C++ SIMD性能优化

// 使用SIMD指令优化的向量加法
//<mmintrin.h> MMX
//<xmmintrin.h>	SSE
//<emmintrin.h>	SSE2
//<pmmintrin.h>	SSE3
//<tmmintrin.h>	SSSE3
//<smmintrin.h>	SSE4.1
//<nmmintrin.h> SSE4.2
//<wmmintrin.h> AES
//<immintrin.h>	AVX, AVX2, FMA, BMI, POPCNT, AVX512
//<x86intrin.h>	Auto(GCC)
//<intrin.h> Auto(MSVC)
#include <emmintrin.h> // 包含SSE2指令集
#include <valarray>
#include <iostream>
#include <chrono>
#include <vector>

__m128i vector_add(__m128i a, __m128i b) {
    return _mm_add_epi32(a, b);
}

void add_vectors(int* a, int* b, int* c, int size) {
    for (int i = 0; i < size; i += 4) {
        __m128i va = _mm_load_si128((__m128i*)(a + i));
        __m128i vb = _mm_load_si128((__m128i*)(b + i));
        __m128i vc = _mm_add_epi32(va, vb);
        _mm_store_si128((__m128i*)(c + i), vc);
    }
}

int test() {
    std::valarray<float> a