; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2

;
; Unary shuffle indices from registers
;

define <2 x double> @var_shuffle_v2f64_v2f64_xx_i64(<2 x double> %x, i64 %i0, i64 %i1) nounwind {
; SSE-LABEL: var_shuffle_v2f64_v2f64_xx_i64:
; SSE:       # %bb.0:
; SSE-NEXT:    andl $1, %esi
; SSE-NEXT:    andl $1, %edi
; SSE-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT:    movhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; SSE-NEXT:    retq
;
; AVX-LABEL: var_shuffle_v2f64_v2f64_xx_i64:
; AVX:       # %bb.0:
; AVX-NEXT:    andl $1, %esi
; AVX-NEXT:    andl $1, %edi
; AVX-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    retq
  %x0 = extractelement <2 x double> %x, i64 %i0
  %x1 = extractelement <2 x double> %x, i64 %i1
  %r0 = insertelement <2 x double> undef, double %x0, i32 0
  %r1 = insertelement <2 x double>   %r0, double %x1, i32 1
  ret <2 x double> %r1
}

define <2 x i64> @var_shuffle_v2i64_v2i64_xx_i64(<2 x i64> %x, i32 %i0, i32 %i1) nounwind {
; SSE-LABEL: var_shuffle_v2i64_v2i64_xx_i64:
; SSE:       # %bb.0:
; SSE-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE-NEXT:    andl $1, %edi
; SSE-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE-NEXT:    andl $1, %esi
; SSE-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; SSE-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE-NEXT:    retq
;
; AVX-LABEL: var_shuffle_v2i64_v2i64_xx_i64:
; AVX:       # %bb.0:
; AVX-NEXT:    # kill: def $esi killed $esi def $rsi
; AVX-NEXT:    # kill: def $edi killed $edi def $rdi
; AVX-NEXT:    andl $1, %edi
; AVX-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    andl $1, %esi
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    vmovlhps {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX-NEXT:    retq
  %x0 = extractelement <2 x i64> %x, i32 %i0
  %x1 = extractelement <2 x i64> %x, i32 %i1
  %r0 = insertelement <2 x i64> undef, i64 %x0, i32 0
  %r1 = insertelement <2 x i64>   %r0, i64 %x1, i32 1
  ret <2 x i64> %r1
}

define <4 x float> @var_shuffle_v4f32_v4f32_xxxx_i32(<4 x float> %x, i32 %i0, i32 %i1, i32 %i2, i32 %i3) nounwind {
; SSE2-LABEL: var_shuffle_v4f32_v4f32_xxxx_i32:
; SSE2:       # %bb.0:
; SSE2-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE2-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE2-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE2-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE2-NEXT:    andl $3, %edi
; SSE2-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE2-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT:    andl $3, %esi
; SSE2-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT:    andl $3, %edx
; SSE2-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT:    andl $3, %ecx
; SSE2-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE2-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: var_shuffle_v4f32_v4f32_xxxx_i32:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSSE3-NEXT:    # kill: def $edx killed $edx def $rdx
; SSSE3-NEXT:    # kill: def $esi killed $esi def $rsi
; SSSE3-NEXT:    # kill: def $edi killed $edi def $rdi
; SSSE3-NEXT:    andl $3, %edi
; SSSE3-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSSE3-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSSE3-NEXT:    andl $3, %esi
; SSSE3-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSSE3-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT:    andl $3, %edx
; SSSE3-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSSE3-NEXT:    andl $3, %ecx
; SSSE3-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSSE3-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSSE3-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: var_shuffle_v4f32_v4f32_xxxx_i32:
; SSE41:       # %bb.0:
; SSE41-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE41-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE41-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE41-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE41-NEXT:    andl $3, %edi
; SSE41-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE41-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE41-NEXT:    andl $3, %esi
; SSE41-NEXT:    andl $3, %edx
; SSE41-NEXT:    andl $3, %ecx
; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; SSE41-NEXT:    retq
;
; AVX-LABEL: var_shuffle_v4f32_v4f32_xxxx_i32:
; AVX:       # %bb.0:
; AVX-NEXT:    # kill: def $ecx killed $ecx def $rcx
; AVX-NEXT:    # kill: def $edx killed $edx def $rdx
; AVX-NEXT:    # kill: def $esi killed $esi def $rsi
; AVX-NEXT:    # kill: def $edi killed $edi def $rdi
; AVX-NEXT:    andl $3, %edi
; AVX-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    andl $3, %esi
; AVX-NEXT:    andl $3, %edx
; AVX-NEXT:    andl $3, %ecx
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; AVX-NEXT:    retq
  %x0 = extractelement <4 x float> %x, i32 %i0
  %x1 = extractelement <4 x float> %x, i32 %i1
  %x2 = extractelement <4 x float> %x, i32 %i2
  %x3 = extractelement <4 x float> %x, i32 %i3
  %r0 = insertelement <4 x float> undef, float %x0, i32 0
  %r1 = insertelement <4 x float>   %r0, float %x1, i32 1
  %r2 = insertelement <4 x float>   %r1, float %x2, i32 2
  %r3 = insertelement <4 x float>   %r2, float %x3, i32 3
  ret <4 x float> %r3
}

define <4 x i32> @var_shuffle_v4i32_v4i32_xxxx_i32(<4 x i32> %x, i32 %i0, i32 %i1, i32 %i2, i32 %i3) nounwind {
; SSE2-LABEL: var_shuffle_v4i32_v4i32_xxxx_i32:
; SSE2:       # %bb.0:
; SSE2-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE2-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE2-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE2-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE2-NEXT:    andl $3, %edi
; SSE2-NEXT:    andl $3, %esi
; SSE2-NEXT:    andl $3, %edx
; SSE2-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE2-NEXT:    andl $3, %ecx
; SSE2-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE2-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: var_shuffle_v4i32_v4i32_xxxx_i32:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSSE3-NEXT:    # kill: def $edx killed $edx def $rdx
; SSSE3-NEXT:    # kill: def $esi killed $esi def $rsi
; SSSE3-NEXT:    # kill: def $edi killed $edi def $rdi
; SSSE3-NEXT:    andl $3, %edi
; SSSE3-NEXT:    andl $3, %esi
; SSSE3-NEXT:    andl $3, %edx
; SSSE3-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSSE3-NEXT:    andl $3, %ecx
; SSSE3-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSSE3-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSSE3-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSSE3-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSSE3-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSSE3-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSSE3-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: var_shuffle_v4i32_v4i32_xxxx_i32:
; SSE41:       # %bb.0:
; SSE41-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE41-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE41-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE41-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE41-NEXT:    andl $3, %edi
; SSE41-NEXT:    andl $3, %esi
; SSE41-NEXT:    andl $3, %edx
; SSE41-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE41-NEXT:    andl $3, %ecx
; SSE41-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE41-NEXT:    pinsrd $1, -24(%rsp,%rsi,4), %xmm0
; SSE41-NEXT:    pinsrd $2, -24(%rsp,%rdx,4), %xmm0
; SSE41-NEXT:    pinsrd $3, -24(%rsp,%rcx,4), %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: var_shuffle_v4i32_v4i32_xxxx_i32:
; AVX:       # %bb.0:
; AVX-NEXT:    # kill: def $ecx killed $ecx def $rcx
; AVX-NEXT:    # kill: def $edx killed $edx def $rdx
; AVX-NEXT:    # kill: def $esi killed $esi def $rsi
; AVX-NEXT:    # kill: def $edi killed $edi def $rdi
; AVX-NEXT:    andl $3, %edi
; AVX-NEXT:    andl $3, %esi
; AVX-NEXT:    andl $3, %edx
; AVX-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    andl $3, %ecx
; AVX-NEXT:    vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vpinsrd $1, -24(%rsp,%rsi,4), %xmm0, %xmm0
; AVX-NEXT:    vpinsrd $2, -24(%rsp,%rdx,4), %xmm0, %xmm0
; AVX-NEXT:    vpinsrd $3, -24(%rsp,%rcx,4), %xmm0, %xmm0
; AVX-NEXT:    retq
  %x0 = extractelement <4 x i32> %x, i32 %i0
  %x1 = extractelement <4 x i32> %x, i32 %i1
  %x2 = extractelement <4 x i32> %x, i32 %i2
  %x3 = extractelement <4 x i32> %x, i32 %i3
  %r0 = insertelement <4 x i32> undef, i32 %x0, i32 0
  %r1 = insertelement <4 x i32>   %r0, i32 %x1, i32 1
  %r2 = insertelement <4 x i32>   %r1, i32 %x2, i32 2
  %r3 = insertelement <4 x i32>   %r2, i32 %x3, i32 3
  ret <4 x i32> %r3
}

define <8 x i16> @var_shuffle_v8i16_v8i16_xxxxxxxx_i16(<8 x i16> %x, i16 %i0, i16 %i1, i16 %i2, i16 %i3, i16 %i4, i16 %i5, i16 %i6, i16 %i7) nounwind {
; SSE2-LABEL: var_shuffle_v8i16_v8i16_xxxxxxxx_i16:
; SSE2:       # %bb.0:
; SSE2-NEXT:    # kill: def $r9d killed $r9d def $r9
; SSE2-NEXT:    # kill: def $r8d killed $r8d def $r8
; SSE2-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE2-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE2-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE2-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE2-NEXT:    movzwl {{[0-9]+}}(%rsp), %r10d
; SSE2-NEXT:    andl $7, %r10d
; SSE2-NEXT:    movzwl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $7, %eax
; SSE2-NEXT:    andl $7, %edi
; SSE2-NEXT:    andl $7, %esi
; SSE2-NEXT:    andl $7, %edx
; SSE2-NEXT:    andl $7, %ecx
; SSE2-NEXT:    andl $7, %r8d
; SSE2-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE2-NEXT:    andl $7, %r9d
; SSE2-NEXT:    movzwl -24(%rsp,%rcx,2), %ecx
; SSE2-NEXT:    movd %ecx, %xmm0
; SSE2-NEXT:    movzwl -24(%rsp,%rdx,2), %ecx
; SSE2-NEXT:    movd %ecx, %xmm1
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT:    movzwl -24(%rsp,%rsi,2), %ecx
; SSE2-NEXT:    movd %ecx, %xmm2
; SSE2-NEXT:    movzwl -24(%rsp,%rdi,2), %ecx
; SSE2-NEXT:    movd %ecx, %xmm0
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT:    movzwl -24(%rsp,%r9,2), %ecx
; SSE2-NEXT:    movd %ecx, %xmm1
; SSE2-NEXT:    movzwl -24(%rsp,%r8,2), %ecx
; SSE2-NEXT:    movd %ecx, %xmm2
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE2-NEXT:    movzwl -24(%rsp,%rax,2), %eax
; SSE2-NEXT:    movd %eax, %xmm1
; SSE2-NEXT:    movzwl -24(%rsp,%r10,2), %eax
; SSE2-NEXT:    movd %eax, %xmm3
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: var_shuffle_v8i16_v8i16_xxxxxxxx_i16:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    # kill: def $r9d killed $r9d def $r9
; SSSE3-NEXT:    # kill: def $r8d killed $r8d def $r8
; SSSE3-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSSE3-NEXT:    # kill: def $edx killed $edx def $rdx
; SSSE3-NEXT:    # kill: def $esi killed $esi def $rsi
; SSSE3-NEXT:    # kill: def $edi killed $edi def $rdi
; SSSE3-NEXT:    movzwl {{[0-9]+}}(%rsp), %r10d
; SSSE3-NEXT:    andl $7, %r10d
; SSSE3-NEXT:    movzwl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $7, %eax
; SSSE3-NEXT:    andl $7, %edi
; SSSE3-NEXT:    andl $7, %esi
; SSSE3-NEXT:    andl $7, %edx
; SSSE3-NEXT:    andl $7, %ecx
; SSSE3-NEXT:    andl $7, %r8d
; SSSE3-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSSE3-NEXT:    andl $7, %r9d
; SSSE3-NEXT:    movzwl -24(%rsp,%rcx,2), %ecx
; SSSE3-NEXT:    movd %ecx, %xmm0
; SSSE3-NEXT:    movzwl -24(%rsp,%rdx,2), %ecx
; SSSE3-NEXT:    movd %ecx, %xmm1
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSSE3-NEXT:    movzwl -24(%rsp,%rsi,2), %ecx
; SSSE3-NEXT:    movd %ecx, %xmm2
; SSSE3-NEXT:    movzwl -24(%rsp,%rdi,2), %ecx
; SSSE3-NEXT:    movd %ecx, %xmm0
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT:    movzwl -24(%rsp,%r9,2), %ecx
; SSSE3-NEXT:    movd %ecx, %xmm1
; SSSE3-NEXT:    movzwl -24(%rsp,%r8,2), %ecx
; SSSE3-NEXT:    movd %ecx, %xmm2
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSSE3-NEXT:    movzwl -24(%rsp,%rax,2), %eax
; SSSE3-NEXT:    movd %eax, %xmm1
; SSSE3-NEXT:    movzwl -24(%rsp,%r10,2), %eax
; SSSE3-NEXT:    movd %eax, %xmm3
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3]
; SSSE3-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: var_shuffle_v8i16_v8i16_xxxxxxxx_i16:
; SSE41:       # %bb.0:
; SSE41-NEXT:    # kill: def $r9d killed $r9d def $r9
; SSE41-NEXT:    # kill: def $r8d killed $r8d def $r8
; SSE41-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE41-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE41-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE41-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE41-NEXT:    movzwl {{[0-9]+}}(%rsp), %r10d
; SSE41-NEXT:    andl $7, %r10d
; SSE41-NEXT:    movzwl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $7, %eax
; SSE41-NEXT:    andl $7, %edi
; SSE41-NEXT:    andl $7, %esi
; SSE41-NEXT:    andl $7, %edx
; SSE41-NEXT:    andl $7, %ecx
; SSE41-NEXT:    andl $7, %r8d
; SSE41-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE41-NEXT:    andl $7, %r9d
; SSE41-NEXT:    movzwl -24(%rsp,%rdi,2), %edi
; SSE41-NEXT:    movd %edi, %xmm0
; SSE41-NEXT:    pinsrw $1, -24(%rsp,%rsi,2), %xmm0
; SSE41-NEXT:    pinsrw $2, -24(%rsp,%rdx,2), %xmm0
; SSE41-NEXT:    pinsrw $3, -24(%rsp,%rcx,2), %xmm0
; SSE41-NEXT:    pinsrw $4, -24(%rsp,%r8,2), %xmm0
; SSE41-NEXT:    pinsrw $5, -24(%rsp,%r9,2), %xmm0
; SSE41-NEXT:    pinsrw $6, -24(%rsp,%rax,2), %xmm0
; SSE41-NEXT:    pinsrw $7, -24(%rsp,%r10,2), %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: var_shuffle_v8i16_v8i16_xxxxxxxx_i16:
; AVX:       # %bb.0:
; AVX-NEXT:    # kill: def $r9d killed $r9d def $r9
; AVX-NEXT:    # kill: def $r8d killed $r8d def $r8
; AVX-NEXT:    # kill: def $ecx killed $ecx def $rcx
; AVX-NEXT:    # kill: def $edx killed $edx def $rdx
; AVX-NEXT:    # kill: def $esi killed $esi def $rsi
; AVX-NEXT:    # kill: def $edi killed $edi def $rdi
; AVX-NEXT:    movzwl {{[0-9]+}}(%rsp), %r10d
; AVX-NEXT:    andl $7, %r10d
; AVX-NEXT:    movzwl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $7, %eax
; AVX-NEXT:    andl $7, %edi
; AVX-NEXT:    andl $7, %esi
; AVX-NEXT:    andl $7, %edx
; AVX-NEXT:    andl $7, %ecx
; AVX-NEXT:    andl $7, %r8d
; AVX-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    andl $7, %r9d
; AVX-NEXT:    movzwl -24(%rsp,%rdi,2), %edi
; AVX-NEXT:    vmovd %edi, %xmm0
; AVX-NEXT:    vpinsrw $1, -24(%rsp,%rsi,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $2, -24(%rsp,%rdx,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $3, -24(%rsp,%rcx,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $4, -24(%rsp,%r8,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $5, -24(%rsp,%r9,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $6, -24(%rsp,%rax,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $7, -24(%rsp,%r10,2), %xmm0, %xmm0
; AVX-NEXT:    retq
  %x0 = extractelement <8 x i16> %x, i16 %i0
  %x1 = extractelement <8 x i16> %x, i16 %i1
  %x2 = extractelement <8 x i16> %x, i16 %i2
  %x3 = extractelement <8 x i16> %x, i16 %i3
  %x4 = extractelement <8 x i16> %x, i16 %i4
  %x5 = extractelement <8 x i16> %x, i16 %i5
  %x6 = extractelement <8 x i16> %x, i16 %i6
  %x7 = extractelement <8 x i16> %x, i16 %i7
  %r0 = insertelement <8 x i16> undef, i16 %x0, i32 0
  %r1 = insertelement <8 x i16>   %r0, i16 %x1, i32 1
  %r2 = insertelement <8 x i16>   %r1, i16 %x2, i32 2
  %r3 = insertelement <8 x i16>   %r2, i16 %x3, i32 3
  %r4 = insertelement <8 x i16>   %r3, i16 %x4, i32 4
  %r5 = insertelement <8 x i16>   %r4, i16 %x5, i32 5
  %r6 = insertelement <8 x i16>   %r5, i16 %x6, i32 6
  %r7 = insertelement <8 x i16>   %r6, i16 %x7, i32 7
  ret <8 x i16> %r7
}

define <16 x i8> @var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8(<16 x i8> %x, i8 %i0, i8 %i1, i8 %i2, i8 %i3, i8 %i4, i8 %i5, i8 %i6, i8 %i7, i8 %i8, i8 %i9, i8 %i10, i8 %i11, i8 %i12, i8 %i13, i8 %i14, i8 %i15) nounwind {
; SSE2-LABEL: var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
; SSE2:       # %bb.0:
; SSE2-NEXT:    # kill: def $r9d killed $r9d def $r9
; SSE2-NEXT:    # kill: def $r8d killed $r8d def $r8
; SSE2-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE2-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE2-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE2-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE2-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm8
; SSE2-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm15
; SSE2-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm9
; SSE2-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm3
; SSE2-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm10
; SSE2-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm7
; SSE2-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm11
; SSE2-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm6
; SSE2-NEXT:    andl $15, %ecx
; SSE2-NEXT:    movzbl -24(%rsp,%rcx), %eax
; SSE2-NEXT:    movd %eax, %xmm12
; SSE2-NEXT:    andl $15, %edx
; SSE2-NEXT:    movzbl -24(%rsp,%rdx), %eax
; SSE2-NEXT:    movd %eax, %xmm5
; SSE2-NEXT:    andl $15, %esi
; SSE2-NEXT:    movzbl -24(%rsp,%rsi), %eax
; SSE2-NEXT:    movd %eax, %xmm13
; SSE2-NEXT:    andl $15, %edi
; SSE2-NEXT:    movzbl -24(%rsp,%rdi), %eax
; SSE2-NEXT:    movd %eax, %xmm0
; SSE2-NEXT:    andl $15, %r9d
; SSE2-NEXT:    movzbl -24(%rsp,%r9), %eax
; SSE2-NEXT:    movd %eax, %xmm14
; SSE2-NEXT:    andl $15, %r8d
; SSE2-NEXT:    movzbl -24(%rsp,%r8), %eax
; SSE2-NEXT:    movd %eax, %xmm1
; SSE2-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm4
; SSE2-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm2
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm15 = xmm15[0],xmm8[0],xmm15[1],xmm8[1],xmm15[2],xmm8[2],xmm15[3],xmm8[3],xmm15[4],xmm8[4],xmm15[5],xmm8[5],xmm15[6],xmm8[6],xmm15[7],xmm8[7]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm15[0],xmm3[1],xmm15[1],xmm3[2],xmm15[2],xmm3[3],xmm15[3]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm10[0],xmm7[1],xmm10[1],xmm7[2],xmm10[2],xmm7[3],xmm10[3],xmm7[4],xmm10[4],xmm7[5],xmm10[5],xmm7[6],xmm10[6],xmm7[7],xmm10[7]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm11[0],xmm6[1],xmm11[1],xmm6[2],xmm11[2],xmm6[3],xmm11[3],xmm6[4],xmm11[4],xmm6[5],xmm11[5],xmm6[6],xmm11[6],xmm6[7],xmm11[7]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm6 = xmm6[0],xmm3[0],xmm6[1],xmm3[1]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm12[0],xmm5[1],xmm12[1],xmm5[2],xmm12[2],xmm5[3],xmm12[3],xmm5[4],xmm12[4],xmm5[5],xmm12[5],xmm5[6],xmm12[6],xmm5[7],xmm12[7]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm13[0],xmm0[1],xmm13[1],xmm0[2],xmm13[2],xmm0[3],xmm13[3],xmm0[4],xmm13[4],xmm0[5],xmm13[5],xmm0[6],xmm13[6],xmm0[7],xmm13[7]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1],xmm0[2],xmm5[2],xmm0[3],xmm5[3]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm14[0],xmm1[1],xmm14[1],xmm1[2],xmm14[2],xmm1[3],xmm14[3],xmm1[4],xmm14[4],xmm1[5],xmm14[5],xmm1[6],xmm14[6],xmm1[7],xmm14[7]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3],xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    # kill: def $r9d killed $r9d def $r9
; SSSE3-NEXT:    # kill: def $r8d killed $r8d def $r8
; SSSE3-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSSE3-NEXT:    # kill: def $edx killed $edx def $rdx
; SSSE3-NEXT:    # kill: def $esi killed $esi def $rsi
; SSSE3-NEXT:    # kill: def $edi killed $edi def $rdi
; SSSE3-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm8
; SSSE3-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm15
; SSSE3-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm9
; SSSE3-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm3
; SSSE3-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm10
; SSSE3-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm7
; SSSE3-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm11
; SSSE3-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm6
; SSSE3-NEXT:    andl $15, %ecx
; SSSE3-NEXT:    movzbl -24(%rsp,%rcx), %eax
; SSSE3-NEXT:    movd %eax, %xmm12
; SSSE3-NEXT:    andl $15, %edx
; SSSE3-NEXT:    movzbl -24(%rsp,%rdx), %eax
; SSSE3-NEXT:    movd %eax, %xmm5
; SSSE3-NEXT:    andl $15, %esi
; SSSE3-NEXT:    movzbl -24(%rsp,%rsi), %eax
; SSSE3-NEXT:    movd %eax, %xmm13
; SSSE3-NEXT:    andl $15, %edi
; SSSE3-NEXT:    movzbl -24(%rsp,%rdi), %eax
; SSSE3-NEXT:    movd %eax, %xmm0
; SSSE3-NEXT:    andl $15, %r9d
; SSSE3-NEXT:    movzbl -24(%rsp,%r9), %eax
; SSSE3-NEXT:    movd %eax, %xmm14
; SSSE3-NEXT:    andl $15, %r8d
; SSSE3-NEXT:    movzbl -24(%rsp,%r8), %eax
; SSSE3-NEXT:    movd %eax, %xmm1
; SSSE3-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm4
; SSSE3-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm2
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm15 = xmm15[0],xmm8[0],xmm15[1],xmm8[1],xmm15[2],xmm8[2],xmm15[3],xmm8[3],xmm15[4],xmm8[4],xmm15[5],xmm8[5],xmm15[6],xmm8[6],xmm15[7],xmm8[7]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm15[0],xmm3[1],xmm15[1],xmm3[2],xmm15[2],xmm3[3],xmm15[3]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm10[0],xmm7[1],xmm10[1],xmm7[2],xmm10[2],xmm7[3],xmm10[3],xmm7[4],xmm10[4],xmm7[5],xmm10[5],xmm7[6],xmm10[6],xmm7[7],xmm10[7]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm11[0],xmm6[1],xmm11[1],xmm6[2],xmm11[2],xmm6[3],xmm11[3],xmm6[4],xmm11[4],xmm6[5],xmm11[5],xmm6[6],xmm11[6],xmm6[7],xmm11[7]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3]
; SSSE3-NEXT:    punpckldq {{.*#+}} xmm6 = xmm6[0],xmm3[0],xmm6[1],xmm3[1]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm12[0],xmm5[1],xmm12[1],xmm5[2],xmm12[2],xmm5[3],xmm12[3],xmm5[4],xmm12[4],xmm5[5],xmm12[5],xmm5[6],xmm12[6],xmm5[7],xmm12[7]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm13[0],xmm0[1],xmm13[1],xmm0[2],xmm13[2],xmm0[3],xmm13[3],xmm0[4],xmm13[4],xmm0[5],xmm13[5],xmm0[6],xmm13[6],xmm0[7],xmm13[7]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1],xmm0[2],xmm5[2],xmm0[3],xmm5[3]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm14[0],xmm1[1],xmm14[1],xmm1[2],xmm14[2],xmm1[3],xmm14[3],xmm1[4],xmm14[4],xmm1[5],xmm14[5],xmm1[6],xmm14[6],xmm1[7],xmm14[7]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3],xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
; SSE41:       # %bb.0:
; SSE41-NEXT:    # kill: def $r9d killed $r9d def $r9
; SSE41-NEXT:    # kill: def $r8d killed $r8d def $r8
; SSE41-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE41-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE41-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE41-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE41-NEXT:    andl $15, %edi
; SSE41-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE41-NEXT:    movzbl -24(%rsp,%rdi), %eax
; SSE41-NEXT:    movd %eax, %xmm0
; SSE41-NEXT:    andl $15, %esi
; SSE41-NEXT:    pinsrb $1, -24(%rsp,%rsi), %xmm0
; SSE41-NEXT:    andl $15, %edx
; SSE41-NEXT:    pinsrb $2, -24(%rsp,%rdx), %xmm0
; SSE41-NEXT:    andl $15, %ecx
; SSE41-NEXT:    pinsrb $3, -24(%rsp,%rcx), %xmm0
; SSE41-NEXT:    andl $15, %r8d
; SSE41-NEXT:    pinsrb $4, -24(%rsp,%r8), %xmm0
; SSE41-NEXT:    andl $15, %r9d
; SSE41-NEXT:    pinsrb $5, -24(%rsp,%r9), %xmm0
; SSE41-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $6, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $7, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $8, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $9, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $10, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $11, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $12, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $13, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $14, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $15, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
; AVX:       # %bb.0:
; AVX-NEXT:    # kill: def $r9d killed $r9d def $r9
; AVX-NEXT:    # kill: def $r8d killed $r8d def $r8
; AVX-NEXT:    # kill: def $ecx killed $ecx def $rcx
; AVX-NEXT:    # kill: def $edx killed $edx def $rdx
; AVX-NEXT:    # kill: def $esi killed $esi def $rsi
; AVX-NEXT:    # kill: def $edi killed $edi def $rdi
; AVX-NEXT:    andl $15, %edi
; AVX-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    movzbl -24(%rsp,%rdi), %eax
; AVX-NEXT:    vmovd %eax, %xmm0
; AVX-NEXT:    andl $15, %esi
; AVX-NEXT:    vpinsrb $1, -24(%rsp,%rsi), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %edx
; AVX-NEXT:    vpinsrb $2, -24(%rsp,%rdx), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %ecx
; AVX-NEXT:    vpinsrb $3, -24(%rsp,%rcx), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %r8d
; AVX-NEXT:    vpinsrb $4, -24(%rsp,%r8), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %r9d
; AVX-NEXT:    vpinsrb $5, -24(%rsp,%r9), %xmm0, %xmm0
; AVX-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $6, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $7, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $8, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $9, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $10, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $11, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $12, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $13, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $14, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    movzbl {{[0-9]+}}(%rsp), %eax
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $15, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    retq
  %x0  = extractelement <16 x i8> %x, i8 %i0
  %x1  = extractelement <16 x i8> %x, i8 %i1
  %x2  = extractelement <16 x i8> %x, i8 %i2
  %x3  = extractelement <16 x i8> %x, i8 %i3
  %x4  = extractelement <16 x i8> %x, i8 %i4
  %x5  = extractelement <16 x i8> %x, i8 %i5
  %x6  = extractelement <16 x i8> %x, i8 %i6
  %x7  = extractelement <16 x i8> %x, i8 %i7
  %x8  = extractelement <16 x i8> %x, i8 %i8
  %x9  = extractelement <16 x i8> %x, i8 %i9
  %x10 = extractelement <16 x i8> %x, i8 %i10
  %x11 = extractelement <16 x i8> %x, i8 %i11
  %x12 = extractelement <16 x i8> %x, i8 %i12
  %x13 = extractelement <16 x i8> %x, i8 %i13
  %x14 = extractelement <16 x i8> %x, i8 %i14
  %x15 = extractelement <16 x i8> %x, i8 %i15
  %r0  = insertelement <16 x i8> undef, i8 %x0 , i32 0
  %r1  = insertelement <16 x i8>  %r0 , i8 %x1 , i32 1
  %r2  = insertelement <16 x i8>  %r1 , i8 %x2 , i32 2
  %r3  = insertelement <16 x i8>  %r2 , i8 %x3 , i32 3
  %r4  = insertelement <16 x i8>  %r3 , i8 %x4 , i32 4
  %r5  = insertelement <16 x i8>  %r4 , i8 %x5 , i32 5
  %r6  = insertelement <16 x i8>  %r5 , i8 %x6 , i32 6
  %r7  = insertelement <16 x i8>  %r6 , i8 %x7 , i32 7
  %r8  = insertelement <16 x i8>  %r7 , i8 %x8 , i32 8
  %r9  = insertelement <16 x i8>  %r8 , i8 %x9 , i32 9
  %r10 = insertelement <16 x i8>  %r9 , i8 %x10, i32 10
  %r11 = insertelement <16 x i8>  %r10, i8 %x11, i32 11
  %r12 = insertelement <16 x i8>  %r11, i8 %x12, i32 12
  %r13 = insertelement <16 x i8>  %r12, i8 %x13, i32 13
  %r14 = insertelement <16 x i8>  %r13, i8 %x14, i32 14
  %r15 = insertelement <16 x i8>  %r14, i8 %x15, i32 15
  ret <16 x i8> %r15
}

;
; Unary shuffle indices from memory
;

define <4 x i32> @mem_shuffle_v4i32_v4i32_xxxx_i32(<4 x i32> %x, i32* %i) nounwind {
; SSE2-LABEL: mem_shuffle_v4i32_v4i32_xxxx_i32:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movl (%rdi), %eax
; SSE2-NEXT:    movl 4(%rdi), %ecx
; SSE2-NEXT:    andl $3, %eax
; SSE2-NEXT:    andl $3, %ecx
; SSE2-NEXT:    movl 8(%rdi), %edx
; SSE2-NEXT:    andl $3, %edx
; SSE2-NEXT:    movl 12(%rdi), %esi
; SSE2-NEXT:    andl $3, %esi
; SSE2-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE2-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE2-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: mem_shuffle_v4i32_v4i32_xxxx_i32:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    movl (%rdi), %eax
; SSSE3-NEXT:    movl 4(%rdi), %ecx
; SSSE3-NEXT:    andl $3, %eax
; SSSE3-NEXT:    andl $3, %ecx
; SSSE3-NEXT:    movl 8(%rdi), %edx
; SSSE3-NEXT:    andl $3, %edx
; SSSE3-NEXT:    movl 12(%rdi), %esi
; SSSE3-NEXT:    andl $3, %esi
; SSSE3-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSSE3-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSSE3-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSSE3-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSSE3-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSSE3-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSSE3-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSSE3-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: mem_shuffle_v4i32_v4i32_xxxx_i32:
; SSE41:       # %bb.0:
; SSE41-NEXT:    movl (%rdi), %eax
; SSE41-NEXT:    movl 4(%rdi), %ecx
; SSE41-NEXT:    andl $3, %eax
; SSE41-NEXT:    andl $3, %ecx
; SSE41-NEXT:    movl 8(%rdi), %edx
; SSE41-NEXT:    andl $3, %edx
; SSE41-NEXT:    movl 12(%rdi), %esi
; SSE41-NEXT:    andl $3, %esi
; SSE41-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE41-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE41-NEXT:    pinsrd $1, -24(%rsp,%rcx,4), %xmm0
; SSE41-NEXT:    pinsrd $2, -24(%rsp,%rdx,4), %xmm0
; SSE41-NEXT:    pinsrd $3, -24(%rsp,%rsi,4), %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: mem_shuffle_v4i32_v4i32_xxxx_i32:
; AVX:       # %bb.0:
; AVX-NEXT:    movl (%rdi), %eax
; AVX-NEXT:    movl 4(%rdi), %ecx
; AVX-NEXT:    andl $3, %eax
; AVX-NEXT:    andl $3, %ecx
; AVX-NEXT:    movl 8(%rdi), %edx
; AVX-NEXT:    andl $3, %edx
; AVX-NEXT:    movl 12(%rdi), %esi
; AVX-NEXT:    andl $3, %esi
; AVX-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vpinsrd $1, -24(%rsp,%rcx,4), %xmm0, %xmm0
; AVX-NEXT:    vpinsrd $2, -24(%rsp,%rdx,4), %xmm0, %xmm0
; AVX-NEXT:    vpinsrd $3, -24(%rsp,%rsi,4), %xmm0, %xmm0
; AVX-NEXT:    retq
  %p0  = getelementptr inbounds i32, i32* %i, i64 0
  %p1  = getelementptr inbounds i32, i32* %i, i64 1
  %p2  = getelementptr inbounds i32, i32* %i, i64 2
  %p3  = getelementptr inbounds i32, i32* %i, i64 3
  %i0  = load i32, i32* %p0, align 4
  %i1  = load i32, i32* %p1, align 4
  %i2  = load i32, i32* %p2, align 4
  %i3  = load i32, i32* %p3, align 4
  %x0 = extractelement <4 x i32> %x, i32 %i0
  %x1 = extractelement <4 x i32> %x, i32 %i1
  %x2 = extractelement <4 x i32> %x, i32 %i2
  %x3 = extractelement <4 x i32> %x, i32 %i3
  %r0 = insertelement <4 x i32> undef, i32 %x0, i32 0
  %r1 = insertelement <4 x i32>   %r0, i32 %x1, i32 1
  %r2 = insertelement <4 x i32>   %r1, i32 %x2, i32 2
  %r3 = insertelement <4 x i32>   %r2, i32 %x3, i32 3
  ret <4 x i32> %r3
}

define <16 x i8> @mem_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8(<16 x i8> %x, i8* %i) nounwind {
; SSE2-LABEL: mem_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
; SSE2:       # %bb.0:
; SSE2-NEXT:    pushq %rbp
; SSE2-NEXT:    pushq %r15
; SSE2-NEXT:    pushq %r14
; SSE2-NEXT:    pushq %r13
; SSE2-NEXT:    pushq %r12
; SSE2-NEXT:    pushq %rbx
; SSE2-NEXT:    movzbl (%rdi), %eax
; SSE2-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; SSE2-NEXT:    movzbl 1(%rdi), %r9d
; SSE2-NEXT:    movzbl 2(%rdi), %r10d
; SSE2-NEXT:    movzbl 3(%rdi), %r11d
; SSE2-NEXT:    movzbl 4(%rdi), %r14d
; SSE2-NEXT:    movzbl 5(%rdi), %r15d
; SSE2-NEXT:    movzbl 6(%rdi), %r12d
; SSE2-NEXT:    movzbl 7(%rdi), %r13d
; SSE2-NEXT:    movzbl 8(%rdi), %ebx
; SSE2-NEXT:    movzbl 9(%rdi), %r8d
; SSE2-NEXT:    movzbl 10(%rdi), %ecx
; SSE2-NEXT:    movzbl 11(%rdi), %edx
; SSE2-NEXT:    movzbl 12(%rdi), %esi
; SSE2-NEXT:    movzbl 13(%rdi), %ebp
; SSE2-NEXT:    movzbl 14(%rdi), %eax
; SSE2-NEXT:    movzbl 15(%rdi), %edi
; SSE2-NEXT:    andl $15, %edi
; SSE2-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE2-NEXT:    movzbl -24(%rsp,%rdi), %edi
; SSE2-NEXT:    movd %edi, %xmm8
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm15
; SSE2-NEXT:    andl $15, %ebp
; SSE2-NEXT:    movzbl -24(%rsp,%rbp), %eax
; SSE2-NEXT:    movd %eax, %xmm9
; SSE2-NEXT:    andl $15, %esi
; SSE2-NEXT:    movzbl -24(%rsp,%rsi), %eax
; SSE2-NEXT:    movd %eax, %xmm3
; SSE2-NEXT:    andl $15, %edx
; SSE2-NEXT:    movzbl -24(%rsp,%rdx), %eax
; SSE2-NEXT:    movd %eax, %xmm10
; SSE2-NEXT:    andl $15, %ecx
; SSE2-NEXT:    movzbl -24(%rsp,%rcx), %eax
; SSE2-NEXT:    movd %eax, %xmm7
; SSE2-NEXT:    andl $15, %r8d
; SSE2-NEXT:    movzbl -24(%rsp,%r8), %eax
; SSE2-NEXT:    movd %eax, %xmm11
; SSE2-NEXT:    andl $15, %ebx
; SSE2-NEXT:    movzbl -24(%rsp,%rbx), %eax
; SSE2-NEXT:    movd %eax, %xmm6
; SSE2-NEXT:    andl $15, %r13d
; SSE2-NEXT:    movzbl -24(%rsp,%r13), %eax
; SSE2-NEXT:    movd %eax, %xmm12
; SSE2-NEXT:    andl $15, %r12d
; SSE2-NEXT:    movzbl -24(%rsp,%r12), %eax
; SSE2-NEXT:    movd %eax, %xmm5
; SSE2-NEXT:    andl $15, %r15d
; SSE2-NEXT:    movzbl -24(%rsp,%r15), %eax
; SSE2-NEXT:    movd %eax, %xmm13
; SSE2-NEXT:    andl $15, %r14d
; SSE2-NEXT:    movzbl -24(%rsp,%r14), %eax
; SSE2-NEXT:    movd %eax, %xmm4
; SSE2-NEXT:    andl $15, %r11d
; SSE2-NEXT:    movzbl -24(%rsp,%r11), %eax
; SSE2-NEXT:    movd %eax, %xmm14
; SSE2-NEXT:    andl $15, %r10d
; SSE2-NEXT:    movzbl -24(%rsp,%r10), %eax
; SSE2-NEXT:    movd %eax, %xmm1
; SSE2-NEXT:    andl $15, %r9d
; SSE2-NEXT:    movzbl -24(%rsp,%r9), %eax
; SSE2-NEXT:    movd %eax, %xmm2
; SSE2-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
; SSE2-NEXT:    andl $15, %eax
; SSE2-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSE2-NEXT:    movd %eax, %xmm0
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm15 = xmm15[0],xmm8[0],xmm15[1],xmm8[1],xmm15[2],xmm8[2],xmm15[3],xmm8[3],xmm15[4],xmm8[4],xmm15[5],xmm8[5],xmm15[6],xmm8[6],xmm15[7],xmm8[7]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm15[0],xmm3[1],xmm15[1],xmm3[2],xmm15[2],xmm3[3],xmm15[3]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm10[0],xmm7[1],xmm10[1],xmm7[2],xmm10[2],xmm7[3],xmm10[3],xmm7[4],xmm10[4],xmm7[5],xmm10[5],xmm7[6],xmm10[6],xmm7[7],xmm10[7]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm11[0],xmm6[1],xmm11[1],xmm6[2],xmm11[2],xmm6[3],xmm11[3],xmm6[4],xmm11[4],xmm6[5],xmm11[5],xmm6[6],xmm11[6],xmm6[7],xmm11[7]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm6 = xmm6[0],xmm3[0],xmm6[1],xmm3[1]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm12[0],xmm5[1],xmm12[1],xmm5[2],xmm12[2],xmm5[3],xmm12[3],xmm5[4],xmm12[4],xmm5[5],xmm12[5],xmm5[6],xmm12[6],xmm5[7],xmm12[7]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm13[0],xmm4[1],xmm13[1],xmm4[2],xmm13[2],xmm4[3],xmm13[3],xmm4[4],xmm13[4],xmm4[5],xmm13[5],xmm4[6],xmm13[6],xmm4[7],xmm13[7]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm14[0],xmm1[1],xmm14[1],xmm1[2],xmm14[2],xmm1[3],xmm14[3],xmm1[4],xmm14[4],xmm1[5],xmm14[5],xmm1[6],xmm14[6],xmm1[7],xmm14[7]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
; SSE2-NEXT:    popq %rbx
; SSE2-NEXT:    popq %r12
; SSE2-NEXT:    popq %r13
; SSE2-NEXT:    popq %r14
; SSE2-NEXT:    popq %r15
; SSE2-NEXT:    popq %rbp
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: mem_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    pushq %rbp
; SSSE3-NEXT:    pushq %r15
; SSSE3-NEXT:    pushq %r14
; SSSE3-NEXT:    pushq %r13
; SSSE3-NEXT:    pushq %r12
; SSSE3-NEXT:    pushq %rbx
; SSSE3-NEXT:    movzbl (%rdi), %eax
; SSSE3-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; SSSE3-NEXT:    movzbl 1(%rdi), %r9d
; SSSE3-NEXT:    movzbl 2(%rdi), %r10d
; SSSE3-NEXT:    movzbl 3(%rdi), %r11d
; SSSE3-NEXT:    movzbl 4(%rdi), %r14d
; SSSE3-NEXT:    movzbl 5(%rdi), %r15d
; SSSE3-NEXT:    movzbl 6(%rdi), %r12d
; SSSE3-NEXT:    movzbl 7(%rdi), %r13d
; SSSE3-NEXT:    movzbl 8(%rdi), %ebx
; SSSE3-NEXT:    movzbl 9(%rdi), %r8d
; SSSE3-NEXT:    movzbl 10(%rdi), %ecx
; SSSE3-NEXT:    movzbl 11(%rdi), %edx
; SSSE3-NEXT:    movzbl 12(%rdi), %esi
; SSSE3-NEXT:    movzbl 13(%rdi), %ebp
; SSSE3-NEXT:    movzbl 14(%rdi), %eax
; SSSE3-NEXT:    movzbl 15(%rdi), %edi
; SSSE3-NEXT:    andl $15, %edi
; SSSE3-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSSE3-NEXT:    movzbl -24(%rsp,%rdi), %edi
; SSSE3-NEXT:    movd %edi, %xmm8
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm15
; SSSE3-NEXT:    andl $15, %ebp
; SSSE3-NEXT:    movzbl -24(%rsp,%rbp), %eax
; SSSE3-NEXT:    movd %eax, %xmm9
; SSSE3-NEXT:    andl $15, %esi
; SSSE3-NEXT:    movzbl -24(%rsp,%rsi), %eax
; SSSE3-NEXT:    movd %eax, %xmm3
; SSSE3-NEXT:    andl $15, %edx
; SSSE3-NEXT:    movzbl -24(%rsp,%rdx), %eax
; SSSE3-NEXT:    movd %eax, %xmm10
; SSSE3-NEXT:    andl $15, %ecx
; SSSE3-NEXT:    movzbl -24(%rsp,%rcx), %eax
; SSSE3-NEXT:    movd %eax, %xmm7
; SSSE3-NEXT:    andl $15, %r8d
; SSSE3-NEXT:    movzbl -24(%rsp,%r8), %eax
; SSSE3-NEXT:    movd %eax, %xmm11
; SSSE3-NEXT:    andl $15, %ebx
; SSSE3-NEXT:    movzbl -24(%rsp,%rbx), %eax
; SSSE3-NEXT:    movd %eax, %xmm6
; SSSE3-NEXT:    andl $15, %r13d
; SSSE3-NEXT:    movzbl -24(%rsp,%r13), %eax
; SSSE3-NEXT:    movd %eax, %xmm12
; SSSE3-NEXT:    andl $15, %r12d
; SSSE3-NEXT:    movzbl -24(%rsp,%r12), %eax
; SSSE3-NEXT:    movd %eax, %xmm5
; SSSE3-NEXT:    andl $15, %r15d
; SSSE3-NEXT:    movzbl -24(%rsp,%r15), %eax
; SSSE3-NEXT:    movd %eax, %xmm13
; SSSE3-NEXT:    andl $15, %r14d
; SSSE3-NEXT:    movzbl -24(%rsp,%r14), %eax
; SSSE3-NEXT:    movd %eax, %xmm4
; SSSE3-NEXT:    andl $15, %r11d
; SSSE3-NEXT:    movzbl -24(%rsp,%r11), %eax
; SSSE3-NEXT:    movd %eax, %xmm14
; SSSE3-NEXT:    andl $15, %r10d
; SSSE3-NEXT:    movzbl -24(%rsp,%r10), %eax
; SSSE3-NEXT:    movd %eax, %xmm1
; SSSE3-NEXT:    andl $15, %r9d
; SSSE3-NEXT:    movzbl -24(%rsp,%r9), %eax
; SSSE3-NEXT:    movd %eax, %xmm2
; SSSE3-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
; SSSE3-NEXT:    andl $15, %eax
; SSSE3-NEXT:    movzbl -24(%rsp,%rax), %eax
; SSSE3-NEXT:    movd %eax, %xmm0
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm15 = xmm15[0],xmm8[0],xmm15[1],xmm8[1],xmm15[2],xmm8[2],xmm15[3],xmm8[3],xmm15[4],xmm8[4],xmm15[5],xmm8[5],xmm15[6],xmm8[6],xmm15[7],xmm8[7]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm15[0],xmm3[1],xmm15[1],xmm3[2],xmm15[2],xmm3[3],xmm15[3]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm10[0],xmm7[1],xmm10[1],xmm7[2],xmm10[2],xmm7[3],xmm10[3],xmm7[4],xmm10[4],xmm7[5],xmm10[5],xmm7[6],xmm10[6],xmm7[7],xmm10[7]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm11[0],xmm6[1],xmm11[1],xmm6[2],xmm11[2],xmm6[3],xmm11[3],xmm6[4],xmm11[4],xmm6[5],xmm11[5],xmm6[6],xmm11[6],xmm6[7],xmm11[7]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3]
; SSSE3-NEXT:    punpckldq {{.*#+}} xmm6 = xmm6[0],xmm3[0],xmm6[1],xmm3[1]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm12[0],xmm5[1],xmm12[1],xmm5[2],xmm12[2],xmm5[3],xmm12[3],xmm5[4],xmm12[4],xmm5[5],xmm12[5],xmm5[6],xmm12[6],xmm5[7],xmm12[7]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm13[0],xmm4[1],xmm13[1],xmm4[2],xmm13[2],xmm4[3],xmm13[3],xmm4[4],xmm13[4],xmm4[5],xmm13[5],xmm4[6],xmm13[6],xmm4[7],xmm13[7]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm14[0],xmm1[1],xmm14[1],xmm1[2],xmm14[2],xmm1[3],xmm14[3],xmm1[4],xmm14[4],xmm1[5],xmm14[5],xmm1[6],xmm14[6],xmm1[7],xmm14[7]
; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
; SSSE3-NEXT:    popq %rbx
; SSSE3-NEXT:    popq %r12
; SSSE3-NEXT:    popq %r13
; SSSE3-NEXT:    popq %r14
; SSSE3-NEXT:    popq %r15
; SSSE3-NEXT:    popq %rbp
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: mem_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
; SSE41:       # %bb.0:
; SSE41-NEXT:    pushq %rbp
; SSE41-NEXT:    pushq %r15
; SSE41-NEXT:    pushq %r14
; SSE41-NEXT:    pushq %r13
; SSE41-NEXT:    pushq %r12
; SSE41-NEXT:    pushq %rbx
; SSE41-NEXT:    movzbl (%rdi), %r9d
; SSE41-NEXT:    andl $15, %r9d
; SSE41-NEXT:    movzbl 1(%rdi), %ebx
; SSE41-NEXT:    movzbl 2(%rdi), %eax
; SSE41-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; SSE41-NEXT:    movzbl 3(%rdi), %r11d
; SSE41-NEXT:    movzbl 4(%rdi), %r14d
; SSE41-NEXT:    movzbl 5(%rdi), %r15d
; SSE41-NEXT:    movzbl 6(%rdi), %r12d
; SSE41-NEXT:    movzbl 7(%rdi), %r13d
; SSE41-NEXT:    movzbl 8(%rdi), %r10d
; SSE41-NEXT:    movzbl 9(%rdi), %r8d
; SSE41-NEXT:    movzbl 10(%rdi), %ecx
; SSE41-NEXT:    movzbl 11(%rdi), %edx
; SSE41-NEXT:    movzbl 12(%rdi), %esi
; SSE41-NEXT:    movzbl 13(%rdi), %ebp
; SSE41-NEXT:    movzbl 14(%rdi), %eax
; SSE41-NEXT:    movzbl 15(%rdi), %edi
; SSE41-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE41-NEXT:    movzbl -24(%rsp,%r9), %r9d
; SSE41-NEXT:    movd %r9d, %xmm0
; SSE41-NEXT:    andl $15, %ebx
; SSE41-NEXT:    pinsrb $1, -24(%rsp,%rbx), %xmm0
; SSE41-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rbx # 8-byte Reload
; SSE41-NEXT:    andl $15, %ebx
; SSE41-NEXT:    pinsrb $2, -24(%rsp,%rbx), %xmm0
; SSE41-NEXT:    andl $15, %r11d
; SSE41-NEXT:    pinsrb $3, -24(%rsp,%r11), %xmm0
; SSE41-NEXT:    andl $15, %r14d
; SSE41-NEXT:    pinsrb $4, -24(%rsp,%r14), %xmm0
; SSE41-NEXT:    andl $15, %r15d
; SSE41-NEXT:    pinsrb $5, -24(%rsp,%r15), %xmm0
; SSE41-NEXT:    andl $15, %r12d
; SSE41-NEXT:    pinsrb $6, -24(%rsp,%r12), %xmm0
; SSE41-NEXT:    andl $15, %r13d
; SSE41-NEXT:    pinsrb $7, -24(%rsp,%r13), %xmm0
; SSE41-NEXT:    andl $15, %r10d
; SSE41-NEXT:    pinsrb $8, -24(%rsp,%r10), %xmm0
; SSE41-NEXT:    andl $15, %r8d
; SSE41-NEXT:    pinsrb $9, -24(%rsp,%r8), %xmm0
; SSE41-NEXT:    andl $15, %ecx
; SSE41-NEXT:    pinsrb $10, -24(%rsp,%rcx), %xmm0
; SSE41-NEXT:    andl $15, %edx
; SSE41-NEXT:    pinsrb $11, -24(%rsp,%rdx), %xmm0
; SSE41-NEXT:    andl $15, %esi
; SSE41-NEXT:    pinsrb $12, -24(%rsp,%rsi), %xmm0
; SSE41-NEXT:    andl $15, %ebp
; SSE41-NEXT:    pinsrb $13, -24(%rsp,%rbp), %xmm0
; SSE41-NEXT:    andl $15, %eax
; SSE41-NEXT:    pinsrb $14, -24(%rsp,%rax), %xmm0
; SSE41-NEXT:    andl $15, %edi
; SSE41-NEXT:    pinsrb $15, -24(%rsp,%rdi), %xmm0
; SSE41-NEXT:    popq %rbx
; SSE41-NEXT:    popq %r12
; SSE41-NEXT:    popq %r13
; SSE41-NEXT:    popq %r14
; SSE41-NEXT:    popq %r15
; SSE41-NEXT:    popq %rbp
; SSE41-NEXT:    retq
;
; AVX-LABEL: mem_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
; AVX:       # %bb.0:
; AVX-NEXT:    pushq %rbp
; AVX-NEXT:    pushq %r15
; AVX-NEXT:    pushq %r14
; AVX-NEXT:    pushq %r13
; AVX-NEXT:    pushq %r12
; AVX-NEXT:    pushq %rbx
; AVX-NEXT:    movzbl (%rdi), %r9d
; AVX-NEXT:    andl $15, %r9d
; AVX-NEXT:    movzbl 1(%rdi), %ebx
; AVX-NEXT:    movzbl 2(%rdi), %eax
; AVX-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; AVX-NEXT:    movzbl 3(%rdi), %r11d
; AVX-NEXT:    movzbl 4(%rdi), %r14d
; AVX-NEXT:    movzbl 5(%rdi), %r15d
; AVX-NEXT:    movzbl 6(%rdi), %r12d
; AVX-NEXT:    movzbl 7(%rdi), %r13d
; AVX-NEXT:    movzbl 8(%rdi), %r10d
; AVX-NEXT:    movzbl 9(%rdi), %r8d
; AVX-NEXT:    movzbl 10(%rdi), %ecx
; AVX-NEXT:    movzbl 11(%rdi), %edx
; AVX-NEXT:    movzbl 12(%rdi), %esi
; AVX-NEXT:    movzbl 13(%rdi), %ebp
; AVX-NEXT:    movzbl 14(%rdi), %eax
; AVX-NEXT:    movzbl 15(%rdi), %edi
; AVX-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    movzbl -24(%rsp,%r9), %r9d
; AVX-NEXT:    vmovd %r9d, %xmm0
; AVX-NEXT:    andl $15, %ebx
; AVX-NEXT:    vpinsrb $1, -24(%rsp,%rbx), %xmm0, %xmm0
; AVX-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rbx # 8-byte Reload
; AVX-NEXT:    andl $15, %ebx
; AVX-NEXT:    vpinsrb $2, -24(%rsp,%rbx), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %r11d
; AVX-NEXT:    vpinsrb $3, -24(%rsp,%r11), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %r14d
; AVX-NEXT:    vpinsrb $4, -24(%rsp,%r14), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %r15d
; AVX-NEXT:    vpinsrb $5, -24(%rsp,%r15), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %r12d
; AVX-NEXT:    vpinsrb $6, -24(%rsp,%r12), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %r13d
; AVX-NEXT:    vpinsrb $7, -24(%rsp,%r13), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %r10d
; AVX-NEXT:    vpinsrb $8, -24(%rsp,%r10), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %r8d
; AVX-NEXT:    vpinsrb $9, -24(%rsp,%r8), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %ecx
; AVX-NEXT:    vpinsrb $10, -24(%rsp,%rcx), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %edx
; AVX-NEXT:    vpinsrb $11, -24(%rsp,%rdx), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %esi
; AVX-NEXT:    vpinsrb $12, -24(%rsp,%rsi), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %ebp
; AVX-NEXT:    vpinsrb $13, -24(%rsp,%rbp), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %eax
; AVX-NEXT:    vpinsrb $14, -24(%rsp,%rax), %xmm0, %xmm0
; AVX-NEXT:    andl $15, %edi
; AVX-NEXT:    vpinsrb $15, -24(%rsp,%rdi), %xmm0, %xmm0
; AVX-NEXT:    popq %rbx
; AVX-NEXT:    popq %r12
; AVX-NEXT:    popq %r13
; AVX-NEXT:    popq %r14
; AVX-NEXT:    popq %r15
; AVX-NEXT:    popq %rbp
; AVX-NEXT:    retq
  %p0  = getelementptr inbounds i8, i8* %i, i64 0
  %p1  = getelementptr inbounds i8, i8* %i, i64 1
  %p2  = getelementptr inbounds i8, i8* %i, i64 2
  %p3  = getelementptr inbounds i8, i8* %i, i64 3
  %p4  = getelementptr inbounds i8, i8* %i, i64 4
  %p5  = getelementptr inbounds i8, i8* %i, i64 5
  %p6  = getelementptr inbounds i8, i8* %i, i64 6
  %p7  = getelementptr inbounds i8, i8* %i, i64 7
  %p8  = getelementptr inbounds i8, i8* %i, i64 8
  %p9  = getelementptr inbounds i8, i8* %i, i64 9
  %p10 = getelementptr inbounds i8, i8* %i, i64 10
  %p11 = getelementptr inbounds i8, i8* %i, i64 11
  %p12 = getelementptr inbounds i8, i8* %i, i64 12
  %p13 = getelementptr inbounds i8, i8* %i, i64 13
  %p14 = getelementptr inbounds i8, i8* %i, i64 14
  %p15 = getelementptr inbounds i8, i8* %i, i64 15
  %i0  = load i8, i8* %p0 , align 4
  %i1  = load i8, i8* %p1 , align 4
  %i2  = load i8, i8* %p2 , align 4
  %i3  = load i8, i8* %p3 , align 4
  %i4  = load i8, i8* %p4 , align 4
  %i5  = load i8, i8* %p5 , align 4
  %i6  = load i8, i8* %p6 , align 4
  %i7  = load i8, i8* %p7 , align 4
  %i8  = load i8, i8* %p8 , align 4
  %i9  = load i8, i8* %p9 , align 4
  %i10 = load i8, i8* %p10, align 4
  %i11 = load i8, i8* %p11, align 4
  %i12 = load i8, i8* %p12, align 4
  %i13 = load i8, i8* %p13, align 4
  %i14 = load i8, i8* %p14, align 4
  %i15 = load i8, i8* %p15, align 4
  %x0  = extractelement <16 x i8> %x, i8 %i0
  %x1  = extractelement <16 x i8> %x, i8 %i1
  %x2  = extractelement <16 x i8> %x, i8 %i2
  %x3  = extractelement <16 x i8> %x, i8 %i3
  %x4  = extractelement <16 x i8> %x, i8 %i4
  %x5  = extractelement <16 x i8> %x, i8 %i5
  %x6  = extractelement <16 x i8> %x, i8 %i6
  %x7  = extractelement <16 x i8> %x, i8 %i7
  %x8  = extractelement <16 x i8> %x, i8 %i8
  %x9  = extractelement <16 x i8> %x, i8 %i9
  %x10 = extractelement <16 x i8> %x, i8 %i10
  %x11 = extractelement <16 x i8> %x, i8 %i11
  %x12 = extractelement <16 x i8> %x, i8 %i12
  %x13 = extractelement <16 x i8> %x, i8 %i13
  %x14 = extractelement <16 x i8> %x, i8 %i14
  %x15 = extractelement <16 x i8> %x, i8 %i15
  %r0  = insertelement <16 x i8> undef, i8 %x0 , i32 0
  %r1  = insertelement <16 x i8>  %r0 , i8 %x1 , i32 1
  %r2  = insertelement <16 x i8>  %r1 , i8 %x2 , i32 2
  %r3  = insertelement <16 x i8>  %r2 , i8 %x3 , i32 3
  %r4  = insertelement <16 x i8>  %r3 , i8 %x4 , i32 4
  %r5  = insertelement <16 x i8>  %r4 , i8 %x5 , i32 5
  %r6  = insertelement <16 x i8>  %r5 , i8 %x6 , i32 6
  %r7  = insertelement <16 x i8>  %r6 , i8 %x7 , i32 7
  %r8  = insertelement <16 x i8>  %r7 , i8 %x8 , i32 8
  %r9  = insertelement <16 x i8>  %r8 , i8 %x9 , i32 9
  %r10 = insertelement <16 x i8>  %r9 , i8 %x10, i32 10
  %r11 = insertelement <16 x i8>  %r10, i8 %x11, i32 11
  %r12 = insertelement <16 x i8>  %r11, i8 %x12, i32 12
  %r13 = insertelement <16 x i8>  %r12, i8 %x13, i32 13
  %r14 = insertelement <16 x i8>  %r13, i8 %x14, i32 14
  %r15 = insertelement <16 x i8>  %r14, i8 %x15, i32 15
  ret <16 x i8> %r15
}

;
; Binary shuffle indices from registers
;

define <4 x float> @var_shuffle_v4f32_v4f32_x0yx_i32(<4 x float> %x, <4 x float> %y, i32 %i0, i32 %i1, i32 %i2, i32 %i3) nounwind {
; SSE-LABEL: var_shuffle_v4f32_v4f32_x0yx_i32:
; SSE:       # %bb.0:
; SSE-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE-NEXT:    andl $3, %edi
; SSE-NEXT:    movaps %xmm1, -{{[0-9]+}}(%rsp)
; SSE-NEXT:    andl $3, %edx
; SSE-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE-NEXT:    andl $3, %ecx
; SSE-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; 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: var_shuffle_v4f32_v4f32_x0yx_i32:
; AVX:       # %bb.0:
; AVX-NEXT:    # kill: def $ecx killed $ecx def $rcx
; AVX-NEXT:    # kill: def $edx killed $edx def $rdx
; AVX-NEXT:    # kill: def $edi killed $edi def $rdi
; AVX-NEXT:    andl $3, %edi
; AVX-NEXT:    vmovaps %xmm1, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    andl $3, %edx
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    andl $3, %ecx
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-NEXT:    vunpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX-NEXT:    vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX-NEXT:    retq
  %x0 = extractelement <4 x float> %x, i32 %i0
  %x1 = extractelement <4 x float> %x, i32 %i1
  %y2 = extractelement <4 x float> %y, i32 %i2
  %x3 = extractelement <4 x float> %x, i32 %i3
  %r0 = insertelement <4 x float> undef, float %x0, i32 0
  %r1 = insertelement <4 x float>   %r0, float 0.0, i32 1
  %r2 = insertelement <4 x float>   %r1, float %y2, i32 2
  %r3 = insertelement <4 x float>   %r2, float %x3, i32 3
  ret <4 x float> %r3
}

define <8 x i16> @var_shuffle_v8i16_v8i16_xyxyxy00_i16(<8 x i16> %x, <8 x i16> %y, i16 %i0, i16 %i1, i16 %i2, i16 %i3, i16 %i4, i16 %i5, i16 %i6, i16 %i7) nounwind {
; SSE2-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
; SSE2:       # %bb.0:
; SSE2-NEXT:    # kill: def $r9d killed $r9d def $r9
; SSE2-NEXT:    # kill: def $r8d killed $r8d def $r8
; SSE2-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE2-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE2-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE2-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE2-NEXT:    andl $7, %edi
; SSE2-NEXT:    andl $7, %esi
; SSE2-NEXT:    andl $7, %edx
; SSE2-NEXT:    andl $7, %ecx
; SSE2-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE2-NEXT:    andl $7, %r8d
; SSE2-NEXT:    movaps %xmm1, -{{[0-9]+}}(%rsp)
; SSE2-NEXT:    andl $7, %r9d
; SSE2-NEXT:    movzwl -24(%rsp,%rcx,2), %eax
; SSE2-NEXT:    movd %eax, %xmm0
; SSE2-NEXT:    movzwl -40(%rsp,%rdx,2), %eax
; SSE2-NEXT:    movd %eax, %xmm1
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT:    movzwl -24(%rsp,%rsi,2), %eax
; SSE2-NEXT:    movd %eax, %xmm2
; SSE2-NEXT:    movzwl -40(%rsp,%rdi,2), %eax
; SSE2-NEXT:    movd %eax, %xmm0
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT:    movzwl -24(%rsp,%r9,2), %eax
; SSE2-NEXT:    movd %eax, %xmm1
; SSE2-NEXT:    movzwl -40(%rsp,%r8,2), %eax
; SSE2-NEXT:    movd %eax, %xmm2
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
; SSSE3:       # %bb.0:
; SSSE3-NEXT:    # kill: def $r9d killed $r9d def $r9
; SSSE3-NEXT:    # kill: def $r8d killed $r8d def $r8
; SSSE3-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSSE3-NEXT:    # kill: def $edx killed $edx def $rdx
; SSSE3-NEXT:    # kill: def $esi killed $esi def $rsi
; SSSE3-NEXT:    # kill: def $edi killed $edi def $rdi
; SSSE3-NEXT:    andl $7, %edi
; SSSE3-NEXT:    andl $7, %esi
; SSSE3-NEXT:    andl $7, %edx
; SSSE3-NEXT:    andl $7, %ecx
; SSSE3-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSSE3-NEXT:    andl $7, %r8d
; SSSE3-NEXT:    movaps %xmm1, -{{[0-9]+}}(%rsp)
; SSSE3-NEXT:    andl $7, %r9d
; SSSE3-NEXT:    movzwl -24(%rsp,%rcx,2), %eax
; SSSE3-NEXT:    movd %eax, %xmm0
; SSSE3-NEXT:    movzwl -40(%rsp,%rdx,2), %eax
; SSSE3-NEXT:    movd %eax, %xmm1
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSSE3-NEXT:    movzwl -24(%rsp,%rsi,2), %eax
; SSSE3-NEXT:    movd %eax, %xmm2
; SSSE3-NEXT:    movzwl -40(%rsp,%rdi,2), %eax
; SSSE3-NEXT:    movd %eax, %xmm0
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT:    movzwl -24(%rsp,%r9,2), %eax
; SSSE3-NEXT:    movd %eax, %xmm1
; SSSE3-NEXT:    movzwl -40(%rsp,%r8,2), %eax
; SSSE3-NEXT:    movd %eax, %xmm2
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSSE3-NEXT:    pxor %xmm1, %xmm1
; SSSE3-NEXT:    punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
; SSE41:       # %bb.0:
; SSE41-NEXT:    # kill: def $r9d killed $r9d def $r9
; SSE41-NEXT:    # kill: def $r8d killed $r8d def $r8
; SSE41-NEXT:    # kill: def $ecx killed $ecx def $rcx
; SSE41-NEXT:    # kill: def $edx killed $edx def $rdx
; SSE41-NEXT:    # kill: def $esi killed $esi def $rsi
; SSE41-NEXT:    # kill: def $edi killed $edi def $rdi
; SSE41-NEXT:    andl $7, %edi
; SSE41-NEXT:    andl $7, %esi
; SSE41-NEXT:    andl $7, %edx
; SSE41-NEXT:    andl $7, %ecx
; SSE41-NEXT:    movdqa %xmm0, -{{[0-9]+}}(%rsp)
; SSE41-NEXT:    andl $7, %r8d
; SSE41-NEXT:    movaps %xmm1, -{{[0-9]+}}(%rsp)
; SSE41-NEXT:    andl $7, %r9d
; SSE41-NEXT:    pxor %xmm0, %xmm0
; SSE41-NEXT:    pinsrw $0, -40(%rsp,%rdi,2), %xmm0
; SSE41-NEXT:    pinsrw $1, -24(%rsp,%rsi,2), %xmm0
; SSE41-NEXT:    pinsrw $2, -40(%rsp,%rdx,2), %xmm0
; SSE41-NEXT:    pinsrw $3, -24(%rsp,%rcx,2), %xmm0
; SSE41-NEXT:    pinsrw $4, -40(%rsp,%r8,2), %xmm0
; SSE41-NEXT:    pinsrw $5, -24(%rsp,%r9,2), %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
; AVX:       # %bb.0:
; AVX-NEXT:    # kill: def $r9d killed $r9d def $r9
; AVX-NEXT:    # kill: def $r8d killed $r8d def $r8
; AVX-NEXT:    # kill: def $ecx killed $ecx def $rcx
; AVX-NEXT:    # kill: def $edx killed $edx def $rdx
; AVX-NEXT:    # kill: def $esi killed $esi def $rsi
; AVX-NEXT:    # kill: def $edi killed $edi def $rdi
; AVX-NEXT:    andl $7, %edi
; AVX-NEXT:    andl $7, %esi
; AVX-NEXT:    andl $7, %edx
; AVX-NEXT:    andl $7, %ecx
; AVX-NEXT:    vmovdqa %xmm0, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    andl $7, %r8d
; AVX-NEXT:    vmovaps %xmm1, -{{[0-9]+}}(%rsp)
; AVX-NEXT:    andl $7, %r9d
; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $0, -40(%rsp,%rdi,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $1, -24(%rsp,%rsi,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $2, -40(%rsp,%rdx,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $3, -24(%rsp,%rcx,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $4, -40(%rsp,%r8,2), %xmm0, %xmm0
; AVX-NEXT:    vpinsrw $5, -24(%rsp,%r9,2), %xmm0, %xmm0
; AVX-NEXT:    retq
  %x0 = extractelement <8 x i16> %x, i16 %i0
  %y1 = extractelement <8 x i16> %y, i16 %i1
  %x2 = extractelement <8 x i16> %x, i16 %i2
  %y3 = extractelement <8 x i16> %y, i16 %i3
  %x4 = extractelement <8 x i16> %x, i16 %i4
  %y5 = extractelement <8 x i16> %y, i16 %i5
  %x6 = extractelement <8 x i16> %x, i16 %i6
  %x7 = extractelement <8 x i16> %x, i16 %i7
  %r0 = insertelement <8 x i16> undef, i16 %x0, i32 0
  %r1 = insertelement <8 x i16>   %r0, i16 %y1, i32 1
  %r2 = insertelement <8 x i16>   %r1, i16 %x2, i32 2
  %r3 = insertelement <8 x i16>   %r2, i16 %y3, i32 3
  %r4 = insertelement <8 x i16>   %r3, i16 %x4, i32 4
  %r5 = insertelement <8 x i16>   %r4, i16 %y5, i32 5
  %r6 = insertelement <8 x i16>   %r5, i16   0, i32 6
  %r7 = insertelement <8 x i16>   %r6, i16   0, i32 7
  ret <8 x i16> %r7
}