#include "route_layer.h"
#include "cuda.h"
#include "blas.h"
#include <stdio.h>

route_layer make_route_layer(int batch, int n, int *input_layers, int *input_sizes)
{
    fprintf(stderr,"Route Layer:");
    route_layer l = {0};
    l.type = ROUTE;
    l.batch = batch;
    l.n = n;
    l.input_layers = input_layers;
    l.input_sizes = input_sizes;
    int i;
    int outputs = 0;
    for(i = 0; i < n; ++i){
        fprintf(stderr," %d", input_layers[i]);
        outputs += input_sizes[i];
    }
    fprintf(stderr, "\n");
    l.outputs = outputs;
    l.inputs = outputs;
    l.delta =  calloc(outputs*batch, sizeof(float));
    l.output = calloc(outputs*batch, sizeof(float));;

    l.forward = forward_route_layer;
    l.backward = backward_route_layer;
    #ifdef GPU
    l.forward_gpu = forward_route_layer_gpu;
    l.backward_gpu = backward_route_layer_gpu;

    l.delta_gpu =  cuda_make_array(l.delta, outputs*batch);
    l.output_gpu = cuda_make_array(l.output, outputs*batch);
    #endif
    return l;
}

void forward_route_layer(const route_layer l, network_state state)
{
    int i, j;
    int offset = 0;
    for(i = 0; i < l.n; ++i){
        int index = l.input_layers[i];
        float *input = state.net.layers[index].output;
        int input_size = l.input_sizes[i];
        for(j = 0; j < l.batch; ++j){
            copy_cpu(input_size, input + j*input_size, 1, l.output + offset + j*l.outputs, 1);
        }
        offset += input_size;
    }
}

void backward_route_layer(const route_layer l, network_state state)
{
    int i, j;
    int offset = 0;
    for(i = 0; i < l.n; ++i){
        int index = l.input_layers[i];
        float *delta = state.net.layers[index].delta;
        int input_size = l.input_sizes[i];
        for(j = 0; j < l.batch; ++j){
            axpy_cpu(input_size, 1, l.delta + offset + j*l.outputs, 1, delta + j*input_size, 1);
        }
        offset += input_size;
    }
}

#ifdef GPU
void forward_route_layer_gpu(const route_layer l, network_state state)
{
    int i, j;
    int offset = 0;
    for(i = 0; i < l.n; ++i){
        int index = l.input_layers[i];
        float *input = state.net.layers[index].output_gpu;
        int input_size = l.input_sizes[i];
        for(j = 0; j < l.batch; ++j){
            copy_ongpu(input_size, input + j*input_size, 1, l.output_gpu + offset + j*l.outputs, 1);
        }
        offset += input_size;
    }
}

void backward_route_layer_gpu(const route_layer l, network_state state)
{
    int i, j;
    int offset = 0;
    for(i = 0; i < l.n; ++i){
        int index = l.input_layers[i];
        float *delta = state.net.layers[index].delta_gpu;
        int input_size = l.input_sizes[i];
        for(j = 0; j < l.batch; ++j){
            axpy_ongpu(input_size, 1, l.delta_gpu + offset + j*l.outputs, 1, delta + j*input_size, 1);
        }
        offset += input_size;
    }
}
#endif