llvm-project/llvm/test/CodeGen/X86/haddsub-2.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse2,+sse3 | FileCheck %s --check-prefix=SSE --check-prefix=SSE3
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse2,+sse3,+ssse3 | FileCheck %s --check-prefix=SSE --check-prefix=SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2

define <4 x float> @hadd_ps_test1(<4 x float> %A, <4 x float> %B) {
; SSE-LABEL: hadd_ps_test1:
; SSE:       # %bb.0:
; SSE-NEXT:    haddps %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: hadd_ps_test1:
; AVX:       # %bb.0:
; AVX-NEXT:    vhaddps %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x float> %A, i32 0
  %vecext1 = extractelement <4 x float> %A, i32 1
  %add = fadd float %vecext, %vecext1
  %vecinit = insertelement <4 x float> undef, float %add, i32 0
  %vecext2 = extractelement <4 x float> %A, i32 2
  %vecext3 = extractelement <4 x float> %A, i32 3
  %add4 = fadd float %vecext2, %vecext3
  %vecinit5 = insertelement <4 x float> %vecinit, float %add4, i32 1
  %vecext6 = extractelement <4 x float> %B, i32 0
  %vecext7 = extractelement <4 x float> %B, i32 1
  %add8 = fadd float %vecext6, %vecext7
  %vecinit9 = insertelement <4 x float> %vecinit5, float %add8, i32 2
  %vecext10 = extractelement <4 x float> %B, i32 2
  %vecext11 = extractelement <4 x float> %B, i32 3
  %add12 = fadd float %vecext10, %vecext11
  %vecinit13 = insertelement <4 x float> %vecinit9, float %add12, i32 3
  ret <4 x float> %vecinit13
}

define <4 x float> @hadd_ps_test2(<4 x float> %A, <4 x float> %B) {
; SSE-LABEL: hadd_ps_test2:
; SSE:       # %bb.0:
; SSE-NEXT:    haddps %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: hadd_ps_test2:
; AVX:       # %bb.0:
; AVX-NEXT:    vhaddps %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x float> %A, i32 2
  %vecext1 = extractelement <4 x float> %A, i32 3
  %add = fadd float %vecext, %vecext1
  %vecinit = insertelement <4 x float> undef, float %add, i32 1
  %vecext2 = extractelement <4 x float> %A, i32 0
  %vecext3 = extractelement <4 x float> %A, i32 1
  %add4 = fadd float %vecext2, %vecext3
  %vecinit5 = insertelement <4 x float> %vecinit, float %add4, i32 0
  %vecext6 = extractelement <4 x float> %B, i32 2
  %vecext7 = extractelement <4 x float> %B, i32 3
  %add8 = fadd float %vecext6, %vecext7
  %vecinit9 = insertelement <4 x float> %vecinit5, float %add8, i32 3
  %vecext10 = extractelement <4 x float> %B, i32 0
  %vecext11 = extractelement <4 x float> %B, i32 1
  %add12 = fadd float %vecext10, %vecext11
  %vecinit13 = insertelement <4 x float> %vecinit9, float %add12, i32 2
  ret <4 x float> %vecinit13
}

define <4 x float> @hsub_ps_test1(<4 x float> %A, <4 x float> %B) {
; SSE-LABEL: hsub_ps_test1:
; SSE:       # %bb.0:
; SSE-NEXT:    hsubps %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: hsub_ps_test1:
; AVX:       # %bb.0:
; AVX-NEXT:    vhsubps %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x float> %A, i32 0
  %vecext1 = extractelement <4 x float> %A, i32 1
  %sub = fsub float %vecext, %vecext1
  %vecinit = insertelement <4 x float> undef, float %sub, i32 0
  %vecext2 = extractelement <4 x float> %A, i32 2
  %vecext3 = extractelement <4 x float> %A, i32 3
  %sub4 = fsub float %vecext2, %vecext3
  %vecinit5 = insertelement <4 x float> %vecinit, float %sub4, i32 1
  %vecext6 = extractelement <4 x float> %B, i32 0
  %vecext7 = extractelement <4 x float> %B, i32 1
  %sub8 = fsub float %vecext6, %vecext7
  %vecinit9 = insertelement <4 x float> %vecinit5, float %sub8, i32 2
  %vecext10 = extractelement <4 x float> %B, i32 2
  %vecext11 = extractelement <4 x float> %B, i32 3
  %sub12 = fsub float %vecext10, %vecext11
  %vecinit13 = insertelement <4 x float> %vecinit9, float %sub12, i32 3
  ret <4 x float> %vecinit13
}

define <4 x float> @hsub_ps_test2(<4 x float> %A, <4 x float> %B) {
; SSE-LABEL: hsub_ps_test2:
; SSE:       # %bb.0:
; SSE-NEXT:    hsubps %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: hsub_ps_test2:
; AVX:       # %bb.0:
; AVX-NEXT:    vhsubps %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x float> %A, i32 2
  %vecext1 = extractelement <4 x float> %A, i32 3
  %sub = fsub float %vecext, %vecext1
  %vecinit = insertelement <4 x float> undef, float %sub, i32 1
  %vecext2 = extractelement <4 x float> %A, i32 0
  %vecext3 = extractelement <4 x float> %A, i32 1
  %sub4 = fsub float %vecext2, %vecext3
  %vecinit5 = insertelement <4 x float> %vecinit, float %sub4, i32 0
  %vecext6 = extractelement <4 x float> %B, i32 2
  %vecext7 = extractelement <4 x float> %B, i32 3
  %sub8 = fsub float %vecext6, %vecext7
  %vecinit9 = insertelement <4 x float> %vecinit5, float %sub8, i32 3
  %vecext10 = extractelement <4 x float> %B, i32 0
  %vecext11 = extractelement <4 x float> %B, i32 1
  %sub12 = fsub float %vecext10, %vecext11
  %vecinit13 = insertelement <4 x float> %vecinit9, float %sub12, i32 2
  ret <4 x float> %vecinit13
}

define <4 x i32> @phadd_d_test1(<4 x i32> %A, <4 x i32> %B) {
; SSE3-LABEL: phadd_d_test1:
; SSE3:       # %bb.0:
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[1,1,2,3]
; SSE3-NEXT:    movd %xmm2, %ecx
; SSE3-NEXT:    addl %eax, %ecx
; SSE3-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; SSE3-NEXT:    movd %xmm2, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %edx
; SSE3-NEXT:    addl %eax, %edx
; SSE3-NEXT:    movd %xmm1, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
; SSE3-NEXT:    movd %xmm0, %esi
; SSE3-NEXT:    addl %eax, %esi
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %edi
; SSE3-NEXT:    addl %eax, %edi
; SSE3-NEXT:    movd %edi, %xmm0
; SSE3-NEXT:    movd %esi, %xmm1
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE3-NEXT:    movd %edx, %xmm2
; SSE3-NEXT:    movd %ecx, %xmm0
; SSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: phadd_d_test1:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    phaddd %xmm1, %xmm0
; SSSE3-NEXT:    retq
;
; AVX-LABEL: phadd_d_test1:
; AVX:       # %bb.0:
; AVX-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x i32> %A, i32 0
  %vecext1 = extractelement <4 x i32> %A, i32 1
  %add = add i32 %vecext, %vecext1
  %vecinit = insertelement <4 x i32> undef, i32 %add, i32 0
  %vecext2 = extractelement <4 x i32> %A, i32 2
  %vecext3 = extractelement <4 x i32> %A, i32 3
  %add4 = add i32 %vecext2, %vecext3
  %vecinit5 = insertelement <4 x i32> %vecinit, i32 %add4, i32 1
  %vecext6 = extractelement <4 x i32> %B, i32 0
  %vecext7 = extractelement <4 x i32> %B, i32 1
  %add8 = add i32 %vecext6, %vecext7
  %vecinit9 = insertelement <4 x i32> %vecinit5, i32 %add8, i32 2
  %vecext10 = extractelement <4 x i32> %B, i32 2
  %vecext11 = extractelement <4 x i32> %B, i32 3
  %add12 = add i32 %vecext10, %vecext11
  %vecinit13 = insertelement <4 x i32> %vecinit9, i32 %add12, i32 3
  ret <4 x i32> %vecinit13
}

define <4 x i32> @phadd_d_test2(<4 x i32> %A, <4 x i32> %B) {
; SSE3-LABEL: phadd_d_test2:
; SSE3:       # %bb.0:
; SSE3-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; SSE3-NEXT:    movd %xmm2, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[3,1,2,3]
; SSE3-NEXT:    movd %xmm2, %ecx
; SSE3-NEXT:    addl %eax, %ecx
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE3-NEXT:    movd %xmm0, %edx
; SSE3-NEXT:    addl %eax, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE3-NEXT:    movd %xmm0, %esi
; SSE3-NEXT:    addl %eax, %esi
; SSE3-NEXT:    movd %esi, %xmm0
; SSE3-NEXT:    pshufd {{.*#+}} xmm2 = xmm1[1,1,2,3]
; SSE3-NEXT:    movd %xmm2, %eax
; SSE3-NEXT:    movd %xmm1, %esi
; SSE3-NEXT:    addl %eax, %esi
; SSE3-NEXT:    movd %esi, %xmm1
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE3-NEXT:    movd %ecx, %xmm2
; SSE3-NEXT:    movd %edx, %xmm0
; SSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: phadd_d_test2:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    phaddd %xmm1, %xmm0
; SSSE3-NEXT:    retq
;
; AVX-LABEL: phadd_d_test2:
; AVX:       # %bb.0:
; AVX-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x i32> %A, i32 2
  %vecext1 = extractelement <4 x i32> %A, i32 3
  %add = add i32 %vecext, %vecext1
  %vecinit = insertelement <4 x i32> undef, i32 %add, i32 1
  %vecext2 = extractelement <4 x i32> %A, i32 0
  %vecext3 = extractelement <4 x i32> %A, i32 1
  %add4 = add i32 %vecext2, %vecext3
  %vecinit5 = insertelement <4 x i32> %vecinit, i32 %add4, i32 0
  %vecext6 = extractelement <4 x i32> %B, i32 3
  %vecext7 = extractelement <4 x i32> %B, i32 2
  %add8 = add i32 %vecext6, %vecext7
  %vecinit9 = insertelement <4 x i32> %vecinit5, i32 %add8, i32 3
  %vecext10 = extractelement <4 x i32> %B, i32 1
  %vecext11 = extractelement <4 x i32> %B, i32 0
  %add12 = add i32 %vecext10, %vecext11
  %vecinit13 = insertelement <4 x i32> %vecinit9, i32 %add12, i32 2
  ret <4 x i32> %vecinit13
}

define <4 x i32> @phsub_d_test1(<4 x i32> %A, <4 x i32> %B) {
; SSE3-LABEL: phsub_d_test1:
; SSE3:       # %bb.0:
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[1,1,2,3]
; SSE3-NEXT:    movd %xmm2, %ecx
; SSE3-NEXT:    subl %ecx, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; SSE3-NEXT:    movd %xmm2, %ecx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %edx
; SSE3-NEXT:    subl %edx, %ecx
; SSE3-NEXT:    movd %xmm1, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
; SSE3-NEXT:    movd %xmm0, %esi
; SSE3-NEXT:    subl %esi, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE3-NEXT:    movd %xmm0, %esi
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %edi
; SSE3-NEXT:    subl %edi, %esi
; SSE3-NEXT:    movd %esi, %xmm0
; SSE3-NEXT:    movd %edx, %xmm1
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE3-NEXT:    movd %ecx, %xmm2
; SSE3-NEXT:    movd %eax, %xmm0
; SSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: phsub_d_test1:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    phsubd %xmm1, %xmm0
; SSSE3-NEXT:    retq
;
; AVX-LABEL: phsub_d_test1:
; AVX:       # %bb.0:
; AVX-NEXT:    vphsubd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x i32> %A, i32 0
  %vecext1 = extractelement <4 x i32> %A, i32 1
  %sub = sub i32 %vecext, %vecext1
  %vecinit = insertelement <4 x i32> undef, i32 %sub, i32 0
  %vecext2 = extractelement <4 x i32> %A, i32 2
  %vecext3 = extractelement <4 x i32> %A, i32 3
  %sub4 = sub i32 %vecext2, %vecext3
  %vecinit5 = insertelement <4 x i32> %vecinit, i32 %sub4, i32 1
  %vecext6 = extractelement <4 x i32> %B, i32 0
  %vecext7 = extractelement <4 x i32> %B, i32 1
  %sub8 = sub i32 %vecext6, %vecext7
  %vecinit9 = insertelement <4 x i32> %vecinit5, i32 %sub8, i32 2
  %vecext10 = extractelement <4 x i32> %B, i32 2
  %vecext11 = extractelement <4 x i32> %B, i32 3
  %sub12 = sub i32 %vecext10, %vecext11
  %vecinit13 = insertelement <4 x i32> %vecinit9, i32 %sub12, i32 3
  ret <4 x i32> %vecinit13
}

define <4 x i32> @phsub_d_test2(<4 x i32> %A, <4 x i32> %B) {
; SSE3-LABEL: phsub_d_test2:
; SSE3:       # %bb.0:
; SSE3-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; SSE3-NEXT:    movd %xmm2, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[3,1,2,3]
; SSE3-NEXT:    movd %xmm2, %ecx
; SSE3-NEXT:    subl %ecx, %eax
; SSE3-NEXT:    movd %xmm0, %ecx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE3-NEXT:    movd %xmm0, %edx
; SSE3-NEXT:    subl %edx, %ecx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE3-NEXT:    movd %xmm0, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %esi
; SSE3-NEXT:    subl %esi, %edx
; SSE3-NEXT:    movd %edx, %xmm0
; SSE3-NEXT:    movd %xmm1, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[1,1,2,3]
; SSE3-NEXT:    movd %xmm1, %esi
; SSE3-NEXT:    subl %esi, %edx
; SSE3-NEXT:    movd %edx, %xmm1
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE3-NEXT:    movd %eax, %xmm2
; SSE3-NEXT:    movd %ecx, %xmm0
; SSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: phsub_d_test2:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    phsubd %xmm1, %xmm0
; SSSE3-NEXT:    retq
;
; AVX-LABEL: phsub_d_test2:
; AVX:       # %bb.0:
; AVX-NEXT:    vphsubd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x i32> %A, i32 2
  %vecext1 = extractelement <4 x i32> %A, i32 3
  %sub = sub i32 %vecext, %vecext1
  %vecinit = insertelement <4 x i32> undef, i32 %sub, i32 1
  %vecext2 = extractelement <4 x i32> %A, i32 0
  %vecext3 = extractelement <4 x i32> %A, i32 1
  %sub4 = sub i32 %vecext2, %vecext3
  %vecinit5 = insertelement <4 x i32> %vecinit, i32 %sub4, i32 0
  %vecext6 = extractelement <4 x i32> %B, i32 2
  %vecext7 = extractelement <4 x i32> %B, i32 3
  %sub8 = sub i32 %vecext6, %vecext7
  %vecinit9 = insertelement <4 x i32> %vecinit5, i32 %sub8, i32 3
  %vecext10 = extractelement <4 x i32> %B, i32 0
  %vecext11 = extractelement <4 x i32> %B, i32 1
  %sub12 = sub i32 %vecext10, %vecext11
  %vecinit13 = insertelement <4 x i32> %vecinit9, i32 %sub12, i32 2
  ret <4 x i32> %vecinit13
}

define <2 x double> @hadd_pd_test1(<2 x double> %A, <2 x double> %B) {
; SSE-LABEL: hadd_pd_test1:
; SSE:       # %bb.0:
; SSE-NEXT:    haddpd %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: hadd_pd_test1:
; AVX:       # %bb.0:
; AVX-NEXT:    vhaddpd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <2 x double> %A, i32 0
  %vecext1 = extractelement <2 x double> %A, i32 1
  %add = fadd double %vecext, %vecext1
  %vecinit = insertelement <2 x double> undef, double %add, i32 0
  %vecext2 = extractelement <2 x double> %B, i32 0
  %vecext3 = extractelement <2 x double> %B, i32 1
  %add2 = fadd double %vecext2, %vecext3
  %vecinit2 = insertelement <2 x double> %vecinit, double %add2, i32 1
  ret <2 x double> %vecinit2
}

define <2 x double> @hadd_pd_test2(<2 x double> %A, <2 x double> %B) {
; SSE-LABEL: hadd_pd_test2:
; SSE:       # %bb.0:
; SSE-NEXT:    haddpd %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: hadd_pd_test2:
; AVX:       # %bb.0:
; AVX-NEXT:    vhaddpd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <2 x double> %A, i32 1
  %vecext1 = extractelement <2 x double> %A, i32 0
  %add = fadd double %vecext, %vecext1
  %vecinit = insertelement <2 x double> undef, double %add, i32 0
  %vecext2 = extractelement <2 x double> %B, i32 1
  %vecext3 = extractelement <2 x double> %B, i32 0
  %add2 = fadd double %vecext2, %vecext3
  %vecinit2 = insertelement <2 x double> %vecinit, double %add2, i32 1
  ret <2 x double> %vecinit2
}

define <2 x double> @hsub_pd_test1(<2 x double> %A, <2 x double> %B) {
; SSE-LABEL: hsub_pd_test1:
; SSE:       # %bb.0:
; SSE-NEXT:    hsubpd %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: hsub_pd_test1:
; AVX:       # %bb.0:
; AVX-NEXT:    vhsubpd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <2 x double> %A, i32 0
  %vecext1 = extractelement <2 x double> %A, i32 1
  %sub = fsub double %vecext, %vecext1
  %vecinit = insertelement <2 x double> undef, double %sub, i32 0
  %vecext2 = extractelement <2 x double> %B, i32 0
  %vecext3 = extractelement <2 x double> %B, i32 1
  %sub2 = fsub double %vecext2, %vecext3
  %vecinit2 = insertelement <2 x double> %vecinit, double %sub2, i32 1
  ret <2 x double> %vecinit2
}

define <2 x double> @hsub_pd_test2(<2 x double> %A, <2 x double> %B) {
; SSE-LABEL: hsub_pd_test2:
; SSE:       # %bb.0:
; SSE-NEXT:    hsubpd %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: hsub_pd_test2:
; AVX:       # %bb.0:
; AVX-NEXT:    vhsubpd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <2 x double> %B, i32 0
  %vecext1 = extractelement <2 x double> %B, i32 1
  %sub = fsub double %vecext, %vecext1
  %vecinit = insertelement <2 x double> undef, double %sub, i32 1
  %vecext2 = extractelement <2 x double> %A, i32 0
  %vecext3 = extractelement <2 x double> %A, i32 1
  %sub2 = fsub double %vecext2, %vecext3
  %vecinit2 = insertelement <2 x double> %vecinit, double %sub2, i32 0
  ret <2 x double> %vecinit2
}

define <4 x double> @avx_vhadd_pd_test(<4 x double> %A, <4 x double> %B) {
; SSE-LABEL: avx_vhadd_pd_test:
; SSE:       # %bb.0:
; SSE-NEXT:    haddpd %xmm1, %xmm0
; SSE-NEXT:    haddpd %xmm3, %xmm2
; SSE-NEXT:    movapd %xmm2, %xmm1
; SSE-NEXT:    retq
;
; AVX-LABEL: avx_vhadd_pd_test:
; AVX:       # %bb.0:
; AVX-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX-NEXT:    vhaddpd %xmm2, %xmm1, %xmm1
; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX-NEXT:    vhaddpd %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x double> %A, i32 0
  %vecext1 = extractelement <4 x double> %A, i32 1
  %add = fadd double %vecext, %vecext1
  %vecinit = insertelement <4 x double> undef, double %add, i32 0
  %vecext2 = extractelement <4 x double> %A, i32 2
  %vecext3 = extractelement <4 x double> %A, i32 3
  %add4 = fadd double %vecext2, %vecext3
  %vecinit5 = insertelement <4 x double> %vecinit, double %add4, i32 1
  %vecext6 = extractelement <4 x double> %B, i32 0
  %vecext7 = extractelement <4 x double> %B, i32 1
  %add8 = fadd double %vecext6, %vecext7
  %vecinit9 = insertelement <4 x double> %vecinit5, double %add8, i32 2
  %vecext10 = extractelement <4 x double> %B, i32 2
  %vecext11 = extractelement <4 x double> %B, i32 3
  %add12 = fadd double %vecext10, %vecext11
  %vecinit13 = insertelement <4 x double> %vecinit9, double %add12, i32 3
  ret <4 x double> %vecinit13
}

define <4 x double> @avx_vhsub_pd_test(<4 x double> %A, <4 x double> %B) {
; SSE-LABEL: avx_vhsub_pd_test:
; SSE:       # %bb.0:
; SSE-NEXT:    hsubpd %xmm1, %xmm0
; SSE-NEXT:    hsubpd %xmm3, %xmm2
; SSE-NEXT:    movapd %xmm2, %xmm1
; SSE-NEXT:    retq
;
; AVX-LABEL: avx_vhsub_pd_test:
; AVX:       # %bb.0:
; AVX-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX-NEXT:    vhsubpd %xmm2, %xmm1, %xmm1
; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX-NEXT:    vhsubpd %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x double> %A, i32 0
  %vecext1 = extractelement <4 x double> %A, i32 1
  %sub = fsub double %vecext, %vecext1
  %vecinit = insertelement <4 x double> undef, double %sub, i32 0
  %vecext2 = extractelement <4 x double> %A, i32 2
  %vecext3 = extractelement <4 x double> %A, i32 3
  %sub4 = fsub double %vecext2, %vecext3
  %vecinit5 = insertelement <4 x double> %vecinit, double %sub4, i32 1
  %vecext6 = extractelement <4 x double> %B, i32 0
  %vecext7 = extractelement <4 x double> %B, i32 1
  %sub8 = fsub double %vecext6, %vecext7
  %vecinit9 = insertelement <4 x double> %vecinit5, double %sub8, i32 2
  %vecext10 = extractelement <4 x double> %B, i32 2
  %vecext11 = extractelement <4 x double> %B, i32 3
  %sub12 = fsub double %vecext10, %vecext11
  %vecinit13 = insertelement <4 x double> %vecinit9, double %sub12, i32 3
  ret <4 x double> %vecinit13
}

define <8 x i32> @avx2_vphadd_d_test(<8 x i32> %A, <8 x i32> %B) {
; SSE3-LABEL: avx2_vphadd_d_test:
; SSE3:       # %bb.0:
; SSE3-NEXT:    movd %xmm0, %ecx
; SSE3-NEXT:    pshufd {{.*#+}} xmm4 = xmm0[1,1,2,3]
; SSE3-NEXT:    movd %xmm4, %r8d
; SSE3-NEXT:    addl %ecx, %r8d
; SSE3-NEXT:    pshufd {{.*#+}} xmm4 = xmm0[2,3,0,1]
; SSE3-NEXT:    movd %xmm4, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %r9d
; SSE3-NEXT:    addl %edx, %r9d
; SSE3-NEXT:    movd %xmm1, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
; SSE3-NEXT:    movd %xmm0, %esi
; SSE3-NEXT:    addl %edx, %esi
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE3-NEXT:    movd %xmm0, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %edi
; SSE3-NEXT:    addl %edx, %edi
; SSE3-NEXT:    movd %xmm2, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,1,2,3]
; SSE3-NEXT:    movd %xmm0, %r10d
; SSE3-NEXT:    addl %eax, %r10d
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %ecx
; SSE3-NEXT:    addl %eax, %ecx
; SSE3-NEXT:    movd %xmm3, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
; SSE3-NEXT:    movd %xmm0, %edx
; SSE3-NEXT:    addl %eax, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[2,3,0,1]
; SSE3-NEXT:    movd %xmm0, %r11d
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    addl %r11d, %eax
; SSE3-NEXT:    movd %edi, %xmm0
; SSE3-NEXT:    movd %esi, %xmm1
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE3-NEXT:    movd %r9d, %xmm2
; SSE3-NEXT:    movd %r8d, %xmm0
; SSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE3-NEXT:    movd %eax, %xmm1
; SSE3-NEXT:    movd %edx, %xmm2
; SSE3-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE3-NEXT:    movd %ecx, %xmm3
; SSE3-NEXT:    movd %r10d, %xmm1
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: avx2_vphadd_d_test:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    phaddd %xmm1, %xmm0
; SSSE3-NEXT:    phaddd %xmm3, %xmm2
; SSSE3-NEXT:    movdqa %xmm2, %xmm1
; SSSE3-NEXT:    retq
;
; AVX1-LABEL: avx2_vphadd_d_test:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vphaddd %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vphaddd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: avx2_vphadd_d_test:
; AVX2:       # %bb.0:
; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT:    vphaddd %xmm2, %xmm1, %xmm1
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm2
; AVX2-NEXT:    vphaddd %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT:    retq
  %vecext = extractelement <8 x i32> %A, i32 0
  %vecext1 = extractelement <8 x i32> %A, i32 1
  %add = add i32 %vecext, %vecext1
  %vecinit = insertelement <8 x i32> undef, i32 %add, i32 0
  %vecext2 = extractelement <8 x i32> %A, i32 2
  %vecext3 = extractelement <8 x i32> %A, i32 3
  %add4 = add i32 %vecext2, %vecext3
  %vecinit5 = insertelement <8 x i32> %vecinit, i32 %add4, i32 1
  %vecext6 = extractelement <8 x i32> %A, i32 4
  %vecext7 = extractelement <8 x i32> %A, i32 5
  %add8 = add i32 %vecext6, %vecext7
  %vecinit9 = insertelement <8 x i32> %vecinit5, i32 %add8, i32 2
  %vecext10 = extractelement <8 x i32> %A, i32 6
  %vecext11 = extractelement <8 x i32> %A, i32 7
  %add12 = add i32 %vecext10, %vecext11
  %vecinit13 = insertelement <8 x i32> %vecinit9, i32 %add12, i32 3
  %vecext14 = extractelement <8 x i32> %B, i32 0
  %vecext15 = extractelement <8 x i32> %B, i32 1
  %add16 = add i32 %vecext14, %vecext15
  %vecinit17 = insertelement <8 x i32> %vecinit13, i32 %add16, i32 4
  %vecext18 = extractelement <8 x i32> %B, i32 2
  %vecext19 = extractelement <8 x i32> %B, i32 3
  %add20 = add i32 %vecext18, %vecext19
  %vecinit21 = insertelement <8 x i32> %vecinit17, i32 %add20, i32 5
  %vecext22 = extractelement <8 x i32> %B, i32 4
  %vecext23 = extractelement <8 x i32> %B, i32 5
  %add24 = add i32 %vecext22, %vecext23
  %vecinit25 = insertelement <8 x i32> %vecinit21, i32 %add24, i32 6
  %vecext26 = extractelement <8 x i32> %B, i32 6
  %vecext27 = extractelement <8 x i32> %B, i32 7
  %add28 = add i32 %vecext26, %vecext27
  %vecinit29 = insertelement <8 x i32> %vecinit25, i32 %add28, i32 7
  ret <8 x i32> %vecinit29
}

define <16 x i16> @avx2_vphadd_w_test(<16 x i16> %a, <16 x i16> %b) nounwind {
; SSE3-LABEL: avx2_vphadd_w_test:
; SSE3:       # %bb.0:
; SSE3-NEXT:    pushq %rbp
; SSE3-NEXT:    pushq %r15
; SSE3-NEXT:    pushq %r14
; SSE3-NEXT:    pushq %r13
; SSE3-NEXT:    pushq %r12
; SSE3-NEXT:    pushq %rbx
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    pextrw $1, %xmm0, %ecx
; SSE3-NEXT:    addl %eax, %ecx
; SSE3-NEXT:    movl %ecx, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; SSE3-NEXT:    pextrw $2, %xmm0, %eax
; SSE3-NEXT:    pextrw $3, %xmm0, %ecx
; SSE3-NEXT:    addl %eax, %ecx
; SSE3-NEXT:    movl %ecx, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; SSE3-NEXT:    pextrw $4, %xmm0, %eax
; SSE3-NEXT:    pextrw $5, %xmm0, %r11d
; SSE3-NEXT:    addl %eax, %r11d
; SSE3-NEXT:    pextrw $6, %xmm0, %eax
; SSE3-NEXT:    pextrw $7, %xmm0, %r15d
; SSE3-NEXT:    addl %eax, %r15d
; SSE3-NEXT:    movd %xmm1, %eax
; SSE3-NEXT:    pextrw $1, %xmm1, %r13d
; SSE3-NEXT:    addl %eax, %r13d
; SSE3-NEXT:    pextrw $2, %xmm1, %eax
; SSE3-NEXT:    pextrw $3, %xmm1, %ebx
; SSE3-NEXT:    addl %eax, %ebx
; SSE3-NEXT:    pextrw $4, %xmm1, %eax
; SSE3-NEXT:    pextrw $5, %xmm1, %r8d
; SSE3-NEXT:    addl %eax, %r8d
; SSE3-NEXT:    pextrw $6, %xmm1, %eax
; SSE3-NEXT:    pextrw $7, %xmm1, %esi
; SSE3-NEXT:    addl %eax, %esi
; SSE3-NEXT:    movd %xmm2, %eax
; SSE3-NEXT:    pextrw $1, %xmm2, %r10d
; SSE3-NEXT:    addl %eax, %r10d
; SSE3-NEXT:    pextrw $2, %xmm2, %eax
; SSE3-NEXT:    pextrw $3, %xmm2, %r14d
; SSE3-NEXT:    addl %eax, %r14d
; SSE3-NEXT:    pextrw $4, %xmm2, %eax
; SSE3-NEXT:    pextrw $5, %xmm2, %r12d
; SSE3-NEXT:    addl %eax, %r12d
; SSE3-NEXT:    pextrw $6, %xmm2, %eax
; SSE3-NEXT:    pextrw $7, %xmm2, %r9d
; SSE3-NEXT:    addl %eax, %r9d
; SSE3-NEXT:    movd %xmm3, %eax
; SSE3-NEXT:    pextrw $1, %xmm3, %ebp
; SSE3-NEXT:    addl %eax, %ebp
; SSE3-NEXT:    pextrw $2, %xmm3, %edx
; SSE3-NEXT:    pextrw $3, %xmm3, %edi
; SSE3-NEXT:    addl %edx, %edi
; SSE3-NEXT:    pextrw $4, %xmm3, %edx
; SSE3-NEXT:    pextrw $5, %xmm3, %ecx
; SSE3-NEXT:    addl %edx, %ecx
; SSE3-NEXT:    pextrw $6, %xmm3, %edx
; SSE3-NEXT:    pextrw $7, %xmm3, %eax
; SSE3-NEXT:    addl %edx, %eax
; SSE3-NEXT:    movd %esi, %xmm8
; SSE3-NEXT:    movd %r8d, %xmm3
; SSE3-NEXT:    movd %ebx, %xmm9
; SSE3-NEXT:    movd %r13d, %xmm4
; SSE3-NEXT:    movd %r15d, %xmm10
; SSE3-NEXT:    movd %r11d, %xmm7
; SSE3-NEXT:    movd {{[-0-9]+}}(%r{{[sb]}}p), %xmm11 # 4-byte Folded Reload
; SSE3-NEXT:    # xmm11 = mem[0],zero,zero,zero
; SSE3-NEXT:    movd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Folded Reload
; SSE3-NEXT:    # xmm0 = mem[0],zero,zero,zero
; SSE3-NEXT:    movd %eax, %xmm12
; SSE3-NEXT:    movd %ecx, %xmm6
; SSE3-NEXT:    movd %edi, %xmm13
; SSE3-NEXT:    movd %ebp, %xmm5
; SSE3-NEXT:    movd %r9d, %xmm14
; SSE3-NEXT:    movd %r12d, %xmm2
; SSE3-NEXT:    movd %r14d, %xmm15
; SSE3-NEXT:    movd %r10d, %xmm1
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm8[0],xmm3[1],xmm8[1],xmm3[2],xmm8[2],xmm3[3],xmm8[3]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm9[0],xmm4[1],xmm9[1],xmm4[2],xmm9[2],xmm4[3],xmm9[3]
; SSE3-NEXT:    punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm7 = xmm7[0],xmm10[0],xmm7[1],xmm10[1],xmm7[2],xmm10[2],xmm7[3],xmm10[3]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm11[0],xmm0[1],xmm11[1],xmm0[2],xmm11[2],xmm0[3],xmm11[3]
; SSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm7[0],xmm0[1],xmm7[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm4[0]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm12[0],xmm6[1],xmm12[1],xmm6[2],xmm12[2],xmm6[3],xmm12[3]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm5 = xmm5[0],xmm13[0],xmm5[1],xmm13[1],xmm5[2],xmm13[2],xmm5[3],xmm13[3]
; SSE3-NEXT:    punpckldq {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[1],xmm6[1]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm15[0],xmm1[1],xmm15[1],xmm1[2],xmm15[2],xmm1[3],xmm15[3]
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm5[0]
; SSE3-NEXT:    popq %rbx
; SSE3-NEXT:    popq %r12
; SSE3-NEXT:    popq %r13
; SSE3-NEXT:    popq %r14
; SSE3-NEXT:    popq %r15
; SSE3-NEXT:    popq %rbp
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: avx2_vphadd_w_test:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    phaddw %xmm1, %xmm0
; SSSE3-NEXT:    phaddw %xmm3, %xmm2
; SSSE3-NEXT:    movdqa %xmm2, %xmm1
; SSSE3-NEXT:    retq
;
; AVX1-LABEL: avx2_vphadd_w_test:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vphaddw %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vphaddw %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: avx2_vphadd_w_test:
; AVX2:       # %bb.0:
; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT:    vphaddw %xmm2, %xmm1, %xmm1
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm2
; AVX2-NEXT:    vphaddw %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT:    retq
  %vecext = extractelement <16 x i16> %a, i32 0
  %vecext1 = extractelement <16 x i16> %a, i32 1
  %add = add i16 %vecext, %vecext1
  %vecinit = insertelement <16 x i16> undef, i16 %add, i32 0
  %vecext4 = extractelement <16 x i16> %a, i32 2
  %vecext6 = extractelement <16 x i16> %a, i32 3
  %add8 = add i16 %vecext4, %vecext6
  %vecinit10 = insertelement <16 x i16> %vecinit, i16 %add8, i32 1
  %vecext11 = extractelement <16 x i16> %a, i32 4
  %vecext13 = extractelement <16 x i16> %a, i32 5
  %add15 = add i16 %vecext11, %vecext13
  %vecinit17 = insertelement <16 x i16> %vecinit10, i16 %add15, i32 2
  %vecext18 = extractelement <16 x i16> %a, i32 6
  %vecext20 = extractelement <16 x i16> %a, i32 7
  %add22 = add i16 %vecext18, %vecext20
  %vecinit24 = insertelement <16 x i16> %vecinit17, i16 %add22, i32 3
  %vecext25 = extractelement <16 x i16> %a, i32 8
  %vecext27 = extractelement <16 x i16> %a, i32 9
  %add29 = add i16 %vecext25, %vecext27
  %vecinit31 = insertelement <16 x i16> %vecinit24, i16 %add29, i32 4
  %vecext32 = extractelement <16 x i16> %a, i32 10
  %vecext34 = extractelement <16 x i16> %a, i32 11
  %add36 = add i16 %vecext32, %vecext34
  %vecinit38 = insertelement <16 x i16> %vecinit31, i16 %add36, i32 5
  %vecext39 = extractelement <16 x i16> %a, i32 12
  %vecext41 = extractelement <16 x i16> %a, i32 13
  %add43 = add i16 %vecext39, %vecext41
  %vecinit45 = insertelement <16 x i16> %vecinit38, i16 %add43, i32 6
  %vecext46 = extractelement <16 x i16> %a, i32 14
  %vecext48 = extractelement <16 x i16> %a, i32 15
  %add50 = add i16 %vecext46, %vecext48
  %vecinit52 = insertelement <16 x i16> %vecinit45, i16 %add50, i32 7
  %vecext53 = extractelement <16 x i16> %b, i32 0
  %vecext55 = extractelement <16 x i16> %b, i32 1
  %add57 = add i16 %vecext53, %vecext55
  %vecinit59 = insertelement <16 x i16> %vecinit52, i16 %add57, i32 8
  %vecext60 = extractelement <16 x i16> %b, i32 2
  %vecext62 = extractelement <16 x i16> %b, i32 3
  %add64 = add i16 %vecext60, %vecext62
  %vecinit66 = insertelement <16 x i16> %vecinit59, i16 %add64, i32 9
  %vecext67 = extractelement <16 x i16> %b, i32 4
  %vecext69 = extractelement <16 x i16> %b, i32 5
  %add71 = add i16 %vecext67, %vecext69
  %vecinit73 = insertelement <16 x i16> %vecinit66, i16 %add71, i32 10
  %vecext74 = extractelement <16 x i16> %b, i32 6
  %vecext76 = extractelement <16 x i16> %b, i32 7
  %add78 = add i16 %vecext74, %vecext76
  %vecinit80 = insertelement <16 x i16> %vecinit73, i16 %add78, i32 11
  %vecext81 = extractelement <16 x i16> %b, i32 8
  %vecext83 = extractelement <16 x i16> %b, i32 9
  %add85 = add i16 %vecext81, %vecext83
  %vecinit87 = insertelement <16 x i16> %vecinit80, i16 %add85, i32 12
  %vecext88 = extractelement <16 x i16> %b, i32 10
  %vecext90 = extractelement <16 x i16> %b, i32 11
  %add92 = add i16 %vecext88, %vecext90
  %vecinit94 = insertelement <16 x i16> %vecinit87, i16 %add92, i32 13
  %vecext95 = extractelement <16 x i16> %b, i32 12
  %vecext97 = extractelement <16 x i16> %b, i32 13
  %add99 = add i16 %vecext95, %vecext97
  %vecinit101 = insertelement <16 x i16> %vecinit94, i16 %add99, i32 14
  %vecext102 = extractelement <16 x i16> %b, i32 14
  %vecext104 = extractelement <16 x i16> %b, i32 15
  %add106 = add i16 %vecext102, %vecext104
  %vecinit108 = insertelement <16 x i16> %vecinit101, i16 %add106, i32 15
  ret <16 x i16> %vecinit108
}

; Verify that we don't select horizontal subs in the following functions.

define <4 x i32> @not_a_hsub_1(<4 x i32> %A, <4 x i32> %B) {
; SSE-LABEL: not_a_hsub_1:
; SSE:       # %bb.0:
; SSE-NEXT:    movd %xmm0, %eax
; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[1,1,2,3]
; SSE-NEXT:    movd %xmm2, %ecx
; SSE-NEXT:    subl %ecx, %eax
; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; SSE-NEXT:    movd %xmm2, %ecx
; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE-NEXT:    movd %xmm0, %edx
; SSE-NEXT:    subl %edx, %ecx
; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
; SSE-NEXT:    movd %xmm0, %edx
; SSE-NEXT:    movd %xmm1, %esi
; SSE-NEXT:    subl %esi, %edx
; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[3,1,2,3]
; SSE-NEXT:    movd %xmm0, %esi
; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE-NEXT:    movd %xmm0, %edi
; SSE-NEXT:    subl %edi, %esi
; SSE-NEXT:    movd %esi, %xmm0
; SSE-NEXT:    movd %edx, %xmm1
; SSE-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE-NEXT:    movd %ecx, %xmm2
; SSE-NEXT:    movd %eax, %xmm0
; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE-NEXT:    retq
;
; AVX-LABEL: not_a_hsub_1:
; AVX:       # %bb.0:
; AVX-NEXT:    vmovd %xmm0, %eax
; AVX-NEXT:    vpextrd $1, %xmm0, %ecx
; AVX-NEXT:    subl %ecx, %eax
; AVX-NEXT:    vpextrd $2, %xmm0, %ecx
; AVX-NEXT:    vpextrd $3, %xmm0, %edx
; AVX-NEXT:    subl %edx, %ecx
; AVX-NEXT:    vpextrd $1, %xmm1, %edx
; AVX-NEXT:    vmovd %xmm1, %esi
; AVX-NEXT:    subl %esi, %edx
; AVX-NEXT:    vpextrd $3, %xmm1, %esi
; AVX-NEXT:    vpextrd $2, %xmm1, %edi
; AVX-NEXT:    subl %edi, %esi
; AVX-NEXT:    vmovd %eax, %xmm0
; AVX-NEXT:    vpinsrd $1, %ecx, %xmm0, %xmm0
; AVX-NEXT:    vpinsrd $2, %edx, %xmm0, %xmm0
; AVX-NEXT:    vpinsrd $3, %esi, %xmm0, %xmm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x i32> %A, i32 0
  %vecext1 = extractelement <4 x i32> %A, i32 1
  %sub = sub i32 %vecext, %vecext1
  %vecinit = insertelement <4 x i32> undef, i32 %sub, i32 0
  %vecext2 = extractelement <4 x i32> %A, i32 2
  %vecext3 = extractelement <4 x i32> %A, i32 3
  %sub4 = sub i32 %vecext2, %vecext3
  %vecinit5 = insertelement <4 x i32> %vecinit, i32 %sub4, i32 1
  %vecext6 = extractelement <4 x i32> %B, i32 1
  %vecext7 = extractelement <4 x i32> %B, i32 0
  %sub8 = sub i32 %vecext6, %vecext7
  %vecinit9 = insertelement <4 x i32> %vecinit5, i32 %sub8, i32 2
  %vecext10 = extractelement <4 x i32> %B, i32 3
  %vecext11 = extractelement <4 x i32> %B, i32 2
  %sub12 = sub i32 %vecext10, %vecext11
  %vecinit13 = insertelement <4 x i32> %vecinit9, i32 %sub12, i32 3
  ret <4 x i32> %vecinit13
}

define <4 x float> @not_a_hsub_2(<4 x float> %A, <4 x float> %B) {
; SSE-LABEL: not_a_hsub_2:
; SSE:       # %bb.0:
; SSE-NEXT:    movaps %xmm0, %xmm2
; SSE-NEXT:    unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
; SSE-NEXT:    movaps %xmm0, %xmm3
; SSE-NEXT:    shufps {{.*#+}} xmm3 = xmm3[3,1],xmm0[2,3]
; SSE-NEXT:    subss %xmm3, %xmm2
; SSE-NEXT:    movshdup {{.*#+}} xmm3 = xmm0[1,1,3,3]
; SSE-NEXT:    subss %xmm3, %xmm0
; SSE-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE-NEXT:    movaps %xmm1, %xmm2
; SSE-NEXT:    shufps {{.*#+}} xmm2 = xmm2[3,1],xmm1[2,3]
; SSE-NEXT:    movaps %xmm1, %xmm3
; SSE-NEXT:    unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm1[1]
; SSE-NEXT:    subss %xmm3, %xmm2
; SSE-NEXT:    movshdup {{.*#+}} xmm3 = xmm1[1,1,3,3]
; SSE-NEXT:    subss %xmm3, %xmm1
; SSE-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE-NEXT:    retq
;
; AVX-LABEL: not_a_hsub_2:
; AVX:       # %bb.0:
; AVX-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
; AVX-NEXT:    vpermilps {{.*#+}} xmm3 = xmm0[3,1,2,3]
; AVX-NEXT:    vsubss %xmm3, %xmm2, %xmm2
; AVX-NEXT:    vmovshdup {{.*#+}} xmm3 = xmm0[1,1,3,3]
; AVX-NEXT:    vsubss %xmm3, %xmm0, %xmm0
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[2,3]
; AVX-NEXT:    vpermilps {{.*#+}} xmm2 = xmm1[3,1,2,3]
; AVX-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm1[1,0]
; AVX-NEXT:    vsubss %xmm3, %xmm2, %xmm2
; AVX-NEXT:    vmovshdup {{.*#+}} xmm3 = xmm1[1,1,3,3]
; AVX-NEXT:    vsubss %xmm3, %xmm1, %xmm1
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0],xmm0[3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm2[0]
; AVX-NEXT:    retq
  %vecext = extractelement <4 x float> %A, i32 2
  %vecext1 = extractelement <4 x float> %A, i32 3
  %sub = fsub float %vecext, %vecext1
  %vecinit = insertelement <4 x float> undef, float %sub, i32 1
  %vecext2 = extractelement <4 x float> %A, i32 0
  %vecext3 = extractelement <4 x float> %A, i32 1
  %sub4 = fsub float %vecext2, %vecext3
  %vecinit5 = insertelement <4 x float> %vecinit, float %sub4, i32 0
  %vecext6 = extractelement <4 x float> %B, i32 3
  %vecext7 = extractelement <4 x float> %B, i32 2
  %sub8 = fsub float %vecext6, %vecext7
  %vecinit9 = insertelement <4 x float> %vecinit5, float %sub8, i32 3
  %vecext10 = extractelement <4 x float> %B, i32 0
  %vecext11 = extractelement <4 x float> %B, i32 1
  %sub12 = fsub float %vecext10, %vecext11
  %vecinit13 = insertelement <4 x float> %vecinit9, float %sub12, i32 2
  ret <4 x float> %vecinit13
}

define <2 x double> @not_a_hsub_3(<2 x double> %A, <2 x double> %B) {
; SSE-LABEL: not_a_hsub_3:
; SSE:       # %bb.0:
; SSE-NEXT:    movapd %xmm1, %xmm2
; SSE-NEXT:    unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm1[1]
; SSE-NEXT:    subsd %xmm2, %xmm1
; SSE-NEXT:    movapd %xmm0, %xmm2
; SSE-NEXT:    unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
; SSE-NEXT:    subsd %xmm0, %xmm2
; SSE-NEXT:    unpcklpd {{.*#+}} xmm2 = xmm2[0],xmm1[0]
; SSE-NEXT:    movapd %xmm2, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: not_a_hsub_3:
; AVX:       # %bb.0:
; AVX-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
; AVX-NEXT:    vsubsd %xmm2, %xmm1, %xmm1
; AVX-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
; AVX-NEXT:    vsubsd %xmm0, %xmm2, %xmm0
; AVX-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX-NEXT:    retq
  %vecext = extractelement <2 x double> %B, i32 0
  %vecext1 = extractelement <2 x double> %B, i32 1
  %sub = fsub double %vecext, %vecext1
  %vecinit = insertelement <2 x double> undef, double %sub, i32 1
  %vecext2 = extractelement <2 x double> %A, i32 1
  %vecext3 = extractelement <2 x double> %A, i32 0
  %sub2 = fsub double %vecext2, %vecext3
  %vecinit2 = insertelement <2 x double> %vecinit, double %sub2, i32 0
  ret <2 x double> %vecinit2
}

; Test AVX horizontal add/sub of packed single/double precision
; floating point values from 256-bit vectors.

define <8 x float> @avx_vhadd_ps(<8 x float> %a, <8 x float> %b) {
; SSE-LABEL: avx_vhadd_ps:
; SSE:       # %bb.0:
; SSE-NEXT:    haddps %xmm2, %xmm0
; SSE-NEXT:    haddps %xmm3, %xmm1
; SSE-NEXT:    retq
;
; AVX-LABEL: avx_vhadd_ps:
; AVX:       # %bb.0:
; AVX-NEXT:    vhaddps %ymm1, %ymm0, %ymm0
; AVX-NEXT:    retq
  %vecext = extractelement <8 x float> %a, i32 0
  %vecext1 = extractelement <8 x float> %a, i32 1
  %add = fadd float %vecext, %vecext1
  %vecinit = insertelement <8 x float> undef, float %add, i32 0
  %vecext2 = extractelement <8 x float> %a, i32 2
  %vecext3 = extractelement <8 x float> %a, i32 3
  %add4 = fadd float %vecext2, %vecext3
  %vecinit5 = insertelement <8 x float> %vecinit, float %add4, i32 1
  %vecext6 = extractelement <8 x float> %b, i32 0
  %vecext7 = extractelement <8 x float> %b, i32 1
  %add8 = fadd float %vecext6, %vecext7
  %vecinit9 = insertelement <8 x float> %vecinit5, float %add8, i32 2
  %vecext10 = extractelement <8 x float> %b, i32 2
  %vecext11 = extractelement <8 x float> %b, i32 3
  %add12 = fadd float %vecext10, %vecext11
  %vecinit13 = insertelement <8 x float> %vecinit9, float %add12, i32 3
  %vecext14 = extractelement <8 x float> %a, i32 4
  %vecext15 = extractelement <8 x float> %a, i32 5
  %add16 = fadd float %vecext14, %vecext15
  %vecinit17 = insertelement <8 x float> %vecinit13, float %add16, i32 4
  %vecext18 = extractelement <8 x float> %a, i32 6
  %vecext19 = extractelement <8 x float> %a, i32 7
  %add20 = fadd float %vecext18, %vecext19
  %vecinit21 = insertelement <8 x float> %vecinit17, float %add20, i32 5
  %vecext22 = extractelement <8 x float> %b, i32 4
  %vecext23 = extractelement <8 x float> %b, i32 5
  %add24 = fadd float %vecext22, %vecext23
  %vecinit25 = insertelement <8 x float> %vecinit21, float %add24, i32 6
  %vecext26 = extractelement <8 x float> %b, i32 6
  %vecext27 = extractelement <8 x float> %b, i32 7
  %add28 = fadd float %vecext26, %vecext27
  %vecinit29 = insertelement <8 x float> %vecinit25, float %add28, i32 7
  ret <8 x float> %vecinit29
}

define <8 x float> @avx_vhsub_ps(<8 x float> %a, <8 x float> %b) {
; SSE-LABEL: avx_vhsub_ps:
; SSE:       # %bb.0:
; SSE-NEXT:    hsubps %xmm2, %xmm0
; SSE-NEXT:    hsubps %xmm3, %xmm1
; SSE-NEXT:    retq
;
; AVX-LABEL: avx_vhsub_ps:
; AVX:       # %bb.0:
; AVX-NEXT:    vhsubps %ymm1, %ymm0, %ymm0
; AVX-NEXT:    retq
  %vecext = extractelement <8 x float> %a, i32 0
  %vecext1 = extractelement <8 x float> %a, i32 1
  %sub = fsub float %vecext, %vecext1
  %vecinit = insertelement <8 x float> undef, float %sub, i32 0
  %vecext2 = extractelement <8 x float> %a, i32 2
  %vecext3 = extractelement <8 x float> %a, i32 3
  %sub4 = fsub float %vecext2, %vecext3
  %vecinit5 = insertelement <8 x float> %vecinit, float %sub4, i32 1
  %vecext6 = extractelement <8 x float> %b, i32 0
  %vecext7 = extractelement <8 x float> %b, i32 1
  %sub8 = fsub float %vecext6, %vecext7
  %vecinit9 = insertelement <8 x float> %vecinit5, float %sub8, i32 2
  %vecext10 = extractelement <8 x float> %b, i32 2
  %vecext11 = extractelement <8 x float> %b, i32 3
  %sub12 = fsub float %vecext10, %vecext11
  %vecinit13 = insertelement <8 x float> %vecinit9, float %sub12, i32 3
  %vecext14 = extractelement <8 x float> %a, i32 4
  %vecext15 = extractelement <8 x float> %a, i32 5
  %sub16 = fsub float %vecext14, %vecext15
  %vecinit17 = insertelement <8 x float> %vecinit13, float %sub16, i32 4
  %vecext18 = extractelement <8 x float> %a, i32 6
  %vecext19 = extractelement <8 x float> %a, i32 7
  %sub20 = fsub float %vecext18, %vecext19
  %vecinit21 = insertelement <8 x float> %vecinit17, float %sub20, i32 5
  %vecext22 = extractelement <8 x float> %b, i32 4
  %vecext23 = extractelement <8 x float> %b, i32 5
  %sub24 = fsub float %vecext22, %vecext23
  %vecinit25 = insertelement <8 x float> %vecinit21, float %sub24, i32 6
  %vecext26 = extractelement <8 x float> %b, i32 6
  %vecext27 = extractelement <8 x float> %b, i32 7
  %sub28 = fsub float %vecext26, %vecext27
  %vecinit29 = insertelement <8 x float> %vecinit25, float %sub28, i32 7
  ret <8 x float> %vecinit29
}

define <4 x double> @avx_hadd_pd(<4 x double> %a, <4 x double> %b) {
; SSE-LABEL: avx_hadd_pd:
; SSE:       # %bb.0:
; SSE-NEXT:    haddpd %xmm2, %xmm0
; SSE-NEXT:    haddpd %xmm3, %xmm1
; SSE-NEXT:    retq
;
; AVX-LABEL: avx_hadd_pd:
; AVX:       # %bb.0:
; AVX-NEXT:    vhaddpd %ymm1, %ymm0, %ymm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x double> %a, i32 0
  %vecext1 = extractelement <4 x double> %a, i32 1
  %add = fadd double %vecext, %vecext1
  %vecinit = insertelement <4 x double> undef, double %add, i32 0
  %vecext2 = extractelement <4 x double> %b, i32 0
  %vecext3 = extractelement <4 x double> %b, i32 1
  %add4 = fadd double %vecext2, %vecext3
  %vecinit5 = insertelement <4 x double> %vecinit, double %add4, i32 1
  %vecext6 = extractelement <4 x double> %a, i32 2
  %vecext7 = extractelement <4 x double> %a, i32 3
  %add8 = fadd double %vecext6, %vecext7
  %vecinit9 = insertelement <4 x double> %vecinit5, double %add8, i32 2
  %vecext10 = extractelement <4 x double> %b, i32 2
  %vecext11 = extractelement <4 x double> %b, i32 3
  %add12 = fadd double %vecext10, %vecext11
  %vecinit13 = insertelement <4 x double> %vecinit9, double %add12, i32 3
  ret <4 x double> %vecinit13
}

define <4 x double> @avx_hsub_pd(<4 x double> %a, <4 x double> %b) {
; SSE-LABEL: avx_hsub_pd:
; SSE:       # %bb.0:
; SSE-NEXT:    hsubpd %xmm2, %xmm0
; SSE-NEXT:    hsubpd %xmm3, %xmm1
; SSE-NEXT:    retq
;
; AVX-LABEL: avx_hsub_pd:
; AVX:       # %bb.0:
; AVX-NEXT:    vhsubpd %ymm1, %ymm0, %ymm0
; AVX-NEXT:    retq
  %vecext = extractelement <4 x double> %a, i32 0
  %vecext1 = extractelement <4 x double> %a, i32 1
  %sub = fsub double %vecext, %vecext1
  %vecinit = insertelement <4 x double> undef, double %sub, i32 0
  %vecext2 = extractelement <4 x double> %b, i32 0
  %vecext3 = extractelement <4 x double> %b, i32 1
  %sub4 = fsub double %vecext2, %vecext3
  %vecinit5 = insertelement <4 x double> %vecinit, double %sub4, i32 1
  %vecext6 = extractelement <4 x double> %a, i32 2
  %vecext7 = extractelement <4 x double> %a, i32 3
  %sub8 = fsub double %vecext6, %vecext7
  %vecinit9 = insertelement <4 x double> %vecinit5, double %sub8, i32 2
  %vecext10 = extractelement <4 x double> %b, i32 2
  %vecext11 = extractelement <4 x double> %b, i32 3
  %sub12 = fsub double %vecext10, %vecext11
  %vecinit13 = insertelement <4 x double> %vecinit9, double %sub12, i32 3
  ret <4 x double> %vecinit13
}

; Test AVX2 horizontal add of packed integer values from 256-bit vectors.

define <8 x i32> @avx2_hadd_d(<8 x i32> %a, <8 x i32> %b) {
; SSE3-LABEL: avx2_hadd_d:
; SSE3:       # %bb.0:
; SSE3-NEXT:    movd %xmm0, %ecx
; SSE3-NEXT:    pshufd {{.*#+}} xmm4 = xmm0[1,1,2,3]
; SSE3-NEXT:    movd %xmm4, %r8d
; SSE3-NEXT:    addl %ecx, %r8d
; SSE3-NEXT:    pshufd {{.*#+}} xmm4 = xmm0[2,3,0,1]
; SSE3-NEXT:    movd %xmm4, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %r9d
; SSE3-NEXT:    addl %edx, %r9d
; SSE3-NEXT:    movd %xmm2, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,1,2,3]
; SSE3-NEXT:    movd %xmm0, %esi
; SSE3-NEXT:    addl %edx, %esi
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
; SSE3-NEXT:    movd %xmm0, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %edi
; SSE3-NEXT:    addl %edx, %edi
; SSE3-NEXT:    movd %xmm1, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
; SSE3-NEXT:    movd %xmm0, %r10d
; SSE3-NEXT:    addl %eax, %r10d
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %ecx
; SSE3-NEXT:    addl %eax, %ecx
; SSE3-NEXT:    movd %xmm3, %eax
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
; SSE3-NEXT:    movd %xmm0, %edx
; SSE3-NEXT:    addl %eax, %edx
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[2,3,0,1]
; SSE3-NEXT:    movd %xmm0, %r11d
; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[3,1,2,3]
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    addl %r11d, %eax
; SSE3-NEXT:    movd %edi, %xmm0
; SSE3-NEXT:    movd %esi, %xmm1
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE3-NEXT:    movd %r9d, %xmm2
; SSE3-NEXT:    movd %r8d, %xmm0
; SSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE3-NEXT:    movd %eax, %xmm1
; SSE3-NEXT:    movd %edx, %xmm2
; SSE3-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE3-NEXT:    movd %ecx, %xmm3
; SSE3-NEXT:    movd %r10d, %xmm1
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: avx2_hadd_d:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    phaddd %xmm2, %xmm0
; SSSE3-NEXT:    phaddd %xmm3, %xmm1
; SSSE3-NEXT:    retq
;
; AVX1-LABEL: avx2_hadd_d:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT:    vphaddd %xmm2, %xmm3, %xmm2
; AVX1-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: avx2_hadd_d:
; AVX2:       # %bb.0:
; AVX2-NEXT:    vphaddd %ymm1, %ymm0, %ymm0
; AVX2-NEXT:    retq
  %vecext = extractelement <8 x i32> %a, i32 0
  %vecext1 = extractelement <8 x i32> %a, i32 1
  %add = add i32 %vecext, %vecext1
  %vecinit = insertelement <8 x i32> undef, i32 %add, i32 0
  %vecext2 = extractelement <8 x i32> %a, i32 2
  %vecext3 = extractelement <8 x i32> %a, i32 3
  %add4 = add i32 %vecext2, %vecext3
  %vecinit5 = insertelement <8 x i32> %vecinit, i32 %add4, i32 1
  %vecext6 = extractelement <8 x i32> %b, i32 0
  %vecext7 = extractelement <8 x i32> %b, i32 1
  %add8 = add i32 %vecext6, %vecext7
  %vecinit9 = insertelement <8 x i32> %vecinit5, i32 %add8, i32 2
  %vecext10 = extractelement <8 x i32> %b, i32 2
  %vecext11 = extractelement <8 x i32> %b, i32 3
  %add12 = add i32 %vecext10, %vecext11
  %vecinit13 = insertelement <8 x i32> %vecinit9, i32 %add12, i32 3
  %vecext14 = extractelement <8 x i32> %a, i32 4
  %vecext15 = extractelement <8 x i32> %a, i32 5
  %add16 = add i32 %vecext14, %vecext15
  %vecinit17 = insertelement <8 x i32> %vecinit13, i32 %add16, i32 4
  %vecext18 = extractelement <8 x i32> %a, i32 6
  %vecext19 = extractelement <8 x i32> %a, i32 7
  %add20 = add i32 %vecext18, %vecext19
  %vecinit21 = insertelement <8 x i32> %vecinit17, i32 %add20, i32 5
  %vecext22 = extractelement <8 x i32> %b, i32 4
  %vecext23 = extractelement <8 x i32> %b, i32 5
  %add24 = add i32 %vecext22, %vecext23
  %vecinit25 = insertelement <8 x i32> %vecinit21, i32 %add24, i32 6
  %vecext26 = extractelement <8 x i32> %b, i32 6
  %vecext27 = extractelement <8 x i32> %b, i32 7
  %add28 = add i32 %vecext26, %vecext27
  %vecinit29 = insertelement <8 x i32> %vecinit25, i32 %add28, i32 7
  ret <8 x i32> %vecinit29
}

define <16 x i16> @avx2_hadd_w(<16 x i16> %a, <16 x i16> %b) nounwind {
; SSE3-LABEL: avx2_hadd_w:
; SSE3:       # %bb.0:
; SSE3-NEXT:    pushq %rbp
; SSE3-NEXT:    pushq %r15
; SSE3-NEXT:    pushq %r14
; SSE3-NEXT:    pushq %r13
; SSE3-NEXT:    pushq %r12
; SSE3-NEXT:    pushq %rbx
; SSE3-NEXT:    movd %xmm0, %eax
; SSE3-NEXT:    pextrw $1, %xmm0, %r10d
; SSE3-NEXT:    addl %eax, %r10d
; SSE3-NEXT:    pextrw $2, %xmm0, %eax
; SSE3-NEXT:    pextrw $3, %xmm0, %r11d
; SSE3-NEXT:    addl %eax, %r11d
; SSE3-NEXT:    pextrw $4, %xmm0, %eax
; SSE3-NEXT:    pextrw $5, %xmm0, %r12d
; SSE3-NEXT:    addl %eax, %r12d
; SSE3-NEXT:    pextrw $6, %xmm0, %eax
; SSE3-NEXT:    pextrw $7, %xmm0, %r13d
; SSE3-NEXT:    addl %eax, %r13d
; SSE3-NEXT:    movd %xmm1, %eax
; SSE3-NEXT:    pextrw $1, %xmm1, %ecx
; SSE3-NEXT:    addl %eax, %ecx
; SSE3-NEXT:    movl %ecx, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; SSE3-NEXT:    pextrw $2, %xmm1, %eax
; SSE3-NEXT:    pextrw $3, %xmm1, %ecx
; SSE3-NEXT:    addl %eax, %ecx
; SSE3-NEXT:    movl %ecx, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; SSE3-NEXT:    pextrw $4, %xmm1, %eax
; SSE3-NEXT:    pextrw $5, %xmm1, %r14d
; SSE3-NEXT:    addl %eax, %r14d
; SSE3-NEXT:    pextrw $6, %xmm1, %esi
; SSE3-NEXT:    pextrw $7, %xmm1, %r15d
; SSE3-NEXT:    addl %esi, %r15d
; SSE3-NEXT:    movd %xmm2, %esi
; SSE3-NEXT:    pextrw $1, %xmm2, %ebp
; SSE3-NEXT:    addl %esi, %ebp
; SSE3-NEXT:    pextrw $2, %xmm2, %esi
; SSE3-NEXT:    pextrw $3, %xmm2, %edi
; SSE3-NEXT:    addl %esi, %edi
; SSE3-NEXT:    pextrw $4, %xmm2, %esi
; SSE3-NEXT:    pextrw $5, %xmm2, %eax
; SSE3-NEXT:    addl %esi, %eax
; SSE3-NEXT:    pextrw $6, %xmm2, %esi
; SSE3-NEXT:    pextrw $7, %xmm2, %ecx
; SSE3-NEXT:    addl %esi, %ecx
; SSE3-NEXT:    movd %xmm3, %ebx
; SSE3-NEXT:    pextrw $1, %xmm3, %r9d
; SSE3-NEXT:    addl %ebx, %r9d
; SSE3-NEXT:    pextrw $2, %xmm3, %edx
; SSE3-NEXT:    pextrw $3, %xmm3, %ebx
; SSE3-NEXT:    addl %edx, %ebx
; SSE3-NEXT:    pextrw $4, %xmm3, %edx
; SSE3-NEXT:    pextrw $5, %xmm3, %esi
; SSE3-NEXT:    addl %edx, %esi
; SSE3-NEXT:    pextrw $6, %xmm3, %r8d
; SSE3-NEXT:    pextrw $7, %xmm3, %edx
; SSE3-NEXT:    addl %r8d, %edx
; SSE3-NEXT:    movd %ecx, %xmm8
; SSE3-NEXT:    movd %eax, %xmm3
; SSE3-NEXT:    movd %edi, %xmm9
; SSE3-NEXT:    movd %ebp, %xmm4
; SSE3-NEXT:    movd %r13d, %xmm10
; SSE3-NEXT:    movd %r12d, %xmm7
; SSE3-NEXT:    movd %r11d, %xmm11
; SSE3-NEXT:    movd %r10d, %xmm0
; SSE3-NEXT:    movd %edx, %xmm12
; SSE3-NEXT:    movd %esi, %xmm6
; SSE3-NEXT:    movd %ebx, %xmm13
; SSE3-NEXT:    movd %r9d, %xmm5
; SSE3-NEXT:    movd %r15d, %xmm14
; SSE3-NEXT:    movd %r14d, %xmm2
; SSE3-NEXT:    movd {{[-0-9]+}}(%r{{[sb]}}p), %xmm15 # 4-byte Folded Reload
; SSE3-NEXT:    # xmm15 = mem[0],zero,zero,zero
; SSE3-NEXT:    movd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 4-byte Folded Reload
; SSE3-NEXT:    # xmm1 = mem[0],zero,zero,zero
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm8[0],xmm3[1],xmm8[1],xmm3[2],xmm8[2],xmm3[3],xmm8[3]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm9[0],xmm4[1],xmm9[1],xmm4[2],xmm9[2],xmm4[3],xmm9[3]
; SSE3-NEXT:    punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm7 = xmm7[0],xmm10[0],xmm7[1],xmm10[1],xmm7[2],xmm10[2],xmm7[3],xmm10[3]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm11[0],xmm0[1],xmm11[1],xmm0[2],xmm11[2],xmm0[3],xmm11[3]
; SSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm7[0],xmm0[1],xmm7[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm4[0]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm12[0],xmm6[1],xmm12[1],xmm6[2],xmm12[2],xmm6[3],xmm12[3]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm5 = xmm5[0],xmm13[0],xmm5[1],xmm13[1],xmm5[2],xmm13[2],xmm5[3],xmm13[3]
; SSE3-NEXT:    punpckldq {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[1],xmm6[1]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3]
; SSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm15[0],xmm1[1],xmm15[1],xmm1[2],xmm15[2],xmm1[3],xmm15[3]
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm5[0]
; SSE3-NEXT:    popq %rbx
; SSE3-NEXT:    popq %r12
; SSE3-NEXT:    popq %r13
; SSE3-NEXT:    popq %r14
; SSE3-NEXT:    popq %r15
; SSE3-NEXT:    popq %rbp
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: avx2_hadd_w:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    phaddw %xmm2, %xmm0
; SSSE3-NEXT:    phaddw %xmm3, %xmm1
; SSSE3-NEXT:    retq
;
; AVX1-LABEL: avx2_hadd_w:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT:    vphaddw %xmm2, %xmm3, %xmm2
; AVX1-NEXT:    vphaddw %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: avx2_hadd_w:
; AVX2:       # %bb.0:
; AVX2-NEXT:    vphaddw %ymm1, %ymm0, %ymm0
; AVX2-NEXT:    retq
  %vecext = extractelement <16 x i16> %a, i32 0
  %vecext1 = extractelement <16 x i16> %a, i32 1
  %add = add i16 %vecext, %vecext1
  %vecinit = insertelement <16 x i16> undef, i16 %add, i32 0
  %vecext4 = extractelement <16 x i16> %a, i32 2
  %vecext6 = extractelement <16 x i16> %a, i32 3
  %add8 = add i16 %vecext4, %vecext6
  %vecinit10 = insertelement <16 x i16> %vecinit, i16 %add8, i32 1
  %vecext11 = extractelement <16 x i16> %a, i32 4
  %vecext13 = extractelement <16 x i16> %a, i32 5
  %add15 = add i16 %vecext11, %vecext13
  %vecinit17 = insertelement <16 x i16> %vecinit10, i16 %add15, i32 2
  %vecext18 = extractelement <16 x i16> %a, i32 6
  %vecext20 = extractelement <16 x i16> %a, i32 7
  %add22 = add i16 %vecext18, %vecext20
  %vecinit24 = insertelement <16 x i16> %vecinit17, i16 %add22, i32 3
  %vecext25 = extractelement <16 x i16> %a, i32 8
  %vecext27 = extractelement <16 x i16> %a, i32 9
  %add29 = add i16 %vecext25, %vecext27
  %vecinit31 = insertelement <16 x i16> %vecinit24, i16 %add29, i32 8
  %vecext32 = extractelement <16 x i16> %a, i32 10
  %vecext34 = extractelement <16 x i16> %a, i32 11
  %add36 = add i16 %vecext32, %vecext34
  %vecinit38 = insertelement <16 x i16> %vecinit31, i16 %add36, i32 9
  %vecext39 = extractelement <16 x i16> %a, i32 12
  %vecext41 = extractelement <16 x i16> %a, i32 13
  %add43 = add i16 %vecext39, %vecext41
  %vecinit45 = insertelement <16 x i16> %vecinit38, i16 %add43, i32 10
  %vecext46 = extractelement <16 x i16> %a, i32 14
  %vecext48 = extractelement <16 x i16> %a, i32 15
  %add50 = add i16 %vecext46, %vecext48
  %vecinit52 = insertelement <16 x i16> %vecinit45, i16 %add50, i32 11
  %vecext53 = extractelement <16 x i16> %b, i32 0
  %vecext55 = extractelement <16 x i16> %b, i32 1
  %add57 = add i16 %vecext53, %vecext55
  %vecinit59 = insertelement <16 x i16> %vecinit52, i16 %add57, i32 4
  %vecext60 = extractelement <16 x i16> %b, i32 2
  %vecext62 = extractelement <16 x i16> %b, i32 3
  %add64 = add i16 %vecext60, %vecext62
  %vecinit66 = insertelement <16 x i16> %vecinit59, i16 %add64, i32 5
  %vecext67 = extractelement <16 x i16> %b, i32 4
  %vecext69 = extractelement <16 x i16> %b, i32 5
  %add71 = add i16 %vecext67, %vecext69
  %vecinit73 = insertelement <16 x i16> %vecinit66, i16 %add71, i32 6
  %vecext74 = extractelement <16 x i16> %b, i32 6
  %vecext76 = extractelement <16 x i16> %b, i32 7
  %add78 = add i16 %vecext74, %vecext76
  %vecinit80 = insertelement <16 x i16> %vecinit73, i16 %add78, i32 7
  %vecext81 = extractelement <16 x i16> %b, i32 8
  %vecext83 = extractelement <16 x i16> %b, i32 9
  %add85 = add i16 %vecext81, %vecext83
  %vecinit87 = insertelement <16 x i16> %vecinit80, i16 %add85, i32 12
  %vecext88 = extractelement <16 x i16> %b, i32 10
  %vecext90 = extractelement <16 x i16> %b, i32 11
  %add92 = add i16 %vecext88, %vecext90
  %vecinit94 = insertelement <16 x i16> %vecinit87, i16 %add92, i32 13
  %vecext95 = extractelement <16 x i16> %b, i32 12
  %vecext97 = extractelement <16 x i16> %b, i32 13
  %add99 = add i16 %vecext95, %vecext97
  %vecinit101 = insertelement <16 x i16> %vecinit94, i16 %add99, i32 14
  %vecext102 = extractelement <16 x i16> %b, i32 14
  %vecext104 = extractelement <16 x i16> %b, i32 15
  %add106 = add i16 %vecext102, %vecext104
  %vecinit108 = insertelement <16 x i16> %vecinit101, i16 %add106, i32 15
  ret <16 x i16> %vecinit108
}