; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX256,AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefixes=AVX,AVX256,AVX512,AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefixes=AVX,AVX256,AVX512,AVX512BW

define i32 @_Z10test_shortPsS_i_128(i16* nocapture readonly, i16* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: _Z10test_shortPsS_i_128:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB0_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movq {{.*#+}} xmm1 = mem[0],zero
; SSE2-NEXT:    movq {{.*#+}} xmm2 = mem[0],zero
; SSE2-NEXT:    movdqa %xmm2, %xmm3
; SSE2-NEXT:    pmulhw %xmm1, %xmm3
; SSE2-NEXT:    pmullw %xmm1, %xmm2
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
; SSE2-NEXT:    paddd %xmm2, %xmm0
; SSE2-NEXT:    addq $8, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB0_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[1,1,1,1]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    movd %xmm0, %eax
; SSE2-NEXT:    retq
;
; AVX-LABEL: _Z10test_shortPsS_i_128:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    movl %edx, %eax
; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX-NEXT:    xorl %ecx, %ecx
; AVX-NEXT:    .p2align 4, 0x90
; AVX-NEXT:  .LBB0_1: # %vector.body
; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX-NEXT:    vpmovsxwd (%rdi,%rcx,2), %xmm1
; AVX-NEXT:    vpmovsxwd (%rsi,%rcx,2), %xmm2
; AVX-NEXT:    vpmulld %xmm1, %xmm2, %xmm1
; AVX-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
; AVX-NEXT:    addq $8, %rcx
; AVX-NEXT:    cmpq %rcx, %rax
; AVX-NEXT:    jne .LBB0_1
; AVX-NEXT:  # %bb.2: # %middle.block
; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vmovd %xmm0, %eax
; AVX-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <4 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i16, i16* %0, i64 %index
  %5 = bitcast i16* %4 to <4 x i16>*
  %wide.load = load <4 x i16>, <4 x i16>* %5, align 2
  %6 = sext <4 x i16> %wide.load to <4 x i32>
  %7 = getelementptr inbounds i16, i16* %1, i64 %index
  %8 = bitcast i16* %7 to <4 x i16>*
  %wide.load14 = load <4 x i16>, <4 x i16>* %8, align 2
  %9 = sext <4 x i16> %wide.load14 to <4 x i32>
  %10 = mul nsw <4 x i32> %9, %6
  %11 = add nsw <4 x i32> %10, %vec.phi
  %index.next = add i64 %index, 8
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf15 = shufflevector <4 x i32> %11, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
  %bin.rdx16 = add <4 x i32> %11, %rdx.shuf15
  %rdx.shuf17 = shufflevector <4 x i32> %bin.rdx16, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <4 x i32> %bin.rdx16, %rdx.shuf17
  %13 = extractelement <4 x i32> %bin.rdx18, i32 0
  ret i32 %13
}

define i32 @_Z10test_shortPsS_i_256(i16* nocapture readonly, i16* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: _Z10test_shortPsS_i_256:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB1_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm2
; SSE2-NEXT:    movdqu (%rsi,%rcx,2), %xmm3
; SSE2-NEXT:    pmaddwd %xmm2, %xmm3
; SSE2-NEXT:    paddd %xmm3, %xmm1
; SSE2-NEXT:    addq $8, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB1_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: _Z10test_shortPsS_i_256:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %edx, %eax
; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    xorl %ecx, %ecx
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB1_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm1
; AVX1-NEXT:    vpmaddwd (%rdi,%rcx,2), %xmm1, %xmm1
; AVX1-NEXT:    vpaddd %xmm0, %xmm1, %xmm1
; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
; AVX1-NEXT:    addq $8, %rcx
; AVX1-NEXT:    cmpq %rcx, %rax
; AVX1-NEXT:    jne .LBB1_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX256-LABEL: _Z10test_shortPsS_i_256:
; AVX256:       # %bb.0: # %entry
; AVX256-NEXT:    movl %edx, %eax
; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX256-NEXT:    xorl %ecx, %ecx
; AVX256-NEXT:    .p2align 4, 0x90
; AVX256-NEXT:  .LBB1_1: # %vector.body
; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX256-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm1
; AVX256-NEXT:    vpmaddwd (%rdi,%rcx,2), %xmm1, %xmm1
; AVX256-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
; AVX256-NEXT:    addq $8, %rcx
; AVX256-NEXT:    cmpq %rcx, %rax
; AVX256-NEXT:    jne .LBB1_1
; AVX256-NEXT:  # %bb.2: # %middle.block
; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vmovd %xmm0, %eax
; AVX256-NEXT:    vzeroupper
; AVX256-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <8 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i16, i16* %0, i64 %index
  %5 = bitcast i16* %4 to <8 x i16>*
  %wide.load = load <8 x i16>, <8 x i16>* %5, align 2
  %6 = sext <8 x i16> %wide.load to <8 x i32>
  %7 = getelementptr inbounds i16, i16* %1, i64 %index
  %8 = bitcast i16* %7 to <8 x i16>*
  %wide.load14 = load <8 x i16>, <8 x i16>* %8, align 2
  %9 = sext <8 x i16> %wide.load14 to <8 x i32>
  %10 = mul nsw <8 x i32> %9, %6
  %11 = add nsw <8 x i32> %10, %vec.phi
  %index.next = add i64 %index, 8
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf = shufflevector <8 x i32> %11, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx = add <8 x i32> %11, %rdx.shuf
  %rdx.shuf15 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx16 = add <8 x i32> %bin.rdx, %rdx.shuf15
  %rdx.shuf17 = shufflevector <8 x i32> %bin.rdx16, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <8 x i32> %bin.rdx16, %rdx.shuf17
  %13 = extractelement <8 x i32> %bin.rdx18, i32 0
  ret i32 %13
}

define i32 @_Z10test_shortPsS_i_512(i16* nocapture readonly, i16* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: _Z10test_shortPsS_i_512:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    pxor %xmm2, %xmm2
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB2_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm3
; SSE2-NEXT:    movdqu 16(%rdi,%rcx,2), %xmm4
; SSE2-NEXT:    movdqu (%rsi,%rcx,2), %xmm5
; SSE2-NEXT:    pmaddwd %xmm3, %xmm5
; SSE2-NEXT:    paddd %xmm5, %xmm2
; SSE2-NEXT:    movdqu 16(%rsi,%rcx,2), %xmm3
; SSE2-NEXT:    pmaddwd %xmm4, %xmm3
; SSE2-NEXT:    paddd %xmm3, %xmm1
; SSE2-NEXT:    addq $16, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB2_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm0, %xmm2
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    paddd %xmm2, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: _Z10test_shortPsS_i_512:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %edx, %eax
; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    xorl %ecx, %ecx
; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB2_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm2
; AVX1-NEXT:    vmovdqu 16(%rsi,%rcx,2), %xmm3
; AVX1-NEXT:    vpmaddwd (%rdi,%rcx,2), %xmm2, %xmm2
; AVX1-NEXT:    vpmaddwd 16(%rdi,%rcx,2), %xmm3, %xmm3
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT:    vpaddd %xmm4, %xmm3, %xmm3
; AVX1-NEXT:    vpaddd %xmm1, %xmm2, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm1, %ymm1
; AVX1-NEXT:    addq $16, %rcx
; AVX1-NEXT:    cmpq %rcx, %rax
; AVX1-NEXT:    jne .LBB2_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT:    vpaddd %xmm3, %xmm2, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: _Z10test_shortPsS_i_512:
; AVX2:       # %bb.0: # %entry
; AVX2-NEXT:    movl %edx, %eax
; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX2-NEXT:    xorl %ecx, %ecx
; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT:    .p2align 4, 0x90
; AVX2-NEXT:  .LBB2_1: # %vector.body
; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX2-NEXT:    vmovdqu (%rsi,%rcx,2), %ymm2
; AVX2-NEXT:    vpmaddwd (%rdi,%rcx,2), %ymm2, %ymm2
; AVX2-NEXT:    vpaddd %ymm1, %ymm2, %ymm1
; AVX2-NEXT:    addq $16, %rcx
; AVX2-NEXT:    cmpq %rcx, %rax
; AVX2-NEXT:    jne .LBB2_1
; AVX2-NEXT:  # %bb.2: # %middle.block
; AVX2-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vmovd %xmm0, %eax
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512-LABEL: _Z10test_shortPsS_i_512:
; AVX512:       # %bb.0: # %entry
; AVX512-NEXT:    movl %edx, %eax
; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX512-NEXT:    xorl %ecx, %ecx
; AVX512-NEXT:    .p2align 4, 0x90
; AVX512-NEXT:  .LBB2_1: # %vector.body
; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX512-NEXT:    vmovdqu (%rsi,%rcx,2), %ymm1
; AVX512-NEXT:    vpmaddwd (%rdi,%rcx,2), %ymm1, %ymm1
; AVX512-NEXT:    vpaddd %zmm0, %zmm1, %zmm0
; AVX512-NEXT:    addq $16, %rcx
; AVX512-NEXT:    cmpq %rcx, %rax
; AVX512-NEXT:    jne .LBB2_1
; AVX512-NEXT:  # %bb.2: # %middle.block
; AVX512-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
; AVX512-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; AVX512-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vmovd %xmm0, %eax
; AVX512-NEXT:    vzeroupper
; AVX512-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <16 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i16, i16* %0, i64 %index
  %5 = bitcast i16* %4 to <16 x i16>*
  %wide.load = load <16 x i16>, <16 x i16>* %5, align 2
  %6 = sext <16 x i16> %wide.load to <16 x i32>
  %7 = getelementptr inbounds i16, i16* %1, i64 %index
  %8 = bitcast i16* %7 to <16 x i16>*
  %wide.load14 = load <16 x i16>, <16 x i16>* %8, align 2
  %9 = sext <16 x i16> %wide.load14 to <16 x i32>
  %10 = mul nsw <16 x i32> %9, %6
  %11 = add nsw <16 x i32> %10, %vec.phi
  %index.next = add i64 %index, 16
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf1 = shufflevector <16 x i32> %11, <16 x i32> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx1 = add <16 x i32> %11, %rdx.shuf1
  %rdx.shuf = shufflevector <16 x i32> %bin.rdx1, <16 x i32> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx = add <16 x i32> %bin.rdx1, %rdx.shuf
  %rdx.shuf15 = shufflevector <16 x i32> %bin.rdx, <16 x i32> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx16 = add <16 x i32> %bin.rdx, %rdx.shuf15
  %rdx.shuf17 = shufflevector <16 x i32> %bin.rdx16, <16 x i32> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <16 x i32> %bin.rdx16, %rdx.shuf17
  %13 = extractelement <16 x i32> %bin.rdx18, i32 0
  ret i32 %13
}

define i32 @_Z10test_shortPsS_i_1024(i16* nocapture readonly, i16* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: _Z10test_shortPsS_i_1024:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm8, %xmm8
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    pxor %xmm2, %xmm2
; SSE2-NEXT:    pxor %xmm4, %xmm4
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    pxor %xmm3, %xmm3
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB3_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm5
; SSE2-NEXT:    movdqu 16(%rdi,%rcx,2), %xmm6
; SSE2-NEXT:    movdqu 32(%rdi,%rcx,2), %xmm7
; SSE2-NEXT:    movdqu 48(%rdi,%rcx,2), %xmm9
; SSE2-NEXT:    movdqu (%rsi,%rcx,2), %xmm0
; SSE2-NEXT:    pmaddwd %xmm5, %xmm0
; SSE2-NEXT:    paddd %xmm0, %xmm2
; SSE2-NEXT:    movdqu 16(%rsi,%rcx,2), %xmm0
; SSE2-NEXT:    pmaddwd %xmm6, %xmm0
; SSE2-NEXT:    paddd %xmm0, %xmm4
; SSE2-NEXT:    movdqu 32(%rsi,%rcx,2), %xmm0
; SSE2-NEXT:    pmaddwd %xmm7, %xmm0
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movdqu 48(%rsi,%rcx,2), %xmm0
; SSE2-NEXT:    pmaddwd %xmm9, %xmm0
; SSE2-NEXT:    paddd %xmm0, %xmm3
; SSE2-NEXT:    addq $16, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB3_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm8, %xmm4
; SSE2-NEXT:    paddd %xmm8, %xmm3
; SSE2-NEXT:    paddd %xmm4, %xmm3
; SSE2-NEXT:    paddd %xmm8, %xmm2
; SSE2-NEXT:    paddd %xmm8, %xmm1
; SSE2-NEXT:    paddd %xmm3, %xmm1
; SSE2-NEXT:    paddd %xmm2, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: _Z10test_shortPsS_i_1024:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %edx, %eax
; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    xorl %ecx, %ecx
; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB3_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm3
; AVX1-NEXT:    vmovdqu 16(%rsi,%rcx,2), %xmm4
; AVX1-NEXT:    vmovdqu 32(%rsi,%rcx,2), %xmm5
; AVX1-NEXT:    vmovdqu 48(%rsi,%rcx,2), %xmm6
; AVX1-NEXT:    vpmaddwd (%rdi,%rcx,2), %xmm3, %xmm3
; AVX1-NEXT:    vpmaddwd 16(%rdi,%rcx,2), %xmm4, %xmm4
; AVX1-NEXT:    vpmaddwd 32(%rdi,%rcx,2), %xmm5, %xmm5
; AVX1-NEXT:    vpmaddwd 48(%rdi,%rcx,2), %xmm6, %xmm6
; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm7
; AVX1-NEXT:    vpaddd %xmm7, %xmm6, %xmm6
; AVX1-NEXT:    vpaddd %xmm2, %xmm5, %xmm2
; AVX1-NEXT:    vinsertf128 $1, %xmm6, %ymm2, %ymm2
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm5
; AVX1-NEXT:    vpaddd %xmm5, %xmm4, %xmm4
; AVX1-NEXT:    vpaddd %xmm1, %xmm3, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm1, %ymm1
; AVX1-NEXT:    addq $16, %rcx
; AVX1-NEXT:    cmpq %rcx, %rax
; AVX1-NEXT:    jne .LBB3_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vpaddd %xmm0, %xmm2, %xmm3
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm5
; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT:    vpaddd %xmm5, %xmm2, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm5, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm4, %xmm2
; AVX1-NEXT:    vpaddd %xmm3, %xmm0, %xmm0
; AVX1-NEXT:    vpaddd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: _Z10test_shortPsS_i_1024:
; AVX2:       # %bb.0: # %entry
; AVX2-NEXT:    movl %edx, %eax
; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX2-NEXT:    xorl %ecx, %ecx
; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    .p2align 4, 0x90
; AVX2-NEXT:  .LBB3_1: # %vector.body
; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX2-NEXT:    vmovdqu (%rsi,%rcx,2), %ymm3
; AVX2-NEXT:    vmovdqu 32(%rsi,%rcx,2), %ymm4
; AVX2-NEXT:    vpmaddwd (%rdi,%rcx,2), %ymm3, %ymm3
; AVX2-NEXT:    vpaddd %ymm1, %ymm3, %ymm1
; AVX2-NEXT:    vpmaddwd 32(%rdi,%rcx,2), %ymm4, %ymm3
; AVX2-NEXT:    vpaddd %ymm2, %ymm3, %ymm2
; AVX2-NEXT:    addq $16, %rcx
; AVX2-NEXT:    cmpq %rcx, %rax
; AVX2-NEXT:    jne .LBB3_1
; AVX2-NEXT:  # %bb.2: # %middle.block
; AVX2-NEXT:    vpaddd %ymm0, %ymm1, %ymm1
; AVX2-NEXT:    vpaddd %ymm0, %ymm2, %ymm0
; AVX2-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vmovd %xmm0, %eax
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: _Z10test_shortPsS_i_1024:
; AVX512F:       # %bb.0: # %entry
; AVX512F-NEXT:    movl %edx, %eax
; AVX512F-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX512F-NEXT:    xorl %ecx, %ecx
; AVX512F-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT:    .p2align 4, 0x90
; AVX512F-NEXT:  .LBB3_1: # %vector.body
; AVX512F-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX512F-NEXT:    vmovdqu (%rsi,%rcx,2), %ymm2
; AVX512F-NEXT:    vmovdqu 32(%rsi,%rcx,2), %ymm3
; AVX512F-NEXT:    vpmaddwd 32(%rdi,%rcx,2), %ymm3, %ymm3
; AVX512F-NEXT:    vpmaddwd (%rdi,%rcx,2), %ymm2, %ymm2
; AVX512F-NEXT:    vinserti64x4 $1, %ymm3, %zmm2, %zmm2
; AVX512F-NEXT:    vpaddd %zmm1, %zmm2, %zmm1
; AVX512F-NEXT:    addq $16, %rcx
; AVX512F-NEXT:    cmpq %rcx, %rax
; AVX512F-NEXT:    jne .LBB3_1
; AVX512F-NEXT:  # %bb.2: # %middle.block
; AVX512F-NEXT:    vpaddd %zmm0, %zmm1, %zmm0
; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
; AVX512F-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512F-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX512F-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512F-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX512F-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512F-NEXT:    vmovd %xmm0, %eax
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: _Z10test_shortPsS_i_1024:
; AVX512BW:       # %bb.0: # %entry
; AVX512BW-NEXT:    movl %edx, %eax
; AVX512BW-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX512BW-NEXT:    xorl %ecx, %ecx
; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512BW-NEXT:    .p2align 4, 0x90
; AVX512BW-NEXT:  .LBB3_1: # %vector.body
; AVX512BW-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX512BW-NEXT:    vmovdqu64 (%rsi,%rcx,2), %zmm2
; AVX512BW-NEXT:    vpmaddwd (%rdi,%rcx,2), %zmm2, %zmm2
; AVX512BW-NEXT:    vpaddd %zmm1, %zmm2, %zmm1
; AVX512BW-NEXT:    addq $16, %rcx
; AVX512BW-NEXT:    cmpq %rcx, %rax
; AVX512BW-NEXT:    jne .LBB3_1
; AVX512BW-NEXT:  # %bb.2: # %middle.block
; AVX512BW-NEXT:    vpaddd %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX512BW-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX512BW-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT:    vmovd %xmm0, %eax
; AVX512BW-NEXT:    vzeroupper
; AVX512BW-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <32 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i16, i16* %0, i64 %index
  %5 = bitcast i16* %4 to <32 x i16>*
  %wide.load = load <32 x i16>, <32 x i16>* %5, align 2
  %6 = sext <32 x i16> %wide.load to <32 x i32>
  %7 = getelementptr inbounds i16, i16* %1, i64 %index
  %8 = bitcast i16* %7 to <32 x i16>*
  %wide.load14 = load <32 x i16>, <32 x i16>* %8, align 2
  %9 = sext <32 x i16> %wide.load14 to <32 x i32>
  %10 = mul nsw <32 x i32> %9, %6
  %11 = add nsw <32 x i32> %10, %vec.phi
  %index.next = add i64 %index, 16
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf2 = shufflevector <32 x i32> %11, <32 x i32> undef, <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx2 = add <32 x i32> %11, %rdx.shuf2
  %rdx.shuf1 = shufflevector <32 x i32> %bin.rdx2, <32 x i32> undef, <32 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx1 = add <32 x i32> %bin.rdx2, %rdx.shuf1
  %rdx.shuf = shufflevector <32 x i32> %bin.rdx1, <32 x i32> undef, <32 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx = add <32 x i32> %bin.rdx1, %rdx.shuf
  %rdx.shuf15 = shufflevector <32 x i32> %bin.rdx, <32 x i32> undef, <32 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx16 = add <32 x i32> %bin.rdx, %rdx.shuf15
  %rdx.shuf17 = shufflevector <32 x i32> %bin.rdx16, <32 x i32> undef, <32 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <32 x i32> %bin.rdx16, %rdx.shuf17
  %13 = extractelement <32 x i32> %bin.rdx18, i32 0
  ret i32 %13
}

define i32 @_Z9test_charPcS_i_128(i8* nocapture readonly, i8* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: _Z9test_charPcS_i_128:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB4_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm1
; SSE2-NEXT:    psraw $8, %xmm2
; SSE2-NEXT:    pmullw %xmm1, %xmm2
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSE2-NEXT:    psrad $16, %xmm1
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    addq $16, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB4_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[1,1,1,1]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    movd %xmm0, %eax
; SSE2-NEXT:    retq
;
; AVX-LABEL: _Z9test_charPcS_i_128:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    movl %edx, %eax
; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX-NEXT:    xorl %ecx, %ecx
; AVX-NEXT:    .p2align 4, 0x90
; AVX-NEXT:  .LBB4_1: # %vector.body
; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX-NEXT:    vpmovsxbd (%rdi,%rcx), %xmm1
; AVX-NEXT:    vpmovsxbd (%rsi,%rcx), %xmm2
; AVX-NEXT:    vpmulld %xmm1, %xmm2, %xmm1
; AVX-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
; AVX-NEXT:    addq $16, %rcx
; AVX-NEXT:    cmpq %rcx, %rax
; AVX-NEXT:    jne .LBB4_1
; AVX-NEXT:  # %bb.2: # %middle.block
; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vmovd %xmm0, %eax
; AVX-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <4 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i8, i8* %0, i64 %index
  %5 = bitcast i8* %4 to <4 x i8>*
  %wide.load = load <4 x i8>, <4 x i8>* %5, align 1
  %6 = sext <4 x i8> %wide.load to <4 x i32>
  %7 = getelementptr inbounds i8, i8* %1, i64 %index
  %8 = bitcast i8* %7 to <4 x i8>*
  %wide.load14 = load <4 x i8>, <4 x i8>* %8, align 1
  %9 = sext <4 x i8> %wide.load14 to <4 x i32>
  %10 = mul nsw <4 x i32> %9, %6
  %11 = add nsw <4 x i32> %10, %vec.phi
  %index.next = add i64 %index, 16
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf17 = shufflevector <4 x i32> %11, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
  %bin.rdx18 = add <4 x i32> %11, %rdx.shuf17
  %rdx.shuf19 = shufflevector <4 x i32> %bin.rdx18, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
  %bin.rdx20 = add <4 x i32> %bin.rdx18, %rdx.shuf19
  %13 = extractelement <4 x i32> %bin.rdx20, i32 0
  ret i32 %13
}

define i32 @_Z9test_charPcS_i_256(i8* nocapture readonly, i8* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: _Z9test_charPcS_i_256:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB5_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movq {{.*#+}} xmm2 = mem[0],zero
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    movq {{.*#+}} xmm3 = mem[0],zero
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm2
; SSE2-NEXT:    psraw $8, %xmm3
; SSE2-NEXT:    pmaddwd %xmm2, %xmm3
; SSE2-NEXT:    paddd %xmm3, %xmm1
; SSE2-NEXT:    addq $16, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB5_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: _Z9test_charPcS_i_256:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %edx, %eax
; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    xorl %ecx, %ecx
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB5_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vpmovsxbw (%rdi,%rcx), %xmm1
; AVX1-NEXT:    vpmovsxbw (%rsi,%rcx), %xmm2
; AVX1-NEXT:    vpmaddwd %xmm1, %xmm2, %xmm1
; AVX1-NEXT:    vpaddd %xmm0, %xmm1, %xmm1
; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
; AVX1-NEXT:    addq $16, %rcx
; AVX1-NEXT:    cmpq %rcx, %rax
; AVX1-NEXT:    jne .LBB5_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX256-LABEL: _Z9test_charPcS_i_256:
; AVX256:       # %bb.0: # %entry
; AVX256-NEXT:    movl %edx, %eax
; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX256-NEXT:    xorl %ecx, %ecx
; AVX256-NEXT:    .p2align 4, 0x90
; AVX256-NEXT:  .LBB5_1: # %vector.body
; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX256-NEXT:    vpmovsxbw (%rdi,%rcx), %xmm1
; AVX256-NEXT:    vpmovsxbw (%rsi,%rcx), %xmm2
; AVX256-NEXT:    vpmaddwd %xmm1, %xmm2, %xmm1
; AVX256-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
; AVX256-NEXT:    addq $16, %rcx
; AVX256-NEXT:    cmpq %rcx, %rax
; AVX256-NEXT:    jne .LBB5_1
; AVX256-NEXT:  # %bb.2: # %middle.block
; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vmovd %xmm0, %eax
; AVX256-NEXT:    vzeroupper
; AVX256-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <8 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i8, i8* %0, i64 %index
  %5 = bitcast i8* %4 to <8 x i8>*
  %wide.load = load <8 x i8>, <8 x i8>* %5, align 1
  %6 = sext <8 x i8> %wide.load to <8 x i32>
  %7 = getelementptr inbounds i8, i8* %1, i64 %index
  %8 = bitcast i8* %7 to <8 x i8>*
  %wide.load14 = load <8 x i8>, <8 x i8>* %8, align 1
  %9 = sext <8 x i8> %wide.load14 to <8 x i32>
  %10 = mul nsw <8 x i32> %9, %6
  %11 = add nsw <8 x i32> %10, %vec.phi
  %index.next = add i64 %index, 16
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf15 = shufflevector <8 x i32> %11, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx16 = add <8 x i32> %11, %rdx.shuf15
  %rdx.shuf17 = shufflevector <8 x i32> %bin.rdx16, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <8 x i32> %bin.rdx16, %rdx.shuf17
  %rdx.shuf19 = shufflevector <8 x i32> %bin.rdx18, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx20 = add <8 x i32> %bin.rdx18, %rdx.shuf19
  %13 = extractelement <8 x i32> %bin.rdx20, i32 0
  ret i32 %13
}

define i32 @_Z9test_charPcS_i_512(i8* nocapture readonly, i8* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: _Z9test_charPcS_i_512:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    pxor %xmm2, %xmm2
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB6_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movdqu (%rdi,%rcx), %xmm3
; SSE2-NEXT:    movdqu (%rsi,%rcx), %xmm4
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1],xmm5[2],xmm3[2],xmm5[3],xmm3[3],xmm5[4],xmm3[4],xmm5[5],xmm3[5],xmm5[6],xmm3[6],xmm5[7],xmm3[7]
; SSE2-NEXT:    psraw $8, %xmm5
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm4[0],xmm6[1],xmm4[1],xmm6[2],xmm4[2],xmm6[3],xmm4[3],xmm6[4],xmm4[4],xmm6[5],xmm4[5],xmm6[6],xmm4[6],xmm6[7],xmm4[7]
; SSE2-NEXT:    psraw $8, %xmm6
; SSE2-NEXT:    pmaddwd %xmm5, %xmm6
; SSE2-NEXT:    paddd %xmm6, %xmm2
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm3 = xmm3[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm3
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm4 = xmm4[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm4
; SSE2-NEXT:    pmaddwd %xmm3, %xmm4
; SSE2-NEXT:    paddd %xmm4, %xmm1
; SSE2-NEXT:    addq $16, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB6_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm0, %xmm2
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    paddd %xmm2, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: _Z9test_charPcS_i_512:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %edx, %eax
; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    xorl %ecx, %ecx
; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB6_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vpmovsxbw 8(%rdi,%rcx), %xmm2
; AVX1-NEXT:    vpmovsxbw (%rdi,%rcx), %xmm3
; AVX1-NEXT:    vpmovsxbw 8(%rsi,%rcx), %xmm4
; AVX1-NEXT:    vpmaddwd %xmm2, %xmm4, %xmm2
; AVX1-NEXT:    vpmovsxbw (%rsi,%rcx), %xmm4
; AVX1-NEXT:    vpmaddwd %xmm3, %xmm4, %xmm3
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT:    vpaddd %xmm4, %xmm2, %xmm2
; AVX1-NEXT:    vpaddd %xmm1, %xmm3, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX1-NEXT:    addq $16, %rcx
; AVX1-NEXT:    cmpq %rcx, %rax
; AVX1-NEXT:    jne .LBB6_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT:    vpaddd %xmm3, %xmm2, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: _Z9test_charPcS_i_512:
; AVX2:       # %bb.0: # %entry
; AVX2-NEXT:    movl %edx, %eax
; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX2-NEXT:    xorl %ecx, %ecx
; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT:    .p2align 4, 0x90
; AVX2-NEXT:  .LBB6_1: # %vector.body
; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX2-NEXT:    vpmovsxbw (%rdi,%rcx), %ymm2
; AVX2-NEXT:    vpmovsxbw (%rsi,%rcx), %ymm3
; AVX2-NEXT:    vpmaddwd %ymm2, %ymm3, %ymm2
; AVX2-NEXT:    vpaddd %ymm1, %ymm2, %ymm1
; AVX2-NEXT:    addq $16, %rcx
; AVX2-NEXT:    cmpq %rcx, %rax
; AVX2-NEXT:    jne .LBB6_1
; AVX2-NEXT:  # %bb.2: # %middle.block
; AVX2-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vmovd %xmm0, %eax
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512-LABEL: _Z9test_charPcS_i_512:
; AVX512:       # %bb.0: # %entry
; AVX512-NEXT:    movl %edx, %eax
; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX512-NEXT:    xorl %ecx, %ecx
; AVX512-NEXT:    .p2align 4, 0x90
; AVX512-NEXT:  .LBB6_1: # %vector.body
; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX512-NEXT:    vpmovsxbw (%rdi,%rcx), %ymm1
; AVX512-NEXT:    vpmovsxbw (%rsi,%rcx), %ymm2
; AVX512-NEXT:    vpmaddwd %ymm1, %ymm2, %ymm1
; AVX512-NEXT:    vpaddd %zmm0, %zmm1, %zmm0
; AVX512-NEXT:    addq $16, %rcx
; AVX512-NEXT:    cmpq %rcx, %rax
; AVX512-NEXT:    jne .LBB6_1
; AVX512-NEXT:  # %bb.2: # %middle.block
; AVX512-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
; AVX512-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; AVX512-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vmovd %xmm0, %eax
; AVX512-NEXT:    vzeroupper
; AVX512-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <16 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i8, i8* %0, i64 %index
  %5 = bitcast i8* %4 to <16 x i8>*
  %wide.load = load <16 x i8>, <16 x i8>* %5, align 1
  %6 = sext <16 x i8> %wide.load to <16 x i32>
  %7 = getelementptr inbounds i8, i8* %1, i64 %index
  %8 = bitcast i8* %7 to <16 x i8>*
  %wide.load14 = load <16 x i8>, <16 x i8>* %8, align 1
  %9 = sext <16 x i8> %wide.load14 to <16 x i32>
  %10 = mul nsw <16 x i32> %9, %6
  %11 = add nsw <16 x i32> %10, %vec.phi
  %index.next = add i64 %index, 16
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf = shufflevector <16 x i32> %11, <16 x i32> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx = add <16 x i32> %11, %rdx.shuf
  %rdx.shuf15 = shufflevector <16 x i32> %bin.rdx, <16 x i32> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx16 = add <16 x i32> %bin.rdx, %rdx.shuf15
  %rdx.shuf17 = shufflevector <16 x i32> %bin.rdx16, <16 x i32> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <16 x i32> %bin.rdx16, %rdx.shuf17
  %rdx.shuf19 = shufflevector <16 x i32> %bin.rdx18, <16 x i32> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx20 = add <16 x i32> %bin.rdx18, %rdx.shuf19
  %13 = extractelement <16 x i32> %bin.rdx20, i32 0
  ret i32 %13
}

define i32 @_Z9test_charPcS_i_1024(i8* nocapture readonly, i8* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: _Z9test_charPcS_i_1024:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm8, %xmm8
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    pxor %xmm2, %xmm2
; SSE2-NEXT:    pxor %xmm4, %xmm4
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    pxor %xmm3, %xmm3
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB7_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movdqu (%rdi,%rcx), %xmm7
; SSE2-NEXT:    movdqu 16(%rdi,%rcx), %xmm10
; SSE2-NEXT:    movdqu (%rsi,%rcx), %xmm0
; SSE2-NEXT:    movdqu 16(%rsi,%rcx), %xmm9
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm7[0],xmm5[1],xmm7[1],xmm5[2],xmm7[2],xmm5[3],xmm7[3],xmm5[4],xmm7[4],xmm5[5],xmm7[5],xmm5[6],xmm7[6],xmm5[7],xmm7[7]
; SSE2-NEXT:    psraw $8, %xmm5
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm0[0],xmm6[1],xmm0[1],xmm6[2],xmm0[2],xmm6[3],xmm0[3],xmm6[4],xmm0[4],xmm6[5],xmm0[5],xmm6[6],xmm0[6],xmm6[7],xmm0[7]
; SSE2-NEXT:    psraw $8, %xmm6
; SSE2-NEXT:    pmaddwd %xmm5, %xmm6
; SSE2-NEXT:    paddd %xmm6, %xmm2
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm5 = xmm5[8],xmm7[8],xmm5[9],xmm7[9],xmm5[10],xmm7[10],xmm5[11],xmm7[11],xmm5[12],xmm7[12],xmm5[13],xmm7[13],xmm5[14],xmm7[14],xmm5[15],xmm7[15]
; SSE2-NEXT:    psraw $8, %xmm5
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm0
; SSE2-NEXT:    pmaddwd %xmm5, %xmm0
; SSE2-NEXT:    paddd %xmm0, %xmm4
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm10[0],xmm0[1],xmm10[1],xmm0[2],xmm10[2],xmm0[3],xmm10[3],xmm0[4],xmm10[4],xmm0[5],xmm10[5],xmm0[6],xmm10[6],xmm0[7],xmm10[7]
; SSE2-NEXT:    psraw $8, %xmm0
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm9[0],xmm5[1],xmm9[1],xmm5[2],xmm9[2],xmm5[3],xmm9[3],xmm5[4],xmm9[4],xmm5[5],xmm9[5],xmm5[6],xmm9[6],xmm5[7],xmm9[7]
; SSE2-NEXT:    psraw $8, %xmm5
; SSE2-NEXT:    pmaddwd %xmm0, %xmm5
; SSE2-NEXT:    paddd %xmm5, %xmm1
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm0 = xmm0[8],xmm10[8],xmm0[9],xmm10[9],xmm0[10],xmm10[10],xmm0[11],xmm10[11],xmm0[12],xmm10[12],xmm0[13],xmm10[13],xmm0[14],xmm10[14],xmm0[15],xmm10[15]
; SSE2-NEXT:    psraw $8, %xmm0
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm5 = xmm5[8],xmm9[8],xmm5[9],xmm9[9],xmm5[10],xmm9[10],xmm5[11],xmm9[11],xmm5[12],xmm9[12],xmm5[13],xmm9[13],xmm5[14],xmm9[14],xmm5[15],xmm9[15]
; SSE2-NEXT:    psraw $8, %xmm5
; SSE2-NEXT:    pmaddwd %xmm0, %xmm5
; SSE2-NEXT:    paddd %xmm5, %xmm3
; SSE2-NEXT:    addq $32, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB7_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm8, %xmm4
; SSE2-NEXT:    paddd %xmm8, %xmm3
; SSE2-NEXT:    paddd %xmm4, %xmm3
; SSE2-NEXT:    paddd %xmm8, %xmm2
; SSE2-NEXT:    paddd %xmm8, %xmm1
; SSE2-NEXT:    paddd %xmm3, %xmm1
; SSE2-NEXT:    paddd %xmm2, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: _Z9test_charPcS_i_1024:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %edx, %eax
; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    xorl %ecx, %ecx
; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB7_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vpmovsxbw 24(%rdi,%rcx), %xmm3
; AVX1-NEXT:    vpmovsxbw 16(%rdi,%rcx), %xmm4
; AVX1-NEXT:    vpmovsxbw 8(%rdi,%rcx), %xmm5
; AVX1-NEXT:    vpmovsxbw (%rdi,%rcx), %xmm6
; AVX1-NEXT:    vpmovsxbw 24(%rsi,%rcx), %xmm7
; AVX1-NEXT:    vpmaddwd %xmm3, %xmm7, %xmm3
; AVX1-NEXT:    vpmovsxbw 16(%rsi,%rcx), %xmm7
; AVX1-NEXT:    vpmaddwd %xmm4, %xmm7, %xmm4
; AVX1-NEXT:    vpmovsxbw 8(%rsi,%rcx), %xmm7
; AVX1-NEXT:    vpmaddwd %xmm5, %xmm7, %xmm5
; AVX1-NEXT:    vpmovsxbw (%rsi,%rcx), %xmm7
; AVX1-NEXT:    vpmaddwd %xmm6, %xmm7, %xmm6
; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm7
; AVX1-NEXT:    vpaddd %xmm7, %xmm3, %xmm3
; AVX1-NEXT:    vpaddd %xmm2, %xmm4, %xmm2
; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm2, %ymm2
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT:    vpaddd %xmm3, %xmm5, %xmm3
; AVX1-NEXT:    vpaddd %xmm1, %xmm6, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm1, %ymm1
; AVX1-NEXT:    addq $32, %rcx
; AVX1-NEXT:    cmpq %rcx, %rax
; AVX1-NEXT:    jne .LBB7_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vpaddd %xmm0, %xmm2, %xmm3
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm5
; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT:    vpaddd %xmm5, %xmm2, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm5, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm4, %xmm2
; AVX1-NEXT:    vpaddd %xmm3, %xmm0, %xmm0
; AVX1-NEXT:    vpaddd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: _Z9test_charPcS_i_1024:
; AVX2:       # %bb.0: # %entry
; AVX2-NEXT:    movl %edx, %eax
; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX2-NEXT:    xorl %ecx, %ecx
; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    .p2align 4, 0x90
; AVX2-NEXT:  .LBB7_1: # %vector.body
; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX2-NEXT:    vpmovsxbw 16(%rdi,%rcx), %ymm3
; AVX2-NEXT:    vpmovsxbw (%rdi,%rcx), %ymm4
; AVX2-NEXT:    vpmovsxbw 16(%rsi,%rcx), %ymm5
; AVX2-NEXT:    vpmaddwd %ymm3, %ymm5, %ymm3
; AVX2-NEXT:    vpaddd %ymm2, %ymm3, %ymm2
; AVX2-NEXT:    vpmovsxbw (%rsi,%rcx), %ymm3
; AVX2-NEXT:    vpmaddwd %ymm4, %ymm3, %ymm3
; AVX2-NEXT:    vpaddd %ymm1, %ymm3, %ymm1
; AVX2-NEXT:    addq $32, %rcx
; AVX2-NEXT:    cmpq %rcx, %rax
; AVX2-NEXT:    jne .LBB7_1
; AVX2-NEXT:  # %bb.2: # %middle.block
; AVX2-NEXT:    vpaddd %ymm0, %ymm1, %ymm1
; AVX2-NEXT:    vpaddd %ymm0, %ymm2, %ymm0
; AVX2-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vmovd %xmm0, %eax
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: _Z9test_charPcS_i_1024:
; AVX512F:       # %bb.0: # %entry
; AVX512F-NEXT:    movl %edx, %eax
; AVX512F-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX512F-NEXT:    xorl %ecx, %ecx
; AVX512F-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT:    .p2align 4, 0x90
; AVX512F-NEXT:  .LBB7_1: # %vector.body
; AVX512F-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX512F-NEXT:    vpmovsxbw (%rdi,%rcx), %ymm2
; AVX512F-NEXT:    vpmovsxbw 16(%rdi,%rcx), %ymm3
; AVX512F-NEXT:    vpmovsxbw (%rsi,%rcx), %ymm4
; AVX512F-NEXT:    vpmaddwd %ymm2, %ymm4, %ymm2
; AVX512F-NEXT:    vpmovsxbw 16(%rsi,%rcx), %ymm4
; AVX512F-NEXT:    vpmaddwd %ymm3, %ymm4, %ymm3
; AVX512F-NEXT:    vinserti64x4 $1, %ymm3, %zmm2, %zmm2
; AVX512F-NEXT:    vpaddd %zmm1, %zmm2, %zmm1
; AVX512F-NEXT:    addq $32, %rcx
; AVX512F-NEXT:    cmpq %rcx, %rax
; AVX512F-NEXT:    jne .LBB7_1
; AVX512F-NEXT:  # %bb.2: # %middle.block
; AVX512F-NEXT:    vpaddd %zmm0, %zmm1, %zmm0
; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
; AVX512F-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512F-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX512F-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512F-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX512F-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512F-NEXT:    vmovd %xmm0, %eax
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: _Z9test_charPcS_i_1024:
; AVX512BW:       # %bb.0: # %entry
; AVX512BW-NEXT:    movl %edx, %eax
; AVX512BW-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX512BW-NEXT:    xorl %ecx, %ecx
; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512BW-NEXT:    .p2align 4, 0x90
; AVX512BW-NEXT:  .LBB7_1: # %vector.body
; AVX512BW-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX512BW-NEXT:    vpmovsxbw (%rdi,%rcx), %zmm2
; AVX512BW-NEXT:    vpmovsxbw (%rsi,%rcx), %zmm3
; AVX512BW-NEXT:    vpmaddwd %zmm2, %zmm3, %zmm2
; AVX512BW-NEXT:    vpaddd %zmm1, %zmm2, %zmm1
; AVX512BW-NEXT:    addq $32, %rcx
; AVX512BW-NEXT:    cmpq %rcx, %rax
; AVX512BW-NEXT:    jne .LBB7_1
; AVX512BW-NEXT:  # %bb.2: # %middle.block
; AVX512BW-NEXT:    vpaddd %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX512BW-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX512BW-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT:    vmovd %xmm0, %eax
; AVX512BW-NEXT:    vzeroupper
; AVX512BW-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <32 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i8, i8* %0, i64 %index
  %5 = bitcast i8* %4 to <32 x i8>*
  %wide.load = load <32 x i8>, <32 x i8>* %5, align 1
  %6 = sext <32 x i8> %wide.load to <32 x i32>
  %7 = getelementptr inbounds i8, i8* %1, i64 %index
  %8 = bitcast i8* %7 to <32 x i8>*
  %wide.load14 = load <32 x i8>, <32 x i8>* %8, align 1
  %9 = sext <32 x i8> %wide.load14 to <32 x i32>
  %10 = mul nsw <32 x i32> %9, %6
  %11 = add nsw <32 x i32> %10, %vec.phi
  %index.next = add i64 %index, 32
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf1 = shufflevector <32 x i32> %11, <32 x i32> undef, <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx1 = add <32 x i32> %11, %rdx.shuf1
  %rdx.shuf = shufflevector <32 x i32> %bin.rdx1, <32 x i32> undef, <32 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx = add <32 x i32> %bin.rdx1, %rdx.shuf
  %rdx.shuf15 = shufflevector <32 x i32> %bin.rdx, <32 x i32> undef, <32 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx32 = add <32 x i32> %bin.rdx, %rdx.shuf15
  %rdx.shuf17 = shufflevector <32 x i32> %bin.rdx32, <32 x i32> undef, <32 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <32 x i32> %bin.rdx32, %rdx.shuf17
  %rdx.shuf19 = shufflevector <32 x i32> %bin.rdx18, <32 x i32> undef, <32 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx20 = add <32 x i32> %bin.rdx18, %rdx.shuf19
  %13 = extractelement <32 x i32> %bin.rdx20, i32 0
  ret i32 %13
}

define i32 @test_unsigned_short_128(i16* nocapture readonly, i16* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: test_unsigned_short_128:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB8_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movq {{.*#+}} xmm1 = mem[0],zero
; SSE2-NEXT:    movq {{.*#+}} xmm2 = mem[0],zero
; SSE2-NEXT:    movdqa %xmm2, %xmm3
; SSE2-NEXT:    pmulhuw %xmm1, %xmm3
; SSE2-NEXT:    pmullw %xmm1, %xmm2
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
; SSE2-NEXT:    paddd %xmm2, %xmm0
; SSE2-NEXT:    addq $16, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB8_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[1,1,1,1]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    movd %xmm0, %eax
; SSE2-NEXT:    retq
;
; AVX-LABEL: test_unsigned_short_128:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    movl %edx, %eax
; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX-NEXT:    xorl %ecx, %ecx
; AVX-NEXT:    .p2align 4, 0x90
; AVX-NEXT:  .LBB8_1: # %vector.body
; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX-NEXT:    vpmovzxwd {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX-NEXT:    vpmovzxwd {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX-NEXT:    vpmulld %xmm1, %xmm2, %xmm1
; AVX-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
; AVX-NEXT:    addq $16, %rcx
; AVX-NEXT:    cmpq %rcx, %rax
; AVX-NEXT:    jne .LBB8_1
; AVX-NEXT:  # %bb.2: # %middle.block
; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vmovd %xmm0, %eax
; AVX-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <4 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i16, i16* %0, i64 %index
  %5 = bitcast i16* %4 to <4 x i16>*
  %wide.load = load <4 x i16>, <4 x i16>* %5, align 2
  %6 = zext <4 x i16> %wide.load to <4 x i32>
  %7 = getelementptr inbounds i16, i16* %1, i64 %index
  %8 = bitcast i16* %7 to <4 x i16>*
  %wide.load14 = load <4 x i16>, <4 x i16>* %8, align 2
  %9 = zext <4 x i16> %wide.load14 to <4 x i32>
  %10 = mul nsw <4 x i32> %9, %6
  %11 = add nsw <4 x i32> %10, %vec.phi
  %index.next = add i64 %index, 16
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf15 = shufflevector <4 x i32> %11, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
  %bin.rdx16 = add <4 x i32> %11, %rdx.shuf15
  %rdx.shuf17 = shufflevector <4 x i32> %bin.rdx16, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <4 x i32> %bin.rdx16, %rdx.shuf17
  %13 = extractelement <4 x i32> %bin.rdx18, i32 0
  ret i32 %13
}

define i32 @test_unsigned_short_256(i16* nocapture readonly, i16* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: test_unsigned_short_256:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB9_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm2
; SSE2-NEXT:    movdqu (%rsi,%rcx,2), %xmm3
; SSE2-NEXT:    movdqa %xmm3, %xmm4
; SSE2-NEXT:    pmulhuw %xmm2, %xmm4
; SSE2-NEXT:    pmullw %xmm2, %xmm3
; SSE2-NEXT:    movdqa %xmm3, %xmm2
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; SSE2-NEXT:    paddd %xmm2, %xmm0
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; SSE2-NEXT:    paddd %xmm3, %xmm1
; SSE2-NEXT:    addq $16, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB9_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[1,1,1,1]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    movd %xmm0, %eax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: test_unsigned_short_256:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %edx, %eax
; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    xorl %ecx, %ecx
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB9_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm1, %xmm3, %xmm1
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm2, %xmm3, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT:    vpaddd %xmm3, %xmm1, %xmm1
; AVX1-NEXT:    vpaddd %xmm0, %xmm2, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT:    addq $16, %rcx
; AVX1-NEXT:    cmpq %rcx, %rax
; AVX1-NEXT:    jne .LBB9_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX256-LABEL: test_unsigned_short_256:
; AVX256:       # %bb.0: # %entry
; AVX256-NEXT:    movl %edx, %eax
; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX256-NEXT:    xorl %ecx, %ecx
; AVX256-NEXT:    .p2align 4, 0x90
; AVX256-NEXT:  .LBB9_1: # %vector.body
; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX256-NEXT:    vpmovzxwd {{.*#+}} ymm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX256-NEXT:    vpmovzxwd {{.*#+}} ymm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX256-NEXT:    vpmulld %ymm1, %ymm2, %ymm1
; AVX256-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
; AVX256-NEXT:    addq $16, %rcx
; AVX256-NEXT:    cmpq %rcx, %rax
; AVX256-NEXT:    jne .LBB9_1
; AVX256-NEXT:  # %bb.2: # %middle.block
; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vmovd %xmm0, %eax
; AVX256-NEXT:    vzeroupper
; AVX256-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <8 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i16, i16* %0, i64 %index
  %5 = bitcast i16* %4 to <8 x i16>*
  %wide.load = load <8 x i16>, <8 x i16>* %5, align 2
  %6 = zext <8 x i16> %wide.load to <8 x i32>
  %7 = getelementptr inbounds i16, i16* %1, i64 %index
  %8 = bitcast i16* %7 to <8 x i16>*
  %wide.load14 = load <8 x i16>, <8 x i16>* %8, align 2
  %9 = zext <8 x i16> %wide.load14 to <8 x i32>
  %10 = mul nsw <8 x i32> %9, %6
  %11 = add nsw <8 x i32> %10, %vec.phi
  %index.next = add i64 %index, 16
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf = shufflevector <8 x i32> %11, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx = add <8 x i32> %11, %rdx.shuf
  %rdx.shuf15 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx16 = add <8 x i32> %bin.rdx, %rdx.shuf15
  %rdx.shuf17 = shufflevector <8 x i32> %bin.rdx16, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <8 x i32> %bin.rdx16, %rdx.shuf17
  %13 = extractelement <8 x i32> %bin.rdx18, i32 0
  ret i32 %13
}

define i32 @test_unsigned_short_512(i16* nocapture readonly, i16* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: test_unsigned_short_512:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    pxor %xmm3, %xmm3
; SSE2-NEXT:    pxor %xmm2, %xmm2
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB10_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm4
; SSE2-NEXT:    movdqu 16(%rdi,%rcx,2), %xmm8
; SSE2-NEXT:    movdqu (%rsi,%rcx,2), %xmm6
; SSE2-NEXT:    movdqu 16(%rsi,%rcx,2), %xmm7
; SSE2-NEXT:    movdqa %xmm6, %xmm5
; SSE2-NEXT:    pmulhuw %xmm4, %xmm5
; SSE2-NEXT:    pmullw %xmm4, %xmm6
; SSE2-NEXT:    movdqa %xmm6, %xmm4
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
; SSE2-NEXT:    paddd %xmm4, %xmm0
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm6 = xmm6[4],xmm5[4],xmm6[5],xmm5[5],xmm6[6],xmm5[6],xmm6[7],xmm5[7]
; SSE2-NEXT:    paddd %xmm6, %xmm1
; SSE2-NEXT:    movdqa %xmm7, %xmm4
; SSE2-NEXT:    pmulhuw %xmm8, %xmm4
; SSE2-NEXT:    pmullw %xmm8, %xmm7
; SSE2-NEXT:    movdqa %xmm7, %xmm5
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm5 = xmm5[0],xmm4[0],xmm5[1],xmm4[1],xmm5[2],xmm4[2],xmm5[3],xmm4[3]
; SSE2-NEXT:    paddd %xmm5, %xmm3
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm7 = xmm7[4],xmm4[4],xmm7[5],xmm4[5],xmm7[6],xmm4[6],xmm7[7],xmm4[7]
; SSE2-NEXT:    paddd %xmm7, %xmm2
; SSE2-NEXT:    addq $16, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB10_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm3, %xmm0
; SSE2-NEXT:    paddd %xmm2, %xmm1
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: test_unsigned_short_512:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %edx, %eax
; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    xorl %ecx, %ecx
; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB10_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm5 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm2, %xmm6, %xmm2
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm3, %xmm6, %xmm3
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm4, %xmm6, %xmm4
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm5, %xmm6, %xmm5
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm6
; AVX1-NEXT:    vpaddd %xmm6, %xmm2, %xmm2
; AVX1-NEXT:    vpaddd %xmm1, %xmm3, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm4, %xmm2
; AVX1-NEXT:    vpaddd %xmm0, %xmm5, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT:    addq $16, %rcx
; AVX1-NEXT:    cmpq %rcx, %rax
; AVX1-NEXT:    jne .LBB10_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT:    vpaddd %xmm3, %xmm2, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test_unsigned_short_512:
; AVX2:       # %bb.0: # %entry
; AVX2-NEXT:    movl %edx, %eax
; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX2-NEXT:    xorl %ecx, %ecx
; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT:    .p2align 4, 0x90
; AVX2-NEXT:  .LBB10_1: # %vector.body
; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmulld %ymm2, %ymm4, %ymm2
; AVX2-NEXT:    vpaddd %ymm1, %ymm2, %ymm1
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmulld %ymm3, %ymm2, %ymm2
; AVX2-NEXT:    vpaddd %ymm0, %ymm2, %ymm0
; AVX2-NEXT:    addq $16, %rcx
; AVX2-NEXT:    cmpq %rcx, %rax
; AVX2-NEXT:    jne .LBB10_1
; AVX2-NEXT:  # %bb.2: # %middle.block
; AVX2-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vmovd %xmm0, %eax
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512-LABEL: test_unsigned_short_512:
; AVX512:       # %bb.0: # %entry
; AVX512-NEXT:    movl %edx, %eax
; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX512-NEXT:    xorl %ecx, %ecx
; AVX512-NEXT:    .p2align 4, 0x90
; AVX512-NEXT:  .LBB10_1: # %vector.body
; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX512-NEXT:    vpmovzxwd {{.*#+}} zmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
; AVX512-NEXT:    vpmovzxwd {{.*#+}} zmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
; AVX512-NEXT:    vpmulld %zmm1, %zmm2, %zmm1
; AVX512-NEXT:    vpaddd %zmm0, %zmm1, %zmm0
; AVX512-NEXT:    addq $16, %rcx
; AVX512-NEXT:    cmpq %rcx, %rax
; AVX512-NEXT:    jne .LBB10_1
; AVX512-NEXT:  # %bb.2: # %middle.block
; AVX512-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
; AVX512-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; AVX512-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vmovd %xmm0, %eax
; AVX512-NEXT:    vzeroupper
; AVX512-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <16 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i16, i16* %0, i64 %index
  %5 = bitcast i16* %4 to <16 x i16>*
  %wide.load = load <16 x i16>, <16 x i16>* %5, align 2
  %6 = zext <16 x i16> %wide.load to <16 x i32>
  %7 = getelementptr inbounds i16, i16* %1, i64 %index
  %8 = bitcast i16* %7 to <16 x i16>*
  %wide.load14 = load <16 x i16>, <16 x i16>* %8, align 2
  %9 = zext <16 x i16> %wide.load14 to <16 x i32>
  %10 = mul nsw <16 x i32> %9, %6
  %11 = add nsw <16 x i32> %10, %vec.phi
  %index.next = add i64 %index, 16
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf1 = shufflevector <16 x i32> %11, <16 x i32> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx1 = add <16 x i32> %11, %rdx.shuf1
  %rdx.shuf = shufflevector <16 x i32> %bin.rdx1, <16 x i32> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx = add <16 x i32> %bin.rdx1, %rdx.shuf
  %rdx.shuf15 = shufflevector <16 x i32> %bin.rdx, <16 x i32> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx16 = add <16 x i32> %bin.rdx, %rdx.shuf15
  %rdx.shuf17 = shufflevector <16 x i32> %bin.rdx16, <16 x i32> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <16 x i32> %bin.rdx16, %rdx.shuf17
  %13 = extractelement <16 x i32> %bin.rdx18, i32 0
  ret i32 %13
}

define i32 @test_unsigned_short_1024(i16* nocapture readonly, i16* nocapture readonly, i32) local_unnamed_addr #0 {
; SSE2-LABEL: test_unsigned_short_1024:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm8, %xmm8
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    pxor %xmm3, %xmm3
; SSE2-NEXT:    pxor %xmm9, %xmm9
; SSE2-NEXT:    pxor %xmm10, %xmm10
; SSE2-NEXT:    pxor %xmm4, %xmm4
; SSE2-NEXT:    pxor %xmm6, %xmm6
; SSE2-NEXT:    pxor %xmm5, %xmm5
; SSE2-NEXT:    pxor %xmm7, %xmm7
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB11_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movdqu 48(%rdi,%rcx,2), %xmm0
; SSE2-NEXT:    movdqu 48(%rsi,%rcx,2), %xmm1
; SSE2-NEXT:    movdqa %xmm1, %xmm2
; SSE2-NEXT:    pmulhuw %xmm0, %xmm2
; SSE2-NEXT:    pmullw %xmm0, %xmm1
; SSE2-NEXT:    movdqa %xmm1, %xmm0
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE2-NEXT:    paddd %xmm0, %xmm7
; SSE2-NEXT:    movdqu 32(%rdi,%rcx,2), %xmm0
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSE2-NEXT:    movdqu 32(%rsi,%rcx,2), %xmm2
; SSE2-NEXT:    paddd %xmm1, %xmm5
; SSE2-NEXT:    movdqa %xmm2, %xmm1
; SSE2-NEXT:    pmulhuw %xmm0, %xmm1
; SSE2-NEXT:    pmullw %xmm0, %xmm2
; SSE2-NEXT:    movdqa %xmm2, %xmm0
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE2-NEXT:    paddd %xmm0, %xmm6
; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm0
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE2-NEXT:    movdqu (%rsi,%rcx,2), %xmm1
; SSE2-NEXT:    paddd %xmm2, %xmm4
; SSE2-NEXT:    movdqa %xmm1, %xmm2
; SSE2-NEXT:    pmulhuw %xmm0, %xmm2
; SSE2-NEXT:    pmullw %xmm0, %xmm1
; SSE2-NEXT:    movdqa %xmm1, %xmm0
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT:    paddd %xmm0, %xmm8
; SSE2-NEXT:    movdqu 16(%rdi,%rcx,2), %xmm0
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE2-NEXT:    movdqu 16(%rsi,%rcx,2), %xmm2
; SSE2-NEXT:    paddd %xmm1, %xmm3
; SSE2-NEXT:    movdqa %xmm2, %xmm1
; SSE2-NEXT:    pmulhuw %xmm0, %xmm1
; SSE2-NEXT:    pmullw %xmm0, %xmm2
; SSE2-NEXT:    movdqa %xmm2, %xmm0
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE2-NEXT:    paddd %xmm0, %xmm9
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE2-NEXT:    paddd %xmm2, %xmm10
; SSE2-NEXT:    addq $16, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB11_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm6, %xmm3
; SSE2-NEXT:    paddd %xmm7, %xmm10
; SSE2-NEXT:    paddd %xmm3, %xmm10
; SSE2-NEXT:    paddd %xmm4, %xmm8
; SSE2-NEXT:    paddd %xmm5, %xmm9
; SSE2-NEXT:    paddd %xmm10, %xmm9
; SSE2-NEXT:    paddd %xmm8, %xmm9
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm9[2,3,2,3]
; SSE2-NEXT:    paddd %xmm9, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: test_unsigned_short_1024:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %edx, %eax
; AVX1-NEXT:    vpxor %xmm8, %xmm8, %xmm8
; AVX1-NEXT:    xorl %ecx, %ecx
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    vpxor %xmm9, %xmm9, %xmm9
; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB11_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm5 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm7 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm12 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm10 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm11 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm4, %xmm1, %xmm1
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm5, %xmm4, %xmm4
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm5 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm6, %xmm5, %xmm5
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm7, %xmm6, %xmm6
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm7 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm0, %xmm7, %xmm13
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm7 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm12, %xmm7, %xmm7
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm10, %xmm0, %xmm10
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX1-NEXT:    vpmulld %xmm11, %xmm0, %xmm11
; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm0
; AVX1-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
; AVX1-NEXT:    vpaddd %xmm2, %xmm4, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm2
; AVX1-NEXT:    vextractf128 $1, %ymm8, %xmm0
; AVX1-NEXT:    vpaddd %xmm0, %xmm5, %xmm0
; AVX1-NEXT:    vpaddd %xmm6, %xmm8, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm8
; AVX1-NEXT:    vextractf128 $1, %ymm9, %xmm0
; AVX1-NEXT:    vpaddd %xmm0, %xmm13, %xmm0
; AVX1-NEXT:    vpaddd %xmm7, %xmm9, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm9
; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm0
; AVX1-NEXT:    vpaddd %xmm0, %xmm10, %xmm0
; AVX1-NEXT:    vpaddd %xmm3, %xmm11, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm3
; AVX1-NEXT:    addq $16, %rcx
; AVX1-NEXT:    cmpq %rcx, %rax
; AVX1-NEXT:    jne .LBB11_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vpaddd %xmm3, %xmm2, %xmm0
; AVX1-NEXT:    vextractf128 $1, %ymm8, %xmm1
; AVX1-NEXT:    vextractf128 $1, %ymm9, %xmm4
; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT:    vpaddd %xmm3, %xmm2, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm4, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vpaddd %xmm0, %xmm9, %xmm0
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpaddd %xmm0, %xmm8, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test_unsigned_short_1024:
; AVX2:       # %bb.0: # %entry
; AVX2-NEXT:    movl %edx, %eax
; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX2-NEXT:    xorl %ecx, %ecx
; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    vpxor %xmm3, %xmm3, %xmm3
; AVX2-NEXT:    .p2align 4, 0x90
; AVX2-NEXT:  .LBB11_1: # %vector.body
; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm5 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm7 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm8 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmulld %ymm4, %ymm8, %ymm4
; AVX2-NEXT:    vpaddd %ymm2, %ymm4, %ymm2
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmulld %ymm5, %ymm4, %ymm4
; AVX2-NEXT:    vpaddd %ymm1, %ymm4, %ymm1
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmulld %ymm6, %ymm4, %ymm4
; AVX2-NEXT:    vpaddd %ymm0, %ymm4, %ymm0
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT:    vpmulld %ymm7, %ymm4, %ymm4
; AVX2-NEXT:    vpaddd %ymm3, %ymm4, %ymm3
; AVX2-NEXT:    addq $16, %rcx
; AVX2-NEXT:    cmpq %rcx, %rax
; AVX2-NEXT:    jne .LBB11_1
; AVX2-NEXT:  # %bb.2: # %middle.block
; AVX2-NEXT:    vpaddd %ymm2, %ymm0, %ymm0
; AVX2-NEXT:    vpaddd %ymm3, %ymm1, %ymm1
; AVX2-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX2-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vmovd %xmm0, %eax
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512-LABEL: test_unsigned_short_1024:
; AVX512:       # %bb.0: # %entry
; AVX512-NEXT:    movl %edx, %eax
; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX512-NEXT:    xorl %ecx, %ecx
; AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512-NEXT:    .p2align 4, 0x90
; AVX512-NEXT:  .LBB11_1: # %vector.body
; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX512-NEXT:    vpmovzxwd {{.*#+}} zmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
; AVX512-NEXT:    vpmovzxwd {{.*#+}} zmm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
; AVX512-NEXT:    vpmovzxwd {{.*#+}} zmm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
; AVX512-NEXT:    vpmulld %zmm2, %zmm4, %zmm2
; AVX512-NEXT:    vpaddd %zmm1, %zmm2, %zmm1
; AVX512-NEXT:    vpmovzxwd {{.*#+}} zmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
; AVX512-NEXT:    vpmulld %zmm3, %zmm2, %zmm2
; AVX512-NEXT:    vpaddd %zmm0, %zmm2, %zmm0
; AVX512-NEXT:    addq $16, %rcx
; AVX512-NEXT:    cmpq %rcx, %rax
; AVX512-NEXT:    jne .LBB11_1
; AVX512-NEXT:  # %bb.2: # %middle.block
; AVX512-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; AVX512-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
; AVX512-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; AVX512-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX512-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vmovd %xmm0, %eax
; AVX512-NEXT:    vzeroupper
; AVX512-NEXT:    retq
entry:
  %3 = zext i32 %2 to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <32 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
  %4 = getelementptr inbounds i16, i16* %0, i64 %index
  %5 = bitcast i16* %4 to <32 x i16>*
  %wide.load = load <32 x i16>, <32 x i16>* %5, align 2
  %6 = zext <32 x i16> %wide.load to <32 x i32>
  %7 = getelementptr inbounds i16, i16* %1, i64 %index
  %8 = bitcast i16* %7 to <32 x i16>*
  %wide.load14 = load <32 x i16>, <32 x i16>* %8, align 2
  %9 = zext <32 x i16> %wide.load14 to <32 x i32>
  %10 = mul nsw <32 x i32> %9, %6
  %11 = add nsw <32 x i32> %10, %vec.phi
  %index.next = add i64 %index, 16
  %12 = icmp eq i64 %index.next, %3
  br i1 %12, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf2 = shufflevector <32 x i32> %11, <32 x i32> undef, <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx2 = add <32 x i32> %11, %rdx.shuf2
  %rdx.shuf1 = shufflevector <32 x i32> %bin.rdx2, <32 x i32> undef, <32 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx1 = add <32 x i32> %bin.rdx2, %rdx.shuf1
  %rdx.shuf = shufflevector <32 x i32> %bin.rdx1, <32 x i32> undef, <32 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx = add <32 x i32> %bin.rdx1, %rdx.shuf
  %rdx.shuf15 = shufflevector <32 x i32> %bin.rdx, <32 x i32> undef, <32 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx16 = add <32 x i32> %bin.rdx, %rdx.shuf15
  %rdx.shuf17 = shufflevector <32 x i32> %bin.rdx16, <32 x i32> undef, <32 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx18 = add <32 x i32> %bin.rdx16, %rdx.shuf17
  %13 = extractelement <32 x i32> %bin.rdx18, i32 0
  ret i32 %13
}

define <4 x i32> @pmaddwd_8(<8 x i16> %A, <8 x i16> %B) {
; SSE2-LABEL: pmaddwd_8:
; SSE2:       # %bb.0:
; SSE2-NEXT:    pmaddwd %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; AVX-LABEL: pmaddwd_8:
; AVX:       # %bb.0:
; AVX-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
   %a = sext <8 x i16> %A to <8 x i32>
   %b = sext <8 x i16> %B to <8 x i32>
   %m = mul nsw <8 x i32> %a, %b
   %odd = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
   %even = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
   %ret = add <4 x i32> %odd, %even
   ret <4 x i32> %ret
}

define <4 x i32> @pmaddwd_8_swapped(<8 x i16> %A, <8 x i16> %B) {
; SSE2-LABEL: pmaddwd_8_swapped:
; SSE2:       # %bb.0:
; SSE2-NEXT:    pmaddwd %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; AVX-LABEL: pmaddwd_8_swapped:
; AVX:       # %bb.0:
; AVX-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
   %a = sext <8 x i16> %A to <8 x i32>
   %b = sext <8 x i16> %B to <8 x i32>
   %m = mul nsw <8 x i32> %a, %b
   %odd = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
   %even = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
   %ret = add <4 x i32> %even, %odd
   ret <4 x i32> %ret
}

define <4 x i32> @larger_mul(<16 x i16> %A, <16 x i16> %B) {
; SSE2-LABEL: larger_mul:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    pmulhw %xmm2, %xmm1
; SSE2-NEXT:    pmullw %xmm2, %xmm0
; SSE2-NEXT:    movdqa %xmm0, %xmm2
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    shufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,3],xmm2[1,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; AVX1-LABEL: larger_mul:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: larger_mul:
; AVX2:       # %bb.0:
; AVX2-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512-LABEL: larger_mul:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vpmovsxwd %ymm0, %zmm0
; AVX512-NEXT:    vpmovsxwd %ymm1, %zmm1
; AVX512-NEXT:    vpmulld %zmm1, %zmm0, %zmm0
; AVX512-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    vzeroupper
; AVX512-NEXT:    retq
   %a = sext <16 x i16> %A to <16 x i32>
   %b = sext <16 x i16> %B to <16 x i32>
   %m = mul nsw <16 x i32> %a, %b
   %odd = shufflevector <16 x i32> %m, <16 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
   %even = shufflevector <16 x i32> %m, <16 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
   %ret = add <4 x i32> %odd, %even
   ret <4 x i32> %ret
}

define <8 x i32> @pmaddwd_16(<16 x i16> %A, <16 x i16> %B) {
; SSE2-LABEL: pmaddwd_16:
; SSE2:       # %bb.0:
; SSE2-NEXT:    pmaddwd %xmm2, %xmm0
; SSE2-NEXT:    pmaddwd %xmm3, %xmm1
; SSE2-NEXT:    retq
;
; AVX1-LABEL: pmaddwd_16:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT:    vpmaddwd %xmm2, %xmm3, %xmm2
; AVX1-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX256-LABEL: pmaddwd_16:
; AVX256:       # %bb.0:
; AVX256-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm0
; AVX256-NEXT:    retq
   %a = sext <16 x i16> %A to <16 x i32>
   %b = sext <16 x i16> %B to <16 x i32>
   %m = mul nsw <16 x i32> %a, %b
   %odd = shufflevector <16 x i32> %m, <16 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
   %even = shufflevector <16 x i32> %m, <16 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
   %ret = add <8 x i32> %odd, %even
   ret <8 x i32> %ret
}

define <16 x i32> @pmaddwd_32(<32 x i16> %A, <32 x i16> %B) {
; SSE2-LABEL: pmaddwd_32:
; SSE2:       # %bb.0:
; SSE2-NEXT:    pmaddwd %xmm4, %xmm0
; SSE2-NEXT:    pmaddwd %xmm5, %xmm1
; SSE2-NEXT:    pmaddwd %xmm6, %xmm2
; SSE2-NEXT:    pmaddwd %xmm7, %xmm3
; SSE2-NEXT:    retq
;
; AVX1-LABEL: pmaddwd_32:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm4
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm5
; AVX1-NEXT:    vpmaddwd %xmm4, %xmm5, %xmm4
; AVX1-NEXT:    vpmaddwd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm0, %ymm0
; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT:    vpmaddwd %xmm2, %xmm4, %xmm2
; AVX1-NEXT:    vpmaddwd %xmm3, %xmm1, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX1-NEXT:    retq
;
; AVX2-LABEL: pmaddwd_32:
; AVX2:       # %bb.0:
; AVX2-NEXT:    vpmaddwd %ymm2, %ymm0, %ymm0
; AVX2-NEXT:    vpmaddwd %ymm3, %ymm1, %ymm1
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: pmaddwd_32:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm3
; AVX512F-NEXT:    vpmaddwd %ymm2, %ymm3, %ymm2
; AVX512F-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm0
; AVX512F-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: pmaddwd_32:
; AVX512BW:       # %bb.0:
; AVX512BW-NEXT:    vpmaddwd %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT:    retq
   %a = sext <32 x i16> %A to <32 x i32>
   %b = sext <32 x i16> %B to <32 x i32>
   %m = mul nsw <32 x i32> %a, %b
   %odd = shufflevector <32 x i32> %m, <32 x i32> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
   %even = shufflevector <32 x i32> %m, <32 x i32> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
   %ret = add <16 x i32> %odd, %even
   ret <16 x i32> %ret
}

define <4 x i32> @pmaddwd_const(<8 x i16> %A) {
; SSE2-LABEL: pmaddwd_const:
; SSE2:       # %bb.0:
; SSE2-NEXT:    pmaddwd {{.*}}(%rip), %xmm0
; SSE2-NEXT:    retq
;
; AVX-LABEL: pmaddwd_const:
; AVX:       # %bb.0:
; AVX-NEXT:    vpmaddwd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    retq
   %a = sext <8 x i16> %A to <8 x i32>
   %m = mul nsw <8 x i32> %a, <i32 32767, i32 -32768, i32 0, i32 0, i32 1, i32 7, i32 42, i32 32>
   %odd = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
   %even = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
   %ret = add <4 x i32> %odd, %even
   ret <4 x i32> %ret
}

; Do not select unsigned i16 multiplication
define <4 x i32> @pmaddwd_negative1(<8 x i16> %A, <8 x i16> %B) {
; SSE2-LABEL: pmaddwd_negative1:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movdqa %xmm0, %xmm2
; SSE2-NEXT:    pmulhuw %xmm1, %xmm2
; SSE2-NEXT:    pmullw %xmm1, %xmm0
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT:    movdqa %xmm0, %xmm2
; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2],xmm1[0,2]
; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; SSE2-NEXT:    paddd %xmm2, %xmm0
; SSE2-NEXT:    retq
;
; AVX1-LABEL: pmaddwd_negative1:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm3 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm2 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; AVX1-NEXT:    vpmulld %xmm2, %xmm3, %xmm2
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
; AVX1-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vphaddd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    retq
;
; AVX256-LABEL: pmaddwd_negative1:
; AVX256:       # %bb.0:
; AVX256-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX256-NEXT:    vpmovzxwd {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
; AVX256-NEXT:    vpmulld %ymm1, %ymm0, %ymm0
; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX256-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vzeroupper
; AVX256-NEXT:    retq
   %a = zext <8 x i16> %A to <8 x i32>
   %b = zext <8 x i16> %B to <8 x i32>
   %m = mul nuw <8 x i32> %a, %b
   %odd = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
   %even = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
   %ret = add <4 x i32> %odd, %even
   ret <4 x i32> %ret
}

; Do not select if constant is too large
define <4 x i32> @pmaddwd_negative2(<8 x i16> %A) {
; SSE2-LABEL: pmaddwd_negative2:
; SSE2:       # %bb.0:
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT:    psrad $16, %xmm1
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psrad $16, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; SSE2-NEXT:    movdqa {{.*#+}} xmm3 = [1,7,42,32]
; SSE2-NEXT:    pshufd {{.*#+}} xmm4 = xmm3[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm2, %xmm4
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
; SSE2-NEXT:    movdqa {{.*#+}} xmm5 = [32768,4294934528,0,0]
; SSE2-NEXT:    pshufd {{.*#+}} xmm6 = xmm5[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm2, %xmm6
; SSE2-NEXT:    shufps {{.*#+}} xmm6 = xmm6[0,2],xmm4[0,2]
; SSE2-NEXT:    pmuludq %xmm3, %xmm0
; SSE2-NEXT:    pmuludq %xmm5, %xmm1
; SSE2-NEXT:    shufps {{.*#+}} xmm1 = xmm1[0,2],xmm0[0,2]
; SSE2-NEXT:    paddd %xmm6, %xmm1
; SSE2-NEXT:    movdqa %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; AVX1-LABEL: pmaddwd_negative2:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpmovsxwd %xmm1, %xmm1
; AVX1-NEXT:    vpmovsxwd %xmm0, %xmm0
; AVX1-NEXT:    vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT:    vpmulld {{.*}}(%rip), %xmm1, %xmm1
; AVX1-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    retq
;
; AVX256-LABEL: pmaddwd_negative2:
; AVX256:       # %bb.0:
; AVX256-NEXT:    vpmovsxwd %xmm0, %ymm0
; AVX256-NEXT:    vpmulld {{.*}}(%rip), %ymm0, %ymm0
; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX256-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vzeroupper
; AVX256-NEXT:    retq
   %a = sext <8 x i16> %A to <8 x i32>
   %m = mul nsw <8 x i32> %a, <i32 32768, i32 -32768, i32 0, i32 0, i32 1, i32 7, i32 42, i32 32>
   %odd = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
   %even = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
   %ret = add <4 x i32> %odd, %even
   ret <4 x i32> %ret
}

define <4 x i32> @jumbled_indices4(<8 x i16> %A, <8 x i16> %B) {
; SSE2-LABEL: jumbled_indices4:
; SSE2:       # %bb.0:
; SSE2-NEXT:    pmaddwd %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; AVX-LABEL: jumbled_indices4:
; AVX:       # %bb.0:
; AVX-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %exta = sext <8 x i16> %A to <8 x i32>
  %extb = sext <8 x i16> %B to <8 x i32>
  %m = mul <8 x i32> %exta, %extb
  %sa = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 3, i32 1, i32 5, i32 6>
  %sb = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 2, i32 0, i32 4, i32 7>
  %a = add <4 x i32> %sa, %sb
  ret <4 x i32> %a
}

define <8 x i32> @jumbled_indices8(<16 x i16> %A, <16 x i16> %B) {
; SSE2-LABEL: jumbled_indices8:
; SSE2:       # %bb.0:
; SSE2-NEXT:    pmaddwd %xmm2, %xmm0
; SSE2-NEXT:    pmaddwd %xmm3, %xmm1
; SSE2-NEXT:    retq
;
; AVX1-LABEL: jumbled_indices8:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT:    vpmaddwd %xmm2, %xmm3, %xmm2
; AVX1-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX256-LABEL: jumbled_indices8:
; AVX256:       # %bb.0:
; AVX256-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm0
; AVX256-NEXT:    retq
  %exta = sext <16 x i16> %A to <16 x i32>
  %extb = sext <16 x i16> %B to <16 x i32>
  %m = mul <16 x i32> %exta, %extb
  %sa = shufflevector <16 x i32> %m, <16 x i32> undef, <8 x i32> <i32 0, i32 2, i32 7, i32 4, i32 11, i32 8, i32 15, i32 12>
  %sb = shufflevector <16 x i32> %m, <16 x i32> undef, <8 x i32> <i32 1, i32 3, i32 6, i32 5, i32 10, i32 9, i32 14, i32 13>
  %a = add <8 x i32> %sa, %sb
  ret <8 x i32> %a
}

define <16 x i32> @jumbled_indices16(<32 x i16> %A, <32 x i16> %B) {
; SSE2-LABEL: jumbled_indices16:
; SSE2:       # %bb.0:
; SSE2-NEXT:    pmaddwd %xmm4, %xmm0
; SSE2-NEXT:    pmaddwd %xmm5, %xmm1
; SSE2-NEXT:    pmaddwd %xmm6, %xmm2
; SSE2-NEXT:    pmaddwd %xmm7, %xmm3
; SSE2-NEXT:    retq
;
; AVX1-LABEL: jumbled_indices16:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm4
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm5
; AVX1-NEXT:    vpmaddwd %xmm4, %xmm5, %xmm4
; AVX1-NEXT:    vpmaddwd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm0, %ymm0
; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm2
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT:    vpmaddwd %xmm2, %xmm4, %xmm2
; AVX1-NEXT:    vpmaddwd %xmm3, %xmm1, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX1-NEXT:    retq
;
; AVX2-LABEL: jumbled_indices16:
; AVX2:       # %bb.0:
; AVX2-NEXT:    vpmaddwd %ymm2, %ymm0, %ymm0
; AVX2-NEXT:    vpmaddwd %ymm3, %ymm1, %ymm1
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: jumbled_indices16:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm3
; AVX512F-NEXT:    vpmaddwd %ymm2, %ymm3, %ymm2
; AVX512F-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm0
; AVX512F-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: jumbled_indices16:
; AVX512BW:       # %bb.0:
; AVX512BW-NEXT:    vpmaddwd %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT:    retq
  %exta = sext <32 x i16> %A to <32 x i32>
  %extb = sext <32 x i16> %B to <32 x i32>
  %m = mul <32 x i32> %exta, %extb
  %sa = shufflevector <32 x i32> %m, <32 x i32> undef, <16 x i32> <i32 2, i32 0, i32 5, i32 6, i32 11, i32 9, i32 15, i32 12, i32 17, i32 18, i32 20, i32 23, i32 27, i32 24, i32 31, i32 29>
  %sb = shufflevector <32 x i32> %m, <32 x i32> undef, <16 x i32> <i32 3, i32 1, i32 4, i32 7, i32 10, i32 8, i32 14, i32 13, i32 16, i32 19, i32 21, i32 22, i32 26, i32 25, i32 30, i32 28>
  %a = add <16 x i32> %sa, %sb
  ret <16 x i32> %a
}

define <32 x i32> @jumbled_indices32(<64 x i16> %A, <64 x i16> %B) {
; SSE2-LABEL: jumbled_indices32:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movq %rdi, %rax
; SSE2-NEXT:    pmaddwd {{[0-9]+}}(%rsp), %xmm0
; SSE2-NEXT:    pmaddwd {{[0-9]+}}(%rsp), %xmm1
; SSE2-NEXT:    pmaddwd {{[0-9]+}}(%rsp), %xmm2
; SSE2-NEXT:    pmaddwd {{[0-9]+}}(%rsp), %xmm3
; SSE2-NEXT:    pmaddwd {{[0-9]+}}(%rsp), %xmm4
; SSE2-NEXT:    pmaddwd {{[0-9]+}}(%rsp), %xmm5
; SSE2-NEXT:    pmaddwd {{[0-9]+}}(%rsp), %xmm6
; SSE2-NEXT:    pmaddwd {{[0-9]+}}(%rsp), %xmm7
; SSE2-NEXT:    movdqa %xmm7, 112(%rdi)
; SSE2-NEXT:    movdqa %xmm6, 96(%rdi)
; SSE2-NEXT:    movdqa %xmm5, 80(%rdi)
; SSE2-NEXT:    movdqa %xmm4, 64(%rdi)
; SSE2-NEXT:    movdqa %xmm3, 48(%rdi)
; SSE2-NEXT:    movdqa %xmm2, 32(%rdi)
; SSE2-NEXT:    movdqa %xmm1, 16(%rdi)
; SSE2-NEXT:    movdqa %xmm0, (%rdi)
; SSE2-NEXT:    retq
;
; AVX1-LABEL: jumbled_indices32:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vextractf128 $1, %ymm4, %xmm8
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm9
; AVX1-NEXT:    vpmaddwd %xmm8, %xmm9, %xmm8
; AVX1-NEXT:    vpmaddwd %xmm4, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm8, %ymm0, %ymm0
; AVX1-NEXT:    vextractf128 $1, %ymm5, %xmm8
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT:    vpmaddwd %xmm4, %xmm8, %xmm4
; AVX1-NEXT:    vpmaddwd %xmm5, %xmm1, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm1, %ymm1
; AVX1-NEXT:    vextractf128 $1, %ymm6, %xmm4
; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm5
; AVX1-NEXT:    vpmaddwd %xmm4, %xmm5, %xmm4
; AVX1-NEXT:    vpmaddwd %xmm6, %xmm2, %xmm2
; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm2, %ymm2
; AVX1-NEXT:    vextractf128 $1, %ymm7, %xmm4
; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm5
; AVX1-NEXT:    vpmaddwd %xmm4, %xmm5, %xmm4
; AVX1-NEXT:    vpmaddwd %xmm7, %xmm3, %xmm3
; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm3, %ymm3
; AVX1-NEXT:    retq
;
; AVX2-LABEL: jumbled_indices32:
; AVX2:       # %bb.0:
; AVX2-NEXT:    vpmaddwd %ymm4, %ymm0, %ymm0
; AVX2-NEXT:    vpmaddwd %ymm5, %ymm1, %ymm1
; AVX2-NEXT:    vpmaddwd %ymm6, %ymm2, %ymm2
; AVX2-NEXT:    vpmaddwd %ymm7, %ymm3, %ymm3
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: jumbled_indices32:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vextracti64x4 $1, %zmm2, %ymm4
; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm5
; AVX512F-NEXT:    vpmaddwd %ymm4, %ymm5, %ymm4
; AVX512F-NEXT:    vpmaddwd %ymm2, %ymm0, %ymm0
; AVX512F-NEXT:    vinserti64x4 $1, %ymm4, %zmm0, %zmm0
; AVX512F-NEXT:    vextracti64x4 $1, %zmm3, %ymm2
; AVX512F-NEXT:    vextracti64x4 $1, %zmm1, %ymm4
; AVX512F-NEXT:    vpmaddwd %ymm2, %ymm4, %ymm2
; AVX512F-NEXT:    vpmaddwd %ymm3, %ymm1, %ymm1
; AVX512F-NEXT:    vinserti64x4 $1, %ymm2, %zmm1, %zmm1
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: jumbled_indices32:
; AVX512BW:       # %bb.0:
; AVX512BW-NEXT:    vpmaddwd %zmm2, %zmm0, %zmm0
; AVX512BW-NEXT:    vpmaddwd %zmm3, %zmm1, %zmm1
; AVX512BW-NEXT:    retq
  %exta = sext <64 x i16> %A to <64 x i32>
  %extb = sext <64 x i16> %B to <64 x i32>
  %m = mul <64 x i32> %exta, %extb
  %sa = shufflevector <64 x i32> %m, <64 x i32> undef, <32 x i32> <i32 1, i32 2, i32 6, i32 5, i32 10, i32 8, i32 14, i32 12, i32 19, i32 17, i32 22, i32 20, i32 25, i32 27, i32 30, i32 28, i32 32, i32 34, i32 37, i32 38, i32 41, i32 43, i32 45, i32 47, i32 50, i32 48, i32 52, i32 54, i32 59, i32 56, i32 61, i32 63>
  %sb = shufflevector <64 x i32> %m, <64 x i32> undef, <32 x i32> <i32 0, i32 3, i32 7, i32 4, i32 11, i32 9, i32 15, i32 13, i32 18, i32 16, i32 23, i32 21, i32 24, i32 26, i32 31, i32 29, i32 33, i32 35, i32 36, i32 39, i32 40, i32 42, i32 44, i32 46, i32 51, i32 49, i32 53, i32 55, i32 58, i32 57, i32 60, i32 62>
  %a = add <32 x i32> %sa, %sb
  ret <32 x i32> %a
}

; NOTE: We're testing with loads because ABI lowering creates a concat_vectors that extract_vector_elt creation can see through.
; This would require the combine to recreate the concat_vectors.
define <4 x i32> @pmaddwd_128(<8 x i16>* %Aptr, <8 x i16>* %Bptr) {
; SSE2-LABEL: pmaddwd_128:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movdqa (%rdi), %xmm0
; SSE2-NEXT:    pmaddwd (%rsi), %xmm0
; SSE2-NEXT:    retq
;
; AVX-LABEL: pmaddwd_128:
; AVX:       # %bb.0:
; AVX-NEXT:    vmovdqa (%rdi), %xmm0
; AVX-NEXT:    vpmaddwd (%rsi), %xmm0, %xmm0
; AVX-NEXT:    retq
  %A = load <8 x i16>, <8 x i16>* %Aptr
  %B = load <8 x i16>, <8 x i16>* %Bptr
  %A_even = shufflevector <8 x i16> %A, <8 x i16> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %A_odd = shufflevector <8 x i16> %A, <8 x i16> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %B_even = shufflevector <8 x i16> %B, <8 x i16> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %B_odd = shufflevector <8 x i16> %B, <8 x i16> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %A_even_ext = sext <4 x i16> %A_even to <4 x i32>
  %B_even_ext = sext <4 x i16> %B_even to <4 x i32>
  %A_odd_ext = sext <4 x i16> %A_odd to <4 x i32>
  %B_odd_ext = sext <4 x i16> %B_odd to <4 x i32>
  %even_mul = mul <4 x i32> %A_even_ext, %B_even_ext
  %odd_mul = mul <4 x i32> %A_odd_ext, %B_odd_ext
  %add = add <4 x i32> %even_mul, %odd_mul
  ret <4 x i32> %add
}

define <8 x i32> @pmaddwd_256(<16 x i16>* %Aptr, <16 x i16>* %Bptr) {
; SSE2-LABEL: pmaddwd_256:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movdqa (%rdi), %xmm0
; SSE2-NEXT:    movdqa 16(%rdi), %xmm1
; SSE2-NEXT:    pmaddwd (%rsi), %xmm0
; SSE2-NEXT:    pmaddwd 16(%rsi), %xmm1
; SSE2-NEXT:    retq
;
; AVX1-LABEL: pmaddwd_256:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vmovdqa (%rdi), %xmm0
; AVX1-NEXT:    vmovdqa 16(%rdi), %xmm1
; AVX1-NEXT:    vpmaddwd 16(%rsi), %xmm1, %xmm1
; AVX1-NEXT:    vpmaddwd (%rsi), %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX256-LABEL: pmaddwd_256:
; AVX256:       # %bb.0:
; AVX256-NEXT:    vmovdqa (%rdi), %ymm0
; AVX256-NEXT:    vpmaddwd (%rsi), %ymm0, %ymm0
; AVX256-NEXT:    retq
  %A = load <16 x i16>, <16 x i16>* %Aptr
  %B = load <16 x i16>, <16 x i16>* %Bptr
  %A_even = shufflevector <16 x i16> %A, <16 x i16> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %A_odd = shufflevector <16 x i16> %A, <16 x i16> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  %B_even = shufflevector <16 x i16> %B, <16 x i16> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %B_odd = shufflevector <16 x i16> %B, <16 x i16> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  %A_even_ext = sext <8 x i16> %A_even to <8 x i32>
  %B_even_ext = sext <8 x i16> %B_even to <8 x i32>
  %A_odd_ext = sext <8 x i16> %A_odd to <8 x i32>
  %B_odd_ext = sext <8 x i16> %B_odd to <8 x i32>
  %even_mul = mul <8 x i32> %A_even_ext, %B_even_ext
  %odd_mul = mul <8 x i32> %A_odd_ext, %B_odd_ext
  %add = add <8 x i32> %even_mul, %odd_mul
  ret <8 x i32> %add
}

define <16 x i32> @pmaddwd_512(<32 x i16>* %Aptr, <32 x i16>* %Bptr) {
; SSE2-LABEL: pmaddwd_512:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movdqa (%rdi), %xmm0
; SSE2-NEXT:    movdqa 16(%rdi), %xmm1
; SSE2-NEXT:    movdqa 32(%rdi), %xmm2
; SSE2-NEXT:    movdqa 48(%rdi), %xmm3
; SSE2-NEXT:    pmaddwd (%rsi), %xmm0
; SSE2-NEXT:    pmaddwd 16(%rsi), %xmm1
; SSE2-NEXT:    pmaddwd 32(%rsi), %xmm2
; SSE2-NEXT:    pmaddwd 48(%rsi), %xmm3
; SSE2-NEXT:    retq
;
; AVX1-LABEL: pmaddwd_512:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vmovdqa (%rdi), %xmm0
; AVX1-NEXT:    vmovdqa 16(%rdi), %xmm1
; AVX1-NEXT:    vmovdqa 32(%rdi), %xmm2
; AVX1-NEXT:    vmovdqa 48(%rdi), %xmm3
; AVX1-NEXT:    vpmaddwd 16(%rsi), %xmm1, %xmm1
; AVX1-NEXT:    vpmaddwd (%rsi), %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT:    vpmaddwd 48(%rsi), %xmm3, %xmm1
; AVX1-NEXT:    vpmaddwd 32(%rsi), %xmm2, %xmm2
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm2, %ymm1
; AVX1-NEXT:    retq
;
; AVX2-LABEL: pmaddwd_512:
; AVX2:       # %bb.0:
; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
; AVX2-NEXT:    vmovdqa 32(%rdi), %ymm1
; AVX2-NEXT:    vpmaddwd (%rsi), %ymm0, %ymm0
; AVX2-NEXT:    vpmaddwd 32(%rsi), %ymm1, %ymm1
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: pmaddwd_512:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vmovdqa (%rdi), %ymm0
; AVX512F-NEXT:    vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT:    vpmaddwd 32(%rsi), %ymm1, %ymm1
; AVX512F-NEXT:    vpmaddwd (%rsi), %ymm0, %ymm0
; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: pmaddwd_512:
; AVX512BW:       # %bb.0:
; AVX512BW-NEXT:    vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT:    vpmaddwd (%rsi), %zmm0, %zmm0
; AVX512BW-NEXT:    retq
  %A = load <32 x i16>, <32 x i16>* %Aptr
  %B = load <32 x i16>, <32 x i16>* %Bptr
  %A_even = shufflevector <32 x i16> %A, <32 x i16> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
  %A_odd = shufflevector <32 x i16> %A, <32 x i16> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
  %B_even = shufflevector <32 x i16> %B, <32 x i16> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
  %B_odd = shufflevector <32 x i16> %B, <32 x i16> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
  %A_even_ext = sext <16 x i16> %A_even to <16 x i32>
  %B_even_ext = sext <16 x i16> %B_even to <16 x i32>
  %A_odd_ext = sext <16 x i16> %A_odd to <16 x i32>
  %B_odd_ext = sext <16 x i16> %B_odd to <16 x i32>
  %even_mul = mul <16 x i32> %A_even_ext, %B_even_ext
  %odd_mul = mul <16 x i32> %A_odd_ext, %B_odd_ext
  %add = add <16 x i32> %even_mul, %odd_mul
  ret <16 x i32> %add
}

define <32 x i32> @pmaddwd_1024(<64 x i16>* %Aptr, <64 x i16>* %Bptr) {
; SSE2-LABEL: pmaddwd_1024:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movq %rdi, %rax
; SSE2-NEXT:    movdqa (%rsi), %xmm0
; SSE2-NEXT:    movdqa 16(%rsi), %xmm1
; SSE2-NEXT:    movdqa 32(%rsi), %xmm2
; SSE2-NEXT:    movdqa 48(%rsi), %xmm3
; SSE2-NEXT:    pmaddwd (%rdx), %xmm0
; SSE2-NEXT:    pmaddwd 16(%rdx), %xmm1
; SSE2-NEXT:    pmaddwd 32(%rdx), %xmm2
; SSE2-NEXT:    pmaddwd 48(%rdx), %xmm3
; SSE2-NEXT:    movdqa 64(%rsi), %xmm4
; SSE2-NEXT:    pmaddwd 64(%rdx), %xmm4
; SSE2-NEXT:    movdqa 80(%rsi), %xmm5
; SSE2-NEXT:    pmaddwd 80(%rdx), %xmm5
; SSE2-NEXT:    movdqa 96(%rsi), %xmm6
; SSE2-NEXT:    pmaddwd 96(%rdx), %xmm6
; SSE2-NEXT:    movdqa 112(%rsi), %xmm7
; SSE2-NEXT:    pmaddwd 112(%rdx), %xmm7
; SSE2-NEXT:    movdqa %xmm7, 112(%rdi)
; SSE2-NEXT:    movdqa %xmm6, 96(%rdi)
; SSE2-NEXT:    movdqa %xmm5, 80(%rdi)
; SSE2-NEXT:    movdqa %xmm4, 64(%rdi)
; SSE2-NEXT:    movdqa %xmm3, 48(%rdi)
; SSE2-NEXT:    movdqa %xmm2, 32(%rdi)
; SSE2-NEXT:    movdqa %xmm1, 16(%rdi)
; SSE2-NEXT:    movdqa %xmm0, (%rdi)
; SSE2-NEXT:    retq
;
; AVX1-LABEL: pmaddwd_1024:
; AVX1:       # %bb.0:
; AVX1-NEXT:    vmovdqa (%rdi), %xmm0
; AVX1-NEXT:    vmovdqa 16(%rdi), %xmm1
; AVX1-NEXT:    vmovdqa 32(%rdi), %xmm2
; AVX1-NEXT:    vmovdqa 48(%rdi), %xmm3
; AVX1-NEXT:    vpmaddwd 16(%rsi), %xmm1, %xmm1
; AVX1-NEXT:    vpmaddwd (%rsi), %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT:    vpmaddwd 48(%rsi), %xmm3, %xmm1
; AVX1-NEXT:    vpmaddwd 32(%rsi), %xmm2, %xmm2
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm2, %ymm1
; AVX1-NEXT:    vmovdqa 80(%rdi), %xmm2
; AVX1-NEXT:    vpmaddwd 80(%rsi), %xmm2, %xmm2
; AVX1-NEXT:    vmovdqa 64(%rdi), %xmm3
; AVX1-NEXT:    vpmaddwd 64(%rsi), %xmm3, %xmm3
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm3, %ymm2
; AVX1-NEXT:    vmovdqa 112(%rdi), %xmm3
; AVX1-NEXT:    vpmaddwd 112(%rsi), %xmm3, %xmm3
; AVX1-NEXT:    vmovdqa 96(%rdi), %xmm4
; AVX1-NEXT:    vpmaddwd 96(%rsi), %xmm4, %xmm4
; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm4, %ymm3
; AVX1-NEXT:    retq
;
; AVX2-LABEL: pmaddwd_1024:
; AVX2:       # %bb.0:
; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
; AVX2-NEXT:    vmovdqa 32(%rdi), %ymm1
; AVX2-NEXT:    vmovdqa 64(%rdi), %ymm2
; AVX2-NEXT:    vmovdqa 96(%rdi), %ymm3
; AVX2-NEXT:    vpmaddwd (%rsi), %ymm0, %ymm0
; AVX2-NEXT:    vpmaddwd 32(%rsi), %ymm1, %ymm1
; AVX2-NEXT:    vpmaddwd 64(%rsi), %ymm2, %ymm2
; AVX2-NEXT:    vpmaddwd 96(%rsi), %ymm3, %ymm3
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: pmaddwd_1024:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vmovdqa (%rdi), %ymm0
; AVX512F-NEXT:    vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT:    vmovdqa 64(%rdi), %ymm2
; AVX512F-NEXT:    vmovdqa 96(%rdi), %ymm3
; AVX512F-NEXT:    vpmaddwd 32(%rsi), %ymm1, %ymm1
; AVX512F-NEXT:    vpmaddwd (%rsi), %ymm0, %ymm0
; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512F-NEXT:    vpmaddwd 96(%rsi), %ymm3, %ymm1
; AVX512F-NEXT:    vpmaddwd 64(%rsi), %ymm2, %ymm2
; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm2, %zmm1
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: pmaddwd_1024:
; AVX512BW:       # %bb.0:
; AVX512BW-NEXT:    vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT:    vmovdqa64 64(%rdi), %zmm1
; AVX512BW-NEXT:    vpmaddwd (%rsi), %zmm0, %zmm0
; AVX512BW-NEXT:    vpmaddwd 64(%rsi), %zmm1, %zmm1
; AVX512BW-NEXT:    retq
  %A = load <64 x i16>, <64 x i16>* %Aptr
  %B = load <64 x i16>, <64 x i16>* %Bptr
  %A_even = shufflevector <64 x i16> %A, <64 x i16> undef, <32 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30, i32 32, i32 34, i32 36, i32 38, i32 40, i32 42, i32 44, i32 46, i32 48, i32 50, i32 52, i32 54, i32 56, i32 58, i32 60, i32 62>
  %A_odd = shufflevector <64 x i16> %A, <64 x i16> undef, <32 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31, i32 33, i32 35, i32 37, i32 39, i32 41, i32 43, i32 45, i32 47, i32 49, i32 51, i32 53, i32 55, i32 57, i32 59, i32 61, i32 63>
  %B_even = shufflevector <64 x i16> %B, <64 x i16> undef, <32 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30, i32 32, i32 34, i32 36, i32 38, i32 40, i32 42, i32 44, i32 46, i32 48, i32 50, i32 52, i32 54, i32 56, i32 58, i32 60, i32 62>
  %B_odd = shufflevector <64 x i16> %B, <64 x i16> undef, <32 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31, i32 33, i32 35, i32 37, i32 39, i32 41, i32 43, i32 45, i32 47, i32 49, i32 51, i32 53, i32 55, i32 57, i32 59, i32 61, i32 63>
  %A_even_ext = sext <32 x i16> %A_even to <32 x i32>
  %B_even_ext = sext <32 x i16> %B_even to <32 x i32>
  %A_odd_ext = sext <32 x i16> %A_odd to <32 x i32>
  %B_odd_ext = sext <32 x i16> %B_odd to <32 x i32>
  %even_mul = mul <32 x i32> %A_even_ext, %B_even_ext
  %odd_mul = mul <32 x i32> %A_odd_ext, %B_odd_ext
  %add = add <32 x i32> %even_mul, %odd_mul
  ret <32 x i32> %add
}

define <4 x i32> @pmaddwd_commuted_mul(<8 x i16>* %Aptr, <8 x i16>* %Bptr) {
; SSE2-LABEL: pmaddwd_commuted_mul:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movdqa (%rdi), %xmm0
; SSE2-NEXT:    pmaddwd (%rsi), %xmm0
; SSE2-NEXT:    retq
;
; AVX-LABEL: pmaddwd_commuted_mul:
; AVX:       # %bb.0:
; AVX-NEXT:    vmovdqa (%rdi), %xmm0
; AVX-NEXT:    vpmaddwd (%rsi), %xmm0, %xmm0
; AVX-NEXT:    retq
  %A = load <8 x i16>, <8 x i16>* %Aptr
  %B = load <8 x i16>, <8 x i16>* %Bptr
  %A_even = shufflevector <8 x i16> %A, <8 x i16> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %A_odd = shufflevector <8 x i16> %A, <8 x i16> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %B_even = shufflevector <8 x i16> %B, <8 x i16> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %B_odd = shufflevector <8 x i16> %B, <8 x i16> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %A_even_ext = sext <4 x i16> %A_even to <4 x i32>
  %B_even_ext = sext <4 x i16> %B_even to <4 x i32>
  %A_odd_ext = sext <4 x i16> %A_odd to <4 x i32>
  %B_odd_ext = sext <4 x i16> %B_odd to <4 x i32>
  %even_mul = mul <4 x i32> %A_even_ext, %B_even_ext
  %odd_mul = mul <4 x i32> %B_odd_ext, %A_odd_ext ; Different order than previous mul
  %add = add <4 x i32> %even_mul, %odd_mul
  ret <4 x i32> %add
}

define <4 x i32> @pmaddwd_swapped_indices(<8 x i16>* %Aptr, <8 x i16>* %Bptr) {
; SSE2-LABEL: pmaddwd_swapped_indices:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movdqa (%rdi), %xmm0
; SSE2-NEXT:    pmaddwd (%rsi), %xmm0
; SSE2-NEXT:    retq
;
; AVX-LABEL: pmaddwd_swapped_indices:
; AVX:       # %bb.0:
; AVX-NEXT:    vmovdqa (%rdi), %xmm0
; AVX-NEXT:    vpmaddwd (%rsi), %xmm0, %xmm0
; AVX-NEXT:    retq
  %A = load <8 x i16>, <8 x i16>* %Aptr
  %B = load <8 x i16>, <8 x i16>* %Bptr
  %A_even = shufflevector <8 x i16> %A, <8 x i16> undef, <4 x i32> <i32 1, i32 2, i32 5, i32 6> ; indices aren't all even
  %A_odd = shufflevector <8 x i16> %A, <8 x i16> undef, <4 x i32> <i32 0, i32 3, i32 4, i32 7> ; indices aren't all odd
  %B_even = shufflevector <8 x i16> %B, <8 x i16> undef, <4 x i32> <i32 1, i32 2, i32 5, i32 6> ; same indices as A
  %B_odd = shufflevector <8 x i16> %B, <8 x i16> undef, <4 x i32> <i32 0, i32 3, i32 4, i32 7> ; same indices as A
  %A_even_ext = sext <4 x i16> %A_even to <4 x i32>
  %B_even_ext = sext <4 x i16> %B_even to <4 x i32>
  %A_odd_ext = sext <4 x i16> %A_odd to <4 x i32>
  %B_odd_ext = sext <4 x i16> %B_odd to <4 x i32>
  %even_mul = mul <4 x i32> %A_even_ext, %B_even_ext
  %odd_mul = mul <4 x i32> %A_odd_ext, %B_odd_ext
  %add = add <4 x i32> %even_mul, %odd_mul
  ret <4 x i32> %add
}

; Negative test were indices aren't paired properly
define <4 x i32> @pmaddwd_bad_indices(<8 x i16>* %Aptr, <8 x i16>* %Bptr) {
; SSE2-LABEL: pmaddwd_bad_indices:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movdqa (%rdi), %xmm0
; SSE2-NEXT:    movdqa (%rsi), %xmm1
; SSE2-NEXT:    pshuflw {{.*#+}} xmm2 = xmm0[2,1,2,3,4,5,6,7]
; SSE2-NEXT:    pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,6,5,6,7]
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; SSE2-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[1,0,3,2,4,5,6,7]
; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,3,2,3,4,5,6,7]
; SSE2-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,7,6,7]
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    pshuflw {{.*#+}} xmm3 = xmm1[0,2,2,3,4,5,6,7]
; SSE2-NEXT:    pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,4,6,6,7]
; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSE2-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[3,1,2,3,4,5,6,7]
; SSE2-NEXT:    pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,7,5,6,7]
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[1,0,3,2,4,5,6,7]
; SSE2-NEXT:    movdqa %xmm2, %xmm4
; SSE2-NEXT:    pmulhw %xmm3, %xmm4
; SSE2-NEXT:    pmullw %xmm3, %xmm2
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3]
; SSE2-NEXT:    movdqa %xmm0, %xmm3
; SSE2-NEXT:    pmulhw %xmm1, %xmm3
; SSE2-NEXT:    pmullw %xmm1, %xmm0
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3]
; SSE2-NEXT:    paddd %xmm2, %xmm0
; SSE2-NEXT:    retq
;
; AVX-LABEL: pmaddwd_bad_indices:
; AVX:       # %bb.0:
; AVX-NEXT:    vmovdqa (%rdi), %xmm0
; AVX-NEXT:    vmovdqa (%rsi), %xmm1
; AVX-NEXT:    vpshufb {{.*#+}} xmm2 = xmm0[2,3,4,5,10,11,12,13,u,u,u,u,u,u,u,u]
; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,6,7,8,9,14,15,u,u,u,u,u,u,u,u]
; AVX-NEXT:    vpshufb {{.*#+}} xmm3 = xmm1[0,1,4,5,8,9,12,13,u,u,u,u,u,u,u,u]
; AVX-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[2,3,6,7,10,11,14,15,u,u,u,u,u,u,u,u]
; AVX-NEXT:    vpmovsxwd %xmm2, %xmm2
; AVX-NEXT:    vpmovsxwd %xmm3, %xmm3
; AVX-NEXT:    vpmulld %xmm3, %xmm2, %xmm2
; AVX-NEXT:    vpmovsxwd %xmm0, %xmm0
; AVX-NEXT:    vpmovsxwd %xmm1, %xmm1
; AVX-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpaddd %xmm0, %xmm2, %xmm0
; AVX-NEXT:    retq
  %A = load <8 x i16>, <8 x i16>* %Aptr
  %B = load <8 x i16>, <8 x i16>* %Bptr
  %A_even = shufflevector <8 x i16> %A, <8 x i16> undef, <4 x i32> <i32 1, i32 2, i32 5, i32 6>
  %A_odd = shufflevector <8 x i16> %A, <8 x i16> undef, <4 x i32> <i32 0, i32 3, i32 4, i32 7>
  %B_even = shufflevector <8 x i16> %B, <8 x i16> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6> ; different indices than A
  %B_odd = shufflevector <8 x i16> %B, <8 x i16> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7> ; different indices than A
  %A_even_ext = sext <4 x i16> %A_even to <4 x i32>
  %B_even_ext = sext <4 x i16> %B_even to <4 x i32>
  %A_odd_ext = sext <4 x i16> %A_odd to <4 x i32>
  %B_odd_ext = sext <4 x i16> %B_odd to <4 x i32>
  %even_mul = mul <4 x i32> %A_even_ext, %B_even_ext
  %odd_mul = mul <4 x i32> %A_odd_ext, %B_odd_ext
  %add = add <4 x i32> %even_mul, %odd_mul
  ret <4 x i32> %add
}

; This test contains two multiplies joined by an add. The result of that add is then reduced to a single element.
; SelectionDAGBuilder should tag the joining add as a vector reduction. We need to recognize that both sides can use pmaddwd
define i32 @madd_double_reduction(<8 x i16>* %arg, <8 x i16>* %arg1, <8 x i16>* %arg2, <8 x i16>* %arg3) {
; SSE2-LABEL: madd_double_reduction:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movdqu (%rdi), %xmm0
; SSE2-NEXT:    movdqu (%rsi), %xmm1
; SSE2-NEXT:    pmaddwd %xmm0, %xmm1
; SSE2-NEXT:    movdqu (%rdx), %xmm0
; SSE2-NEXT:    movdqu (%rcx), %xmm2
; SSE2-NEXT:    pmaddwd %xmm0, %xmm2
; SSE2-NEXT:    paddd %xmm1, %xmm2
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[2,3,2,3]
; SSE2-NEXT:    paddd %xmm2, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX-LABEL: madd_double_reduction:
; AVX:       # %bb.0:
; AVX-NEXT:    vmovdqu (%rdi), %xmm0
; AVX-NEXT:    vpmaddwd (%rsi), %xmm0, %xmm0
; AVX-NEXT:    vmovdqu (%rdx), %xmm1
; AVX-NEXT:    vpmaddwd (%rcx), %xmm1, %xmm1
; AVX-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vmovd %xmm0, %eax
; AVX-NEXT:    retq
  %tmp = load <8 x i16>, <8 x i16>* %arg, align 1
  %tmp6 = load <8 x i16>, <8 x i16>* %arg1, align 1
  %tmp7 = sext <8 x i16> %tmp to <8 x i32>
  %tmp17 = sext <8 x i16> %tmp6 to <8 x i32>
  %tmp19 = mul nsw <8 x i32> %tmp7, %tmp17
  %tmp20 = load <8 x i16>, <8 x i16>* %arg2, align 1
  %tmp21 = load <8 x i16>, <8 x i16>* %arg3, align 1
  %tmp22 = sext <8 x i16> %tmp20 to <8 x i32>
  %tmp23 = sext <8 x i16> %tmp21 to <8 x i32>
  %tmp25 = mul nsw <8 x i32> %tmp22, %tmp23
  %tmp26 = add nuw nsw <8 x i32> %tmp25, %tmp19
  %tmp29 = shufflevector <8 x i32> %tmp26, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
  %tmp30 = add <8 x i32> %tmp26, %tmp29
  %tmp31 = shufflevector <8 x i32> %tmp30, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %tmp32 = add <8 x i32> %tmp30, %tmp31
  %tmp33 = shufflevector <8 x i32> %tmp32, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %tmp34 = add <8 x i32> %tmp32, %tmp33
  %tmp35 = extractelement <8 x i32> %tmp34, i64 0
  ret i32 %tmp35
}

define i32 @madd_quad_reduction(<8 x i16>* %arg, <8 x i16>* %arg1, <8 x i16>* %arg2, <8 x i16>* %arg3, <8 x i16>* %arg4, <8 x i16>* %arg5, <8 x i16>* %arg6, <8 x i16>* %arg7) {
; SSE2-LABEL: madd_quad_reduction:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movq {{[0-9]+}}(%rsp), %r10
; SSE2-NEXT:    movq {{[0-9]+}}(%rsp), %rax
; SSE2-NEXT:    movdqu (%rdi), %xmm0
; SSE2-NEXT:    movdqu (%rsi), %xmm1
; SSE2-NEXT:    pmaddwd %xmm0, %xmm1
; SSE2-NEXT:    movdqu (%rdx), %xmm0
; SSE2-NEXT:    movdqu (%rcx), %xmm2
; SSE2-NEXT:    pmaddwd %xmm0, %xmm2
; SSE2-NEXT:    movdqu (%r8), %xmm0
; SSE2-NEXT:    movdqu (%r9), %xmm3
; SSE2-NEXT:    pmaddwd %xmm0, %xmm3
; SSE2-NEXT:    paddd %xmm1, %xmm3
; SSE2-NEXT:    movdqu (%rax), %xmm0
; SSE2-NEXT:    movdqu (%r10), %xmm1
; SSE2-NEXT:    pmaddwd %xmm0, %xmm1
; SSE2-NEXT:    paddd %xmm3, %xmm1
; SSE2-NEXT:    paddd %xmm2, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX-LABEL: madd_quad_reduction:
; AVX:       # %bb.0:
; AVX-NEXT:    movq {{[0-9]+}}(%rsp), %r10
; AVX-NEXT:    movq {{[0-9]+}}(%rsp), %rax
; AVX-NEXT:    vmovdqu (%rdi), %xmm0
; AVX-NEXT:    vpmaddwd (%rsi), %xmm0, %xmm0
; AVX-NEXT:    vmovdqu (%rdx), %xmm1
; AVX-NEXT:    vpmaddwd (%rcx), %xmm1, %xmm1
; AVX-NEXT:    vmovdqu (%r8), %xmm2
; AVX-NEXT:    vpmaddwd (%r9), %xmm2, %xmm2
; AVX-NEXT:    vpaddd %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vmovdqu (%rax), %xmm2
; AVX-NEXT:    vpmaddwd (%r10), %xmm2, %xmm2
; AVX-NEXT:    vpaddd %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vmovd %xmm0, %eax
; AVX-NEXT:    retq
  %tmp = load <8 x i16>, <8 x i16>* %arg, align 1
  %tmp6 = load <8 x i16>, <8 x i16>* %arg1, align 1
  %tmp7 = sext <8 x i16> %tmp to <8 x i32>
  %tmp17 = sext <8 x i16> %tmp6 to <8 x i32>
  %tmp19 = mul nsw <8 x i32> %tmp7, %tmp17
  %tmp20 = load <8 x i16>, <8 x i16>* %arg2, align 1
  %tmp21 = load <8 x i16>, <8 x i16>* %arg3, align 1
  %tmp22 = sext <8 x i16> %tmp20 to <8 x i32>
  %tmp23 = sext <8 x i16> %tmp21 to <8 x i32>
  %tmp25 = mul nsw <8 x i32> %tmp22, %tmp23
  %tmp26 = add nuw nsw <8 x i32> %tmp25, %tmp19

  %tmp40 = load <8 x i16>, <8 x i16>* %arg4, align 1
  %tmp41 = load <8 x i16>, <8 x i16>* %arg5, align 1
  %tmp42 = sext <8 x i16> %tmp40 to <8 x i32>
  %tmp43 = sext <8 x i16> %tmp41 to <8 x i32>
  %tmp45 = mul nsw <8 x i32> %tmp42, %tmp43
  %tmp56 = add nuw nsw <8 x i32> %tmp26, %tmp45

  %tmp50 = load <8 x i16>, <8 x i16>* %arg6, align 1
  %tmp51 = load <8 x i16>, <8 x i16>* %arg7, align 1
  %tmp52 = sext <8 x i16> %tmp50 to <8 x i32>
  %tmp53 = sext <8 x i16> %tmp51 to <8 x i32>
  %tmp55 = mul nsw <8 x i32> %tmp52, %tmp53
  %tmp57 = add nuw nsw <8 x i32> %tmp55, %tmp56

  %tmp29 = shufflevector <8 x i32> %tmp57, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
  %tmp30 = add <8 x i32> %tmp57, %tmp29
  %tmp31 = shufflevector <8 x i32> %tmp30, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %tmp32 = add <8 x i32> %tmp30, %tmp31
  %tmp33 = shufflevector <8 x i32> %tmp32, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %tmp34 = add <8 x i32> %tmp32, %tmp33
  %tmp35 = extractelement <8 x i32> %tmp34, i64 0
  ret i32 %tmp35
}

define i64 @sum_and_sum_of_squares(i8* %a, i32 %n) {
; SSE2-LABEL: sum_and_sum_of_squares:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %esi, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    pxor %xmm2, %xmm2
; SSE2-NEXT:    pxor %xmm3, %xmm3
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB33_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movq {{.*#+}} xmm4 = mem[0],zero
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3],xmm4[4],xmm0[4],xmm4[5],xmm0[5],xmm4[6],xmm0[6],xmm4[7],xmm0[7]
; SSE2-NEXT:    movdqa %xmm4, %xmm5
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm5 = xmm5[0],xmm0[0],xmm5[1],xmm0[1],xmm5[2],xmm0[2],xmm5[3],xmm0[3]
; SSE2-NEXT:    paddd %xmm5, %xmm2
; SSE2-NEXT:    movdqa %xmm4, %xmm5
; SSE2-NEXT:    punpckhwd {{.*#+}} xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7]
; SSE2-NEXT:    paddd %xmm5, %xmm3
; SSE2-NEXT:    pmaddwd %xmm4, %xmm4
; SSE2-NEXT:    paddd %xmm4, %xmm1
; SSE2-NEXT:    addq $8, %rdi
; SSE2-NEXT:    addq $-8, %rax
; SSE2-NEXT:    jne .LBB33_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm3, %xmm2
; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[2,3,2,3]
; SSE2-NEXT:    paddd %xmm2, %xmm3
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm3[1,1,1,1]
; SSE2-NEXT:    paddd %xmm3, %xmm2
; SSE2-NEXT:    movd %xmm2, %ecx
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    shlq $32, %rcx
; SSE2-NEXT:    orq %rcx, %rax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: sum_and_sum_of_squares:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %esi, %eax
; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB33_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vpmovzxbd {{.*#+}} xmm2 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
; AVX1-NEXT:    vpmovzxbd {{.*#+}} xmm3 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT:    vpaddd %xmm4, %xmm3, %xmm4
; AVX1-NEXT:    vpaddd %xmm1, %xmm2, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm1, %ymm1
; AVX1-NEXT:    vpmaddwd %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    vpmaddwd %xmm3, %xmm3, %xmm3
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm4
; AVX1-NEXT:    vpaddd %xmm4, %xmm3, %xmm3
; AVX1-NEXT:    vpaddd %xmm0, %xmm2, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm0, %ymm0
; AVX1-NEXT:    addq $8, %rdi
; AVX1-NEXT:    addq $-8, %rax
; AVX1-NEXT:    jne .LBB33_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm1[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm1[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vmovd %xmm1, %ecx
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    shlq $32, %rcx
; AVX1-NEXT:    orq %rcx, %rax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX256-LABEL: sum_and_sum_of_squares:
; AVX256:       # %bb.0: # %entry
; AVX256-NEXT:    movl %esi, %eax
; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX256-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX256-NEXT:    .p2align 4, 0x90
; AVX256-NEXT:  .LBB33_1: # %vector.body
; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX256-NEXT:    vpmovzxbd {{.*#+}} ymm2 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
; AVX256-NEXT:    vpaddd %ymm1, %ymm2, %ymm1
; AVX256-NEXT:    vpmaddwd %ymm2, %ymm2, %ymm2
; AVX256-NEXT:    vpaddd %ymm0, %ymm2, %ymm0
; AVX256-NEXT:    addq $8, %rdi
; AVX256-NEXT:    addq $-8, %rax
; AVX256-NEXT:    jne .LBB33_1
; AVX256-NEXT:  # %bb.2: # %middle.block
; AVX256-NEXT:    vextracti128 $1, %ymm1, %xmm2
; AVX256-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
; AVX256-NEXT:    vpshufd {{.*#+}} xmm2 = xmm1[2,3,2,3]
; AVX256-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
; AVX256-NEXT:    vpshufd {{.*#+}} xmm2 = xmm1[1,1,1,1]
; AVX256-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
; AVX256-NEXT:    vmovd %xmm1, %ecx
; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vmovd %xmm0, %eax
; AVX256-NEXT:    shlq $32, %rcx
; AVX256-NEXT:    orq %rcx, %rax
; AVX256-NEXT:    vzeroupper
; AVX256-NEXT:    retq
entry:
  %0 = zext i32 %n to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <8 x i32> [ %6, %vector.body ], [ zeroinitializer, %entry ]
  %sum.phi = phi <8 x i32> [ %4, %vector.body ], [ zeroinitializer, %entry ]
  %1 = getelementptr inbounds i8, i8* %a, i64 %index
  %2 = bitcast i8* %1 to <8 x i8>*
  %wide.load = load <8 x i8>, <8 x i8>* %2, align 1
  %3 = zext <8 x i8> %wide.load to <8 x i32>
  %4 = add nsw <8 x i32> %3, %sum.phi
  %5 = mul nsw <8 x i32> %3, %3
  %6 = add nsw <8 x i32> %5, %vec.phi
  %index.next = add i64 %index, 8
  %7 = icmp eq i64 %index.next, %0
  br i1 %7, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf35 = shufflevector <8 x i32> %4, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx36 = add <8 x i32> %4, %rdx.shuf35
  %rdx.shuf37 = shufflevector <8 x i32> %bin.rdx36, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx38 = add <8 x i32> %bin.rdx36, %rdx.shuf37
  %rdx.shuf39 = shufflevector <8 x i32> %bin.rdx38, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx40 = add <8 x i32> %bin.rdx38, %rdx.shuf39
  %8 = extractelement <8 x i32> %bin.rdx40, i32 0
  %rdx.shuf = shufflevector <8 x i32> %6, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx = add <8 x i32> %6, %rdx.shuf
  %rdx.shuf31 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx32 = add <8 x i32> %bin.rdx, %rdx.shuf31
  %rdx.shuf33 = shufflevector <8 x i32> %bin.rdx32, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx34 = add <8 x i32> %bin.rdx32, %rdx.shuf33
  %9 = extractelement <8 x i32> %bin.rdx34, i32 0
  %tmp = zext i32 %8 to i64
  %tmp28 = shl nuw i64 %tmp, 32
  %tmp29 = zext i32 %9 to i64
  %tmp30 = or i64 %tmp28, %tmp29
  ret i64 %tmp30
}

define i32 @sum_of_square_differences(i8* %a, i8* %b, i32 %n) {
; SSE2-LABEL: sum_of_square_differences:
; SSE2:       # %bb.0: # %entry
; SSE2-NEXT:    movl %edx, %eax
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    xorl %ecx, %ecx
; SSE2-NEXT:    pxor %xmm1, %xmm1
; SSE2-NEXT:    .p2align 4, 0x90
; SSE2-NEXT:  .LBB34_1: # %vector.body
; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
; SSE2-NEXT:    movq {{.*#+}} xmm2 = mem[0],zero
; SSE2-NEXT:    movq {{.*#+}} xmm3 = mem[0],zero
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
; SSE2-NEXT:    psubw %xmm2, %xmm3
; SSE2-NEXT:    pmaddwd %xmm3, %xmm3
; SSE2-NEXT:    paddd %xmm3, %xmm1
; SSE2-NEXT:    addq $8, %rcx
; SSE2-NEXT:    cmpq %rcx, %rax
; SSE2-NEXT:    jne .LBB34_1
; SSE2-NEXT:  # %bb.2: # %middle.block
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; SSE2-NEXT:    paddd %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    movd %xmm1, %eax
; SSE2-NEXT:    retq
;
; AVX1-LABEL: sum_of_square_differences:
; AVX1:       # %bb.0: # %entry
; AVX1-NEXT:    movl %edx, %eax
; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    xorl %ecx, %ecx
; AVX1-NEXT:    .p2align 4, 0x90
; AVX1-NEXT:  .LBB34_1: # %vector.body
; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX1-NEXT:    vpmovzxbw {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX1-NEXT:    vpmovzxbw {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX1-NEXT:    vpsubw %xmm1, %xmm2, %xmm1
; AVX1-NEXT:    vpmaddwd %xmm1, %xmm1, %xmm1
; AVX1-NEXT:    vpaddd %xmm0, %xmm1, %xmm1
; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
; AVX1-NEXT:    addq $8, %rcx
; AVX1-NEXT:    cmpq %rcx, %rax
; AVX1-NEXT:    jne .LBB34_1
; AVX1-NEXT:  # %bb.2: # %middle.block
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovd %xmm0, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX256-LABEL: sum_of_square_differences:
; AVX256:       # %bb.0: # %entry
; AVX256-NEXT:    movl %edx, %eax
; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; AVX256-NEXT:    xorl %ecx, %ecx
; AVX256-NEXT:    .p2align 4, 0x90
; AVX256-NEXT:  .LBB34_1: # %vector.body
; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
; AVX256-NEXT:    vpmovzxbw {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX256-NEXT:    vpmovzxbw {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX256-NEXT:    vpsubw %xmm1, %xmm2, %xmm1
; AVX256-NEXT:    vpmaddwd %xmm1, %xmm1, %xmm1
; AVX256-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
; AVX256-NEXT:    addq $8, %rcx
; AVX256-NEXT:    cmpq %rcx, %rax
; AVX256-NEXT:    jne .LBB34_1
; AVX256-NEXT:  # %bb.2: # %middle.block
; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
; AVX256-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
; AVX256-NEXT:    vmovd %xmm0, %eax
; AVX256-NEXT:    vzeroupper
; AVX256-NEXT:    retq
entry:
  %0 = zext i32 %n to i64
  br label %vector.body

vector.body:
  %index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
  %vec.phi = phi <8 x i32> [ %9, %vector.body ], [ zeroinitializer, %entry ]
  %1 = getelementptr inbounds i8, i8* %a, i64 %index
  %2 = bitcast i8* %1 to <8 x i8>*
  %wide.load = load <8 x i8>, <8 x i8>* %2, align 1
  %3 = zext <8 x i8> %wide.load to <8 x i32>
  %4 = getelementptr inbounds i8, i8* %b, i64 %index
  %5 = bitcast i8* %4 to <8 x i8>*
  %wide.load2 = load <8 x i8>, <8 x i8>* %5, align 1
  %6 = zext <8 x i8> %wide.load2 to <8 x i32>
  %7 = sub <8 x i32> %6, %3
  %8 = mul <8 x i32> %7, %7
  %9 = add nsw <8 x i32> %8, %vec.phi
  %index.next = add i64 %index, 8
  %10 = icmp eq i64 %index.next, %0
  br i1 %10, label %middle.block, label %vector.body

middle.block:
  %rdx.shuf = shufflevector <8 x i32> %9, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx = add <8 x i32> %9, %rdx.shuf
  %rdx.shuf31 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx32 = add <8 x i32> %bin.rdx, %rdx.shuf31
  %rdx.shuf33 = shufflevector <8 x i32> %bin.rdx32, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %bin.rdx34 = add <8 x i32> %bin.rdx32, %rdx.shuf33
  %11 = extractelement <8 x i32> %bin.rdx34, i32 0
  ret i32 %11
}