void multiply(float* a, float* b, float* c, int istart, int iend, int size);
void multiply_sampled(float* a, float* b, float* c, int istart, int iend, int size);
void multiply(float* a, float* b, float* c, int istart, int iend, int size);
void multiply_sampled(float* a, float* b, float* c, int istart, int iend, int size);