std1.0.0-beta-7 SafeC docs

std :: ml::gpu_cuda

Function std::cuda_copy_rows

#include <std/ml/gpu_cuda.h> source ยท definition

int cuda_copy_rows(
    struct CudaBuf src,
    unsigned long srcOff,
    unsigned long srcStride,
    struct CudaBuf dst,
    unsigned long dstOff,
    unsigned long dstStride,
    unsigned long rowLen,
    unsigned long rows,
)

Strided 2D copy, one queued kernel: for r < rows, c < rowLen, dst[dstOff + rdstStride + c] = src[srcOff + rsrcStride + c]. Rows must not overlap (rowLen <= both strides when rows > 1).