https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109537
--- Comment #1 from Li Jia He <helijia.i at foxmail dot com> ---
Update gcc's assembly as gcc did not turn on auto vectorization during O2,
The compilation command for gcc is 'cc1 unroll.c -O3 -funroll-loops',
The compilation command for clang is 'clang unroll.c -O3 -S'
'''
$ cat unroll.gcc.s
.file "unroll.c"
.text
.p2align 4
.globl matrix_add_const
.type matrix_add_const, @function
matrix_add_const:
.LFB0:
.cfi_startproc
movl %edi, %ecx
movl %edx, %edi
testl %ecx, %ecx
jle .L1
leal -1(%rcx), %eax
cmpl $2, %eax
jbe .L6
movl %ecx, %r9d
movd %edx, %xmm2
movq %rsi, %r10
shrl $2, %r9d
pshufd $0, %xmm2, %xmm0
salq $4, %r9
leaq (%r9,%rsi), %r8
subq $16, %r9
shrq $4, %r9
addq $1, %r9
andl $7, %r9d
je .L4
cmpq $1, %r9
je .L29
cmpq $2, %r9
je .L30
cmpq $3, %r9
je .L31
cmpq $4, %r9
je .L32
cmpq $5, %r9
je .L33
cmpq $6, %r9
jne .L45
.L34:
movdqu (%r10), %xmm3
addq $16, %r10
paddd %xmm0, %xmm3
movups %xmm3, -16(%r10)
.L33:
movdqu (%r10), %xmm4
addq $16, %r10
paddd %xmm0, %xmm4
movups %xmm4, -16(%r10)
.L32:
movdqu (%r10), %xmm5
addq $16, %r10
paddd %xmm0, %xmm5
movups %xmm5, -16(%r10)
.L31:
movdqu (%r10), %xmm6
addq $16, %r10
paddd %xmm0, %xmm6
movups %xmm6, -16(%r10)
.L30:
movdqu (%r10), %xmm7
addq $16, %r10
paddd %xmm0, %xmm7
movups %xmm7, -16(%r10)
.L29:
movdqu (%r10), %xmm8
addq $16, %r10
paddd %xmm0, %xmm8
movups %xmm8, -16(%r10)
cmpq %r8, %r10
je .L43
.L4:
movdqu (%r10), %xmm9
movdqu 16(%r10), %xmm10
subq $-128, %r10
movdqu -96(%r10), %xmm11
movdqu -80(%r10), %xmm12
movdqu -64(%r10), %xmm13
paddd %xmm0, %xmm9
paddd %xmm0, %xmm10
movdqu -48(%r10), %xmm14
movdqu -32(%r10), %xmm15
movdqu -16(%r10), %xmm2
paddd %xmm0, %xmm11
paddd %xmm0, %xmm12
paddd %xmm0, %xmm13
paddd %xmm0, %xmm14
movups %xmm9, -128(%r10)
paddd %xmm0, %xmm15
paddd %xmm0, %xmm2
movups %xmm10, -112(%r10)
movups %xmm11, -96(%r10)
movups %xmm12, -80(%r10)
movups %xmm13, -64(%r10)
movups %xmm14, -48(%r10)
movups %xmm15, -32(%r10)
movups %xmm2, -16(%r10)
cmpq %r8, %r10
jne .L4
.L43:
movl %ecx, %edx
andl $-4, %edx
testb $3, %cl
je .L46
.L3:
movslq %edx, %r11
leal 1(%rdx), %eax
salq $2, %r11
addl %edi, (%rsi,%r11)
cmpl %eax, %ecx
jle .L1
addl $2, %edx
addl %edi, 4(%rsi,%r11)
cmpl %edx, %ecx
jle .L1
addl %edi, 8(%rsi,%r11)
.L1:
ret
.p2align 4,,10
.p2align 3
.L46:
ret
.p2align 4,,10
.p2align 3
.L45:
movdqu (%rsi), %xmm1
leaq 16(%rsi), %r10
paddd %xmm0, %xmm1
movups %xmm1, (%rsi)
jmp .L34
.L6:
xorl %edx, %edx
jmp .L3
.cfi_endproc
.LFE0:
.size matrix_add_const, .-matrix_add_const
.ident "GCC: (GNU) 13.0.0 20221022 (experimental)"
.section .note.GNU-stack,"",@progbits
'''
