Some say that the equivalent of "hello world" code in the data parallel world is matrix multiplication :)

Below is the before C++ AMP and after C++ AMP code. For more on what it all means, watch the recording of my C++ AMP introduction (the example below is part of the session).

    void MatrixMultiply(vector<float>& vC, 
			    const vector<float>& vA,
			    const vector<float>& vB, 
			    int M, int N, int W )
    {
        for (int y = 0; y < M; y++) 
        {
            for (int x = 0; x < N; x++) 
            {
                float sum = 0;
                for(int i = 0; i < W; i++)
                {
                    sum += vA[y * W + i] * vB[i * N + x];
                }
                vC[y * N + x] = sum;
	    }
        }
    }

Change the function to use C++ AMP and hence offload the computation to the GPU, and now the calling code (which I am not showing) needs no changes and the overall operation gives you really nice speed up for large datasets… 

    #include <amp.h>
    using namespace concurrency;

    void MatrixMultiply(vector<float>& vC, 
			    const vector<float>& vA,
			    const vector<float>& vB, 
			    int M, int N, int W )
    {
        array_view<const float,2>      a(M, W, vA);
        array_view<const float,2>      b(W, N, vB);
        array_view<writeonly<float>,2> c(M, N, vC); 

        parallel_for_each(
            c.grid,
            [=](index<2> idx) mutable restrict(direct3d) 
            {
                float sum = 0;
                for(int i = 0; i < a.x; i++) 
                {
                    sum += a(idx.y, i) * b(i, idx.x);
                }
                c[idx] = sum;
            }
        );
    }

Again, you can understand the elements above, by using my C++ AMP presentation slides and recording…

Stay tuned for more…

---

Comments about this post welcome at the original blog.