#include "blas.h"
#include "math.h"

void shortcut_cpu(float *out, int w, int h, int c, int batch, int sample, float *add, int stride, int c2)
{
    int i,j,k,b;
    for(b = 0; b < batch; ++b){
        for(k = 0; k < c && k < c2; ++k){
            for(j = 0; j < h/sample; ++j){
                for(i = 0; i < w/sample; ++i){
                    int out_index = i*sample + w*(j*sample + h*(k + c*b));
                    int add_index = b*w*stride/sample*h*stride/sample*c2 + i*stride + w*stride/sample*(j*stride + h*stride/sample*k);
                    out[out_index] += add[add_index];
                }
            }
        }
    }
}

void mean_cpu(float *x, int batch, int filters, int spatial, float *mean)
{
    float scale = 1./(batch * spatial);
    int i,j,k;
    for(i = 0; i < filters; ++i){
        mean[i] = 0;
        for(j = 0; j < batch; ++j){
            for(k = 0; k < spatial; ++k){
                int index = j*filters*spatial + i*spatial + k;
                mean[i] += x[index];
            }
        }
        mean[i] *= scale;
    }
}

void variance_cpu(float *x, float *mean, int batch, int filters, int spatial, float *variance)
{
    float scale = 1./(batch * spatial);
    int i,j,k;
    for(i = 0; i < filters; ++i){
        variance[i] = 0;
        for(j = 0; j < batch; ++j){
            for(k = 0; k < spatial; ++k){
                int index = j*filters*spatial + i*spatial + k;
                variance[i] += pow((x[index] - mean[i]), 2);
            }
        }
        variance[i] *= scale;
    }
}

void normalize_cpu(float *x, float *mean, float *variance, int batch, int filters, int spatial)
{
    int b, f, i;
    for(b = 0; b < batch; ++b){
        for(f = 0; f < filters; ++f){
            for(i = 0; i < spatial; ++i){
                int index = b*filters*spatial + f*spatial + i;
                x[index] = (x[index] - mean[f])/(sqrt(variance[f]));
            }
        }
    }
}

void const_cpu(int N, float ALPHA, float *X, int INCX)
{
    int i;
    for(i = 0; i < N; ++i) X[i*INCX] = ALPHA;
}

void mul_cpu(int N, float *X, int INCX, float *Y, int INCY)
{
    int i;
    for(i = 0; i < N; ++i) Y[i*INCY] *= X[i*INCX];
}

void pow_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY)
{
    int i;
    for(i = 0; i < N; ++i) Y[i*INCY] = pow(X[i*INCX], ALPHA);
}

void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY)
{
    int i;
    for(i = 0; i < N; ++i) Y[i*INCY] += ALPHA*X[i*INCX];
}

void scal_cpu(int N, float ALPHA, float *X, int INCX)
{
    int i;
    for(i = 0; i < N; ++i) X[i*INCX] *= ALPHA;
}

void copy_cpu(int N, float *X, int INCX, float *Y, int INCY)
{
    int i;
    for(i = 0; i < N; ++i) Y[i*INCY] = X[i*INCX];
}

float dot_cpu(int N, float *X, int INCX, float *Y, int INCY)
{
    int i;
    float dot = 0;
    for(i = 0; i < N; ++i) dot += X[i*INCX] * Y[i*INCY];
    return dot;
}