#ifndef GEMM_H
#define GEMM_H

void gemm(int TA, int TB, int M, int N, int K, float ALPHA, 
                    float *A, int lda, 
                    float *B, int ldb,
                    float BETA,
                    float *C, int ldc);

void gemm_cpu(int TA, int TB, int M, int N, int K, float ALPHA, 
        float *A, int lda, 
        float *B, int ldb,
        float BETA,
        float *C, int ldc);

#ifdef GPU
void gemm_ongpu(int TA, int TB, int M, int N, int K, float ALPHA, 
        float *A_gpu, int lda, 
        float *B_gpu, int ldb,
        float BETA,
        float *C_gpu, int ldc);

void gemm_gpu(int TA, int TB, int M, int N, int K, float ALPHA, 
        float *A, int lda, 
        float *B, int ldb,
        float BETA,
        float *C, int ldc);
#endif
#endif