Index: lib/CodeGen/SelectionDAG/TargetLowering.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -1460,6 +1460,22 @@
                                      TLO, Depth + 1))
         return true;
 
+      // Try calling SimplifyDemandedBits, converting demanded elts to the bits
+      // of the large element.
+      // TODO - bigendian once we have test coverage.
+      if (TLO.DAG.getDataLayout().isLittleEndian()) {
+        APInt EltBits = APInt::getAllOnesValue(EltSizeInBits);
+        unsigned SrcEltSizeInBits = SrcVT.getScalarSizeInBits();
+        APInt SrcDemandedBits = APInt::getNullValue(SrcEltSizeInBits);
+        for (unsigned i = 0; i != NumElts; ++i)
+          if (DemandedElts[i])
+            SrcDemandedBits.insertBits(EltBits, (i % Scale) * EltSizeInBits);
+
+        KnownBits Known;
+        if (SimplifyDemandedBits(Src, SrcDemandedBits, Known, TLO, Depth + 1))
+          return true;
+      }
+
       // If the src element is zero/undef then all the output elements will be -
       // only demanded elements are guaranteed to be correct.
       for (unsigned i = 0; i != NumSrcElts; ++i) {
Index: test/CodeGen/X86/known-bits-vector.ll
===================================================================
--- test/CodeGen/X86/known-bits-vector.ll
+++ test/CodeGen/X86/known-bits-vector.ll
@@ -158,20 +158,12 @@
 define <4 x float> @knownbits_mask_or_shuffle_uitofp(<4 x i32> %a0) nounwind {
 ; X32-LABEL: knownbits_mask_or_shuffle_uitofp:
 ; X32:       # %bb.0:
-; X32-NEXT:    vpor {{\.LCPI.*}}, %xmm0, %xmm0
-; X32-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; X32-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,6,6]
-; X32-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
-; X32-NEXT:    vcvtdq2ps %xmm0, %xmm0
+; X32-NEXT:    vmovaps {{.*#+}} xmm0 = [6.5535E+4,6.5535E+4,6.5535E+4,6.5535E+4]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: knownbits_mask_or_shuffle_uitofp:
 ; X64:       # %bb.0:
-; X64-NEXT:    vpor {{.*}}(%rip), %xmm0, %xmm0
-; X64-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; X64-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,6,6]
-; X64-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
-; X64-NEXT:    vcvtdq2ps %xmm0, %xmm0
+; X64-NEXT:    vmovaps {{.*#+}} xmm0 = [6.5535E+4,6.5535E+4,6.5535E+4,6.5535E+4]
 ; X64-NEXT:    retq
   %1 = and <4 x i32> %a0, <i32 -1, i32 -1, i32 255, i32 4085>
   %2 = or <4 x i32> %1, <i32 65535, i32 65535, i32 65535, i32 65535>
Index: test/CodeGen/X86/known-signbits-vector.ll
===================================================================
--- test/CodeGen/X86/known-signbits-vector.ll
+++ test/CodeGen/X86/known-signbits-vector.ll
@@ -239,7 +239,8 @@
 ;
 ; X64-LABEL: signbits_ashr_concat_ashr_extract_sitofp:
 ; X64:       # %bb.0:
-; X64-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[1,3,2,3]
+; X64-NEXT:    vpsrlq $32, %xmm0, %xmm0
+; X64-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
 ; X64-NEXT:    vcvtdq2pd %xmm0, %xmm0
 ; X64-NEXT:    retq
   %1 = ashr <2 x i64> %a0, <i64 16, i64 16>
@@ -255,20 +256,13 @@
 ; X32-LABEL: signbits_ashr_sext_sextinreg_and_extract_sitofp:
 ; X32:       # %bb.0:
 ; X32-NEXT:    pushl %eax
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    vpsrlq $60, %xmm0, %xmm2
 ; X32-NEXT:    vpsrlq $61, %xmm0, %xmm0
 ; X32-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm2[4,5,6,7]
 ; X32-NEXT:    vmovdqa {{.*#+}} xmm2 = [4,0,0,0,8,0,0,0]
 ; X32-NEXT:    vpxor %xmm2, %xmm0, %xmm0
 ; X32-NEXT:    vpsubq %xmm2, %xmm0, %xmm0
-; X32-NEXT:    vpinsrd $0, %eax, %xmm1, %xmm1
-; X32-NEXT:    sarl $31, %eax
-; X32-NEXT:    vpinsrd $1, %eax, %xmm1, %xmm1
-; X32-NEXT:    vpsllq $20, %xmm1, %xmm1
-; X32-NEXT:    vpsrad $20, %xmm1, %xmm2
-; X32-NEXT:    vpsrlq $20, %xmm1, %xmm1
-; X32-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3],xmm1[4,5],xmm2[6,7]
+; X32-NEXT:    vpinsrd $0, {{[0-9]+}}(%esp), %xmm1, %xmm1
 ; X32-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; X32-NEXT:    vmovd %xmm0, %eax
 ; X32-NEXT:    vcvtsi2ssl %eax, %xmm3, %xmm0
Index: test/CodeGen/X86/reduce-trunc-shl.ll
===================================================================
--- test/CodeGen/X86/reduce-trunc-shl.ll
+++ test/CodeGen/X86/reduce-trunc-shl.ll
@@ -72,11 +72,7 @@
 ;
 ; AVX2-LABEL: trunc_shl_17_v8i16_v8i32:
 ; AVX2:       # %bb.0:
-; AVX2-NEXT:    vpslld $17, %ymm0, %ymm0
-; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
-; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX2-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
-; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    vxorps %xmm0, %xmm0, %xmm0
 ; AVX2-NEXT:    retq
   %shl = shl <8 x i32> %a, <i32 17, i32 17, i32 17, i32 17, i32 17, i32 17, i32 17, i32 17>
   %conv = trunc <8 x i32> %shl to <8 x i16>
Index: test/CodeGen/X86/shrink_vmul.ll
===================================================================
--- test/CodeGen/X86/shrink_vmul.ll
+++ test/CodeGen/X86/shrink_vmul.ll
@@ -1154,10 +1154,7 @@
 ; X86-SSE-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
 ; X86-SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,1,1,3]
 ; X86-SSE-NEXT:    pmuludq %xmm0, %xmm1
-; X86-SSE-NEXT:    pmuludq %xmm0, %xmm2
-; X86-SSE-NEXT:    psllq $32, %xmm2
-; X86-SSE-NEXT:    paddq %xmm1, %xmm2
-; X86-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
+; X86-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
 ; X86-SSE-NEXT:    movq %xmm0, (%esi,%ecx,4)
 ; X86-SSE-NEXT:    popl %esi
 ; X86-SSE-NEXT:    retl
@@ -1191,10 +1188,7 @@
 ; X64-SSE-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
 ; X64-SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,1,1,3]
 ; X64-SSE-NEXT:    pmuludq %xmm0, %xmm1
-; X64-SSE-NEXT:    pmuludq %xmm0, %xmm2
-; X64-SSE-NEXT:    psllq $32, %xmm2
-; X64-SSE-NEXT:    paddq %xmm1, %xmm2
-; X64-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
+; X64-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
 ; X64-SSE-NEXT:    movq %xmm0, (%rax,%rdx,4)
 ; X64-SSE-NEXT:    retq
 ;
@@ -1952,15 +1946,7 @@
 ; X86-SSE-NEXT:    pxor %xmm1, %xmm1
 ; X86-SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
 ; X86-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
-; X86-SSE-NEXT:    movdqa {{.*#+}} xmm2 = <0,u,65536,u>
-; X86-SSE-NEXT:    pmuludq %xmm2, %xmm1
-; X86-SSE-NEXT:    movdqa %xmm2, %xmm3
-; X86-SSE-NEXT:    psrlq $32, %xmm3
-; X86-SSE-NEXT:    pmuludq %xmm0, %xmm3
-; X86-SSE-NEXT:    paddq %xmm1, %xmm3
-; X86-SSE-NEXT:    psllq $32, %xmm3
-; X86-SSE-NEXT:    pmuludq %xmm2, %xmm0
-; X86-SSE-NEXT:    paddq %xmm3, %xmm0
+; X86-SSE-NEXT:    pmuludq {{\.LCPI.*}}, %xmm0
 ; X86-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
 ; X86-SSE-NEXT:    movq %xmm0, (%edx,%eax,4)
 ; X86-SSE-NEXT:    retl
@@ -1986,13 +1972,10 @@
 ; X64-SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
 ; X64-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
 ; X64-SSE-NEXT:    movl $65536, %ecx # imm = 0x10000
-; X64-SSE-NEXT:    movq %rcx, %xmm2
-; X64-SSE-NEXT:    pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
-; X64-SSE-NEXT:    pmuludq %xmm2, %xmm0
-; X64-SSE-NEXT:    pmuludq %xmm1, %xmm2
-; X64-SSE-NEXT:    psllq $32, %xmm2
-; X64-SSE-NEXT:    paddq %xmm0, %xmm2
-; X64-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
+; X64-SSE-NEXT:    movq %rcx, %xmm1
+; X64-SSE-NEXT:    pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
+; X64-SSE-NEXT:    pmuludq %xmm0, %xmm1
+; X64-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
 ; X64-SSE-NEXT:    movq %xmm0, (%rax,%rsi,4)
 ; X64-SSE-NEXT:    retq
 ;
@@ -2037,16 +2020,7 @@
 ; X86-SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,0,2,1,4,5,6,7]
 ; X86-SSE-NEXT:    psrad $16, %xmm0
 ; X86-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
-; X86-SSE-NEXT:    movdqa {{.*#+}} xmm1 = <0,u,32768,u>
-; X86-SSE-NEXT:    pxor %xmm2, %xmm2
-; X86-SSE-NEXT:    pmuludq %xmm1, %xmm2
-; X86-SSE-NEXT:    movdqa %xmm1, %xmm3
-; X86-SSE-NEXT:    psrlq $32, %xmm3
-; X86-SSE-NEXT:    pmuludq %xmm0, %xmm3
-; X86-SSE-NEXT:    paddq %xmm2, %xmm3
-; X86-SSE-NEXT:    psllq $32, %xmm3
-; X86-SSE-NEXT:    pmuludq %xmm1, %xmm0
-; X86-SSE-NEXT:    paddq %xmm3, %xmm0
+; X86-SSE-NEXT:    pmuludq {{\.LCPI.*}}, %xmm0
 ; X86-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
 ; X86-SSE-NEXT:    movq %xmm0, (%edx,%eax,4)
 ; X86-SSE-NEXT:    retl
@@ -2072,12 +2046,8 @@
 ; X64-SSE-NEXT:    movl $32768, %ecx # imm = 0x8000
 ; X64-SSE-NEXT:    movq %rcx, %xmm1
 ; X64-SSE-NEXT:    pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
-; X64-SSE-NEXT:    pmuludq %xmm1, %xmm0
-; X64-SSE-NEXT:    pxor %xmm2, %xmm2
-; X64-SSE-NEXT:    pmuludq %xmm1, %xmm2
-; X64-SSE-NEXT:    psllq $32, %xmm2
-; X64-SSE-NEXT:    paddq %xmm0, %xmm2
-; X64-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
+; X64-SSE-NEXT:    pmuludq %xmm0, %xmm1
+; X64-SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
 ; X64-SSE-NEXT:    movq %xmm0, (%rax,%rsi,4)
 ; X64-SSE-NEXT:    retq
 ;
Index: test/CodeGen/X86/vector-trunc-math-widen.ll
===================================================================
--- test/CodeGen/X86/vector-trunc-math-widen.ll
+++ test/CodeGen/X86/vector-trunc-math-widen.ll
@@ -1823,26 +1823,8 @@
 define <4 x i32> @trunc_mul_v4i64_v4i32(<4 x i64> %a0, <4 x i64> %a1) nounwind {
 ; SSE-LABEL: trunc_mul_v4i64_v4i32:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movdqa %xmm1, %xmm4
-; SSE-NEXT:    psrlq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm3, %xmm4
-; SSE-NEXT:    movdqa %xmm3, %xmm5
-; SSE-NEXT:    psrlq $32, %xmm5
-; SSE-NEXT:    pmuludq %xmm1, %xmm5
-; SSE-NEXT:    paddq %xmm4, %xmm5
-; SSE-NEXT:    psllq $32, %xmm5
 ; SSE-NEXT:    pmuludq %xmm3, %xmm1
-; SSE-NEXT:    paddq %xmm5, %xmm1
-; SSE-NEXT:    movdqa %xmm0, %xmm3
-; SSE-NEXT:    psrlq $32, %xmm3
-; SSE-NEXT:    pmuludq %xmm2, %xmm3
-; SSE-NEXT:    movdqa %xmm2, %xmm4
-; SSE-NEXT:    psrlq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm0, %xmm4
-; SSE-NEXT:    paddq %xmm3, %xmm4
-; SSE-NEXT:    psllq $32, %xmm4
 ; SSE-NEXT:    pmuludq %xmm2, %xmm0
-; SSE-NEXT:    paddq %xmm4, %xmm0
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
 ; SSE-NEXT:    retq
 ;
@@ -2089,94 +2071,14 @@
 define <16 x i8> @trunc_mul_v16i64_v16i8(<16 x i64> %a0, <16 x i64> %a1) nounwind {
 ; SSE-LABEL: trunc_mul_v16i64_v16i8:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm8
-; SSE-NEXT:    movdqa %xmm0, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    movdqa %xmm8, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm0, %xmm10
-; SSE-NEXT:    paddq %xmm9, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm9
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm8, %xmm0
-; SSE-NEXT:    paddq %xmm10, %xmm0
-; SSE-NEXT:    movdqa %xmm1, %xmm8
-; SSE-NEXT:    psrlq $32, %xmm8
-; SSE-NEXT:    pmuludq %xmm9, %xmm8
-; SSE-NEXT:    movdqa %xmm9, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm1, %xmm10
-; SSE-NEXT:    paddq %xmm8, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm8
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm9, %xmm1
-; SSE-NEXT:    paddq %xmm10, %xmm1
-; SSE-NEXT:    movdqa %xmm2, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    movdqa %xmm8, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm2, %xmm10
-; SSE-NEXT:    paddq %xmm9, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm9
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm8, %xmm2
-; SSE-NEXT:    paddq %xmm10, %xmm2
-; SSE-NEXT:    movdqa %xmm3, %xmm8
-; SSE-NEXT:    psrlq $32, %xmm8
-; SSE-NEXT:    pmuludq %xmm9, %xmm8
-; SSE-NEXT:    movdqa %xmm9, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm3, %xmm10
-; SSE-NEXT:    paddq %xmm8, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm8
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm9, %xmm3
-; SSE-NEXT:    paddq %xmm10, %xmm3
-; SSE-NEXT:    movdqa %xmm4, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    movdqa %xmm8, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm4, %xmm10
-; SSE-NEXT:    paddq %xmm9, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm9
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm8, %xmm4
-; SSE-NEXT:    paddq %xmm10, %xmm4
-; SSE-NEXT:    movdqa %xmm5, %xmm8
-; SSE-NEXT:    psrlq $32, %xmm8
-; SSE-NEXT:    pmuludq %xmm9, %xmm8
-; SSE-NEXT:    movdqa %xmm9, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm5, %xmm10
-; SSE-NEXT:    paddq %xmm8, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm8
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm9, %xmm5
-; SSE-NEXT:    paddq %xmm10, %xmm5
-; SSE-NEXT:    movdqa %xmm6, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    movdqa %xmm8, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm6, %xmm10
-; SSE-NEXT:    paddq %xmm9, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm9
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm8, %xmm6
-; SSE-NEXT:    paddq %xmm10, %xmm6
-; SSE-NEXT:    movdqa %xmm7, %xmm8
-; SSE-NEXT:    psrlq $32, %xmm8
-; SSE-NEXT:    pmuludq %xmm9, %xmm8
-; SSE-NEXT:    movdqa %xmm9, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm7, %xmm10
-; SSE-NEXT:    paddq %xmm8, %xmm10
-; SSE-NEXT:    pmuludq %xmm9, %xmm7
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    paddq %xmm10, %xmm7
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm0
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm1
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm2
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm3
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm4
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm5
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm6
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %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
@@ -2601,22 +2503,11 @@
 define <4 x i32> @trunc_mul_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_mul_const_v4i64_v4i32:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [2,3]
-; SSE-NEXT:    movdqa %xmm1, %xmm3
-; SSE-NEXT:    pmuludq %xmm2, %xmm3
-; SSE-NEXT:    psrlq $32, %xmm1
-; SSE-NEXT:    pmuludq %xmm2, %xmm1
-; SSE-NEXT:    psllq $32, %xmm1
-; SSE-NEXT:    paddq %xmm3, %xmm1
 ; SSE-NEXT:    movl $1, %eax
 ; SSE-NEXT:    movq %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:    movdqa %xmm0, %xmm3
-; SSE-NEXT:    pmuludq %xmm2, %xmm3
-; SSE-NEXT:    psrlq $32, %xmm0
 ; SSE-NEXT:    pmuludq %xmm2, %xmm0
-; SSE-NEXT:    psllq $32, %xmm0
-; SSE-NEXT:    paddq %xmm3, %xmm0
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
 ; SSE-NEXT:    retq
 ;
@@ -2773,61 +2664,14 @@
 ; SSE-NEXT:    movl $1, %eax
 ; SSE-NEXT:    movq %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:    movdqa %xmm0, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm0
 ; SSE-NEXT:    pmuludq %xmm8, %xmm0
-; SSE-NEXT:    psllq $32, %xmm0
-; SSE-NEXT:    paddq %xmm9, %xmm0
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [2,3]
-; SSE-NEXT:    movdqa %xmm1, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm1
-; SSE-NEXT:    pmuludq %xmm8, %xmm1
-; SSE-NEXT:    psllq $32, %xmm1
-; SSE-NEXT:    paddq %xmm9, %xmm1
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [4,5]
-; SSE-NEXT:    movdqa %xmm2, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm2
-; SSE-NEXT:    pmuludq %xmm8, %xmm2
-; SSE-NEXT:    psllq $32, %xmm2
-; SSE-NEXT:    paddq %xmm9, %xmm2
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [6,7]
-; SSE-NEXT:    movdqa %xmm3, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm3
-; SSE-NEXT:    pmuludq %xmm8, %xmm3
-; SSE-NEXT:    psllq $32, %xmm3
-; SSE-NEXT:    paddq %xmm9, %xmm3
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [8,9]
-; SSE-NEXT:    movdqa %xmm4, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm8, %xmm4
-; SSE-NEXT:    psllq $32, %xmm4
-; SSE-NEXT:    paddq %xmm9, %xmm4
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [10,11]
-; SSE-NEXT:    movdqa %xmm5, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm5
-; SSE-NEXT:    pmuludq %xmm8, %xmm5
-; SSE-NEXT:    psllq $32, %xmm5
-; SSE-NEXT:    paddq %xmm9, %xmm5
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [12,13]
-; SSE-NEXT:    movdqa %xmm6, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm6
-; SSE-NEXT:    pmuludq %xmm8, %xmm6
-; SSE-NEXT:    psllq $32, %xmm6
-; SSE-NEXT:    paddq %xmm9, %xmm6
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [14,15]
-; SSE-NEXT:    movdqa %xmm7, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm7
-; SSE-NEXT:    pmuludq %xmm8, %xmm7
-; SSE-NEXT:    psllq $32, %xmm7
-; SSE-NEXT:    paddq %xmm9, %xmm7
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm1
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm2
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm3
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm4
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm5
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm6
+; SSE-NEXT:    pmuludq {{.*}}(%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
@@ -5538,17 +5382,10 @@
 ; SSE:       # %bb.0:
 ; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[0,1,1,3]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[2,1,3,3]
-; SSE-NEXT:    pshufd {{.*#+}} xmm4 = xmm1[0,1,1,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[0,1,1,3]
+; SSE-NEXT:    pmuludq %xmm2, %xmm0
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
-; SSE-NEXT:    pmuludq %xmm1, %xmm3
-; SSE-NEXT:    pxor %xmm0, %xmm0
-; SSE-NEXT:    pmuludq %xmm0, %xmm1
-; SSE-NEXT:    psllq $32, %xmm1
-; SSE-NEXT:    paddq %xmm3, %xmm1
-; SSE-NEXT:    pmuludq %xmm4, %xmm2
-; SSE-NEXT:    pmuludq %xmm4, %xmm0
-; SSE-NEXT:    psllq $32, %xmm0
-; SSE-NEXT:    paddq %xmm2, %xmm0
+; SSE-NEXT:    pmuludq %xmm3, %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
 ; SSE-NEXT:    paddd {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
@@ -5569,39 +5406,14 @@
 define <4 x i32> @mul_add_self_v4i64_v4i32(<4 x i32> %a0, <4 x i32> %a1) nounwind {
 ; SSE-LABEL: mul_add_self_v4i64_v4i32:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
-; SSE-NEXT:    movdqa %xmm3, %xmm4
-; SSE-NEXT:    psrad $31, %xmm4
-; SSE-NEXT:    punpckldq {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
-; SSE-NEXT:    movdqa %xmm0, %xmm5
-; SSE-NEXT:    psrad $31, %xmm5
-; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm6 = xmm1[2,3,0,1]
-; SSE-NEXT:    movdqa %xmm6, %xmm7
-; SSE-NEXT:    psrad $31, %xmm7
-; SSE-NEXT:    punpckldq {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1]
-; SSE-NEXT:    movdqa %xmm1, %xmm2
-; SSE-NEXT:    psrad $31, %xmm2
-; SSE-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,1,1,3]
-; SSE-NEXT:    pmuludq %xmm0, %xmm2
-; SSE-NEXT:    pmuludq %xmm1, %xmm0
-; SSE-NEXT:    pshufd {{.*#+}} xmm5 = xmm5[0,1,1,3]
-; SSE-NEXT:    pmuludq %xmm1, %xmm5
-; SSE-NEXT:    paddq %xmm5, %xmm2
-; SSE-NEXT:    psllq $32, %xmm2
-; SSE-NEXT:    paddq %xmm0, %xmm2
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm7[0,1,1,3]
-; SSE-NEXT:    pmuludq %xmm3, %xmm0
-; SSE-NEXT:    pmuludq %xmm6, %xmm3
-; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm4[0,1,1,3]
-; SSE-NEXT:    pmuludq %xmm6, %xmm1
-; SSE-NEXT:    paddq %xmm1, %xmm0
-; SSE-NEXT:    psllq $32, %xmm0
-; SSE-NEXT:    paddq %xmm3, %xmm0
-; SSE-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2],xmm0[0,2]
-; SSE-NEXT:    paddd %xmm2, %xmm2
-; SSE-NEXT:    movdqa %xmm2, %xmm0
+; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[0,1,1,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[2,1,3,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[0,1,1,3]
+; SSE-NEXT:    pmuludq %xmm2, %xmm0
+; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
+; SSE-NEXT:    pmuludq %xmm3, %xmm1
+; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; SSE-NEXT:    paddd %xmm0, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX-LABEL: mul_add_self_v4i64_v4i32:
@@ -5623,18 +5435,11 @@
 ; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[0,1,1,3]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[2,1,3,3]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm4 = xmm1[0,1,1,3]
+; SSE-NEXT:    pmuludq %xmm2, %xmm4
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
-; SSE-NEXT:    pmuludq %xmm1, %xmm3
-; SSE-NEXT:    pxor %xmm5, %xmm5
-; SSE-NEXT:    pmuludq %xmm5, %xmm1
-; SSE-NEXT:    psllq $32, %xmm1
-; SSE-NEXT:    paddq %xmm3, %xmm1
-; SSE-NEXT:    pmuludq %xmm4, %xmm2
-; SSE-NEXT:    pmuludq %xmm4, %xmm5
-; SSE-NEXT:    psllq $32, %xmm5
-; SSE-NEXT:    paddq %xmm2, %xmm5
-; SSE-NEXT:    shufps {{.*#+}} xmm5 = xmm5[0,2],xmm1[0,2]
-; SSE-NEXT:    paddd %xmm5, %xmm0
+; SSE-NEXT:    pmuludq %xmm3, %xmm1
+; SSE-NEXT:    shufps {{.*#+}} xmm4 = xmm4[0,2],xmm1[0,2]
+; SSE-NEXT:    paddd %xmm4, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX-LABEL: mul_add_multiuse_v4i64_v4i32:
Index: test/CodeGen/X86/vector-trunc-math.ll
===================================================================
--- test/CodeGen/X86/vector-trunc-math.ll
+++ test/CodeGen/X86/vector-trunc-math.ll
@@ -1823,26 +1823,8 @@
 define <4 x i32> @trunc_mul_v4i64_v4i32(<4 x i64> %a0, <4 x i64> %a1) nounwind {
 ; SSE-LABEL: trunc_mul_v4i64_v4i32:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movdqa %xmm1, %xmm4
-; SSE-NEXT:    psrlq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm3, %xmm4
-; SSE-NEXT:    movdqa %xmm3, %xmm5
-; SSE-NEXT:    psrlq $32, %xmm5
-; SSE-NEXT:    pmuludq %xmm1, %xmm5
-; SSE-NEXT:    paddq %xmm4, %xmm5
-; SSE-NEXT:    psllq $32, %xmm5
 ; SSE-NEXT:    pmuludq %xmm3, %xmm1
-; SSE-NEXT:    paddq %xmm5, %xmm1
-; SSE-NEXT:    movdqa %xmm0, %xmm3
-; SSE-NEXT:    psrlq $32, %xmm3
-; SSE-NEXT:    pmuludq %xmm2, %xmm3
-; SSE-NEXT:    movdqa %xmm2, %xmm4
-; SSE-NEXT:    psrlq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm0, %xmm4
-; SSE-NEXT:    paddq %xmm3, %xmm4
-; SSE-NEXT:    psllq $32, %xmm4
 ; SSE-NEXT:    pmuludq %xmm2, %xmm0
-; SSE-NEXT:    paddq %xmm4, %xmm0
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
 ; SSE-NEXT:    retq
 ;
@@ -2089,94 +2071,14 @@
 define <16 x i8> @trunc_mul_v16i64_v16i8(<16 x i64> %a0, <16 x i64> %a1) nounwind {
 ; SSE-LABEL: trunc_mul_v16i64_v16i8:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm8
-; SSE-NEXT:    movdqa %xmm0, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    movdqa %xmm8, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm0, %xmm10
-; SSE-NEXT:    paddq %xmm9, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm9
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm8, %xmm0
-; SSE-NEXT:    paddq %xmm10, %xmm0
-; SSE-NEXT:    movdqa %xmm1, %xmm8
-; SSE-NEXT:    psrlq $32, %xmm8
-; SSE-NEXT:    pmuludq %xmm9, %xmm8
-; SSE-NEXT:    movdqa %xmm9, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm1, %xmm10
-; SSE-NEXT:    paddq %xmm8, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm8
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm9, %xmm1
-; SSE-NEXT:    paddq %xmm10, %xmm1
-; SSE-NEXT:    movdqa %xmm2, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    movdqa %xmm8, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm2, %xmm10
-; SSE-NEXT:    paddq %xmm9, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm9
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm8, %xmm2
-; SSE-NEXT:    paddq %xmm10, %xmm2
-; SSE-NEXT:    movdqa %xmm3, %xmm8
-; SSE-NEXT:    psrlq $32, %xmm8
-; SSE-NEXT:    pmuludq %xmm9, %xmm8
-; SSE-NEXT:    movdqa %xmm9, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm3, %xmm10
-; SSE-NEXT:    paddq %xmm8, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm8
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm9, %xmm3
-; SSE-NEXT:    paddq %xmm10, %xmm3
-; SSE-NEXT:    movdqa %xmm4, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    movdqa %xmm8, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm4, %xmm10
-; SSE-NEXT:    paddq %xmm9, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm9
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm8, %xmm4
-; SSE-NEXT:    paddq %xmm10, %xmm4
-; SSE-NEXT:    movdqa %xmm5, %xmm8
-; SSE-NEXT:    psrlq $32, %xmm8
-; SSE-NEXT:    pmuludq %xmm9, %xmm8
-; SSE-NEXT:    movdqa %xmm9, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm5, %xmm10
-; SSE-NEXT:    paddq %xmm8, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm8
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm9, %xmm5
-; SSE-NEXT:    paddq %xmm10, %xmm5
-; SSE-NEXT:    movdqa %xmm6, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    movdqa %xmm8, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm6, %xmm10
-; SSE-NEXT:    paddq %xmm9, %xmm10
-; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm9
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm8, %xmm6
-; SSE-NEXT:    paddq %xmm10, %xmm6
-; SSE-NEXT:    movdqa %xmm7, %xmm8
-; SSE-NEXT:    psrlq $32, %xmm8
-; SSE-NEXT:    pmuludq %xmm9, %xmm8
-; SSE-NEXT:    movdqa %xmm9, %xmm10
-; SSE-NEXT:    psrlq $32, %xmm10
-; SSE-NEXT:    pmuludq %xmm7, %xmm10
-; SSE-NEXT:    paddq %xmm8, %xmm10
-; SSE-NEXT:    pmuludq %xmm9, %xmm7
-; SSE-NEXT:    psllq $32, %xmm10
-; SSE-NEXT:    paddq %xmm10, %xmm7
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm0
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm1
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm2
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm3
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm4
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm5
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %xmm6
+; SSE-NEXT:    pmuludq {{[0-9]+}}(%rsp), %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
@@ -2601,22 +2503,11 @@
 define <4 x i32> @trunc_mul_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
 ; SSE-LABEL: trunc_mul_const_v4i64_v4i32:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [2,3]
-; SSE-NEXT:    movdqa %xmm1, %xmm3
-; SSE-NEXT:    pmuludq %xmm2, %xmm3
-; SSE-NEXT:    psrlq $32, %xmm1
-; SSE-NEXT:    pmuludq %xmm2, %xmm1
-; SSE-NEXT:    psllq $32, %xmm1
-; SSE-NEXT:    paddq %xmm3, %xmm1
 ; SSE-NEXT:    movl $1, %eax
 ; SSE-NEXT:    movq %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:    movdqa %xmm0, %xmm3
-; SSE-NEXT:    pmuludq %xmm2, %xmm3
-; SSE-NEXT:    psrlq $32, %xmm0
 ; SSE-NEXT:    pmuludq %xmm2, %xmm0
-; SSE-NEXT:    psllq $32, %xmm0
-; SSE-NEXT:    paddq %xmm3, %xmm0
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
 ; SSE-NEXT:    retq
 ;
@@ -2773,61 +2664,14 @@
 ; SSE-NEXT:    movl $1, %eax
 ; SSE-NEXT:    movq %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:    movdqa %xmm0, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm0
 ; SSE-NEXT:    pmuludq %xmm8, %xmm0
-; SSE-NEXT:    psllq $32, %xmm0
-; SSE-NEXT:    paddq %xmm9, %xmm0
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [2,3]
-; SSE-NEXT:    movdqa %xmm1, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm1
-; SSE-NEXT:    pmuludq %xmm8, %xmm1
-; SSE-NEXT:    psllq $32, %xmm1
-; SSE-NEXT:    paddq %xmm9, %xmm1
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [4,5]
-; SSE-NEXT:    movdqa %xmm2, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm2
-; SSE-NEXT:    pmuludq %xmm8, %xmm2
-; SSE-NEXT:    psllq $32, %xmm2
-; SSE-NEXT:    paddq %xmm9, %xmm2
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [6,7]
-; SSE-NEXT:    movdqa %xmm3, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm3
-; SSE-NEXT:    pmuludq %xmm8, %xmm3
-; SSE-NEXT:    psllq $32, %xmm3
-; SSE-NEXT:    paddq %xmm9, %xmm3
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [8,9]
-; SSE-NEXT:    movdqa %xmm4, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm4
-; SSE-NEXT:    pmuludq %xmm8, %xmm4
-; SSE-NEXT:    psllq $32, %xmm4
-; SSE-NEXT:    paddq %xmm9, %xmm4
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [10,11]
-; SSE-NEXT:    movdqa %xmm5, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm5
-; SSE-NEXT:    pmuludq %xmm8, %xmm5
-; SSE-NEXT:    psllq $32, %xmm5
-; SSE-NEXT:    paddq %xmm9, %xmm5
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [12,13]
-; SSE-NEXT:    movdqa %xmm6, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm6
-; SSE-NEXT:    pmuludq %xmm8, %xmm6
-; SSE-NEXT:    psllq $32, %xmm6
-; SSE-NEXT:    paddq %xmm9, %xmm6
-; SSE-NEXT:    movdqa {{.*#+}} xmm8 = [14,15]
-; SSE-NEXT:    movdqa %xmm7, %xmm9
-; SSE-NEXT:    pmuludq %xmm8, %xmm9
-; SSE-NEXT:    psrlq $32, %xmm7
-; SSE-NEXT:    pmuludq %xmm8, %xmm7
-; SSE-NEXT:    psllq $32, %xmm7
-; SSE-NEXT:    paddq %xmm9, %xmm7
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm1
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm2
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm3
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm4
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm5
+; SSE-NEXT:    pmuludq {{.*}}(%rip), %xmm6
+; SSE-NEXT:    pmuludq {{.*}}(%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
@@ -5538,17 +5382,10 @@
 ; SSE:       # %bb.0:
 ; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[0,1,1,3]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[2,1,3,3]
-; SSE-NEXT:    pshufd {{.*#+}} xmm4 = xmm1[0,1,1,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[0,1,1,3]
+; SSE-NEXT:    pmuludq %xmm2, %xmm0
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
-; SSE-NEXT:    pmuludq %xmm1, %xmm3
-; SSE-NEXT:    pxor %xmm0, %xmm0
-; SSE-NEXT:    pmuludq %xmm0, %xmm1
-; SSE-NEXT:    psllq $32, %xmm1
-; SSE-NEXT:    paddq %xmm3, %xmm1
-; SSE-NEXT:    pmuludq %xmm4, %xmm2
-; SSE-NEXT:    pmuludq %xmm4, %xmm0
-; SSE-NEXT:    psllq $32, %xmm0
-; SSE-NEXT:    paddq %xmm2, %xmm0
+; SSE-NEXT:    pmuludq %xmm3, %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
 ; SSE-NEXT:    paddd {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
@@ -5569,39 +5406,14 @@
 define <4 x i32> @mul_add_self_v4i64_v4i32(<4 x i32> %a0, <4 x i32> %a1) nounwind {
 ; SSE-LABEL: mul_add_self_v4i64_v4i32:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
-; SSE-NEXT:    movdqa %xmm3, %xmm4
-; SSE-NEXT:    psrad $31, %xmm4
-; SSE-NEXT:    punpckldq {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
-; SSE-NEXT:    movdqa %xmm0, %xmm5
-; SSE-NEXT:    psrad $31, %xmm5
-; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm6 = xmm1[2,3,0,1]
-; SSE-NEXT:    movdqa %xmm6, %xmm7
-; SSE-NEXT:    psrad $31, %xmm7
-; SSE-NEXT:    punpckldq {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1]
-; SSE-NEXT:    movdqa %xmm1, %xmm2
-; SSE-NEXT:    psrad $31, %xmm2
-; SSE-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,1,1,3]
-; SSE-NEXT:    pmuludq %xmm0, %xmm2
-; SSE-NEXT:    pmuludq %xmm1, %xmm0
-; SSE-NEXT:    pshufd {{.*#+}} xmm5 = xmm5[0,1,1,3]
-; SSE-NEXT:    pmuludq %xmm1, %xmm5
-; SSE-NEXT:    paddq %xmm5, %xmm2
-; SSE-NEXT:    psllq $32, %xmm2
-; SSE-NEXT:    paddq %xmm0, %xmm2
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm7[0,1,1,3]
-; SSE-NEXT:    pmuludq %xmm3, %xmm0
-; SSE-NEXT:    pmuludq %xmm6, %xmm3
-; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm4[0,1,1,3]
-; SSE-NEXT:    pmuludq %xmm6, %xmm1
-; SSE-NEXT:    paddq %xmm1, %xmm0
-; SSE-NEXT:    psllq $32, %xmm0
-; SSE-NEXT:    paddq %xmm3, %xmm0
-; SSE-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2],xmm0[0,2]
-; SSE-NEXT:    paddd %xmm2, %xmm2
-; SSE-NEXT:    movdqa %xmm2, %xmm0
+; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[0,1,1,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[2,1,3,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[0,1,1,3]
+; SSE-NEXT:    pmuludq %xmm2, %xmm0
+; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
+; SSE-NEXT:    pmuludq %xmm3, %xmm1
+; SSE-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; SSE-NEXT:    paddd %xmm0, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX-LABEL: mul_add_self_v4i64_v4i32:
@@ -5623,18 +5435,11 @@
 ; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[0,1,1,3]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[2,1,3,3]
 ; SSE-NEXT:    pshufd {{.*#+}} xmm4 = xmm1[0,1,1,3]
+; SSE-NEXT:    pmuludq %xmm2, %xmm4
 ; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
-; SSE-NEXT:    pmuludq %xmm1, %xmm3
-; SSE-NEXT:    pxor %xmm5, %xmm5
-; SSE-NEXT:    pmuludq %xmm5, %xmm1
-; SSE-NEXT:    psllq $32, %xmm1
-; SSE-NEXT:    paddq %xmm3, %xmm1
-; SSE-NEXT:    pmuludq %xmm4, %xmm2
-; SSE-NEXT:    pmuludq %xmm4, %xmm5
-; SSE-NEXT:    psllq $32, %xmm5
-; SSE-NEXT:    paddq %xmm2, %xmm5
-; SSE-NEXT:    shufps {{.*#+}} xmm5 = xmm5[0,2],xmm1[0,2]
-; SSE-NEXT:    paddd %xmm5, %xmm0
+; SSE-NEXT:    pmuludq %xmm3, %xmm1
+; SSE-NEXT:    shufps {{.*#+}} xmm4 = xmm4[0,2],xmm1[0,2]
+; SSE-NEXT:    paddd %xmm4, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX-LABEL: mul_add_multiuse_v4i64_v4i32: