move sgemm_direct function declarations

common_level3.h

@@ -47,12 +47,12 @@ __global__ void cuda_dgemm_kernel(int, int, int, double *, double *, double *);
 extern "C" {
 #endif
 
-extern void sgemm_kernel_direct(BLASLONG M, BLASLONG N, BLASLONG K,
+void sgemm_direct(BLASLONG M, BLASLONG N, BLASLONG K,
 	float * A, BLASLONG strideA,
 	float * B, BLASLONG strideB,
 	float * R, BLASLONG strideR);
 
-extern int sgemm_kernel_direct_performant(BLASLONG M, BLASLONG N, BLASLONG K);
+int sgemm_direct_performant(BLASLONG M, BLASLONG N, BLASLONG K);
 
 
 int shgemm_beta(BLASLONG, BLASLONG, BLASLONG, float,

common_param.h

@@ -175,6 +175,9 @@ BLASLONG (*ismin_k) (BLASLONG, float *, BLASLONG);
   int    (*ssymv_L) (BLASLONG, BLASLONG, float,  float  *, BLASLONG, float  *, BLASLONG, float  *, BLASLONG, float *);
   int    (*ssymv_U) (BLASLONG, BLASLONG, float,  float  *, BLASLONG, float  *, BLASLONG, float  *, BLASLONG, float *);
 
+  void (*sgemm_direct) (BLASLONG, BLASLONG, BLASLONG, float *, BLASLONG , float *, BLASLONG , float * , BLASLONG);
+  int  (*sgemm_direct_performant) (BLASLONG M, BLASLONG N, BLASLONG K);
+
   int    (*sgemm_kernel   )(BLASLONG, BLASLONG, BLASLONG, float, float *, float *, float *, BLASLONG);
   int    (*sgemm_beta     )(BLASLONG, BLASLONG, BLASLONG, float, float *, BLASLONG, float *, BLASLONG, float  *, BLASLONG);