求解这段simd代码原理

uint32_t parse_8digits_simd_ssse3 (char* str) {
const __m128i mul1 = _mm_set_epi32(0, 0, 0x010A0A64, 0x14C814C8);
const __m128i mul2 = _mm_set_epi32(0, 0, 0x0001000A, 0x00FA61A8);
const __m128i mask = _mm_set1_epi8(0x0F);
__m128i v;
v = _mm_loadl_epi64((__m128i*)(void*)str);
v = _mm_and_si128(v, mask);
v = _mm_madd_epi16(_mm_maddubs_epi16(mul1, v), mul2);
v = _mm_add_epi32(_mm_add_epi32(v, v), _mm_shuffle_epi32(v, 1));
return (uint32_t)_mm_cvtsi128_si32(v);
}

顶

没头没尾的谁知道你的mm是啥

你真的有必要造这么底层的轮子吗，只有最底层组件才这么极端重视速度吧
你发的SO答案里就有解释
http://0x80.pl/articles/simd-parsing-int-sequences.html
指令作用不清楚的话可以查Intel Intrinsics Guide