How to copy none sequential data to a GPU memory buffer in OpenCL?

Question

I know how i would copy a array from Host to GPU. But what happens if i have a column major matrix stored on host that i want to copy to a buffer on the GPU.

Are there other ways then copying one element at the time in a forloop ?

A_host [0 3 6 1 4 7 2 5 8].

GPUBuffer = [0 1 2 3 4 5 6 7 8].

Answer 1

在这种情况下，如果矩阵足够大，您可能希望“按原样”将其发送到GPU，并插入一个额外的转置内核（或将其合并到您的第一个内核）。