#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 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();

#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, float mod);
#endif
#endif