tensor_tiled_copy(Trans)

#include <stdio.h>
#include <stdlib.h>
#include "kupl_mma.h"
using namespace kupl::tensor;

int main()
{
    constexpr int MATRIX_M = 32;
    constexpr int MATRIX_N = 512;
    double *dst = (double*)malloc(sizeof(double) * MATRIX_M * MATRIX_N);
    double *src = (double*)malloc(sizeof(double) * MATRIX_M * MATRIX_N);
    for (int i = 0; i < MATRIX_M; i++) {
        for (int j = 0; j < MATRIX_N; j++) {
            dst[i * MATRIX_N + j] = 0.0;
            src[i * MATRIX_N + j] = i * MATRIX_N + j;
        }
    }

    auto shape_d = make_shape(Int<MATRIX_M>{}, Int<MATRIX_N>{});
    auto shape_s = make_shape(Int<MATRIX_M>{}, Int<MATRIX_N>{});

    auto stride_d = make_stride(Int<1>{}, Int<MATRIX_M>{});
    auto stride_s = make_stride(Int<MATRIX_N>{}, Int<1>{});

    auto layout_d = make_layout(shape_d, stride_d);
    auto layout_s = make_layout(shape_s, stride_s);

    auto atom_copy_shape = make_shape(Int<1>{}, Int<MATRIX_N>{});
    auto tiled_copy = make_tiled_copy(Ops<COPY_32x1_F64_RM2CM>{}, atom_copy_shape);

    auto tensor_d = make_tensor(dst, layout_d);
    auto tensor_s = make_tensor(src, layout_s);
    tensor_tiled_copy(tiled_copy, tensor_d, tensor_s);

    free(src);
    free(dst);
    return 0;
}