#ifndef BLAS_H
#define BLAS_H
void pm(int M, int N, float *A);
float *random_matrix(int rows, int cols);
void time_random_matrix(int TA, int TB, int m, int k, int n);

void test_blas();

void const_cpu(int N, float ALPHA, float *X, int INCX);
void pow_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY);
void mul_cpu(int N, float *X, int INCX, float *Y, int INCY);

void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY);
void copy_cpu(int N, float *X, int INCX, float *Y, int INCY);
void scal_cpu(int N, float ALPHA, float *X, int INCX);
float dot_cpu(int N, float *X, int INCX, float *Y, int INCY);
void test_gpu_blas();

void mean_cpu(float *x, int batch, int filters, int spatial, float *mean);
void variance_cpu(float *x, float *mean, int batch, int filters, int spatial, float *variance);
void normalize_cpu(float *x, float *mean, float *variance, int batch, int filters, int spatial);

#ifdef GPU
void axpy_ongpu(int N, float ALPHA, float * X, int INCX, float * Y, int INCY);
void axpy_ongpu_offset(int N, float ALPHA, float * X, int OFFX, int INCX, float * Y, int OFFY, int INCY);
void copy_ongpu(int N, float * X, int INCX, float * Y, int INCY);
void copy_ongpu_offset(int N, float * X, int OFFX, int INCX, float * Y, int OFFY, int INCY);
void scal_ongpu(int N, float ALPHA, float * X, int INCX);
void mask_ongpu(int N, float * X, float mask_num, float * mask);
void const_ongpu(int N, float ALPHA, float *X, int INCX);
void pow_ongpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY);
void mul_ongpu(int N, float *X, int INCX, float *Y, int INCY);
void fill_ongpu(int N, float ALPHA, float * X, int INCX);

void mean_gpu(float *x, int batch, int filters, int spatial, float *mean);
void variance_gpu(float *x, float *mean, int batch, int filters, int spatial, float *variance);
void normalize_gpu(float *x, float *mean, float *variance, int batch, int filters, int spatial);

void mean_delta_gpu(float *delta, float *variance, int batch, int filters, int spatial, float *mean_delta);
void variance_delta_gpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *variance_delta);
void normalize_delta_gpu(float *x, float *mean, float *variance, float *mean_delta, float *variance_delta, int batch, int filters, int spatial, float *delta);

void fast_mean_delta_gpu(float *delta, float *variance, int batch, int filters, int spatial, float *spatial_mean_delta, float *mean_delta);
void fast_variance_delta_gpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *spatial_variance_delta, float *variance_delta);

void fast_variance_gpu(float *x, float *mean, int batch, int filters, int spatial, float *spatial_variance, float *variance);
void fast_mean_gpu(float *x, int batch, int filters, int spatial, float *spatial_mean, float *mean);
#endif
#endif