c++ - AVX2 在 Haswell 上比 SSE 慢

Question

我有以下代码(正常、SSE 和 AVX):

int testSSE(const aligned_vector & ghs, const aligned_vector & lhs) {
    int result[4] __attribute__((aligned(16))) = {0};
    __m128i vresult = _mm_set1_epi32(0);
    __m128i v1, v2, vmax;

    for (int k = 0; k < ghs.size(); k += 4) {
        v1 = _mm_load_si128((__m128i *) & lhs[k]);
        v2 = _mm_load_si128((__m128i *) & ghs[k]);
        vmax = _mm_add_epi32(v1, v2);
        vresult = _mm_max_epi32(vresult, vmax);
    }
    _mm_store_si128((__m128i *) result, vresult);
    int mymax = result[0];
    for (int k = 1; k < 4; k++) {
        if (result[k] > mymax) {
            mymax = result[k];
        }
    }
    return mymax;
}

 int testAVX(const aligned_vector & ghs, const aligned_vector & lhs) {
    int result[8] __attribute__((aligned(32))) = {0};
    __m256i vresult = _mm256_set1_epi32(0);
    __m256i v1, v2, vmax;

    for (int k = 0; k < ghs.size(); k += 8) {
        v1 = _mm256_load_si256((__m256i *) & ghs[ k]);
        v2 = _mm256_load_si256((__m256i *) & lhs[k]);
        vmax = _mm256_add_epi32(v1, v2);
        vresult = _mm256_max_epi32(vresult, vmax);
    }
    _mm256_store_si256((__m256i *) result, vresult);
    int mymax = result[0];
    for (int k = 1; k < 8; k++) {
        if (result[k] > mymax) {
            mymax = result[k];
        }
    }
    return mymax;
}

int testNormal(const aligned_vector & ghs, const aligned_vector & lhs) {
    int max = 0;
    int tempMax;
    for (int k = 0; k < ghs.size(); k++) {
        tempMax = lhs[k] + ghs[k];
        if (max < tempMax) {
            max = tempMax;
        }
    }
    return max;
}

所有这些功能都使用以下代码进行测试:

void alignTestSSE() {
    aligned_vector lhs;
    aligned_vector ghs;

    int mySize = 4096;
    int FinalResult;
    int nofTestCases = 1000;
    double time, time1, time2, time3;
    vector<int> lhs2;
    vector<int> ghs2;

    lhs.resize(mySize);
    ghs.resize(mySize);
    lhs2.resize(mySize);
    ghs2.resize(mySize);

    srand(1);
    for (int k = 0; k < mySize; k++) {
        lhs[k] = randomNodeID(1000000);
        lhs2[k] = lhs[k];
        ghs[k] = randomNodeID(1000000);
        ghs2[k] = ghs[k];
    }
    /* Warming UP */
    for (int k = 0; k < nofTestCases; k++) {
        FinalResult = testNormal(lhs, ghs);
    }

    for (int k = 0; k < nofTestCases; k++) {
        FinalResult = testSSE(lhs, ghs);
    }

    for (int k = 0; k < nofTestCases; k++) {
        FinalResult = testAVX(lhs, ghs);
    }

    cout << "===========================" << endl;
    time = timestamp();
    for (int k = 0; k < nofTestCases; k++) {
        FinalResult = testSSE(lhs, ghs);
    }
    time = timestamp() - time;
    time1 = time;
    cout << "SSE took " << time << " s" << endl;
    cout << "SSE Result: " << FinalResult << endl;

    time = timestamp();
    for (int k = 0; k < nofTestCases; k++) {
        FinalResult = testAVX(lhs, ghs);
    }
    time = timestamp() - time;
    time3 = time;
    cout << "AVX took " << time << " s" << endl;
    cout << "AVX Result: " << FinalResult << endl;



    time = timestamp();
    for (int k = 0; k < nofTestCases; k++) {
        FinalResult = testNormal(lhs, ghs);
    }
    time = timestamp() - time;
    cout << "Normal took " << time << " s" << endl;
    cout << "Normal Result: " << FinalResult << endl;
    cout << "SpeedUP SSE= " << time / time1 << " s" << endl;
    cout << "SpeedUP AVX= " << time / time3 << " s" << endl;
    cout << "===========================" << endl;
    ghs.clear();
    lhs.clear();
}

在哪里

inline double timestamp() {
    struct timeval tp;
    gettimeofday(&tp, NULL);
    return double(tp.tv_sec) + tp.tv_usec / 1000000.;
}

和

typedef vector<int, aligned_allocator<int, sizeof (int)> > aligned_vector;

是使用 https://gist.github.com/donny-dont/1471329 的 AlignedAllocator 的对齐 vector

我有一个 intel-i7 haswell 4771，以及最新的 Ubuntu 14.04 64 位和 gcc 4.8.2。一切都是最新的。我用 -march=native -mtune=native -O3 -m64 编译。

结果是:

SSE took 0.000375986 s
SSE Result: 1982689
AVX took 0.000459909 s
AVX Result: 1982689
Normal took 0.00315714 s
Normal Result: 1982689
SpeedUP SSE= 8.39696 s
SpeedUP AVX= 6.8647 s

这表明完全相同的代码在 AVX2 上比 SSE 慢 22%。我做错了什么还是这是正常行为？

Answer 1

我将您的代码转换为更普通的 C++(纯数组、无 vector 等)，清理它并在禁用自动矢量化的情况下对其进行测试并获得了合理的结果:

#include <iostream>
using namespace std;

#include <sys/time.h>
#include <cstdlib>
#include <cstdint>

#include <immintrin.h>

inline double timestamp() {
    struct timeval tp;
    gettimeofday(&tp, NULL);
    return double(tp.tv_sec) + tp.tv_usec / 1000000.;
}

int testSSE(const int32_t * ghs, const int32_t * lhs, size_t n) {
    int result[4] __attribute__((aligned(16))) = {0};
    __m128i vresult = _mm_set1_epi32(0);
    __m128i v1, v2, vmax;

    for (int k = 0; k < n; k += 4) {
        v1 = _mm_load_si128((__m128i *) & lhs[k]);
        v2 = _mm_load_si128((__m128i *) & ghs[k]);
        vmax = _mm_add_epi32(v1, v2);
        vresult = _mm_max_epi32(vresult, vmax);
    }
    _mm_store_si128((__m128i *) result, vresult);
    int mymax = result[0];
    for (int k = 1; k < 4; k++) {
        if (result[k] > mymax) {
            mymax = result[k];
        }
    }
    return mymax;
}

int testAVX(const int32_t * ghs, const int32_t * lhs, size_t n) {
    int result[8] __attribute__((aligned(32))) = {0};
    __m256i vresult = _mm256_set1_epi32(0);
    __m256i v1, v2, vmax;

    for (int k = 0; k < n; k += 8) {
        v1 = _mm256_load_si256((__m256i *) & ghs[k]);
        v2 = _mm256_load_si256((__m256i *) & lhs[k]);
        vmax = _mm256_add_epi32(v1, v2);
        vresult = _mm256_max_epi32(vresult, vmax);
    }
    _mm256_store_si256((__m256i *) result, vresult);
    int mymax = result[0];
    for (int k = 1; k < 8; k++) {
        if (result[k] > mymax) {
            mymax = result[k];
        }
    }
    return mymax;
}

int testNormal(const int32_t * ghs, const int32_t * lhs, size_t n) {
    int max = 0;
    int tempMax;
    for (int k = 0; k < n; k++) {
        tempMax = lhs[k] + ghs[k];
        if (max < tempMax) {
            max = tempMax;
        }
    }
    return max;
}

void alignTestSSE() {

    int n = 4096;
    int normalResult, sseResult, avxResult;
    int nofTestCases = 1000;
    double time, normalTime, sseTime, avxTime;

    int lhs[n] __attribute__ ((aligned(32)));
    int ghs[n] __attribute__ ((aligned(32)));

    for (int k = 0; k < n; k++) {
        lhs[k] = arc4random();
        ghs[k] = arc4random();
    }

    /* Warming UP */
    for (int k = 0; k < nofTestCases; k++) {
        normalResult = testNormal(lhs, ghs, n);
    }

    for (int k = 0; k < nofTestCases; k++) {
        sseResult = testSSE(lhs, ghs, n);
    }

    for (int k = 0; k < nofTestCases; k++) {
        avxResult = testAVX(lhs, ghs, n);
    }

    time = timestamp();
    for (int k = 0; k < nofTestCases; k++) {
        normalResult = testNormal(lhs, ghs, n);
    }
    normalTime = timestamp() - time;

    time = timestamp();
    for (int k = 0; k < nofTestCases; k++) {
        sseResult = testSSE(lhs, ghs, n);
    }
    sseTime = timestamp() - time;

    time = timestamp();
    for (int k = 0; k < nofTestCases; k++) {
        avxResult = testAVX(lhs, ghs, n);
    }
    avxTime = timestamp() - time;

    cout << "===========================" << endl;
    cout << "Normal took " << normalTime << " s" << endl;
    cout << "Normal Result: " << normalResult << endl;
    cout << "SSE took " << sseTime << " s" << endl;
    cout << "SSE Result: " << sseResult << endl;
    cout << "AVX took " << avxTime << " s" << endl;
    cout << "AVX Result: " << avxResult << endl;
    cout << "SpeedUP SSE= " << normalTime / sseTime << endl;
    cout << "SpeedUP AVX= " << normalTime / avxTime << endl;
    cout << "===========================" << endl;

}

int main()
{
    alignTestSSE();
    return 0;
}

测试:

$ clang++ -Wall -mavx2 -O3 -fno-vectorize SO_avx.cpp && ./a.out
===========================
Normal took 0.00324106 s
Normal Result: 2143749391
SSE took 0.000527859 s
SSE Result: 2143749391
AVX took 0.000221968 s
AVX Result: 2143749391
SpeedUP SSE= 6.14002
SpeedUP AVX= 14.6015
===========================

我建议你尝试上面的代码，使用 -fno-vectorize(或者 -fno-tree-vectorize 如果使用 g++)，看看你是否得到类似的结果.如果您这样做了，那么您可以向后处理您的原始代码，以查看不一致可能来自何处。