Function ggml_compute_forward_silu_back_f32

ggml.c:9105–9148

// ggml_compute_forward_silu_back

static void ggml_compute_forward_silu_back_f32(
        const struct ggml_compute_params * params,
        const struct ggml_tensor * src0,
        const struct ggml_tensor * grad,
        struct ggml_tensor * dst) {
    GGML_ASSERT(ggml_is_contiguous_except_dim_1(grad));
    GGML_ASSERT(ggml_is_contiguous_except_dim_1(src0));
    GGML_ASSERT(ggml_is_contiguous_except_dim_1(dst));
    GGML_ASSERT(ggml_are_same_shape(src0, dst));
    GGML_ASSERT(ggml_are_same_shape(src0, grad));

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

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

    const int nc = src0->ne[0];
    const int nr = ggml_nrows(src0);

    // 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);

    for (int i1 = ir0; i1 < ir1; i1++) {
        ggml_vec_silu_backward_f32(nc,
                (float *) ((char *) dst->data  + i1*( dst->nb[1])),
                (float *) ((char *) src0->data + i1*(src0->nb[1])),
                (float *) ((char *) grad->data + i1*(grad->nb[1])));

#ifndef NDEBUG
        for (int k = 0; k < nc; k++) {
            const float x = ((float *) ((char *) dst->data + i1*( dst->nb[1])))[k];
            UNUSED(x);
            assert(!isnan(x));
            assert(!isinf(x));
        }
#endif
    }
}

static void ggml_compute_forward_silu_back(
        const struct ggml_compute_params * params,