Код: Выделить всё
template
int32_t countsearch(const uint32_t *base, uint32_t needle) {
uint32_t count = 0;
// #pragma clang loop vectorize(disable)
for (const uint32_t *probe = base; probe < base + N; probe++) {
if (*probe < needle)
count++;
}
return count;
}
Код: Выделить всё
int countsearch(unsigned int const*, unsigned int): # @int countsearch(unsigned int const*, unsigned int)
vmovd xmm0, esi
vpbroadcastd ymm0, xmm0
vpbroadcastd ymm1, dword ptr [rip + .LCPI0_0] # ymm1 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
vpxor ymm2, ymm1, ymmword ptr [rdi]
vpxor ymm0, ymm0, ymm1
vpcmpgtd ymm0, ymm0, ymm2
cmp dword ptr [rdi + 32], esi
vpsrld ymm1, ymm0, 31
vextracti128 xmm1, ymm1, 1
vpsubd ymm0, ymm1, ymm0
vpshufd xmm1, xmm0, 78 # xmm1 = xmm0[2,3,0,1]
vpaddd ymm0, ymm0, ymm1
vphaddd ymm0, ymm0, ymm0
vmovd eax, xmm0
adc eax, 0
cmp dword ptr [rdi + 36], esi
adc eax, 0
vzeroupper
ret
Код: Выделить всё
-disable-loop-vectorization
-disable-vectorization
-fno-vectorize
-fno-tree-vectorize
Подробнее здесь: https://stackoverflow.com/questions/514 ... n-in-clang