Took forever to generate the goasm about c2goasm HOT 2 OPEN

.text
.intel_syntax noprefix
.file    "tes.c"
.globl   TesSum                  # -- Begin function TesSum
.p2align 4, 0x90
.type    TesSum, @function

TesSum:
# @TesSum
# %bb.0:
push rbp
mov  rbp, rsp
and  rsp, -8

# kill: def $esi killed $esi def $rsi
# kill: def $edi killed $edi def $rdi
	lea eax, [rdi + rsi]
	mov rsp, rbp
	pop rbp
	ret

.Lfunc_end0:
	.size TesSum, .Lfunc_end0-TesSum

# -- End function
.section .rodata.cst16, "aM", @progbits, 16
.p2align 4               # -- Begin function TesByteSlice

.LCPI1_0:
	.byte 0                       # 0x0
	.byte 1                       # 0x1
	.byte 2                       # 0x2
	.byte 3                       # 0x3
	.byte 4                       # 0x4
	.byte 5                       # 0x5
	.byte 6                       # 0x6
	.byte 7                       # 0x7
	.byte 8                       # 0x8
	.byte 9                       # 0x9
	.byte 10                      # 0xa
	.byte 11                      # 0xb
	.byte 12                      # 0xc
	.byte 13                      # 0xd
	.byte 14                      # 0xe
	.byte 15                      # 0xf

.LCPI1_1:
	.zero 16, 16

.LCPI1_2:
	.zero 16, 32

.LCPI1_3:
	.zero 16, 48

.LCPI1_4:
	.zero 16, 64

.LCPI1_5:
	.zero 16, 80

.LCPI1_6:
	.zero 16, 96

.LCPI1_7:
	.zero 16, 112

.LCPI1_8:
	.zero    16, 128
	.text
	.globl   TesByteSlice
	.p2align 4, 0x90
	.type    TesByteSlice, @function

TesByteSlice:
# @TesByteSlice
# %bb.0:
push rbp
mov  rbp, rsp
and  rsp, -8
test rsi, rsi
je   .LBB1_13

# %bb.1:
cmp rsi, 15
ja  .LBB1_3

# %bb.2:
	xor eax, eax
	jmp .LBB1_12

.LBB1_3:
	mov rax, rsi
	and rax, -16
	lea rdx, [rax - 16]
	mov rcx, rdx
	shr rcx, 4
	add rcx, 1
	mov r8d, ecx
	and r8d, 7
	cmp rdx, 112
	jae .LBB1_5

# %bb.4:
	movdqa xmm2, xmmword ptr [rip + .LCPI1_0] # xmm2 = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]
	xor    edx, edx
	jmp    .LBB1_7

.LBB1_5:
	sub      rcx, r8
	movdqa   xmm2, xmmword ptr [rip + .LCPI1_0] # xmm2 = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]
	xor      edx, edx
	movdqa   xmm8, xmmword ptr [rip + .LCPI1_1] # xmm8 = [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16]
	movdqa   xmm9, xmmword ptr [rip + .LCPI1_2] # xmm9 = [32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32]
	movdqa   xmm3, xmmword ptr [rip + .LCPI1_3] # xmm3 = [48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48, 48]
	movdqa   xmm4, xmmword ptr [rip + .LCPI1_4] # xmm4 = [64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64]
	movdqa   xmm5, xmmword ptr [rip + .LCPI1_5] # xmm5 = [80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80]
	movdqa   xmm6, xmmword ptr [rip + .LCPI1_6] # xmm6 = [96, 96, 96, 96, 96, 96, 96, 96, 96, 96, 96, 96, 96, 96, 96, 96]
	movdqa   xmm7, xmmword ptr [rip + .LCPI1_7] # xmm7 = [112, 112, 112, 112, 112, 112, 112, 112, 112, 112, 112, 112, 112, 112, 112, 112]
	movdqa   xmm1, xmmword ptr [rip + .LCPI1_8] # xmm1 = [128, 128, 128, 128, 128, 128, 128, 128, 128, 128, 128, 128, 128, 128, 128, 128]
	.p2align 4, 0x90
	.LBB1_6:                                # =>This Inner Loop Header: Depth=1
	movdqu   xmmword ptr [rdi + rdx], xmm2
	movdqa   xmm0, xmm2
	paddb    xmm0, xmm8
	movdqu   xmmword ptr [rdi + rdx + 16], xmm0
	movdqa   xmm0, xmm2
	paddb    xmm0, xmm9
	movdqu   xmmword ptr [rdi + rdx + 32], xmm0
	movdqa   xmm0, xmm2
	paddb    xmm0, xmm3
	movdqu   xmmword ptr [rdi + rdx + 48], xmm0
	movdqa   xmm0, xmm2
	paddb    xmm0, xmm4
	movdqu   xmmword ptr [rdi + rdx + 64], xmm0
	movdqa   xmm0, xmm2
	paddb    xmm0, xmm5
	movdqu   xmmword ptr [rdi + rdx + 80], xmm0
	movdqa   xmm0, xmm2
	paddb    xmm0, xmm6
	movdqu   xmmword ptr [rdi + rdx + 96], xmm0
	movdqa   xmm0, xmm2
	paddb    xmm0, xmm7
	movdqu   xmmword ptr [rdi + rdx + 112], xmm0
	sub      rdx, -128
	pxor     xmm2, xmm1
	add      rcx, -8
	jne      .LBB1_6

.LBB1_7:
	test r8, r8
	je   .LBB1_10

# %bb.8:
add      rdx, rdi
neg      r8
movdqa   xmm1, xmmword ptr [rip + .LCPI1_1] # xmm1 = [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16]
.p2align 4, 0x90
.LBB1_9:                                # =>This Inner Loop Header: Depth=1
movdqu   xmmword ptr [rdx], xmm2
paddb    xmm2, xmm1
add      rdx, 16
inc      r8
jne      .LBB1_9

.LBB1_10:
	cmp rax, rsi
	je  .LBB1_13

# %bb.11:
add      rdi, rax
.p2align 4, 0x90
.LBB1_12:                               # =>This Inner Loop Header: Depth=1
mov      byte ptr [rdi], al
add      rdi, 1
add      rax, 1
cmp      rsi, rax
jne      .LBB1_12

.LBB1_13:
	mov eax, 1
	mov rsp, rbp
	pop rbp
	ret

.Lfunc_end1:
	.size TesByteSlice, .Lfunc_end1-TesByteSlice

# -- End function
.ident   "clang version 10.0.0-4ubuntu1 "
.section ".note.GNU-stack", "", @progbits
.addrsig