Function ggml_compute_forward_repeat_f32

ggml.c:8340–8381

// ggml_compute_forward_repeat

static void ggml_compute_forward_repeat_f32(
        const struct ggml_compute_params * params,
        const struct ggml_tensor * src0,
        struct ggml_tensor * dst) {
    GGML_ASSERT(params->ith == 0);
    GGML_ASSERT(ggml_can_repeat(src0, dst));

    if (params->type == GGML_TASK_INIT || params->type == GGML_TASK_FINALIZE) {
        return;
    }

    GGML_TENSOR_UNARY_OP_LOCALS

    // guaranteed to be an integer due to the check in ggml_can_repeat
    const int nr0 = (int)(ne0/ne00);
    const int nr1 = (int)(ne1/ne01);
    const int nr2 = (int)(ne2/ne02);
    const int nr3 = (int)(ne3/ne03);

    // TODO: support for transposed / permuted tensors
    GGML_ASSERT(nb0  == sizeof(float));
    GGML_ASSERT(nb00 == sizeof(float));

    // TODO: maybe this is not optimal?
    for                         (int i3 = 0; i3 < nr3;  i3++) {
        for                     (int k3 = 0; k3 < ne03; k3++) {
            for                 (int i2 = 0; i2 < nr2;  i2++) {
                for             (int k2 = 0; k2 < ne02; k2++) {
                    for         (int i1 = 0; i1 < nr1;  i1++) {
                        for     (int k1 = 0; k1 < ne01; k1++) {
                            for (int i0 = 0; i0 < nr0;  i0++) {
                                ggml_vec_cpy_f32(ne00,
                                        (float *) ((char *)  dst->data + (i3*ne03 + k3)*nb3  + (i2*ne02 + k2)*nb2  + (i1*ne01 + k1)*nb1  + (i0*ne00)*nb0),
                                        (float *) ((char *) src0->data + (          k3)*nb03 + (          k2)*nb02 + (          k1)*nb01));
                            }
                        }
                    }
                }
            }
        }
    }
}

static void ggml_compute_forward_repeat_f16(
        const struct ggml_compute_params * params,