SIMD或不SIMD - 跨平台

Question

我需要知道如何以某种方式编写一些可并行化问题的C++跨平台实现,以便我可以利用SIMD(SSE,SPU等)(如果可用).同时我希望能够在运行时在SIMD之间切换而不是SIMD.

你会如何建议我解决这个问题？ (当然我不想为所有可能的选项多次实现该问题)

我可以看到这对C++来说可能不是一件容易的事,但我相信我错过了一些东西.到目前为止,我的想法看起来像这样......类cStream将是单个字段的数组.使用多个cStream我可以实现SoA(阵列结构).然后使用一些函数我可以伪造我需要在整个cStream上执行的Lambda函数.

// just for example I'm not expecting this code to compile
cStream a; // something like float[1024]
cStream b;
cStream c;

void Foo()
{
    for_each(
        AssignSIMD(c, MulSIMD(AddSIMD(a, b), a)));
}

其中for_each将负责增加流的当前指针以及使用SIMD和没有SIMD内联仿函数的主体.

像这样的事情:

// just for example I'm not expecting this code to compile
for_each(functor<T> f)
{
#ifdef USE_SIMD
    if (simdEnabled)
        real_for_each(f<true>()); // true means use SIMD
    else
#endif
        real_for_each(f<false>());
}

请注意,如果启用SIMD,则检查一次,并且循环位于主仿函数周围.

Answer 1

如果有人感兴趣，这是我用来测试我在阅读 Paul 发布的库时提出的新想法的脏代码。

谢谢保罗！

// This is just a conceptual test
// I haven't profile the code and I haven't verified if the result is correct
#include <xmmintrin.h>


// This class is doing all the math
template <bool SIMD>
class cStreamF32
{
private:
    void*       m_data;
    void*       m_dataEnd;
    __m128*     m_current128;
    float*      m_current32;

public:
    cStreamF32(int size)
    {
        if (SIMD)
            m_data = _mm_malloc(sizeof(float) * size, 16);
        else
            m_data = new float[size];
    }
    ~cStreamF32()
    {
        if (SIMD)
            _mm_free(m_data);
        else
            delete[] (float*)m_data;
    }

    inline void Begin()
    {
        if (SIMD)
            m_current128 = (__m128*)m_data;
        else
            m_current32 = (float*)m_data;
    }

    inline bool Next()
    {
        if (SIMD)
        {
            m_current128++;
            return m_current128 < m_dataEnd;
        }
        else
        {
            m_current32++;
            return m_current32 < m_dataEnd;
        }
    }

    inline void operator=(const __m128 x)
    {
        *m_current128 = x;
    }
    inline void operator=(const float x)
    {
        *m_current32 = x;
    }

    inline __m128 operator+(const cStreamF32<true>& x)
    {
        return _mm_add_ss(*m_current128, *x.m_current128);
    }
    inline float operator+(const cStreamF32<false>& x)
    {
        return *m_current32 + *x.m_current32;
    }

    inline __m128 operator+(const __m128 x)
    {
        return _mm_add_ss(*m_current128, x);
    }
    inline float operator+(const float x)
    {
        return *m_current32 + x;
    }

    inline __m128 operator*(const cStreamF32<true>& x)
    {
        return _mm_mul_ss(*m_current128, *x.m_current128);
    }
    inline float operator*(const cStreamF32<false>& x)
    {
        return *m_current32 * *x.m_current32;
    }

    inline __m128 operator*(const __m128 x)
    {
        return _mm_mul_ss(*m_current128, x);
    }
    inline float operator*(const float x)
    {
        return *m_current32 * x;
    }
};

// Executes both functors
template<class T1, class T2>
void Execute(T1& functor1, T2& functor2)
{
    functor1.Begin();
    do
    {
        functor1.Exec();
    }
    while (functor1.Next());

    functor2.Begin();
    do
    {
        functor2.Exec();
    }
    while (functor2.Next());
}

// This is the implementation of the problem
template <bool SIMD>
class cTestFunctor
{
private:
    cStreamF32<SIMD> a;
    cStreamF32<SIMD> b;
    cStreamF32<SIMD> c;

public:
    cTestFunctor() : a(1024), b(1024), c(1024) { }

    inline void Exec()
    {
        c = a + b * a;
    }

    inline void Begin()
    {
        a.Begin();
        b.Begin();
        c.Begin();
    }

    inline bool Next()
    {
        a.Next();
        b.Next();
        return c.Next();
    }
};


int main (int argc, char * const argv[]) 
{
    cTestFunctor<true> functor1;
    cTestFunctor<false> functor2;

    Execute(functor1, functor2);

    return 0;
}