Fun with ALF: 第 5 回 オーバーラップI/Oバッファを利用した行列の加算

/* ---------------------------------------------- */ 
/* matrix declaration for the two cases           */ 
/* ---------------------------------------------- */ 
#ifdef C_A_B // C = A + B 
       alf_data_int32_t mat_a[ROW_SIZE][COL_SIZE]; // the matrix a 
       alf_data_int32_t mat_b[ROW_SIZE][COL_SIZE]; // the matrix b 
       alf_data_int32_t mat_c[ROW_SIZE][COL_SIZE]; // the matrix c 
#else // A = A + B 
       alf_data_int32_t mat_a[ROW_SIZE][COL_SIZE]; // the matrix a 
       alf_data_int32_t mat_b[ROW_SIZE][COL_SIZE]; // the matrix b 
#endif

for (i = 0; i < ROW_SIZE; i+=PART_SIZE){ 
     if(i+PART_SIZE <= ROW_SIZE) 
        wb_parm.num_data = PART_SIZE; 
     else 
        wb_parm.num_data = ROW_SIZE - i; 

     alf_wb_create(task_handle, ALF_WB_SINGLE, 0, &wb_handle); 

     #ifdef C_A_B // C = A + B 
            // 入力データ A, B 
            alf_wb_dtl_begin(wb_handle, ALF_BUF_OVL_IN, 0); // オフセットは 0 
            alf_wb_dtl_entry_add(wb_handle, &mat_a[i][0], wb_parm.num_data*COL_SIZE, 
             ALF_DATA_INT32); // A 
            alf_wb_dtl_entry_add(wb_handle, &mat_b[i][0], wb_parm.num_data*COL_SIZE, 
             ALF_DATA_INT32); // B 
            alf_wb_dtl_end(wb_handle); 

            // 出力データ C は、入力データ A と同じ領域
            // オフセットは 0 、つまり入力データ A と同じ領域
            alf_wb_dtl_begin(wb_handle, ALF_BUF_OVL_OUT, 0); 
            alf_wb_dtl_entry_add(wb_handle, &mat_c[i][0], wb_parm.num_data*COL_SIZE, 
             ALF_DATA_INT32); // C 
            alf_wb_dtl_end(wb_handle); 
     
      #else // A = A + B 
            // 入力および出力データ A 
            alf_wb_dtl_begin(wb_handle, ALF_BUF_OVL_INOUT, 0); // offset 0 
            alf_wb_dtl_entry_add(wb_handle, &mat_a[i][0], wb_parm.num_data*COL_SIZE, 
             ALF_DATA_INT32); // A 
            alf_wb_dtl_end(wb_handle); 

            // 入力データ B は、A の後ろに配置する
            alf_wb_dtl_begin(wb_handle, ALF_BUF_OVL_IN, 
             wb_parm.num_data*COL_SIZE*sizeof(alf_data_int32_t)); 
            alf_wb_dtl_entry_add(wb_handle, &mat_b[i][0], wb_parm.num_data*COL_SIZE, 
             ALF_DATA_INT32); // B 
            alf_wb_dtl_end(wb_handle); 
      #endif 
      alf_wb_parm_add(wb_handle, (void *)&wb_parm, sizeof(wb_parm)/sizeof(unsigned int), 
       ALF_DATA_INT32, 0); 
      alf_wb_enqueue(wb_handle); 
}

/* ---------------------------------------------- */ 
/* the accelerator side code                      */ 
/* ---------------------------------------------- */ 
/* the computation kernel function                */ 
int comp_kernel(void *p_task_context, void *p_parm_ctx_buffer, 
                void *p_input_buffer, void *p_output_buffer, 
                void *p_inout_buffer, unsigned int current_count, 
                unsigned int total_count) 
{ 
  unsigned int i, cnt; 
  int *sa, *sb, *sc; 
  my_wb_parms_t *p_parm = (my_wb_parms_t *) p_parm_context; 

  cnt = p_parm->num_data * COL_SIZE; 

  sa = (int *) p_inout_buffer; 
  sb = sa + cnt; 
  sc = sa; 

  for (i = 0; i < cnt; i ++) 
       sc[i] = sa[i] + sb[i]; 

  return 0; 
}