4i64_v4i32:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_and_const_v4i64_v4i32:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = and <4 x i64> %a0, <i64 0, i64 1, i64 2, i64 3>
   %2 = trunc <4 x i64> %1 to <4 x i32>
   ret <4 x i32> %2
 }
 
 define <8 x i16> @trunc_and_const_v8i64_v8i16(<8 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_and_const_v8i64_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm4
-; SSE-NEXT:    pslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    pand %xmm0, %xmm4
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm1
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm2
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm3
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm0[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
-; SSE-NEXT:    movsd {{.*#+}} xmm0 = xmm2[0],xmm0[1]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSE-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
+; SSE-NEXT:    andpd {{.*}}(%rip), %xmm2
+; SSE-NEXT:    movapd %xmm2, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_and_const_v8i64_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm0, %ymm0
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm1, %ymm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_and_const_v8i64_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; 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
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_and_const_v8i64_v8i16:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpandq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = and <8 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
   %2 = trunc <8 x i64> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <8 x i16> @trunc_and_const_v8i32_v8i16(<8 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_and_const_v8i32_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm0
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    pslld $16, %xmm1
 ; SSE-NEXT:    psrad $16, %xmm1
 ; SSE-NEXT:    pslld $16, %xmm0
 ; SSE-NEXT:    psrad $16, %xmm0
 ; SSE-NEXT:    packssdw %xmm1, %xmm0
+; SSE-NEXT:    pand {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_and_const_v8i32_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm0, %ymm0
 ; 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:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_and_const_v8i32_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpand {{.*}}(%rip), %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
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_and_const_v8i32_v8i16:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpmovdw %zmm0, %ymm0
-; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = and <8 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   %2 = trunc <8 x i32> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <16 x i8> @trunc_and_const_v16i64_v16i8(<16 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_and_const_v16i64_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm8
-; SSE-NEXT:    pslldq {{.*#+}} xmm8 = zero,zero,zero,zero,zero,zero,zero,zero,xmm8[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm1
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm2
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm3
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm4
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm5
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm6
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm7
-; SSE-NEXT:    movdqa {{.*#+}} xmm9 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
-; SSE-NEXT:    pand %xmm9, %xmm7
-; SSE-NEXT:    pand %xmm9, %xmm6
+; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
+; SSE-NEXT:    pand %xmm8, %xmm7
+; SSE-NEXT:    pand %xmm8, %xmm6
 ; SSE-NEXT:    packuswb %xmm7, %xmm6
-; SSE-NEXT:    pand %xmm9, %xmm5
-; SSE-NEXT:    pand %xmm9, %xmm4
+; SSE-NEXT:    pand %xmm8, %xmm5
+; SSE-NEXT:    pand %xmm8, %xmm4
 ; SSE-NEXT:    packuswb %xmm5, %xmm4
 ; SSE-NEXT:    packuswb %xmm6, %xmm4
-; SSE-NEXT:    pand %xmm9, %xmm3
-; SSE-NEXT:    pand %xmm9, %xmm2
+; SSE-NEXT:    pand %xmm8, %xmm3
+; SSE-NEXT:    pand %xmm8, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
-; SSE-NEXT:    pand %xmm9, %xmm1
-; SSE-NEXT:    pand %xmm9, %xmm8
+; SSE-NEXT:    pand %xmm8, %xmm1
 ; SSE-NEXT:    pand %xmm8, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm4, %xmm0
+; SSE-NEXT:    pand {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_and_const_v16i64_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm0, %ymm0
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm1, %ymm1
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm2, %ymm2
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm3, %ymm3
 ; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm4
 ; AVX1-NEXT:    vmovaps {{.*#+}} xmm5 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vandps %xmm5, %xmm4, %xmm4
 ; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
 ; AVX1-NEXT:    vpackuswb %xmm4, %xmm3, %xmm3
 ; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm4
 ; AVX1-NEXT:    vandps %xmm5, %xmm4, %xmm4
 ; AVX1-NEXT:    vandps %xmm5, %xmm2, %xmm2
 ; AVX1-NEXT:    vpackuswb %xmm4, %xmm2, %xmm2
 ; AVX1-NEXT:    vpackuswb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm1, %xmm1
 ; AVX1-NEXT:    vpackuswb %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_and_const_v16i64_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm3, %ymm3
-; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm2, %ymm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
 ; 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]
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
+; AVX2-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_and_const_v16i64_v16i8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpandq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512F-NEXT:    vpandq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512F-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_and_const_v16i64_v16i8:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpandq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512BW-NEXT:    vpandq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512BW-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512BW-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512BW-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_and_const_v16i64_v16i8:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpandq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512DQ-NEXT:    vpandq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512DQ-NEXT:    vinserti32x8 $1, %ymm1, %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = and <16 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
   %2 = trunc <16 x i64> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_and_const_v16i32_v16i8(<16 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_and_const_v16i32_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm0
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm1
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm2
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm3
 ; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
 ; SSE-NEXT:    pand %xmm4, %xmm3
 ; SSE-NEXT:    pand %xmm4, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm4, %xmm1
 ; SSE-NEXT:    pand %xmm4, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
+; SSE-NEXT:    pand {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_and_const_v16i32_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm0, %ymm0
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm1, %ymm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vmovaps {{.*#+}} xmm3 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
 ; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vandps %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vandps %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_and_const_v16i32_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm1, %ymm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [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]
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_and_const_v16i32_v16i8:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpandd {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = and <16 x i32> %a0, <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>
   %2 = trunc <16 x i32> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_and_const_v16i16_v16i8(<16 x i16> %a0) nounwind {
 ; SSE-LABEL: trunc_and_const_v16i16_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm0
-; SSE-NEXT:    pand {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
 ; SSE-NEXT:    pand %xmm2, %xmm1
 ; SSE-NEXT:    pand %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
+; SSE-NEXT:    pand {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_and_const_v16i16_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vandps {{.*}}(%rip), %ymm0, %ymm0
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_and_const_v16i16_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_and_const_v16i16_v16i8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
 ; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_and_const_v16i16_v16i8:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
+; AVX512BW-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
-; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512BW-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_and_const_v16i16_v16i8:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpand {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovsxwd %ymm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vpand {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = and <16 x i16> %a0, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
   %2 = trunc <16 x i16> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 ;
 ; xor

 
 ;
 ; xor to constant
 ;
 
 define <4 x i32> @trunc_xor_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_xor_const_v4i64_v4i32:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm2
-; SSE-NEXT:    pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    pxor %xmm2, %xmm0
-; SSE-NEXT:    xorps {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; SSE-NEXT:    xorps {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_xor_const_v4i64_v4i32:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm0, %ymm0
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vxorps {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_xor_const_v4i64_v4i32:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_xor_const_v4i64_v4i32:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = xor <4 x i64> %a0, <i64 0, i64 1, i64 2, i64 3>
   %2 = trunc <4 x i64> %1 to <4 x i32>
   ret <4 x i32> %2
 }
 
 define <8 x i16> @trunc_xor_const_v8i64_v8i16(<8 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_xor_const_v8i64_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm4
-; SSE-NEXT:    pslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    pxor %xmm0, %xmm4
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm1
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm2
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm3
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm0[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
-; SSE-NEXT:    movsd {{.*#+}} xmm0 = xmm2[0],xmm0[1]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSE-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
+; SSE-NEXT:    xorpd {{.*}}(%rip), %xmm2
+; SSE-NEXT:    movapd %xmm2, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_xor_const_v8i64_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm0, %ymm0
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm1, %ymm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_xor_const_v8i64_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; 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
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_xor_const_v8i64_v8i16:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpxorq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = xor <8 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
   %2 = trunc <8 x i64> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <8 x i16> @trunc_xor_const_v8i32_v8i16(<8 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_xor_const_v8i32_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm0
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    pslld $16, %xmm1
 ; SSE-NEXT:    psrad $16, %xmm1
 ; SSE-NEXT:    pslld $16, %xmm0
 ; SSE-NEXT:    psrad $16, %xmm0
 ; SSE-NEXT:    packssdw %xmm1, %xmm0
+; SSE-NEXT:    pxor {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_xor_const_v8i32_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm0, %ymm0
 ; 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:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_xor_const_v8i32_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %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
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_xor_const_v8i32_v8i16:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpmovdw %zmm0, %ymm0
-; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = xor <8 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   %2 = trunc <8 x i32> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <16 x i8> @trunc_xor_const_v16i64_v16i8(<16 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_xor_const_v16i64_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm8
-; SSE-NEXT:    pslldq {{.*#+}} xmm8 = zero,zero,zero,zero,zero,zero,zero,zero,xmm8[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    pxor %xmm8, %xmm0
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm1
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm2
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm3
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm4
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm5
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm6
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm7
 ; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
 ; SSE-NEXT:    pand %xmm8, %xmm7
 ; SSE-NEXT:    pand %xmm8, %xmm6
 ; SSE-NEXT:    packuswb %xmm7, %xmm6
 ; SSE-NEXT:    pand %xmm8, %xmm5
 ; SSE-NEXT:    pand %xmm8, %xmm4
 ; SSE-NEXT:    packuswb %xmm5, %xmm4
 ; SSE-NEXT:    packuswb %xmm6, %xmm4
 ; SSE-NEXT:    pand %xmm8, %xmm3
 ; SSE-NEXT:    pand %xmm8, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm8, %xmm1
 ; SSE-NEXT:    pand %xmm8, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm4, %xmm0
+; SSE-NEXT:    pxor {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_xor_const_v16i64_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm0, %ymm0
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm1, %ymm1
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm2, %ymm2
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm3, %ymm3
 ; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm4
 ; AVX1-NEXT:    vmovaps {{.*#+}} xmm5 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vandps %xmm5, %xmm4, %xmm4
 ; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
 ; AVX1-NEXT:    vpackuswb %xmm4, %xmm3, %xmm3
 ; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm4
 ; AVX1-NEXT:    vandps %xmm5, %xmm4, %xmm4
 ; AVX1-NEXT:    vandps %xmm5, %xmm2, %xmm2
 ; AVX1-NEXT:    vpackuswb %xmm4, %xmm2, %xmm2
 ; AVX1-NEXT:    vpackuswb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm1, %xmm1
 ; AVX1-NEXT:    vpackuswb %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_xor_const_v16i64_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %ymm3, %ymm3
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %ymm2, %ymm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
 ; 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]
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
+; AVX2-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_xor_const_v16i64_v16i8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpxorq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512F-NEXT:    vpxorq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512F-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_xor_const_v16i64_v16i8:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpxorq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512BW-NEXT:    vpxorq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512BW-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512BW-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512BW-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_xor_const_v16i64_v16i8:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpxorq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512DQ-NEXT:    vpxorq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512DQ-NEXT:    vinserti32x8 $1, %ymm1, %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = xor <16 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
   %2 = trunc <16 x i64> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_xor_const_v16i32_v16i8(<16 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_xor_const_v16i32_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm0
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm1
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm2
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm3
 ; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
 ; SSE-NEXT:    pand %xmm4, %xmm3
 ; SSE-NEXT:    pand %xmm4, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm4, %xmm1
 ; SSE-NEXT:    pand %xmm4, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
+; SSE-NEXT:    pxor {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_xor_const_v16i32_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm0, %ymm0
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm1, %ymm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vmovaps {{.*#+}} xmm3 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
 ; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vandps %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vandps %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_xor_const_v16i32_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %ymm1, %ymm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [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]
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_xor_const_v16i32_v16i8:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpxord {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = xor <16 x i32> %a0, <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>
   %2 = trunc <16 x i32> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_xor_const_v16i16_v16i8(<16 x i16> %a0) nounwind {
 ; SSE-LABEL: trunc_xor_const_v16i16_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm0
-; SSE-NEXT:    pxor {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
 ; SSE-NEXT:    pand %xmm2, %xmm1
 ; SSE-NEXT:    pand %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
+; SSE-NEXT:    pxor {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_xor_const_v16i16_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vxorps {{.*}}(%rip), %ymm0, %ymm0
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_xor_const_v16i16_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_xor_const_v16i16_v16i8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
 ; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_xor_const_v16i16_v16i8:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
+; AVX512BW-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
-; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512BW-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_xor_const_v16i16_v16i8:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovsxwd %ymm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = xor <16 x i16> %a0, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
   %2 = trunc <16 x i16> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 ;
 ; or

 
 ;
 ; or to constant
 ;
 
 define <4 x i32> @trunc_or_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_or_const_v4i64_v4i32:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm2
-; SSE-NEXT:    pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    por %xmm2, %xmm0
-; SSE-NEXT:    orps {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; SSE-NEXT:    orps {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_or_const_v4i64_v4i32:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm0, %ymm0
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vorps {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_or_const_v4i64_v4i32:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpor {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_or_const_v4i64_v4i32:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpor {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = or <4 x i64> %a0, <i64 0, i64 1, i64 2, i64 3>
   %2 = trunc <4 x i64> %1 to <4 x i32>
   ret <4 x i32> %2
 }
 
 define <8 x i16> @trunc_or_const_v8i64_v8i16(<8 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_or_const_v8i64_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm4
-; SSE-NEXT:    pslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    por %xmm0, %xmm4
-; SSE-NEXT:    por {{.*}}(%rip), %xmm1
-; SSE-NEXT:    por {{.*}}(%rip), %xmm2
-; SSE-NEXT:    por {{.*}}(%rip), %xmm3
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm0[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3]
-; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
 ; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
-; SSE-NEXT:    movsd {{.*#+}} xmm0 = xmm2[0],xmm0[1]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
+; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSE-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
+; SSE-NEXT:    orpd {{.*}}(%rip), %xmm2
+; SSE-NEXT:    movapd %xmm2, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_or_const_v8i64_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm0, %ymm0
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm1, %ymm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
 ; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_or_const_v8i64_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpor {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vpor {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; 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
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_or_const_v8i64_v8i16:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vporq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovqw %zmm0, %xmm0
+; AVX512-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = or <8 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
   %2 = trunc <8 x i64> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <8 x i16> @trunc_or_const_v8i32_v8i16(<8 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_or_const_v8i32_v8i16:
 ; SSE:       # BB#0:
-; SSE-NEXT:    por {{.*}}(%rip), %xmm0
-; SSE-NEXT:    por {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    pslld $16, %xmm1
 ; SSE-NEXT:    psrad $16, %xmm1
 ; SSE-NEXT:    pslld $16, %xmm0
 ; SSE-NEXT:    psrad $16, %xmm0
 ; SSE-NEXT:    packssdw %xmm1, %xmm0
+; SSE-NEXT:    por {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_or_const_v8i32_v8i16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm0, %ymm0
 ; 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:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_or_const_v8i32_v8i16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpor {{.*}}(%rip), %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
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX2-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_or_const_v8i32_v8i16:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpor {{.*}}(%rip), %ymm0, %ymm0
+; AVX512-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpmovdw %zmm0, %ymm0
-; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = or <8 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   %2 = trunc <8 x i32> %1 to <8 x i16>
   ret <8 x i16> %2
 }
 
 define <16 x i8> @trunc_or_const_v16i64_v16i8(<16 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_or_const_v16i64_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movl $1, %eax
-; SSE-NEXT:    movd %rax, %xmm8
-; SSE-NEXT:    pslldq {{.*#+}} xmm8 = zero,zero,zero,zero,zero,zero,zero,zero,xmm8[0,1,2,3,4,5,6,7]
-; SSE-NEXT:    por %xmm8, %xmm0
-; SSE-NEXT:    por {{.*}}(%rip), %xmm1
-; SSE-NEXT:    por {{.*}}(%rip), %xmm2
-; SSE-NEXT:    por {{.*}}(%rip), %xmm3
-; SSE-NEXT:    por {{.*}}(%rip), %xmm4
-; SSE-NEXT:    por {{.*}}(%rip), %xmm5
-; SSE-NEXT:    por {{.*}}(%rip), %xmm6
-; SSE-NEXT:    por {{.*}}(%rip), %xmm7
 ; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
 ; SSE-NEXT:    pand %xmm8, %xmm7
 ; SSE-NEXT:    pand %xmm8, %xmm6
 ; SSE-NEXT:    packuswb %xmm7, %xmm6
 ; SSE-NEXT:    pand %xmm8, %xmm5
 ; SSE-NEXT:    pand %xmm8, %xmm4
 ; SSE-NEXT:    packuswb %xmm5, %xmm4
 ; SSE-NEXT:    packuswb %xmm6, %xmm4
 ; SSE-NEXT:    pand %xmm8, %xmm3
 ; SSE-NEXT:    pand %xmm8, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm8, %xmm1
 ; SSE-NEXT:    pand %xmm8, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm4, %xmm0
+; SSE-NEXT:    por {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_or_const_v16i64_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm0, %ymm0
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm1, %ymm1
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm2, %ymm2
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm3, %ymm3
 ; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm4
 ; AVX1-NEXT:    vmovaps {{.*#+}} xmm5 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vandps %xmm5, %xmm4, %xmm4
 ; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
 ; AVX1-NEXT:    vpackuswb %xmm4, %xmm3, %xmm3
 ; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm4
 ; AVX1-NEXT:    vandps %xmm5, %xmm4, %xmm4
 ; AVX1-NEXT:    vandps %xmm5, %xmm2, %xmm2
 ; AVX1-NEXT:    vpackuswb %xmm4, %xmm2, %xmm2
 ; AVX1-NEXT:    vpackuswb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm1, %xmm1
 ; AVX1-NEXT:    vpackuswb %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm3, %xmm3
 ; AVX1-NEXT:    vandps %xmm5, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_or_const_v16i64_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpor {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vpor {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpor {{.*}}(%rip), %ymm3, %ymm3
-; AVX2-NEXT:    vpor {{.*}}(%rip), %ymm2, %ymm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
 ; 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]
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm2, %ymm2
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
+; AVX2-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_or_const_v16i64_v16i8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vporq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512F-NEXT:    vporq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512F-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_or_const_v16i64_v16i8:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vporq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512BW-NEXT:    vporq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512BW-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512BW-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512BW-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_or_const_v16i64_v16i8:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vporq {{.*}}(%rip), %zmm1, %zmm1
-; AVX512DQ-NEXT:    vporq {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm1, %ymm1
 ; AVX512DQ-NEXT:    vinserti32x8 $1, %ymm1, %zmm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = or <16 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
   %2 = trunc <16 x i64> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_or_const_v16i32_v16i8(<16 x i32> %a0) nounwind {
 ; SSE-LABEL: trunc_or_const_v16i32_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    por {{.*}}(%rip), %xmm0
-; SSE-NEXT:    por {{.*}}(%rip), %xmm1
-; SSE-NEXT:    por {{.*}}(%rip), %xmm2
-; SSE-NEXT:    por {{.*}}(%rip), %xmm3
 ; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
 ; SSE-NEXT:    pand %xmm4, %xmm3
 ; SSE-NEXT:    pand %xmm4, %xmm2
 ; SSE-NEXT:    packuswb %xmm3, %xmm2
 ; SSE-NEXT:    pand %xmm4, %xmm1
 ; SSE-NEXT:    pand %xmm4, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
 ; SSE-NEXT:    packuswb %xmm2, %xmm0
+; SSE-NEXT:    por {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_or_const_v16i32_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm0, %ymm0
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm1, %ymm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vmovaps {{.*#+}} xmm3 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
 ; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vandps %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vandps %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_or_const_v16i32_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpor {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpor {{.*}}(%rip), %ymm1, %ymm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [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]
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm0, %ymm0
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: trunc_or_const_v16i32_v16i8:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpord {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %1 = or <16 x i32> %a0, <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>
   %2 = trunc <16 x i32> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 define <16 x i8> @trunc_or_const_v16i16_v16i8(<16 x i16> %a0) nounwind {
 ; SSE-LABEL: trunc_or_const_v16i16_v16i8:
 ; SSE:       # BB#0:
-; SSE-NEXT:    por {{.*}}(%rip), %xmm0
-; SSE-NEXT:    por {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
 ; SSE-NEXT:    pand %xmm2, %xmm1
 ; SSE-NEXT:    pand %xmm2, %xmm0
 ; SSE-NEXT:    packuswb %xmm1, %xmm0
+; SSE-NEXT:    por {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: trunc_or_const_v16i16_v16i8:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vorps {{.*}}(%rip), %ymm0, %ymm0
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: trunc_or_const_v16i16_v16i8:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpor {{.*}}(%rip), %ymm0, %ymm0
 ; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_or_const_v16i16_v16i8:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpor {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
 ; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: trunc_or_const_v16i16_v16i8:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpor {{.*}}(%rip), %ymm0, %ymm0
+; AVX512BW-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
 ; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
-; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512BW-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: trunc_or_const_v16i16_v16i8:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpor {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovsxwd %ymm0, %zmm0
 ; AVX512DQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512DQ-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = or <16 x i16> %a0, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
   %2 = trunc <16 x i16> %1 to <16 x i8>
   ret <16 x i8> %2
 }
 
 ;
 ; complex patterns - often created by vectorizer
 ;
 
 define <4 x i32> @mul_add_v4i64_v4i32(<4 x i32> %a0, <4 x i32> %a1) nounwind {
 ; SSE-LABEL: mul_add_v4i64_v4i32:
 ; SSE:       # BB#0:
 ; SSE-NEXT:    movdqa %xmm0, %xmm2
-; SSE-NEXT:    psrad $31, %xmm2
-; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
-; SSE-NEXT:    movdqa %xmm3, %xmm2
-; SSE-NEXT:    psrad $31, %xmm2
-; SSE-NEXT:    punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
-; SSE-NEXT:    movdqa %xmm1, %xmm4
-; SSE-NEXT:    psrad $31, %xmm4
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
-; SSE-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,1,1,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[2,1,3,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm1[0,1,1,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
 ; SSE-NEXT:    movdqa %xmm2, %xmm4
-; SSE-NEXT:    psrad $31, %xmm4
-; SSE-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
-; SSE-NEXT:    movdqa %xmm3, %xmm4
 ; SSE-NEXT:    psrlq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm2, %xmm4
-; SSE-NEXT:    movdqa %xmm2, %xmm5
+; SSE-NEXT:    pmuludq %xmm1, %xmm4
+; SSE-NEXT:    movdqa %xmm1, %xmm5
 ; SSE-NEXT:    psrlq $32, %xmm5
-; SSE-NEXT:    pmuludq %xmm3, %xmm5
+; SSE-NEXT:    pmuludq %xmm2, %xmm5
 ; SSE-NEXT:    paddq %xmm4, %xmm5
 ; SSE-NEXT:    psllq $32, %xmm5
-; SSE-NEXT:    pmuludq %xmm3, %xmm2
+; SSE-NEXT:    pmuludq %xmm1, %xmm2
 ; SSE-NEXT:    paddq %xmm5, %xmm2
-; SSE-NEXT:    movdqa %xmm0, %xmm3
-; SSE-NEXT:    psrlq $32, %xmm3
-; SSE-NEXT:    pmuludq %xmm1, %xmm3
-; SSE-NEXT:    movdqa %xmm1, %xmm4
+; SSE-NEXT:    movdqa %xmm0, %xmm1
+; SSE-NEXT:    psrlq $32, %xmm1
+; SSE-NEXT:    pmuludq %xmm3, %xmm1
+; SSE-NEXT:    movdqa %xmm3, %xmm4
 ; SSE-NEXT:    psrlq $32, %xmm4
 ; SSE-NEXT:    pmuludq %xmm0, %xmm4
-; SSE-NEXT:    paddq %xmm3, %xmm4
+; SSE-NEXT:    paddq %xmm1, %xmm4
 ; SSE-NEXT:    psllq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm1, %xmm0
+; SSE-NEXT:    pmuludq %xmm3, %xmm0
 ; SSE-NEXT:    paddq %xmm4, %xmm0
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm0
-; SSE-NEXT:    paddq {{.*}}(%rip), %xmm2
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
+; SSE-NEXT:    paddd {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: mul_add_v4i64_v4i32:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpmovsxdq %xmm0, %xmm2
-; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; AVX1-NEXT:    vpmovsxdq %xmm0, %xmm0
-; AVX1-NEXT:    vpmovsxdq %xmm1, %xmm3
-; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
-; AVX1-NEXT:    vpmovsxdq %xmm1, %xmm1
-; AVX1-NEXT:    vpmuldq %xmm1, %xmm0, %xmm0
-; AVX1-NEXT:    vpmuldq %xmm3, %xmm2, %xmm1
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT:    vpaddq {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm1[0,2],xmm0[0,2]
+; AVX1-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: mul_add_v4i64_v4i32:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpmovsxdq %xmm0, %ymm0
-; AVX2-NEXT:    vpmovsxdq %xmm1, %ymm1
-; AVX2-NEXT:    vpmuldq %ymm1, %ymm0, %ymm0
-; AVX2-NEXT:    vpaddq {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
-; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
-; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: mul_add_v4i64_v4i32:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vpmovsxdq %xmm0, %ymm0
-; AVX512F-NEXT:    vpmovsxdq %xmm1, %ymm1
-; AVX512F-NEXT:    vpmuldq %ymm1, %ymm0, %ymm0
-; AVX512F-NEXT:    vpaddq {{.*}}(%rip), %ymm0, %ymm0
-; AVX512F-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512F-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512F-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
+; AVX512F-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512BW-LABEL: mul_add_v4i64_v4i32:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpmovsxdq %xmm0, %ymm0
-; AVX512BW-NEXT:    vpmovsxdq %xmm1, %ymm1
-; AVX512BW-NEXT:    vpmuldq %ymm1, %ymm0, %ymm0
-; AVX512BW-NEXT:    vpaddq {{.*}}(%rip), %ymm0, %ymm0
-; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512BW-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQ-LABEL: mul_add_v4i64_v4i32:
 ; AVX512DQ:       # BB#0:
-; AVX512DQ-NEXT:    vpmovsxdq %xmm0, %ymm0
-; AVX512DQ-NEXT:    vpmovsxdq %xmm1, %ymm1
+; AVX512DQ-NEXT:    vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX512DQ-NEXT:    vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
 ; AVX512DQ-NEXT:    vpmullq %zmm1, %zmm0, %zmm0
-; AVX512DQ-NEXT:    vpaddq {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovqd %zmm0, %ymm0
-; AVX512DQ-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512DQ-NEXT:    vpaddd {{.*}}(%rip), %xmm0, %xmm0
 ; AVX512DQ-NEXT:    retq
   %1 = sext <4 x i32> %a0 to <4 x i64>
   %2 = sext <4 x i32> %a1 to <4 x i64>
   %3 = mul <4 x i64> %1, %2
   %4 = add <4 x i64> %3, <i64 -3, i64 -1, i64 1, i64 3>
   %5 = trunc <4 x i64> %4 to <4 x i32>
   ret <4 x i32> %5
 }