llvm-project/llvm/test/CodeGen/X86/pmul.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512BW

define <16 x i8> @mul_v16i8c(<16 x i8> %i) nounwind  {
; SSE2-LABEL: mul_v16i8c:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
; SSE2-NEXT:    psraw $8, %xmm1
; SSE2-NEXT:    movdqa %xmm0, %xmm2
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm2 = xmm2[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm2
; SSE2-NEXT:    pmullw %xmm1, %xmm2
; SSE2-NEXT:    movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT:    pand %xmm3, %xmm2
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm0
; SSE2-NEXT:    pmullw %xmm1, %xmm0
; SSE2-NEXT:    pand %xmm3, %xmm0
; SSE2-NEXT:    packuswb %xmm2, %xmm0
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v16i8c:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pmovsxbw %xmm0, %xmm1
; SSE41-NEXT:    pmovsxbw {{.*}}(%rip), %xmm2
; SSE41-NEXT:    pmullw %xmm2, %xmm1
; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; SSE41-NEXT:    pand %xmm3, %xmm1
; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm0, %xmm0
; SSE41-NEXT:    pmullw %xmm2, %xmm0
; SSE41-NEXT:    pand %xmm3, %xmm0
; SSE41-NEXT:    packuswb %xmm0, %xmm1
; SSE41-NEXT:    movdqa %xmm1, %xmm0
; SSE41-NEXT:    retq
;
; AVX2-LABEL: mul_v16i8c:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX2-NEXT:    vpmovsxbw {{.*}}(%rip), %ymm1
; AVX2-NEXT:    vpmullw %ymm1, %ymm0, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: mul_v16i8c:
; AVX512F:       # BB#0: # %entry
; AVX512F-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX512F-NEXT:    vpmovsxbw {{.*}}(%rip), %ymm1
; AVX512F-NEXT:    vpmullw %ymm1, %ymm0, %ymm0
; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: mul_v16i8c:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX512BW-NEXT:    vpmovsxbw {{.*}}(%rip), %ymm1
; AVX512BW-NEXT:    vpmullw %ymm1, %ymm0, %ymm0
; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
; AVX512BW-NEXT:    retq
entry:
  %A = mul <16 x i8> %i, < i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117 >
  ret <16 x i8> %A
}

define <8 x i16> @mul_v8i16c(<8 x i16> %i) nounwind  {
; SSE-LABEL: mul_v8i16c:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    pmullw {{.*}}(%rip), %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: mul_v8i16c:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpmullw {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %A = mul <8 x i16> %i, < i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117 >
  ret <8 x i16> %A
}

define <4 x i32> @mul_v4i32c(<4 x i32> %i) nounwind  {
; SSE2-LABEL: mul_v4i32c:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [117,117,117,117]
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    pmuludq %xmm1, %xmm2
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v4i32c:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pmulld {{.*}}(%rip), %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: mul_v4i32c:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpbroadcastd {{.*}}(%rip), %xmm1
; AVX-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %A = mul <4 x i32> %i, < i32 117, i32 117, i32 117, i32 117 >
  ret <4 x i32> %A
}

define <2 x i64> @mul_v2i64c(<2 x i64> %i) nounwind  {
; SSE-LABEL: mul_v2i64c:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    movdqa {{.*#+}} xmm1 = [117,117]
; SSE-NEXT:    movdqa %xmm0, %xmm2
; SSE-NEXT:    pmuludq %xmm1, %xmm2
; SSE-NEXT:    psrlq $32, %xmm0
; SSE-NEXT:    pmuludq %xmm1, %xmm0
; SSE-NEXT:    psllq $32, %xmm0
; SSE-NEXT:    paddq %xmm2, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: mul_v2i64c:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vmovdqa {{.*#+}} xmm1 = [117,117]
; AVX-NEXT:    vpmuludq %xmm1, %xmm0, %xmm2
; AVX-NEXT:    vpsrlq $32, %xmm0, %xmm0
; AVX-NEXT:    vpmuludq %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpsllq $32, %xmm0, %xmm0
; AVX-NEXT:    vpaddq %xmm0, %xmm2, %xmm0
; AVX-NEXT:    retq
entry:
  %A = mul <2 x i64> %i, < i64 117, i64 117 >
  ret <2 x i64> %A
}

define <16 x i8> @mul_v16i8(<16 x i8> %i, <16 x i8> %j) nounwind  {
; SSE2-LABEL: mul_v16i8:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    movdqa %xmm1, %xmm2
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm2 = xmm2[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm2
; SSE2-NEXT:    movdqa %xmm0, %xmm3
; 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:    pmullw %xmm2, %xmm3
; SSE2-NEXT:    movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT:    pand %xmm2, %xmm3
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm1
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm0
; SSE2-NEXT:    pmullw %xmm1, %xmm0
; SSE2-NEXT:    pand %xmm2, %xmm0
; SSE2-NEXT:    packuswb %xmm3, %xmm0
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v16i8:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pmovsxbw %xmm1, %xmm3
; SSE41-NEXT:    pmovsxbw %xmm0, %xmm2
; SSE41-NEXT:    pmullw %xmm3, %xmm2
; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; SSE41-NEXT:    pand %xmm3, %xmm2
; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm1, %xmm1
; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm0, %xmm0
; SSE41-NEXT:    pmullw %xmm1, %xmm0
; SSE41-NEXT:    pand %xmm3, %xmm0
; SSE41-NEXT:    packuswb %xmm0, %xmm2
; SSE41-NEXT:    movdqa %xmm2, %xmm0
; SSE41-NEXT:    retq
;
; AVX2-LABEL: mul_v16i8:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vpmovsxbw %xmm1, %ymm1
; AVX2-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX2-NEXT:    vpmullw %ymm1, %ymm0, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: mul_v16i8:
; AVX512F:       # BB#0: # %entry
; AVX512F-NEXT:    vpmovsxbw %xmm1, %ymm1
; AVX512F-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX512F-NEXT:    vpmullw %ymm1, %ymm0, %ymm0
; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: mul_v16i8:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpmovsxbw %xmm1, %ymm1
; AVX512BW-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX512BW-NEXT:    vpmullw %ymm1, %ymm0, %ymm0
; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
; AVX512BW-NEXT:    retq
entry:
  %A = mul <16 x i8> %i, %j
  ret <16 x i8> %A
}

define <8 x i16> @mul_v8i16(<8 x i16> %i, <8 x i16> %j) nounwind  {
; SSE-LABEL: mul_v8i16:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    pmullw %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: mul_v8i16:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpmullw %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %A = mul <8 x i16> %i, %j
  ret <8 x i16> %A
}

define <4 x i32> @mul_v4i32(<4 x i32> %i, <4 x i32> %j) nounwind  {
; SSE2-LABEL: mul_v4i32:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm1, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm2, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v4i32:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pmulld %xmm1, %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: mul_v4i32:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %A = mul <4 x i32> %i, %j
  ret <4 x i32> %A
}

define <2 x i64> @mul_v2i64(<2 x i64> %i, <2 x i64> %j) nounwind  {
; SSE-LABEL: mul_v2i64:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    movdqa %xmm0, %xmm2
; SSE-NEXT:    pmuludq %xmm1, %xmm2
; SSE-NEXT:    movdqa %xmm1, %xmm3
; SSE-NEXT:    psrlq $32, %xmm3
; SSE-NEXT:    pmuludq %xmm0, %xmm3
; SSE-NEXT:    psllq $32, %xmm3
; SSE-NEXT:    psrlq $32, %xmm0
; SSE-NEXT:    pmuludq %xmm1, %xmm0
; SSE-NEXT:    psllq $32, %xmm0
; SSE-NEXT:    paddq %xmm3, %xmm0
; SSE-NEXT:    paddq %xmm2, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: mul_v2i64:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpmuludq %xmm1, %xmm0, %xmm2
; AVX-NEXT:    vpsrlq $32, %xmm1, %xmm3
; AVX-NEXT:    vpmuludq %xmm3, %xmm0, %xmm3
; AVX-NEXT:    vpsllq $32, %xmm3, %xmm3
; AVX-NEXT:    vpsrlq $32, %xmm0, %xmm0
; AVX-NEXT:    vpmuludq %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpsllq $32, %xmm0, %xmm0
; AVX-NEXT:    vpaddq %xmm0, %xmm3, %xmm0
; AVX-NEXT:    vpaddq %xmm0, %xmm2, %xmm0
; AVX-NEXT:    retq
entry:
  %A = mul <2 x i64> %i, %j
  ret <2 x i64> %A
}

declare void @foo()

define <4 x i32> @mul_v4i32spill(<4 x i32> %i, <4 x i32> %j) nounwind  {
; SSE2-LABEL: mul_v4i32spill:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    subq $40, %rsp
; SSE2-NEXT:    movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
; SSE2-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; SSE2-NEXT:    callq foo
; SSE2-NEXT:    movdqa (%rsp), %xmm0 # 16-byte Reload
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
; SSE2-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm2 # 16-byte Reload
; SSE2-NEXT:    pmuludq %xmm2, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm1, %xmm2
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT:    addq $40, %rsp
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v4i32spill:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    subq $40, %rsp
; SSE41-NEXT:    movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
; SSE41-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; SSE41-NEXT:    callq foo
; SSE41-NEXT:    movdqa (%rsp), %xmm0 # 16-byte Reload
; SSE41-NEXT:    pmulld {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
; SSE41-NEXT:    addq $40, %rsp
; SSE41-NEXT:    retq
;
; AVX-LABEL: mul_v4i32spill:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    vmovaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    callq foo
; AVX-NEXT:    vmovdqa (%rsp), %xmm0 # 16-byte Reload
; AVX-NEXT:    vpmulld {{[0-9]+}}(%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    retq
entry:
  ; Use a call to force spills.
  call void @foo()
  %A = mul <4 x i32> %i, %j
  ret <4 x i32> %A
}

define <2 x i64> @mul_v2i64spill(<2 x i64> %i, <2 x i64> %j) nounwind  {
; SSE-LABEL: mul_v2i64spill:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    subq $40, %rsp
; SSE-NEXT:    movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
; SSE-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; SSE-NEXT:    callq foo
; SSE-NEXT:    movdqa (%rsp), %xmm0 # 16-byte Reload
; SSE-NEXT:    movdqa %xmm0, %xmm2
; SSE-NEXT:    movdqa {{[0-9]+}}(%rsp), %xmm3 # 16-byte Reload
; SSE-NEXT:    pmuludq %xmm3, %xmm2
; SSE-NEXT:    movdqa %xmm3, %xmm1
; SSE-NEXT:    psrlq $32, %xmm1
; SSE-NEXT:    pmuludq %xmm0, %xmm1
; SSE-NEXT:    psllq $32, %xmm1
; SSE-NEXT:    psrlq $32, %xmm0
; SSE-NEXT:    pmuludq %xmm3, %xmm0
; SSE-NEXT:    psllq $32, %xmm0
; SSE-NEXT:    paddq %xmm1, %xmm0
; SSE-NEXT:    paddq %xmm2, %xmm0
; SSE-NEXT:    addq $40, %rsp
; SSE-NEXT:    retq
;
; AVX2-LABEL: mul_v2i64spill:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    subq $40, %rsp
; AVX2-NEXT:    vmovaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
; AVX2-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX2-NEXT:    callq foo
; AVX2-NEXT:    vmovdqa {{[0-9]+}}(%rsp), %xmm2 # 16-byte Reload
; AVX2-NEXT:    vmovdqa (%rsp), %xmm4 # 16-byte Reload
; AVX2-NEXT:    vpmuludq %xmm2, %xmm4, %xmm0
; AVX2-NEXT:    vpsrlq $32, %xmm2, %xmm1
; AVX2-NEXT:    vmovdqa %xmm2, %xmm3
; AVX2-NEXT:    vpmuludq %xmm1, %xmm4, %xmm1
; AVX2-NEXT:    vpsllq $32, %xmm1, %xmm1
; AVX2-NEXT:    vpsrlq $32, %xmm4, %xmm2
; AVX2-NEXT:    vpmuludq %xmm3, %xmm2, %xmm2
; AVX2-NEXT:    vpsllq $32, %xmm2, %xmm2
; AVX2-NEXT:    vpaddq %xmm2, %xmm1, %xmm1
; AVX2-NEXT:    vpaddq %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    addq $40, %rsp
; AVX2-NEXT:    retq
;
; AVX512-LABEL: mul_v2i64spill:
; AVX512:       # BB#0: # %entry
; AVX512-NEXT:    subq $40, %rsp
; AVX512-NEXT:    vmovaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
; AVX512-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX512-NEXT:    callq foo
; AVX512-NEXT:    vmovdqa {{[0-9]+}}(%rsp), %xmm2 # 16-byte Reload
; AVX512-NEXT:    vmovdqa (%rsp), %xmm4 # 16-byte Reload
; AVX512-NEXT:    vpmuludq %xmm2, %xmm4, %xmm0
; AVX512-NEXT:    vpsrlq $32, %xmm2, %xmm1
; AVX512-NEXT:    vmovdqa64 %zmm2, %zmm3
; AVX512-NEXT:    vpmuludq %xmm1, %xmm4, %xmm1
; AVX512-NEXT:    vpsllq $32, %xmm1, %xmm1
; AVX512-NEXT:    vpsrlq $32, %xmm4, %xmm2
; AVX512-NEXT:    vpmuludq %xmm3, %xmm2, %xmm2
; AVX512-NEXT:    vpsllq $32, %xmm2, %xmm2
; AVX512-NEXT:    vpaddq %xmm2, %xmm1, %xmm1
; AVX512-NEXT:    vpaddq %xmm1, %xmm0, %xmm0
; AVX512-NEXT:    addq $40, %rsp
; AVX512-NEXT:    retq
entry:
  ; Use a call to force spills.
  call void @foo()
  %A = mul <2 x i64> %i, %j
  ret <2 x i64> %A
}

define <32 x i8> @mul_v32i8c(<32 x i8> %i) nounwind  {
; SSE2-LABEL: mul_v32i8c:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    movdqa {{.*#+}} xmm2 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
; SSE2-NEXT:    psraw $8, %xmm2
; SSE2-NEXT:    movdqa %xmm0, %xmm3
; 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:    pmullw %xmm2, %xmm3
; SSE2-NEXT:    movdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT:    pand %xmm4, %xmm3
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm0
; SSE2-NEXT:    pmullw %xmm2, %xmm0
; SSE2-NEXT:    pand %xmm4, %xmm0
; SSE2-NEXT:    packuswb %xmm3, %xmm0
; SSE2-NEXT:    movdqa %xmm1, %xmm3
; 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:    pmullw %xmm2, %xmm3
; SSE2-NEXT:    pand %xmm4, %xmm3
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm1
; SSE2-NEXT:    pmullw %xmm2, %xmm1
; SSE2-NEXT:    pand %xmm4, %xmm1
; SSE2-NEXT:    packuswb %xmm3, %xmm1
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v32i8c:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pmovsxbw %xmm0, %xmm2
; SSE41-NEXT:    pmovsxbw {{.*}}(%rip), %xmm4
; SSE41-NEXT:    pmullw %xmm4, %xmm2
; SSE41-NEXT:    movdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
; SSE41-NEXT:    pand %xmm5, %xmm2
; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm0, %xmm0
; SSE41-NEXT:    pmullw %xmm4, %xmm0
; SSE41-NEXT:    pand %xmm5, %xmm0
; SSE41-NEXT:    packuswb %xmm0, %xmm2
; SSE41-NEXT:    pmovsxbw %xmm1, %xmm3
; SSE41-NEXT:    pmullw %xmm4, %xmm3
; SSE41-NEXT:    pand %xmm5, %xmm3
; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm0, %xmm0
; SSE41-NEXT:    pmullw %xmm4, %xmm0
; SSE41-NEXT:    pand %xmm5, %xmm0
; SSE41-NEXT:    packuswb %xmm0, %xmm3
; SSE41-NEXT:    movdqa %xmm2, %xmm0
; SSE41-NEXT:    movdqa %xmm3, %xmm1
; SSE41-NEXT:    retq
;
; AVX2-LABEL: mul_v32i8c:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vpmovsxbw %xmm1, %ymm1
; AVX2-NEXT:    vpmovsxbw {{.*}}(%rip), %ymm2
; AVX2-NEXT:    vpmullw %ymm2, %ymm1, %ymm1
; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm3
; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX2-NEXT:    vpshufb %xmm4, %xmm3, %xmm3
; AVX2-NEXT:    vpshufb %xmm4, %xmm1, %xmm1
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
; AVX2-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX2-NEXT:    vpmullw %ymm2, %ymm0, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm2
; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
; AVX2-NEXT:    vpshufb %xmm4, %xmm0, %xmm0
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: mul_v32i8c:
; AVX512F:       # BB#0: # %entry
; AVX512F-NEXT:    vpmovsxbw %xmm0, %ymm1
; AVX512F-NEXT:    vpmovsxbw {{.*}}(%rip), %ymm2
; AVX512F-NEXT:    vpmullw %ymm2, %ymm1, %ymm1
; AVX512F-NEXT:    vpmovsxwd %ymm1, %zmm1
; AVX512F-NEXT:    vpmovdb %zmm1, %xmm1
; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm0
; AVX512F-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX512F-NEXT:    vpmullw %ymm2, %ymm0, %ymm0
; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
; AVX512F-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: mul_v32i8c:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vmovdqa {{.*#+}} ymm1 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
; AVX512BW-NEXT:    vpmovsxbw %ymm1, %zmm1
; AVX512BW-NEXT:    vpmovsxbw %ymm0, %zmm0
; AVX512BW-NEXT:    vpmullw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT:    retq
entry:
  %A = mul <32 x i8> %i, < i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117 >
  ret <32 x i8> %A
}

define <16 x i16> @mul_v16i16c(<16 x i16> %i) nounwind  {
; SSE-LABEL: mul_v16i16c:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [117,117,117,117,117,117,117,117]
; SSE-NEXT:    pmullw %xmm2, %xmm0
; SSE-NEXT:    pmullw %xmm2, %xmm1
; SSE-NEXT:    retq
;
; AVX-LABEL: mul_v16i16c:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpmullw {{.*}}(%rip), %ymm0, %ymm0
; AVX-NEXT:    retq
entry:
  %A = mul <16 x i16> %i, < i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117, i16 117 >
  ret <16 x i16> %A
}

define <8 x i32> @mul_v8i32c(<8 x i32> %i) nounwind  {
; SSE2-LABEL: mul_v8i32c:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    movdqa {{.*#+}} xmm2 = [117,117,117,117]
; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm2, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    pmuludq %xmm2, %xmm3
; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm2, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT:    pmuludq %xmm2, %xmm3
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm3[0,2,2,3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v8i32c:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [117,117,117,117]
; SSE41-NEXT:    pmulld %xmm2, %xmm0
; SSE41-NEXT:    pmulld %xmm2, %xmm1
; SSE41-NEXT:    retq
;
; AVX-LABEL: mul_v8i32c:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpbroadcastd {{.*}}(%rip), %ymm1
; AVX-NEXT:    vpmulld %ymm1, %ymm0, %ymm0
; AVX-NEXT:    retq
entry:
  %A = mul <8 x i32> %i, < i32 117, i32 117, i32 117, i32 117, i32 117, i32 117, i32 117, i32 117 >
  ret <8 x i32> %A
}

define <4 x i64> @mul_v4i64c(<4 x i64> %i) nounwind  {
; SSE-LABEL: mul_v4i64c:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    movdqa {{.*#+}} xmm2 = [117,117]
; SSE-NEXT:    movdqa %xmm0, %xmm3
; SSE-NEXT:    pmuludq %xmm2, %xmm3
; SSE-NEXT:    psrlq $32, %xmm0
; SSE-NEXT:    pmuludq %xmm2, %xmm0
; SSE-NEXT:    psllq $32, %xmm0
; SSE-NEXT:    paddq %xmm3, %xmm0
; SSE-NEXT:    movdqa %xmm1, %xmm3
; SSE-NEXT:    pmuludq %xmm2, %xmm3
; SSE-NEXT:    psrlq $32, %xmm1
; SSE-NEXT:    pmuludq %xmm2, %xmm1
; SSE-NEXT:    psllq $32, %xmm1
; SSE-NEXT:    paddq %xmm3, %xmm1
; SSE-NEXT:    retq
;
; AVX-LABEL: mul_v4i64c:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpbroadcastq {{.*}}(%rip), %ymm1
; AVX-NEXT:    vpmuludq %ymm1, %ymm0, %ymm2
; AVX-NEXT:    vpsrlq $32, %ymm0, %ymm0
; AVX-NEXT:    vpmuludq %ymm1, %ymm0, %ymm0
; AVX-NEXT:    vpsllq $32, %ymm0, %ymm0
; AVX-NEXT:    vpaddq %ymm0, %ymm2, %ymm0
; AVX-NEXT:    retq
entry:
  %A = mul <4 x i64> %i, < i64 117, i64 117, i64 117, i64 117 >
  ret <4 x i64> %A
}

define <32 x i8> @mul_v32i8(<32 x i8> %i, <32 x i8> %j) nounwind  {
; SSE2-LABEL: mul_v32i8:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    movdqa %xmm2, %xmm4
; 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:    movdqa %xmm0, %xmm5
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm5 = xmm5[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm5
; SSE2-NEXT:    pmullw %xmm4, %xmm5
; SSE2-NEXT:    movdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT:    pand %xmm4, %xmm5
; 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, %xmm2
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm0
; SSE2-NEXT:    pmullw %xmm2, %xmm0
; SSE2-NEXT:    pand %xmm4, %xmm0
; SSE2-NEXT:    packuswb %xmm5, %xmm0
; SSE2-NEXT:    movdqa %xmm3, %xmm2
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm2 = xmm2[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm2
; SSE2-NEXT:    movdqa %xmm1, %xmm5
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm5 = xmm5[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm5
; SSE2-NEXT:    pmullw %xmm2, %xmm5
; SSE2-NEXT:    pand %xmm4, %xmm5
; 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, %xmm3
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm1
; SSE2-NEXT:    pmullw %xmm3, %xmm1
; SSE2-NEXT:    pand %xmm4, %xmm1
; SSE2-NEXT:    packuswb %xmm5, %xmm1
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v32i8:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pmovsxbw %xmm2, %xmm5
; SSE41-NEXT:    pmovsxbw %xmm0, %xmm4
; SSE41-NEXT:    pmullw %xmm5, %xmm4
; SSE41-NEXT:    movdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
; SSE41-NEXT:    pand %xmm5, %xmm4
; SSE41-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm2, %xmm2
; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm0, %xmm0
; SSE41-NEXT:    pmullw %xmm2, %xmm0
; SSE41-NEXT:    pand %xmm5, %xmm0
; SSE41-NEXT:    packuswb %xmm0, %xmm4
; SSE41-NEXT:    pmovsxbw %xmm3, %xmm0
; SSE41-NEXT:    pmovsxbw %xmm1, %xmm2
; SSE41-NEXT:    pmullw %xmm0, %xmm2
; SSE41-NEXT:    pand %xmm5, %xmm2
; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm3[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm0, %xmm0
; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm1, %xmm1
; SSE41-NEXT:    pmullw %xmm0, %xmm1
; SSE41-NEXT:    pand %xmm5, %xmm1
; SSE41-NEXT:    packuswb %xmm1, %xmm2
; SSE41-NEXT:    movdqa %xmm4, %xmm0
; SSE41-NEXT:    movdqa %xmm2, %xmm1
; SSE41-NEXT:    retq
;
; AVX2-LABEL: mul_v32i8:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT:    vpmovsxbw %xmm2, %ymm2
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm3
; AVX2-NEXT:    vpmovsxbw %xmm3, %ymm3
; AVX2-NEXT:    vpmullw %ymm2, %ymm3, %ymm2
; AVX2-NEXT:    vextracti128 $1, %ymm2, %xmm3
; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX2-NEXT:    vpshufb %xmm4, %xmm3, %xmm3
; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; AVX2-NEXT:    vpmovsxbw %xmm1, %ymm1
; AVX2-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX2-NEXT:    vpmullw %ymm1, %ymm0, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vpshufb %xmm4, %xmm1, %xmm1
; AVX2-NEXT:    vpshufb %xmm4, %xmm0, %xmm0
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT:    vinserti128 $1, %xmm2, %ymm0, %ymm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: mul_v32i8:
; AVX512F:       # BB#0: # %entry
; AVX512F-NEXT:    vpmovsxbw %xmm1, %ymm2
; AVX512F-NEXT:    vpmovsxbw %xmm0, %ymm3
; AVX512F-NEXT:    vpmullw %ymm2, %ymm3, %ymm2
; AVX512F-NEXT:    vpmovsxwd %ymm2, %zmm2
; AVX512F-NEXT:    vpmovdb %zmm2, %xmm2
; AVX512F-NEXT:    vextracti128 $1, %ymm1, %xmm1
; AVX512F-NEXT:    vpmovsxbw %xmm1, %ymm1
; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm0
; AVX512F-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX512F-NEXT:    vpmullw %ymm1, %ymm0, %ymm0
; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
; AVX512F-NEXT:    vinserti128 $1, %xmm0, %ymm2, %ymm0
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: mul_v32i8:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpmovsxbw %ymm1, %zmm1
; AVX512BW-NEXT:    vpmovsxbw %ymm0, %zmm0
; AVX512BW-NEXT:    vpmullw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT:    retq
entry:
  %A = mul <32 x i8> %i, %j
  ret <32 x i8> %A
}

define <16 x i16> @mul_v16i16(<16 x i16> %i, <16 x i16> %j) nounwind  {
; SSE-LABEL: mul_v16i16:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    pmullw %xmm2, %xmm0
; SSE-NEXT:    pmullw %xmm3, %xmm1
; SSE-NEXT:    retq
;
; AVX-LABEL: mul_v16i16:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpmullw %ymm1, %ymm0, %ymm0
; AVX-NEXT:    retq
entry:
  %A = mul <16 x i16> %i, %j
  ret <16 x i16> %A
}

define <8 x i32> @mul_v8i32(<8 x i32> %i, <8 x i32> %j) nounwind  {
; SSE2-LABEL: mul_v8i32:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm2, %xmm0
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm4, %xmm2
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm3, %xmm1
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
; SSE2-NEXT:    pmuludq %xmm2, %xmm3
; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm3[0,2,2,3]
; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v8i32:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pmulld %xmm2, %xmm0
; SSE41-NEXT:    pmulld %xmm3, %xmm1
; SSE41-NEXT:    retq
;
; AVX-LABEL: mul_v8i32:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpmulld %ymm1, %ymm0, %ymm0
; AVX-NEXT:    retq
entry:
  %A = mul <8 x i32> %i, %j
  ret <8 x i32> %A
}

define <4 x i64> @mul_v4i64(<4 x i64> %i, <4 x i64> %j) nounwind  {
; SSE-LABEL: mul_v4i64:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    movdqa %xmm0, %xmm4
; SSE-NEXT:    pmuludq %xmm2, %xmm4
; SSE-NEXT:    movdqa %xmm2, %xmm5
; SSE-NEXT:    psrlq $32, %xmm5
; SSE-NEXT:    pmuludq %xmm0, %xmm5
; SSE-NEXT:    psllq $32, %xmm5
; SSE-NEXT:    psrlq $32, %xmm0
; SSE-NEXT:    pmuludq %xmm2, %xmm0
; SSE-NEXT:    psllq $32, %xmm0
; SSE-NEXT:    paddq %xmm5, %xmm0
; SSE-NEXT:    paddq %xmm4, %xmm0
; SSE-NEXT:    movdqa %xmm1, %xmm2
; SSE-NEXT:    pmuludq %xmm3, %xmm2
; SSE-NEXT:    movdqa %xmm3, %xmm4
; SSE-NEXT:    psrlq $32, %xmm4
; SSE-NEXT:    pmuludq %xmm1, %xmm4
; SSE-NEXT:    psllq $32, %xmm4
; SSE-NEXT:    psrlq $32, %xmm1
; SSE-NEXT:    pmuludq %xmm3, %xmm1
; SSE-NEXT:    psllq $32, %xmm1
; SSE-NEXT:    paddq %xmm4, %xmm1
; SSE-NEXT:    paddq %xmm2, %xmm1
; SSE-NEXT:    retq
;
; AVX-LABEL: mul_v4i64:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpmuludq %ymm1, %ymm0, %ymm2
; AVX-NEXT:    vpsrlq $32, %ymm1, %ymm3
; AVX-NEXT:    vpmuludq %ymm3, %ymm0, %ymm3
; AVX-NEXT:    vpsllq $32, %ymm3, %ymm3
; AVX-NEXT:    vpsrlq $32, %ymm0, %ymm0
; AVX-NEXT:    vpmuludq %ymm1, %ymm0, %ymm0
; AVX-NEXT:    vpsllq $32, %ymm0, %ymm0
; AVX-NEXT:    vpaddq %ymm0, %ymm3, %ymm0
; AVX-NEXT:    vpaddq %ymm0, %ymm2, %ymm0
; AVX-NEXT:    retq
entry:
  %A = mul <4 x i64> %i, %j
  ret <4 x i64> %A
}

define <64 x i8> @mul_v64i8c(<64 x i8> %i) nounwind  {
; SSE2-LABEL: mul_v64i8c:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    movdqa {{.*#+}} xmm4 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
; SSE2-NEXT:    psraw $8, %xmm4
; SSE2-NEXT:    movdqa %xmm0, %xmm6
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm6 = xmm6[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm6
; SSE2-NEXT:    pmullw %xmm4, %xmm6
; SSE2-NEXT:    movdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT:    pand %xmm5, %xmm6
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm0
; SSE2-NEXT:    pmullw %xmm4, %xmm0
; SSE2-NEXT:    pand %xmm5, %xmm0
; SSE2-NEXT:    packuswb %xmm6, %xmm0
; SSE2-NEXT:    movdqa %xmm1, %xmm6
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm6 = xmm6[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm6
; SSE2-NEXT:    pmullw %xmm4, %xmm6
; SSE2-NEXT:    pand %xmm5, %xmm6
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm1
; SSE2-NEXT:    pmullw %xmm4, %xmm1
; SSE2-NEXT:    pand %xmm5, %xmm1
; SSE2-NEXT:    packuswb %xmm6, %xmm1
; SSE2-NEXT:    movdqa %xmm2, %xmm6
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm6 = xmm6[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm6
; SSE2-NEXT:    pmullw %xmm4, %xmm6
; SSE2-NEXT:    pand %xmm5, %xmm6
; 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, %xmm2
; SSE2-NEXT:    pmullw %xmm4, %xmm2
; SSE2-NEXT:    pand %xmm5, %xmm2
; SSE2-NEXT:    packuswb %xmm6, %xmm2
; SSE2-NEXT:    movdqa %xmm3, %xmm6
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm6 = xmm6[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm6
; SSE2-NEXT:    pmullw %xmm4, %xmm6
; SSE2-NEXT:    pand %xmm5, %xmm6
; 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, %xmm3
; SSE2-NEXT:    pmullw %xmm4, %xmm3
; SSE2-NEXT:    pand %xmm5, %xmm3
; SSE2-NEXT:    packuswb %xmm6, %xmm3
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v64i8c:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    movdqa %xmm1, %xmm4
; SSE41-NEXT:    movdqa %xmm0, %xmm1
; SSE41-NEXT:    pmovsxbw %xmm1, %xmm0
; SSE41-NEXT:    pmovsxbw {{.*}}(%rip), %xmm6
; SSE41-NEXT:    pmullw %xmm6, %xmm0
; SSE41-NEXT:    movdqa {{.*#+}} xmm7 = [255,255,255,255,255,255,255,255]
; SSE41-NEXT:    pand %xmm7, %xmm0
; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm1, %xmm1
; SSE41-NEXT:    pmullw %xmm6, %xmm1
; SSE41-NEXT:    pand %xmm7, %xmm1
; SSE41-NEXT:    packuswb %xmm1, %xmm0
; SSE41-NEXT:    pmovsxbw %xmm4, %xmm1
; SSE41-NEXT:    pmullw %xmm6, %xmm1
; SSE41-NEXT:    pand %xmm7, %xmm1
; SSE41-NEXT:    pshufd {{.*#+}} xmm4 = xmm4[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm4, %xmm4
; SSE41-NEXT:    pmullw %xmm6, %xmm4
; SSE41-NEXT:    pand %xmm7, %xmm4
; SSE41-NEXT:    packuswb %xmm4, %xmm1
; SSE41-NEXT:    pmovsxbw %xmm2, %xmm4
; SSE41-NEXT:    pmullw %xmm6, %xmm4
; SSE41-NEXT:    pand %xmm7, %xmm4
; SSE41-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm2, %xmm2
; SSE41-NEXT:    pmullw %xmm6, %xmm2
; SSE41-NEXT:    pand %xmm7, %xmm2
; SSE41-NEXT:    packuswb %xmm2, %xmm4
; SSE41-NEXT:    pmovsxbw %xmm3, %xmm5
; SSE41-NEXT:    pmullw %xmm6, %xmm5
; SSE41-NEXT:    pand %xmm7, %xmm5
; SSE41-NEXT:    pshufd {{.*#+}} xmm2 = xmm3[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm2, %xmm2
; SSE41-NEXT:    pmullw %xmm6, %xmm2
; SSE41-NEXT:    pand %xmm7, %xmm2
; SSE41-NEXT:    packuswb %xmm2, %xmm5
; SSE41-NEXT:    movdqa %xmm4, %xmm2
; SSE41-NEXT:    movdqa %xmm5, %xmm3
; SSE41-NEXT:    retq
;
; AVX2-LABEL: mul_v64i8c:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm2
; AVX2-NEXT:    vpmovsxbw %xmm2, %ymm2
; AVX2-NEXT:    vpmovsxbw {{.*}}(%rip), %ymm3
; AVX2-NEXT:    vpmullw %ymm3, %ymm2, %ymm2
; AVX2-NEXT:    vextracti128 $1, %ymm2, %xmm4
; AVX2-NEXT:    vmovdqa {{.*#+}} xmm5 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX2-NEXT:    vpshufb %xmm5, %xmm4, %xmm4
; AVX2-NEXT:    vpshufb %xmm5, %xmm2, %xmm2
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm4[0]
; AVX2-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX2-NEXT:    vpmullw %ymm3, %ymm0, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm4
; AVX2-NEXT:    vpshufb %xmm5, %xmm4, %xmm4
; AVX2-NEXT:    vpshufb %xmm5, %xmm0, %xmm0
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm4[0]
; AVX2-NEXT:    vinserti128 $1, %xmm2, %ymm0, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT:    vpmovsxbw %xmm2, %ymm2
; AVX2-NEXT:    vpmullw %ymm3, %ymm2, %ymm2
; AVX2-NEXT:    vextracti128 $1, %ymm2, %xmm4
; AVX2-NEXT:    vpshufb %xmm5, %xmm4, %xmm4
; AVX2-NEXT:    vpshufb %xmm5, %xmm2, %xmm2
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm4[0]
; AVX2-NEXT:    vpmovsxbw %xmm1, %ymm1
; AVX2-NEXT:    vpmullw %ymm3, %ymm1, %ymm1
; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm3
; AVX2-NEXT:    vpshufb %xmm5, %xmm3, %xmm3
; AVX2-NEXT:    vpshufb %xmm5, %xmm1, %xmm1
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
; AVX2-NEXT:    vinserti128 $1, %xmm2, %ymm1, %ymm1
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: mul_v64i8c:
; AVX512F:       # BB#0: # %entry
; AVX512F-NEXT:    vpmovsxbw %xmm0, %ymm2
; AVX512F-NEXT:    vpmovsxbw {{.*}}(%rip), %ymm3
; AVX512F-NEXT:    vpmullw %ymm3, %ymm2, %ymm2
; AVX512F-NEXT:    vpmovsxwd %ymm2, %zmm2
; AVX512F-NEXT:    vpmovdb %zmm2, %xmm2
; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm0
; AVX512F-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX512F-NEXT:    vpmullw %ymm3, %ymm0, %ymm0
; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
; AVX512F-NEXT:    vinserti128 $1, %xmm0, %ymm2, %ymm0
; AVX512F-NEXT:    vpmovsxbw %xmm1, %ymm2
; AVX512F-NEXT:    vpmullw %ymm3, %ymm2, %ymm2
; AVX512F-NEXT:    vpmovsxwd %ymm2, %zmm2
; AVX512F-NEXT:    vpmovdb %zmm2, %xmm2
; AVX512F-NEXT:    vextracti128 $1, %ymm1, %xmm1
; AVX512F-NEXT:    vpmovsxbw %xmm1, %ymm1
; AVX512F-NEXT:    vpmullw %ymm3, %ymm1, %ymm1
; AVX512F-NEXT:    vpmovsxwd %ymm1, %zmm1
; AVX512F-NEXT:    vpmovdb %zmm1, %xmm1
; AVX512F-NEXT:    vinserti128 $1, %xmm1, %ymm2, %ymm1
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: mul_v64i8c:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vmovdqa {{.*#+}} ymm1 = [117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117,117]
; AVX512BW-NEXT:    vpmovsxbw %ymm1, %zmm1
; AVX512BW-NEXT:    vpmovsxbw %ymm0, %zmm2
; AVX512BW-NEXT:    vpmullw %zmm1, %zmm2, %zmm2
; AVX512BW-NEXT:    vpmovwb %zmm2, %ymm2
; AVX512BW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
; AVX512BW-NEXT:    vpmovsxbw %ymm0, %zmm0
; AVX512BW-NEXT:    vpmullw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT:    vinserti64x4 $1, %ymm0, %zmm2, %zmm0
; AVX512BW-NEXT:    retq
entry:
  %A = mul <64 x i8> %i, < i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117, i8 117 >
  ret <64 x i8> %A
}

define <64 x i8> @mul_v64i8(<64 x i8> %i, <64 x i8> %j) nounwind  {
; SSE2-LABEL: mul_v64i8:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    movdqa %xmm4, %xmm8
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm8 = xmm8[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm8
; SSE2-NEXT:    movdqa %xmm0, %xmm9
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm9 = xmm9[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm9
; SSE2-NEXT:    pmullw %xmm8, %xmm9
; SSE2-NEXT:    movdqa {{.*#+}} xmm8 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT:    pand %xmm8, %xmm9
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm4 = xmm4[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm4
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm0
; SSE2-NEXT:    pmullw %xmm4, %xmm0
; SSE2-NEXT:    pand %xmm8, %xmm0
; SSE2-NEXT:    packuswb %xmm9, %xmm0
; SSE2-NEXT:    movdqa %xmm5, %xmm9
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm9 = xmm9[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm9
; SSE2-NEXT:    movdqa %xmm1, %xmm4
; 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:    pmullw %xmm9, %xmm4
; SSE2-NEXT:    pand %xmm8, %xmm4
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm5 = xmm5[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm5
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm1
; SSE2-NEXT:    pmullw %xmm5, %xmm1
; SSE2-NEXT:    pand %xmm8, %xmm1
; SSE2-NEXT:    packuswb %xmm4, %xmm1
; SSE2-NEXT:    movdqa %xmm6, %xmm4
; 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:    movdqa %xmm2, %xmm5
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm5 = xmm5[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm5
; SSE2-NEXT:    pmullw %xmm4, %xmm5
; SSE2-NEXT:    pand %xmm8, %xmm5
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm6 = xmm6[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm6
; 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, %xmm2
; SSE2-NEXT:    pmullw %xmm6, %xmm2
; SSE2-NEXT:    pand %xmm8, %xmm2
; SSE2-NEXT:    packuswb %xmm5, %xmm2
; SSE2-NEXT:    movdqa %xmm7, %xmm4
; 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:    movdqa %xmm3, %xmm5
; SSE2-NEXT:    punpckhbw {{.*#+}} xmm5 = xmm5[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT:    psraw $8, %xmm5
; SSE2-NEXT:    pmullw %xmm4, %xmm5
; SSE2-NEXT:    pand %xmm8, %xmm5
; SSE2-NEXT:    punpcklbw {{.*#+}} xmm7 = xmm7[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT:    psraw $8, %xmm7
; 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, %xmm3
; SSE2-NEXT:    pmullw %xmm7, %xmm3
; SSE2-NEXT:    pand %xmm8, %xmm3
; SSE2-NEXT:    packuswb %xmm5, %xmm3
; SSE2-NEXT:    retq
;
; SSE41-LABEL: mul_v64i8:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    movdqa %xmm1, %xmm8
; SSE41-NEXT:    movdqa %xmm0, %xmm1
; SSE41-NEXT:    pmovsxbw %xmm4, %xmm9
; SSE41-NEXT:    pmovsxbw %xmm1, %xmm0
; SSE41-NEXT:    pmullw %xmm9, %xmm0
; SSE41-NEXT:    movdqa {{.*#+}} xmm9 = [255,255,255,255,255,255,255,255]
; SSE41-NEXT:    pand %xmm9, %xmm0
; SSE41-NEXT:    pshufd {{.*#+}} xmm4 = xmm4[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm4, %xmm4
; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm1, %xmm1
; SSE41-NEXT:    pmullw %xmm4, %xmm1
; SSE41-NEXT:    pand %xmm9, %xmm1
; SSE41-NEXT:    packuswb %xmm1, %xmm0
; SSE41-NEXT:    pmovsxbw %xmm5, %xmm4
; SSE41-NEXT:    pmovsxbw %xmm8, %xmm1
; SSE41-NEXT:    pmullw %xmm4, %xmm1
; SSE41-NEXT:    pand %xmm9, %xmm1
; SSE41-NEXT:    pshufd {{.*#+}} xmm4 = xmm5[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm4, %xmm4
; SSE41-NEXT:    pshufd {{.*#+}} xmm5 = xmm8[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm5, %xmm5
; SSE41-NEXT:    pmullw %xmm4, %xmm5
; SSE41-NEXT:    pand %xmm9, %xmm5
; SSE41-NEXT:    packuswb %xmm5, %xmm1
; SSE41-NEXT:    pmovsxbw %xmm6, %xmm5
; SSE41-NEXT:    pmovsxbw %xmm2, %xmm4
; SSE41-NEXT:    pmullw %xmm5, %xmm4
; SSE41-NEXT:    pand %xmm9, %xmm4
; SSE41-NEXT:    pshufd {{.*#+}} xmm5 = xmm6[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm5, %xmm5
; SSE41-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm2, %xmm2
; SSE41-NEXT:    pmullw %xmm5, %xmm2
; SSE41-NEXT:    pand %xmm9, %xmm2
; SSE41-NEXT:    packuswb %xmm2, %xmm4
; SSE41-NEXT:    pmovsxbw %xmm7, %xmm2
; SSE41-NEXT:    pmovsxbw %xmm3, %xmm5
; SSE41-NEXT:    pmullw %xmm2, %xmm5
; SSE41-NEXT:    pand %xmm9, %xmm5
; SSE41-NEXT:    pshufd {{.*#+}} xmm2 = xmm7[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm2, %xmm2
; SSE41-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[2,3,0,1]
; SSE41-NEXT:    pmovsxbw %xmm3, %xmm3
; SSE41-NEXT:    pmullw %xmm2, %xmm3
; SSE41-NEXT:    pand %xmm9, %xmm3
; SSE41-NEXT:    packuswb %xmm3, %xmm5
; SSE41-NEXT:    movdqa %xmm4, %xmm2
; SSE41-NEXT:    movdqa %xmm5, %xmm3
; SSE41-NEXT:    retq
;
; AVX2-LABEL: mul_v64i8:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vextracti128 $1, %ymm2, %xmm4
; AVX2-NEXT:    vpmovsxbw %xmm4, %ymm4
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm5
; AVX2-NEXT:    vpmovsxbw %xmm5, %ymm5
; AVX2-NEXT:    vpmullw %ymm4, %ymm5, %ymm5
; AVX2-NEXT:    vextracti128 $1, %ymm5, %xmm6
; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX2-NEXT:    vpshufb %xmm4, %xmm6, %xmm6
; AVX2-NEXT:    vpshufb %xmm4, %xmm5, %xmm5
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm5 = xmm5[0],xmm6[0]
; AVX2-NEXT:    vpmovsxbw %xmm2, %ymm2
; AVX2-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX2-NEXT:    vpmullw %ymm2, %ymm0, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm2
; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
; AVX2-NEXT:    vpshufb %xmm4, %xmm0, %xmm0
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX2-NEXT:    vinserti128 $1, %xmm5, %ymm0, %ymm0
; AVX2-NEXT:    vextracti128 $1, %ymm3, %xmm2
; AVX2-NEXT:    vpmovsxbw %xmm2, %ymm2
; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm5
; AVX2-NEXT:    vpmovsxbw %xmm5, %ymm5
; AVX2-NEXT:    vpmullw %ymm2, %ymm5, %ymm2
; AVX2-NEXT:    vextracti128 $1, %ymm2, %xmm5
; AVX2-NEXT:    vpshufb %xmm4, %xmm5, %xmm5
; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm5[0]
; AVX2-NEXT:    vpmovsxbw %xmm3, %ymm3
; AVX2-NEXT:    vpmovsxbw %xmm1, %ymm1
; AVX2-NEXT:    vpmullw %ymm3, %ymm1, %ymm1
; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm3
; AVX2-NEXT:    vpshufb %xmm4, %xmm3, %xmm3
; AVX2-NEXT:    vpshufb %xmm4, %xmm1, %xmm1
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
; AVX2-NEXT:    vinserti128 $1, %xmm2, %ymm1, %ymm1
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: mul_v64i8:
; AVX512F:       # BB#0: # %entry
; AVX512F-NEXT:    vpmovsxbw %xmm2, %ymm4
; AVX512F-NEXT:    vpmovsxbw %xmm0, %ymm5
; AVX512F-NEXT:    vpmullw %ymm4, %ymm5, %ymm4
; AVX512F-NEXT:    vpmovsxwd %ymm4, %zmm4
; AVX512F-NEXT:    vpmovdb %zmm4, %xmm4
; AVX512F-NEXT:    vextracti128 $1, %ymm2, %xmm2
; AVX512F-NEXT:    vpmovsxbw %xmm2, %ymm2
; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm0
; AVX512F-NEXT:    vpmovsxbw %xmm0, %ymm0
; AVX512F-NEXT:    vpmullw %ymm2, %ymm0, %ymm0
; AVX512F-NEXT:    vpmovsxwd %ymm0, %zmm0
; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
; AVX512F-NEXT:    vinserti128 $1, %xmm0, %ymm4, %ymm0
; AVX512F-NEXT:    vpmovsxbw %xmm3, %ymm2
; AVX512F-NEXT:    vpmovsxbw %xmm1, %ymm4
; AVX512F-NEXT:    vpmullw %ymm2, %ymm4, %ymm2
; AVX512F-NEXT:    vpmovsxwd %ymm2, %zmm2
; AVX512F-NEXT:    vpmovdb %zmm2, %xmm2
; AVX512F-NEXT:    vextracti128 $1, %ymm3, %xmm3
; AVX512F-NEXT:    vpmovsxbw %xmm3, %ymm3
; AVX512F-NEXT:    vextracti128 $1, %ymm1, %xmm1
; AVX512F-NEXT:    vpmovsxbw %xmm1, %ymm1
; AVX512F-NEXT:    vpmullw %ymm3, %ymm1, %ymm1
; AVX512F-NEXT:    vpmovsxwd %ymm1, %zmm1
; AVX512F-NEXT:    vpmovdb %zmm1, %xmm1
; AVX512F-NEXT:    vinserti128 $1, %xmm1, %ymm2, %ymm1
; AVX512F-NEXT:    retq
;
; AVX512BW-LABEL: mul_v64i8:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpmovsxbw %ymm1, %zmm2
; AVX512BW-NEXT:    vpmovsxbw %ymm0, %zmm3
; AVX512BW-NEXT:    vpmullw %zmm2, %zmm3, %zmm2
; AVX512BW-NEXT:    vpmovwb %zmm2, %ymm2
; AVX512BW-NEXT:    vextracti64x4 $1, %zmm1, %ymm1
; AVX512BW-NEXT:    vpmovsxbw %ymm1, %zmm1
; AVX512BW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
; AVX512BW-NEXT:    vpmovsxbw %ymm0, %zmm0
; AVX512BW-NEXT:    vpmullw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT:    vinserti64x4 $1, %ymm0, %zmm2, %zmm0
; AVX512BW-NEXT:    retq
entry:
  %A = mul <64 x i8> %i, %j
  ret <64 x i8> %A
}