考虑以下两个片段:
#define ALIGN_BYTES 32
#define ASSUME_ALIGNED(x) x = __builtin_assume_aligned(x, ALIGN_BYTES)
void fn0(const float *restrict a0, const float *restrict a1,
float *restrict b, int n)
{
ASSUME_ALIGNED(a0); ASSUME_ALIGNED(a1); ASSUME_ALIGNED(b);
for (int i = 0; i < n; ++i)
b[i] = a0[i] + a1[i];
}
void fn1(const float *restrict *restrict a, float *restrict b, int n)
{
ASSUME_ALIGNED(a[0]); ASSUME_ALIGNED(a[1]); ASSUME_ALIGNED(b);
for (int i = 0; i < n; ++i)
b[i] = a[0][i] + a[1][i];
}
当我编译该函数时,gcc-4.7.2 -Ofast -march=native -std=c99 -ftree-vectorizer-verbose=5 -S test.c -Wall
我发现 GCC 为第二个函数插入了别名检查。
我怎样才能防止这种情况,使得生成的程序集与 forfn1
的程序集相同fn0
?(当参数的数量从 3 个增加到 30 个时,参数传递方法 ( fn0
) 变得很麻烦,并且该fn1
方法中的别名检查数量变得荒谬。)
组装(x86-64,支持 AVX 的芯片);在 .LFB10 处混叠杂物
fn0:
.LFB9:
.cfi_startproc
testl %ecx, %ecx
jle .L1
movl %ecx, %r10d
shrl $3, %r10d
leal 0(,%r10,8), %r9d
testl %r9d, %r9d
je .L8
cmpl $7, %ecx
jbe .L8
xorl %eax, %eax
xorl %r8d, %r8d
.p2align 4,,10
.p2align 3
.L4:
vmovaps (%rsi,%rax), %ymm0
addl $1, %r8d
vaddps (%rdi,%rax), %ymm0, %ymm0
vmovaps %ymm0, (%rdx,%rax)
addq $32, %rax
cmpl %r8d, %r10d
ja .L4
cmpl %r9d, %ecx
je .L1
.L3:
movslq %r9d, %rax
salq $2, %rax
addq %rax, %rdi
addq %rax, %rsi
addq %rax, %rdx
xorl %eax, %eax
.p2align 4,,10
.p2align 3
.L6:
vmovss (%rsi,%rax,4), %xmm0
vaddss (%rdi,%rax,4), %xmm0, %xmm0
vmovss %xmm0, (%rdx,%rax,4)
addq $1, %rax
leal (%r9,%rax), %r8d
cmpl %r8d, %ecx
jg .L6
.L1:
vzeroupper
ret
.L8:
xorl %r9d, %r9d
jmp .L3
.cfi_endproc
.LFE9:
.size fn0, .-fn0
.p2align 4,,15
.globl fn1
.type fn1, @function
fn1:
.LFB10:
.cfi_startproc
testq %rdx, %rdx
movq (%rdi), %r8
movq 8(%rdi), %r9
je .L12
leaq 32(%rsi), %rdi
movq %rdx, %r10
leaq 32(%r8), %r11
shrq $3, %r10
cmpq %rdi, %r8
leaq 0(,%r10,8), %rax
setae %cl
cmpq %r11, %rsi
setae %r11b
orl %r11d, %ecx
cmpq %rdi, %r9
leaq 32(%r9), %r11
setae %dil
cmpq %r11, %rsi
setae %r11b
orl %r11d, %edi
andl %edi, %ecx
cmpq $7, %rdx
seta %dil
testb %dil, %cl
je .L19
testq %rax, %rax
je .L19
xorl %ecx, %ecx
xorl %edi, %edi
.p2align 4,,10
.p2align 3
.L15:
vmovaps (%r9,%rcx), %ymm0
addq $1, %rdi
vaddps (%r8,%rcx), %ymm0, %ymm0
vmovaps %ymm0, (%rsi,%rcx)
addq $32, %rcx
cmpq %rdi, %r10
ja .L15
cmpq %rax, %rdx
je .L12
.p2align 4,,10
.p2align 3
.L20:
vmovss (%r9,%rax,4), %xmm0
vaddss (%r8,%rax,4), %xmm0, %xmm0
vmovss %xmm0, (%rsi,%rax,4)
addq $1, %rax
cmpq %rax, %rdx
ja .L20
.L12:
vzeroupper
ret
.L19:
xorl %eax, %eax
jmp .L20
.cfi_endproc