%res = trunc <512 x i16> %lshr to <512 x i8>
ret <512 x i8> %res
}
+
+; This is not an avg, but its structurally similar and previously caused a crash
+; because the constants can't be read with APInt::getZExtValue.
+define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind {
+; SSE2-LABEL: not_avg_v16i8_wide_constants:
+; SSE2: # %bb.0:
+; SSE2-NEXT: pushq %rbp
+; SSE2-NEXT: pushq %r15
+; SSE2-NEXT: pushq %r14
+; SSE2-NEXT: pushq %r13
+; SSE2-NEXT: pushq %r12
+; SSE2-NEXT: pushq %rbx
+; SSE2-NEXT: subq $56, %rsp
+; SSE2-NEXT: movaps (%rdi), %xmm1
+; SSE2-NEXT: movaps (%rsi), %xmm0
+; SSE2-NEXT: movaps %xmm1, -{{[0-9]+}}(%rsp)
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %edi
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r15d
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %edx
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r13d
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r10d
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r9d
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebx
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r12d
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebp
+; SSE2-NEXT: movq %rbp, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebp
+; SSE2-NEXT: movq %rbp, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebp
+; SSE2-NEXT: movq %rbp, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebp
+; SSE2-NEXT: movq %rbp, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ebp
+; SSE2-NEXT: movq %rbp, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r11d
+; SSE2-NEXT: addq %rax, %r11
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: addq %rdi, %rax
+; SSE2-NEXT: movq %rax, %rdi
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r14d
+; SSE2-NEXT: addq %r15, %r14
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: addq %rsi, %rax
+; SSE2-NEXT: movq %rax, %r15
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %esi
+; SSE2-NEXT: addq %rdx, %rsi
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r8d
+; SSE2-NEXT: addq %r13, %r8
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: addq %r10, %rax
+; SSE2-NEXT: movq %rax, %r10
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: addq %rcx, %rax
+; SSE2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %r13d
+; SSE2-NEXT: addq %r9, %r13
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %ecx
+; SSE2-NEXT: addq %rbx, %rcx
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: addq %r12, %rax
+; SSE2-NEXT: movq %rax, %r9
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: addq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; SSE2-NEXT: movq %rax, %rbp
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: addq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; SSE2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: addq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; SSE2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: addq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; SSE2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
+; SSE2-NEXT: addq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; SSE2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: xorl %eax, %eax
+; SSE2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: addq $-1, %r11
+; SSE2-NEXT: movq %r11, {{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movl $0, %r12d
+; SSE2-NEXT: adcq $-1, %r12
+; SSE2-NEXT: addq $-1, %rdi
+; SSE2-NEXT: movq %rdi, {{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movl $0, %edx
+; SSE2-NEXT: adcq $-1, %rdx
+; SSE2-NEXT: addq $-1, %r14
+; SSE2-NEXT: movq %r14, {{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movl $0, %edi
+; SSE2-NEXT: adcq $-1, %rdi
+; SSE2-NEXT: addq $-1, %r15
+; SSE2-NEXT: movq %r15, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movl $0, %eax
+; SSE2-NEXT: adcq $-1, %rax
+; SSE2-NEXT: addq $-1, %rsi
+; SSE2-NEXT: movq %rsi, (%rsp) # 8-byte Spill
+; SSE2-NEXT: movl $0, %r15d
+; SSE2-NEXT: adcq $-1, %r15
+; SSE2-NEXT: addq $-1, %r8
+; SSE2-NEXT: movq %r8, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movl $0, %r14d
+; SSE2-NEXT: adcq $-1, %r14
+; SSE2-NEXT: addq $-1, %r10
+; SSE2-NEXT: movq %r10, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movl $0, %esi
+; SSE2-NEXT: adcq $-1, %rsi
+; SSE2-NEXT: movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; SSE2-NEXT: addq $-1, %r10
+; SSE2-NEXT: movl $0, %esi
+; SSE2-NEXT: adcq $-1, %rsi
+; SSE2-NEXT: movq %rsi, %r8
+; SSE2-NEXT: addq $-1, %r13
+; SSE2-NEXT: movl $0, %esi
+; SSE2-NEXT: adcq $-1, %rsi
+; SSE2-NEXT: movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: addq $-1, %rcx
+; SSE2-NEXT: movl $0, %esi
+; SSE2-NEXT: adcq $-1, %rsi
+; SSE2-NEXT: addq $-1, %r9
+; SSE2-NEXT: movq %r9, {{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movl $0, %r9d
+; SSE2-NEXT: adcq $-1, %r9
+; SSE2-NEXT: addq $-1, %rbp
+; SSE2-NEXT: movq %rbp, {{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: movl $0, %r11d
+; SSE2-NEXT: adcq $-1, %r11
+; SSE2-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; SSE2-NEXT: movl $0, %ebx
+; SSE2-NEXT: adcq $-1, %rbx
+; SSE2-NEXT: movq %rbx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; SSE2-NEXT: movl $0, %ebp
+; SSE2-NEXT: adcq $-1, %rbp
+; SSE2-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; SSE2-NEXT: movl $0, %ebx
+; SSE2-NEXT: adcq $-1, %rbx
+; SSE2-NEXT: movq %rbx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; SSE2-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; SSE2-NEXT: adcq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; SSE2-NEXT: shldq $63, %rcx, %rsi
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %rbx # 8-byte Reload
+; SSE2-NEXT: shldq $63, %r13, %rbx
+; SSE2-NEXT: shldq $63, %r10, %r8
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; SSE2-NEXT: shldq $63, %rcx, %r10
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; SSE2-NEXT: shldq $63, %rcx, %r14
+; SSE2-NEXT: movq (%rsp), %rcx # 8-byte Reload
+; SSE2-NEXT: shldq $63, %rcx, %r15
+; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; SSE2-NEXT: shldq $63, %rcx, %rdi
+; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; SSE2-NEXT: shldq $63, %rcx, %rdx
+; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; SSE2-NEXT: shldq $63, %rcx, %r12
+; SSE2-NEXT: movq %r12, %xmm11
+; SSE2-NEXT: movq %rdx, %xmm5
+; SSE2-NEXT: movq %rdi, %xmm13
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; SSE2-NEXT: shrdq $1, %rax, %rcx
+; SSE2-NEXT: movq %rcx, %xmm15
+; SSE2-NEXT: shrq %rax
+; SSE2-NEXT: movq %rax, %xmm8
+; SSE2-NEXT: movq %r15, %xmm9
+; SSE2-NEXT: movq %r14, %xmm6
+; SSE2-NEXT: movq %r10, %xmm7
+; SSE2-NEXT: movq %r8, %xmm0
+; SSE2-NEXT: movdqa %xmm0, -{{[0-9]+}}(%rsp) # 16-byte Spill
+; SSE2-NEXT: movq %rbx, %xmm10
+; SSE2-NEXT: movq %rsi, %xmm4
+; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; SSE2-NEXT: shrdq $1, %r9, %rax
+; SSE2-NEXT: movq %rax, %xmm1
+; SSE2-NEXT: shrq %r9
+; SSE2-NEXT: movq %r9, %xmm12
+; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; SSE2-NEXT: shrdq $1, %r11, %rax
+; SSE2-NEXT: movq %rax, %xmm2
+; SSE2-NEXT: shrq %r11
+; SSE2-NEXT: movq %r11, %xmm14
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; SSE2-NEXT: shrdq $1, %rcx, %rax
+; SSE2-NEXT: movq %rax, %xmm3
+; SSE2-NEXT: movq %rcx, %rax
+; SSE2-NEXT: shrq %rax
+; SSE2-NEXT: pslldq {{.*#+}} xmm11 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm11[0]
+; SSE2-NEXT: pslldq {{.*#+}} xmm5 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm5[0,1]
+; SSE2-NEXT: pand {{.*}}(%rip), %xmm5
+; SSE2-NEXT: por %xmm11, %xmm5
+; SSE2-NEXT: movq %rax, %xmm11
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; SSE2-NEXT: movq %rbp, %rcx
+; SSE2-NEXT: shrdq $1, %rcx, %rax
+; SSE2-NEXT: pslldq {{.*#+}} xmm13 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm13[0,1,2]
+; SSE2-NEXT: punpcklqdq {{.*#+}} xmm15 = xmm15[0],xmm8[0]
+; SSE2-NEXT: movdqa {{.*#+}} xmm0 = [255,255,255,255,255,255,255,255,255,255,255,255,255,0,255,255]
+; SSE2-NEXT: pshufd {{.*#+}} xmm15 = xmm15[0,1,2,0]
+; SSE2-NEXT: pand %xmm0, %xmm15
+; SSE2-NEXT: pandn %xmm13, %xmm0
+; SSE2-NEXT: movq %rax, %xmm8
+; SSE2-NEXT: shrq %rcx
+; SSE2-NEXT: por %xmm15, %xmm0
+; SSE2-NEXT: movdqa {{.*#+}} xmm13 = [65535,65535,65535,65535,65535,65535,65535,0]
+; SSE2-NEXT: pand %xmm13, %xmm0
+; SSE2-NEXT: pandn %xmm5, %xmm13
+; SSE2-NEXT: movq %rcx, %xmm15
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; SSE2-NEXT: shrdq $1, %rcx, %rax
+; SSE2-NEXT: por %xmm0, %xmm13
+; SSE2-NEXT: pslldq {{.*#+}} xmm9 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm9[0,1,2,3,4]
+; SSE2-NEXT: movdqa {{.*#+}} xmm0 = [255,255,255,255,255,255,255,255,255,255,255,0,255,255,255,255]
+; SSE2-NEXT: pslldq {{.*#+}} xmm6 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm6[0,1,2,3,4,5]
+; SSE2-NEXT: pand %xmm0, %xmm6
+; SSE2-NEXT: pandn %xmm9, %xmm0
+; SSE2-NEXT: movq %rax, %xmm9
+; SSE2-NEXT: shrq %rcx
+; SSE2-NEXT: por %xmm6, %xmm0
+; SSE2-NEXT: pslldq {{.*#+}} xmm7 = zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm7[0,1,2,3,4,5,6]
+; SSE2-NEXT: movdqa {{.*#+}} xmm6 = [255,255,255,255,255,255,255,255,255,0,255,255,255,255,255,255]
+; SSE2-NEXT: pshufd $68, -{{[0-9]+}}(%rsp), %xmm5 # 16-byte Folded Reload
+; SSE2-NEXT: # xmm5 = mem[0,1,0,1]
+; SSE2-NEXT: pand %xmm6, %xmm5
+; SSE2-NEXT: pandn %xmm7, %xmm6
+; SSE2-NEXT: movq %rcx, %xmm7
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; SSE2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; SSE2-NEXT: shrdq $1, %rax, %rcx
+; SSE2-NEXT: por %xmm5, %xmm6
+; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [65535,65535,65535,65535,65535,0,65535,65535]
+; SSE2-NEXT: pand %xmm5, %xmm6
+; SSE2-NEXT: pandn %xmm0, %xmm5
+; SSE2-NEXT: movq %rcx, %xmm0
+; SSE2-NEXT: shrq %rax
+; SSE2-NEXT: por %xmm6, %xmm5
+; SSE2-NEXT: movq %rax, %xmm6
+; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm5[0,1,2,2]
+; SSE2-NEXT: punpckhdq {{.*#+}} xmm5 = xmm5[2],xmm13[2],xmm5[3],xmm13[3]
+; SSE2-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm10[0],xmm4[1],xmm10[1],xmm4[2],xmm10[2],xmm4[3],xmm10[3],xmm4[4],xmm10[4],xmm4[5],xmm10[5],xmm4[6],xmm10[6],xmm4[7],xmm10[7]
+; SSE2-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm12[0]
+; SSE2-NEXT: pslld $24, %xmm1
+; SSE2-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm14[0]
+; SSE2-NEXT: movdqa {{.*#+}} xmm10 = [255,255,255,0,255,255,255,255,255,255,255,255,255,255,255,255]
+; SSE2-NEXT: pslld $16, %xmm2
+; SSE2-NEXT: pand %xmm10, %xmm2
+; SSE2-NEXT: pandn %xmm1, %xmm10
+; SSE2-NEXT: por %xmm2, %xmm10
+; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [65535,0,65535,65535,65535,65535,65535,65535]
+; SSE2-NEXT: pand %xmm1, %xmm4
+; SSE2-NEXT: pandn %xmm10, %xmm1
+; SSE2-NEXT: por %xmm4, %xmm1
+; SSE2-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm11[0]
+; SSE2-NEXT: psllq $56, %xmm3
+; SSE2-NEXT: punpcklqdq {{.*#+}} xmm8 = xmm8[0],xmm15[0]
+; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,0,255,255,255,255,255,255,255,255]
+; SSE2-NEXT: psllq $48, %xmm8
+; SSE2-NEXT: pand %xmm2, %xmm8
+; SSE2-NEXT: pandn %xmm3, %xmm2
+; SSE2-NEXT: por %xmm8, %xmm2
+; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [65535,65535,65535,0,65535,65535,65535,65535]
+; SSE2-NEXT: punpcklqdq {{.*#+}} xmm9 = xmm9[0],xmm7[0]
+; SSE2-NEXT: psllq $40, %xmm9
+; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,255,255,255,255,0,255,255,255,255,255,255,255,255,255,255]
+; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
+; SSE2-NEXT: pand %xmm4, %xmm0
+; SSE2-NEXT: pandn %xmm9, %xmm4
+; SSE2-NEXT: por %xmm0, %xmm4
+; SSE2-NEXT: pand %xmm3, %xmm4
+; SSE2-NEXT: pandn %xmm2, %xmm3
+; SSE2-NEXT: por %xmm3, %xmm4
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[1,1,2,3]
+; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE2-NEXT: movsd {{.*#+}} xmm5 = xmm1[0],xmm5[1]
+; SSE2-NEXT: movupd %xmm5, (%rax)
+; SSE2-NEXT: addq $56, %rsp
+; SSE2-NEXT: popq %rbx
+; SSE2-NEXT: popq %r12
+; SSE2-NEXT: popq %r13
+; SSE2-NEXT: popq %r14
+; SSE2-NEXT: popq %r15
+; SSE2-NEXT: popq %rbp
+; SSE2-NEXT: retq
+;
+; AVX1-LABEL: not_avg_v16i8_wide_constants:
+; AVX1: # %bb.0:
+; AVX1-NEXT: pushq %rbp
+; AVX1-NEXT: pushq %r15
+; AVX1-NEXT: pushq %r14
+; AVX1-NEXT: pushq %r13
+; AVX1-NEXT: pushq %r12
+; AVX1-NEXT: pushq %rbx
+; AVX1-NEXT: subq $24, %rsp
+; AVX1-NEXT: movq %rsi, %r8
+; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm0 = 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: vpmovzxwd {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm2, %rcx
+; AVX1-NEXT: vmovq %xmm2, %rax
+; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm1, %rbx
+; AVX1-NEXT: vmovq %xmm1, %rbp
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm1, %r10
+; AVX1-NEXT: vmovq %xmm1, %r12
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm0, %r15
+; AVX1-NEXT: vmovq %xmm0, %r14
+; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm0 = 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: vpmovzxwd {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm2, %rdx
+; AVX1-NEXT: vmovq %xmm2, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX1-NEXT: vmovq %xmm1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; 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: vpmovzxwd {{.*#+}} xmm3 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm4 = xmm3[0],zero,xmm3[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm4, %r9
+; AVX1-NEXT: addq %rcx, %r9
+; AVX1-NEXT: vmovq %xmm4, %r13
+; AVX1-NEXT: addq %rax, %r13
+; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[2,3,0,1]
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm3 = xmm3[0],zero,xmm3[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm3, %rcx
+; AVX1-NEXT: addq %rbx, %rcx
+; AVX1-NEXT: vmovq %xmm3, %r11
+; AVX1-NEXT: addq %rbp, %r11
+; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
+; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm3 = xmm2[0],zero,xmm2[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm3, %rax
+; AVX1-NEXT: addq %r10, %rax
+; AVX1-NEXT: movq %rax, %rsi
+; AVX1-NEXT: vmovq %xmm3, %rax
+; AVX1-NEXT: addq %r12, %rax
+; AVX1-NEXT: movq %rax, %rbx
+; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm2, %rax
+; AVX1-NEXT: addq %r15, %rax
+; AVX1-NEXT: movq %rax, %r15
+; AVX1-NEXT: vmovq %xmm2, %rax
+; AVX1-NEXT: addq %r14, %rax
+; AVX1-NEXT: movq %rax, %r14
+; AVX1-NEXT: vmovq %xmm1, %rax
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; 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: vpmovzxwd {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm3 = xmm2[0],zero,xmm2[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm3, %rbp
+; AVX1-NEXT: addq %rdx, %rbp
+; AVX1-NEXT: movq %rbp, %r8
+; AVX1-NEXT: vmovq %xmm3, %rbp
+; AVX1-NEXT: addq -{{[0-9]+}}(%rsp), %rbp # 8-byte Folded Reload
+; AVX1-NEXT: movq %rbp, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm2, %rdx
+; AVX1-NEXT: addq -{{[0-9]+}}(%rsp), %rdx # 8-byte Folded Reload
+; AVX1-NEXT: movq %rdx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: vmovq %xmm2, %rdx
+; AVX1-NEXT: addq -{{[0-9]+}}(%rsp), %rdx # 8-byte Folded Reload
+; AVX1-NEXT: movq %rdx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm2, %rdx
+; AVX1-NEXT: addq -{{[0-9]+}}(%rsp), %rdx # 8-byte Folded Reload
+; AVX1-NEXT: movq %rdx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: vmovq %xmm2, %r12
+; AVX1-NEXT: addq %rax, %r12
+; AVX1-NEXT: vpextrq $1, %xmm0, %rax
+; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
+; AVX1-NEXT: vpextrq $1, %xmm1, %r10
+; AVX1-NEXT: addq %rax, %r10
+; AVX1-NEXT: vmovq %xmm0, %rax
+; AVX1-NEXT: vmovq %xmm1, %rdi
+; AVX1-NEXT: addq %rax, %rdi
+; AVX1-NEXT: addq $-1, %r9
+; AVX1-NEXT: movq %r9, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: movl $0, %eax
+; AVX1-NEXT: adcq $-1, %rax
+; AVX1-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: addq $-1, %r13
+; AVX1-NEXT: movq %r13, {{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: movl $0, %eax
+; AVX1-NEXT: adcq $-1, %rax
+; AVX1-NEXT: movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: addq $-1, %rcx
+; AVX1-NEXT: movq %rcx, (%rsp) # 8-byte Spill
+; AVX1-NEXT: movl $0, %eax
+; AVX1-NEXT: adcq $-1, %rax
+; AVX1-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: addq $-1, %r11
+; AVX1-NEXT: movq %r11, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: movl $0, %eax
+; AVX1-NEXT: adcq $-1, %rax
+; AVX1-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: addq $-1, %rsi
+; AVX1-NEXT: movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: movl $0, %eax
+; AVX1-NEXT: adcq $-1, %rax
+; AVX1-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: addq $-1, %rbx
+; AVX1-NEXT: movq %rbx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: movl $0, %eax
+; AVX1-NEXT: adcq $-1, %rax
+; AVX1-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: addq $-1, %r15
+; AVX1-NEXT: movq %r15, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: movl $0, %ebp
+; AVX1-NEXT: adcq $-1, %rbp
+; AVX1-NEXT: addq $-1, %r14
+; AVX1-NEXT: movq %r14, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: movl $0, %r15d
+; AVX1-NEXT: adcq $-1, %r15
+; AVX1-NEXT: addq $-1, %r8
+; AVX1-NEXT: movq %r8, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: movl $0, %eax
+; AVX1-NEXT: adcq $-1, %rax
+; AVX1-NEXT: movq %rax, %rsi
+; AVX1-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX1-NEXT: movl $0, %r13d
+; AVX1-NEXT: adcq $-1, %r13
+; AVX1-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX1-NEXT: movl $0, %r14d
+; AVX1-NEXT: adcq $-1, %r14
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; AVX1-NEXT: addq $-1, %rdx
+; AVX1-NEXT: movl $0, %r11d
+; AVX1-NEXT: adcq $-1, %r11
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX1-NEXT: addq $-1, %rax
+; AVX1-NEXT: movl $0, %ebx
+; AVX1-NEXT: adcq $-1, %rbx
+; AVX1-NEXT: addq $-1, %r12
+; AVX1-NEXT: movl $0, %r9d
+; AVX1-NEXT: adcq $-1, %r9
+; AVX1-NEXT: addq $-1, %r10
+; AVX1-NEXT: movl $0, %r8d
+; AVX1-NEXT: adcq $-1, %r8
+; AVX1-NEXT: addq $-1, %rdi
+; AVX1-NEXT: movl $0, %ecx
+; AVX1-NEXT: adcq $-1, %rcx
+; AVX1-NEXT: shldq $63, %rdi, %rcx
+; AVX1-NEXT: movq %rcx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: shldq $63, %r10, %r8
+; AVX1-NEXT: shldq $63, %r12, %r9
+; AVX1-NEXT: shldq $63, %rax, %rbx
+; AVX1-NEXT: shldq $63, %rdx, %r11
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rdx, %r14
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rdx, %r13
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rax, %rsi
+; AVX1-NEXT: movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rax, %r15
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rax, %rbp
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rax, %rsi
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rax, %rcx
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rdi # 8-byte Reload
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rax, %rdi
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %r12 # 8-byte Reload
+; AVX1-NEXT: movq (%rsp), %rax # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rax, %r12
+; AVX1-NEXT: movq {{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; AVX1-NEXT: movq {{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rax, %r10
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; AVX1-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX1-NEXT: shldq $63, %rdx, %rax
+; AVX1-NEXT: vmovq %rax, %xmm8
+; AVX1-NEXT: vmovq %r10, %xmm0
+; AVX1-NEXT: vmovq %r12, %xmm1
+; AVX1-NEXT: vmovq %rdi, %xmm11
+; AVX1-NEXT: vmovq %rcx, %xmm2
+; AVX1-NEXT: vmovq %rsi, %xmm13
+; AVX1-NEXT: vmovq %rbp, %xmm14
+; AVX1-NEXT: vmovq %r15, %xmm15
+; AVX1-NEXT: vmovq -{{[0-9]+}}(%rsp), %xmm9 # 8-byte Folded Reload
+; AVX1-NEXT: # xmm9 = mem[0],zero
+; AVX1-NEXT: vmovq %r13, %xmm10
+; AVX1-NEXT: vmovq %r14, %xmm12
+; AVX1-NEXT: vmovq %r11, %xmm3
+; AVX1-NEXT: vmovq %rbx, %xmm4
+; AVX1-NEXT: vmovq %r9, %xmm5
+; AVX1-NEXT: vmovq %r8, %xmm6
+; AVX1-NEXT: vmovq -{{[0-9]+}}(%rsp), %xmm7 # 8-byte Folded Reload
+; AVX1-NEXT: # xmm7 = mem[0],zero
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm8 = xmm0[0],xmm8[0]
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm11[0],xmm1[0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm8 = xmm8[0,2],xmm0[0,2]
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm13[0],xmm2[0]
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm15[0],xmm14[0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm11 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
+; AVX1-NEXT: vpshufb %xmm1, %xmm8, %xmm0
+; AVX1-NEXT: vpshufb %xmm1, %xmm11, %xmm2
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm2 = xmm10[0],xmm9[0]
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm12[0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[0,2],xmm3[0,2]
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm3 = xmm5[0],xmm4[0]
+; AVX1-NEXT: vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX1-NEXT: vpshufb %xmm4, %xmm0, %xmm0
+; AVX1-NEXT: vpshufb %xmm1, %xmm2, %xmm2
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm5 = xmm7[0],xmm6[0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm3 = xmm3[0,2],xmm5[0,2]
+; AVX1-NEXT: vpshufb %xmm1, %xmm3, %xmm1
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
+; AVX1-NEXT: vpshufb %xmm4, %xmm1, %xmm1
+; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; AVX1-NEXT: vmovdqu %xmm0, (%rax)
+; AVX1-NEXT: addq $24, %rsp
+; AVX1-NEXT: popq %rbx
+; AVX1-NEXT: popq %r12
+; AVX1-NEXT: popq %r13
+; AVX1-NEXT: popq %r14
+; AVX1-NEXT: popq %r15
+; AVX1-NEXT: popq %rbp
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: not_avg_v16i8_wide_constants:
+; AVX2: # %bb.0:
+; AVX2-NEXT: pushq %rbp
+; AVX2-NEXT: pushq %r15
+; AVX2-NEXT: pushq %r14
+; AVX2-NEXT: pushq %r13
+; AVX2-NEXT: pushq %r12
+; AVX2-NEXT: pushq %rbx
+; AVX2-NEXT: subq $16, %rsp
+; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm0 = 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
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-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
+; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
+; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
+; AVX2-NEXT: vpextrq $1, %xmm3, %rcx
+; AVX2-NEXT: vmovq %xmm3, %rax
+; AVX2-NEXT: vpextrq $1, %xmm2, %rbx
+; AVX2-NEXT: vmovq %xmm2, %rdx
+; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm1
+; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
+; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
+; AVX2-NEXT: vpextrq $1, %xmm2, %rdi
+; AVX2-NEXT: vmovq %xmm2, %r11
+; AVX2-NEXT: vpextrq $1, %xmm1, %r13
+; AVX2-NEXT: vmovq %xmm1, %r12
+; AVX2-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
+; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
+; AVX2-NEXT: vpextrq $1, %xmm2, %rbp
+; AVX2-NEXT: vmovq %xmm2, %r10
+; AVX2-NEXT: vpextrq $1, %xmm1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX2-NEXT: vmovq %xmm1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT: vpextrq $1, %xmm1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX2-NEXT: vmovq %xmm1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX2-NEXT: vpmovzxbw {{.*#+}} 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,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
+; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
+; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero
+; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm3 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
+; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm4
+; AVX2-NEXT: vpextrq $1, %xmm4, %r15
+; AVX2-NEXT: addq %rcx, %r15
+; AVX2-NEXT: vmovq %xmm4, %r9
+; AVX2-NEXT: addq %rax, %r9
+; AVX2-NEXT: vpextrq $1, %xmm3, %rax
+; AVX2-NEXT: addq %rbx, %rax
+; AVX2-NEXT: movq %rax, %rbx
+; AVX2-NEXT: vmovq %xmm3, %rax
+; AVX2-NEXT: addq %rdx, %rax
+; AVX2-NEXT: movq %rax, %r8
+; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm2
+; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
+; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
+; AVX2-NEXT: vpextrq $1, %xmm3, %rax
+; AVX2-NEXT: addq %rdi, %rax
+; AVX2-NEXT: movq %rax, %rcx
+; AVX2-NEXT: vmovq %xmm3, %rax
+; AVX2-NEXT: addq %r11, %rax
+; AVX2-NEXT: movq %rax, %r11
+; AVX2-NEXT: vpextrq $1, %xmm2, %r14
+; AVX2-NEXT: addq %r13, %r14
+; AVX2-NEXT: vmovq %xmm2, %rax
+; AVX2-NEXT: addq %r12, %rax
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-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
+; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
+; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
+; AVX2-NEXT: vpextrq $1, %xmm3, %rax
+; AVX2-NEXT: addq %rbp, %rax
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: vmovq %xmm3, %rax
+; AVX2-NEXT: addq %r10, %rax
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: vpextrq $1, %xmm2, %rax
+; AVX2-NEXT: addq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: vmovq %xmm2, %rax
+; AVX2-NEXT: addq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm1
+; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
+; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
+; AVX2-NEXT: vpextrq $1, %xmm2, %rbp
+; AVX2-NEXT: addq -{{[0-9]+}}(%rsp), %rbp # 8-byte Folded Reload
+; AVX2-NEXT: vmovq %xmm2, %r10
+; AVX2-NEXT: addq -{{[0-9]+}}(%rsp), %r10 # 8-byte Folded Reload
+; AVX2-NEXT: vpextrq $1, %xmm0, %rax
+; AVX2-NEXT: vpextrq $1, %xmm1, %rdi
+; AVX2-NEXT: addq %rax, %rdi
+; AVX2-NEXT: vmovq %xmm0, %rdx
+; AVX2-NEXT: vmovq %xmm1, %rsi
+; AVX2-NEXT: addq %rdx, %rsi
+; AVX2-NEXT: addq $-1, %r15
+; AVX2-NEXT: movq %r15, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: movl $0, %eax
+; AVX2-NEXT: adcq $-1, %rax
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: addq $-1, %r9
+; AVX2-NEXT: movq %r9, {{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: movl $0, %eax
+; AVX2-NEXT: adcq $-1, %rax
+; AVX2-NEXT: movq %rax, (%rsp) # 8-byte Spill
+; AVX2-NEXT: addq $-1, %rbx
+; AVX2-NEXT: movq %rbx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: movl $0, %eax
+; AVX2-NEXT: adcq $-1, %rax
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: addq $-1, %r8
+; AVX2-NEXT: movq %r8, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: movl $0, %r13d
+; AVX2-NEXT: adcq $-1, %r13
+; AVX2-NEXT: addq $-1, %rcx
+; AVX2-NEXT: movq %rcx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: movl $0, %eax
+; AVX2-NEXT: adcq $-1, %rax
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: addq $-1, %r11
+; AVX2-NEXT: movq %r11, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: movl $0, %r15d
+; AVX2-NEXT: adcq $-1, %r15
+; AVX2-NEXT: addq $-1, %r14
+; AVX2-NEXT: movq %r14, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: movl $0, %ebx
+; AVX2-NEXT: adcq $-1, %rbx
+; AVX2-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX2-NEXT: movl $0, %r8d
+; AVX2-NEXT: adcq $-1, %r8
+; AVX2-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX2-NEXT: movl $0, %eax
+; AVX2-NEXT: adcq $-1, %rax
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX2-NEXT: movl $0, %eax
+; AVX2-NEXT: adcq $-1, %rax
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX2-NEXT: movl $0, %r12d
+; AVX2-NEXT: adcq $-1, %r12
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX2-NEXT: addq $-1, %rcx
+; AVX2-NEXT: movl $0, %r11d
+; AVX2-NEXT: adcq $-1, %r11
+; AVX2-NEXT: addq $-1, %rbp
+; AVX2-NEXT: movl $0, %r14d
+; AVX2-NEXT: adcq $-1, %r14
+; AVX2-NEXT: addq $-1, %r10
+; AVX2-NEXT: movl $0, %r9d
+; AVX2-NEXT: adcq $-1, %r9
+; AVX2-NEXT: addq $-1, %rdi
+; AVX2-NEXT: movl $0, %edx
+; AVX2-NEXT: adcq $-1, %rdx
+; AVX2-NEXT: addq $-1, %rsi
+; AVX2-NEXT: movl $0, %eax
+; AVX2-NEXT: adcq $-1, %rax
+; AVX2-NEXT: shldq $63, %rsi, %rax
+; AVX2-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX2-NEXT: shldq $63, %rdi, %rdx
+; AVX2-NEXT: shldq $63, %r10, %r9
+; AVX2-NEXT: shldq $63, %rbp, %r14
+; AVX2-NEXT: shldq $63, %rcx, %r11
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rcx, %r12
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rcx, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %r10 # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rcx, %r10
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rcx, %r8
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rax, %rbx
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rax, %r15
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rcx, %rax
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rcx, %r13
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rcx, %rbp
+; AVX2-NEXT: movq (%rsp), %rdi # 8-byte Reload
+; AVX2-NEXT: movq {{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rcx, %rdi
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX2-NEXT: movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; AVX2-NEXT: shldq $63, %rcx, %rsi
+; AVX2-NEXT: vmovq %rsi, %xmm8
+; AVX2-NEXT: vmovq %rdi, %xmm9
+; AVX2-NEXT: vmovq %rbp, %xmm10
+; AVX2-NEXT: vmovq %r13, %xmm11
+; AVX2-NEXT: vmovq %rax, %xmm12
+; AVX2-NEXT: vmovq %r15, %xmm13
+; AVX2-NEXT: vmovq %rbx, %xmm14
+; AVX2-NEXT: vmovq %r8, %xmm15
+; AVX2-NEXT: vmovq %r10, %xmm0
+; AVX2-NEXT: vmovq -{{[0-9]+}}(%rsp), %xmm1 # 8-byte Folded Reload
+; AVX2-NEXT: # xmm1 = mem[0],zero
+; AVX2-NEXT: vmovq %r12, %xmm2
+; AVX2-NEXT: vmovq %r11, %xmm3
+; AVX2-NEXT: vmovq %r14, %xmm4
+; AVX2-NEXT: vmovq %r9, %xmm5
+; AVX2-NEXT: vmovq %rdx, %xmm6
+; AVX2-NEXT: vmovq -{{[0-9]+}}(%rsp), %xmm7 # 8-byte Folded Reload
+; AVX2-NEXT: # xmm7 = mem[0],zero
+; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm8 = xmm9[0],xmm8[0]
+; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm9 = xmm11[0],xmm10[0]
+; AVX2-NEXT: vinserti128 $1, %xmm8, %ymm9, %ymm8
+; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm9 = xmm13[0],xmm12[0]
+; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm10 = xmm15[0],xmm14[0]
+; AVX2-NEXT: vinserti128 $1, %xmm9, %ymm10, %ymm9
+; AVX2-NEXT: vpshufd {{.*#+}} ymm8 = ymm8[0,2,2,3,4,6,6,7]
+; AVX2-NEXT: vpermq {{.*#+}} ymm8 = ymm8[0,2,2,3]
+; AVX2-NEXT: vpshufd {{.*#+}} ymm9 = ymm9[0,2,2,3,4,6,6,7]
+; AVX2-NEXT: vpermq {{.*#+}} ymm9 = ymm9[0,2,2,3]
+; AVX2-NEXT: vinserti128 $1, %xmm9, %ymm8, %ymm8
+; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm3[0],xmm2[0]
+; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
+; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
+; AVX2-NEXT: vpshufb %ymm1, %ymm8, %ymm2
+; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
+; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm3 = xmm5[0],xmm4[0]
+; AVX2-NEXT: vmovdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX2-NEXT: vpshufb %xmm4, %xmm2, %xmm2
+; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm5 = xmm7[0],xmm6[0]
+; AVX2-NEXT: vinserti128 $1, %xmm3, %ymm5, %ymm3
+; AVX2-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
+; AVX2-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
+; AVX2-NEXT: vinserti128 $1, %xmm3, %ymm0, %ymm0
+; AVX2-NEXT: vpshufb %ymm1, %ymm0, %ymm0
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT: vpshufb %xmm4, %xmm0, %xmm0
+; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
+; AVX2-NEXT: vmovdqu %xmm0, (%rax)
+; AVX2-NEXT: addq $16, %rsp
+; AVX2-NEXT: popq %rbx
+; AVX2-NEXT: popq %r12
+; AVX2-NEXT: popq %r13
+; AVX2-NEXT: popq %r14
+; AVX2-NEXT: popq %r15
+; AVX2-NEXT: popq %rbp
+; AVX2-NEXT: vzeroupper
+; AVX2-NEXT: retq
+;
+; AVX512-LABEL: not_avg_v16i8_wide_constants:
+; AVX512: # %bb.0:
+; AVX512-NEXT: pushq %rbp
+; AVX512-NEXT: pushq %r15
+; AVX512-NEXT: pushq %r14
+; AVX512-NEXT: pushq %r13
+; AVX512-NEXT: pushq %r12
+; AVX512-NEXT: pushq %rbx
+; AVX512-NEXT: subq $24, %rsp
+; AVX512-NEXT: vpmovzxbw {{.*#+}} ymm0 = 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 {{.*#+}} ymm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
+; AVX512-NEXT: vextracti128 $1, %ymm1, %xmm2
+; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
+; AVX512-NEXT: vextracti128 $1, %ymm2, %xmm3
+; AVX512-NEXT: vpextrq $1, %xmm3, %rcx
+; AVX512-NEXT: vmovq %xmm3, %rax
+; AVX512-NEXT: vpextrq $1, %xmm2, %rbx
+; AVX512-NEXT: vmovq %xmm2, %rbp
+; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
+; AVX512-NEXT: vextracti128 $1, %ymm1, %xmm2
+; AVX512-NEXT: vpextrq $1, %xmm2, %rdi
+; AVX512-NEXT: vmovq %xmm2, %r8
+; AVX512-NEXT: vpextrq $1, %xmm1, %r13
+; AVX512-NEXT: vmovq %xmm1, %r12
+; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm0
+; AVX512-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
+; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
+; AVX512-NEXT: vextracti128 $1, %ymm1, %xmm2
+; AVX512-NEXT: vpextrq $1, %xmm2, %r15
+; AVX512-NEXT: vmovq %xmm2, %r14
+; AVX512-NEXT: vpextrq $1, %xmm1, %rdx
+; AVX512-NEXT: vmovq %xmm1, %r9
+; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX512-NEXT: vpextrq $1, %xmm1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX512-NEXT: vmovq %xmm1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX512-NEXT: vpmovzxbw {{.*#+}} 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,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 {{.*#+}} ymm2 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
+; AVX512-NEXT: vextracti128 $1, %ymm2, %xmm3
+; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm3 = xmm3[0],zero,xmm3[1],zero,xmm3[2],zero,xmm3[3],zero
+; AVX512-NEXT: vextracti128 $1, %ymm3, %xmm4
+; AVX512-NEXT: vpextrq $1, %xmm4, %rsi
+; AVX512-NEXT: addq %rcx, %rsi
+; AVX512-NEXT: vmovq %xmm4, %rcx
+; AVX512-NEXT: addq %rax, %rcx
+; AVX512-NEXT: vpextrq $1, %xmm3, %rax
+; AVX512-NEXT: addq %rbx, %rax
+; AVX512-NEXT: movq %rax, %rbx
+; AVX512-NEXT: vmovq %xmm3, %rax
+; AVX512-NEXT: addq %rbp, %rax
+; AVX512-NEXT: movq %rax, %r10
+; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
+; AVX512-NEXT: vextracti128 $1, %ymm2, %xmm3
+; AVX512-NEXT: vpextrq $1, %xmm3, %rax
+; AVX512-NEXT: addq %rdi, %rax
+; AVX512-NEXT: movq %rax, %rdi
+; AVX512-NEXT: vmovq %xmm3, %rax
+; AVX512-NEXT: addq %r8, %rax
+; AVX512-NEXT: movq %rax, %r8
+; AVX512-NEXT: vpextrq $1, %xmm2, %rbp
+; AVX512-NEXT: addq %r13, %rbp
+; AVX512-NEXT: vmovq %xmm2, %r11
+; AVX512-NEXT: addq %r12, %r11
+; AVX512-NEXT: vextracti128 $1, %ymm1, %xmm1
+; AVX512-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
+; AVX512-NEXT: vextracti128 $1, %ymm1, %xmm2
+; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
+; AVX512-NEXT: vextracti128 $1, %ymm2, %xmm3
+; AVX512-NEXT: vpextrq $1, %xmm3, %rax
+; AVX512-NEXT: addq %r15, %rax
+; AVX512-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: vmovq %xmm3, %rax
+; AVX512-NEXT: addq %r14, %rax
+; AVX512-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: vpextrq $1, %xmm2, %rax
+; AVX512-NEXT: addq %rdx, %rax
+; AVX512-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: vmovq %xmm2, %rax
+; AVX512-NEXT: addq %r9, %rax
+; AVX512-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
+; AVX512-NEXT: vextracti128 $1, %ymm1, %xmm2
+; AVX512-NEXT: vpextrq $1, %xmm2, %rax
+; AVX512-NEXT: addq -{{[0-9]+}}(%rsp), %rax # 8-byte Folded Reload
+; AVX512-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: vmovq %xmm2, %r14
+; AVX512-NEXT: addq -{{[0-9]+}}(%rsp), %r14 # 8-byte Folded Reload
+; AVX512-NEXT: vpextrq $1, %xmm0, %rax
+; AVX512-NEXT: vpextrq $1, %xmm1, %r9
+; AVX512-NEXT: addq %rax, %r9
+; AVX512-NEXT: vmovq %xmm0, %rax
+; AVX512-NEXT: vmovq %xmm1, %rdx
+; AVX512-NEXT: addq %rax, %rdx
+; AVX512-NEXT: addq $-1, %rsi
+; AVX512-NEXT: movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: movl $0, %eax
+; AVX512-NEXT: adcq $-1, %rax
+; AVX512-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: addq $-1, %rcx
+; AVX512-NEXT: movq %rcx, {{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: movl $0, %eax
+; AVX512-NEXT: adcq $-1, %rax
+; AVX512-NEXT: movq %rax, {{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: addq $-1, %rbx
+; AVX512-NEXT: movq %rbx, (%rsp) # 8-byte Spill
+; AVX512-NEXT: movl $0, %eax
+; AVX512-NEXT: adcq $-1, %rax
+; AVX512-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: addq $-1, %r10
+; AVX512-NEXT: movq %r10, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: movl $0, %eax
+; AVX512-NEXT: adcq $-1, %rax
+; AVX512-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: addq $-1, %rdi
+; AVX512-NEXT: movq %rdi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: movl $0, %eax
+; AVX512-NEXT: adcq $-1, %rax
+; AVX512-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: addq $-1, %r8
+; AVX512-NEXT: movq %r8, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: movl $0, %eax
+; AVX512-NEXT: adcq $-1, %rax
+; AVX512-NEXT: movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: addq $-1, %rbp
+; AVX512-NEXT: movq %rbp, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: movl $0, %r13d
+; AVX512-NEXT: adcq $-1, %r13
+; AVX512-NEXT: addq $-1, %r11
+; AVX512-NEXT: movq %r11, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: movl $0, %r15d
+; AVX512-NEXT: adcq $-1, %r15
+; AVX512-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX512-NEXT: movl $0, %eax
+; AVX512-NEXT: adcq $-1, %rax
+; AVX512-NEXT: movq %rax, %rsi
+; AVX512-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX512-NEXT: movl $0, %r12d
+; AVX512-NEXT: adcq $-1, %r12
+; AVX512-NEXT: addq $-1, -{{[0-9]+}}(%rsp) # 8-byte Folded Spill
+; AVX512-NEXT: movl $0, %ebx
+; AVX512-NEXT: adcq $-1, %rbx
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; AVX512-NEXT: addq $-1, %rbp
+; AVX512-NEXT: movl $0, %r11d
+; AVX512-NEXT: adcq $-1, %r11
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX512-NEXT: addq $-1, %rax
+; AVX512-NEXT: movl $0, %r10d
+; AVX512-NEXT: adcq $-1, %r10
+; AVX512-NEXT: addq $-1, %r14
+; AVX512-NEXT: movl $0, %r8d
+; AVX512-NEXT: adcq $-1, %r8
+; AVX512-NEXT: addq $-1, %r9
+; AVX512-NEXT: movl $0, %edi
+; AVX512-NEXT: adcq $-1, %rdi
+; AVX512-NEXT: addq $-1, %rdx
+; AVX512-NEXT: movl $0, %ecx
+; AVX512-NEXT: adcq $-1, %rcx
+; AVX512-NEXT: shldq $63, %rdx, %rcx
+; AVX512-NEXT: movq %rcx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: shldq $63, %r9, %rdi
+; AVX512-NEXT: shldq $63, %r14, %r8
+; AVX512-NEXT: shldq $63, %rax, %r10
+; AVX512-NEXT: shldq $63, %rbp, %r11
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rdx, %rbx
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rdx, %r12
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rdx, %rsi
+; AVX512-NEXT: movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rax, %r15
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rax, %r13
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rsi # 8-byte Reload
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rax, %rsi
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rcx # 8-byte Reload
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rax, %rcx
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rdx, %rax
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %r14 # 8-byte Reload
+; AVX512-NEXT: movq (%rsp), %rdx # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rdx, %r14
+; AVX512-NEXT: movq {{[0-9]+}}(%rsp), %r9 # 8-byte Reload
+; AVX512-NEXT: movq {{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rdx, %r9
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rdx # 8-byte Reload
+; AVX512-NEXT: movq -{{[0-9]+}}(%rsp), %rbp # 8-byte Reload
+; AVX512-NEXT: shldq $63, %rdx, %rbp
+; AVX512-NEXT: vmovq %rbp, %xmm8
+; AVX512-NEXT: vmovq %r9, %xmm9
+; AVX512-NEXT: vmovq %r14, %xmm10
+; AVX512-NEXT: vmovq %rax, %xmm11
+; AVX512-NEXT: vmovq %rcx, %xmm12
+; AVX512-NEXT: vmovq %rsi, %xmm13
+; AVX512-NEXT: vmovq %r13, %xmm14
+; AVX512-NEXT: vmovq %r15, %xmm15
+; AVX512-NEXT: vmovq -{{[0-9]+}}(%rsp), %xmm0 # 8-byte Folded Reload
+; AVX512-NEXT: # xmm0 = mem[0],zero
+; AVX512-NEXT: vmovq %r12, %xmm1
+; AVX512-NEXT: vmovq %rbx, %xmm2
+; AVX512-NEXT: vmovq %r11, %xmm3
+; AVX512-NEXT: vmovq %r10, %xmm4
+; AVX512-NEXT: vmovq %r8, %xmm5
+; AVX512-NEXT: vmovq %rdi, %xmm6
+; AVX512-NEXT: vmovq -{{[0-9]+}}(%rsp), %xmm7 # 8-byte Folded Reload
+; AVX512-NEXT: # xmm7 = mem[0],zero
+; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm8 = xmm9[0],xmm8[0]
+; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm9 = xmm11[0],xmm10[0]
+; AVX512-NEXT: vinserti128 $1, %xmm8, %ymm9, %ymm8
+; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm9 = xmm13[0],xmm12[0]
+; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm10 = xmm15[0],xmm14[0]
+; AVX512-NEXT: vinserti128 $1, %xmm9, %ymm10, %ymm9
+; AVX512-NEXT: vinserti64x4 $1, %ymm8, %zmm9, %zmm8
+; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm3[0],xmm2[0]
+; AVX512-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
+; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm5[0],xmm4[0]
+; AVX512-NEXT: vpmovqd %zmm8, %ymm2
+; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm3 = xmm7[0],xmm6[0]
+; AVX512-NEXT: vinserti128 $1, %xmm1, %ymm3, %ymm1
+; AVX512-NEXT: vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512-NEXT: vpmovqd %zmm0, %ymm0
+; AVX512-NEXT: vinserti64x4 $1, %ymm0, %zmm2, %zmm0
+; AVX512-NEXT: vpmovdb %zmm0, (%rax)
+; AVX512-NEXT: addq $24, %rsp
+; AVX512-NEXT: popq %rbx
+; AVX512-NEXT: popq %r12
+; AVX512-NEXT: popq %r13
+; AVX512-NEXT: popq %r14
+; AVX512-NEXT: popq %r15
+; AVX512-NEXT: popq %rbp
+; AVX512-NEXT: vzeroupper
+; AVX512-NEXT: retq
+ %1 = load <16 x i8>, <16 x i8>* %a
+ %2 = load <16 x i8>, <16 x i8>* %b
+ %3 = zext <16 x i8> %1 to <16 x i128>
+ %4 = zext <16 x i8> %2 to <16 x i128>
+ %5 = add nuw nsw <16 x i128> %3, <i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1, i128 -1>
+ %6 = add nuw nsw <16 x i128> %5, %4
+ %7 = lshr <16 x i128> %6, <i128 1, i128 1, i128 1, i128 1, i128 1, i128 1, i128 1, i128 1, i128 1, i128 1, i128 1, i128 1, i128 1, i128 1, i128 1, i128 1>
+ %8 = trunc <16 x i128> %7 to <16 x i8>
+ store <16 x i8> %8, <16 x i8>* undef, align 4
+ ret void
+}