Function ggml_compute_forward_acc_f32

ggml.c:7566–7643

// ggml_compute_forward_acc

static void ggml_compute_forward_acc_f32(
        const struct ggml_compute_params * params,
        const struct ggml_tensor * src0,
        const struct ggml_tensor * src1,
        struct ggml_tensor * dst) {
    GGML_ASSERT(ggml_are_same_shape(src0, dst));
    GGML_ASSERT(ggml_is_contiguous(dst) && ggml_is_contiguous(src0));

    // view src0 and dst with these strides and data offset inbytes during acc
    // nb0 is implicitely element_size because src0 and dst are contiguous
    size_t nb1     = ((int32_t *) dst->op_params)[0];
    size_t nb2     = ((int32_t *) dst->op_params)[1];
    size_t nb3     = ((int32_t *) dst->op_params)[2];
    size_t offset  = ((int32_t *) dst->op_params)[3];
    bool   inplace = (bool) ((int32_t *) dst->op_params)[4];

    if (!inplace && (params->type == GGML_TASK_INIT)) {
        // memcpy needs to be synchronized across threads to avoid race conditions.
        // => do it in INIT phase
        memcpy(
            ((char *)  dst->data),
            ((char *) src0->data),
            ggml_nbytes(dst));
    }

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

    const int ith = params->ith;
    const int nth = params->nth;

    const int nr = ggml_nrows(src1);
    const int nc = src1->ne[0];

    GGML_TENSOR_LOCALS(int64_t, ne1, src1, ne)
    GGML_TENSOR_LOCALS(size_t,  nb1, src1, nb)

    // src0 and dst as viewed during acc
    const size_t nb0 = ggml_element_size(src0);

    const size_t nb00 = nb0;
    const size_t nb01 = nb1;
    const size_t nb02 = nb2;
    const size_t nb03 = nb3;

    GGML_ASSERT(offset + (ne10 == 0 ? 0 : ne10-1)*nb0  + (ne11 == 0 ? 0 : ne11-1)*nb1  + (ne12 == 0 ? 0 : ne12-1)*nb2  + (ne13 == 0 ? 0 : ne13-1)*nb3  < ggml_nbytes(dst));
    GGML_ASSERT(offset + (ne10 == 0 ? 0 : ne10-1)*nb00 + (ne11 == 0 ? 0 : ne11-1)*nb01 + (ne12 == 0 ? 0 : ne12-1)*nb02 + (ne13 == 0 ? 0 : ne13-1)*nb03 < ggml_nbytes(src0));

    GGML_ASSERT(nb10 == sizeof(float));

    // rows per thread
    const int dr = (nr + nth - 1)/nth;

    // row range for this thread
    const int ir0 = dr*ith;
    const int ir1 = MIN(ir0 + dr, nr);