Fun with ALF: 第 1 回 大きな行列の加算

float mat_a[NUM_ROW][NUM_COL]; 
float mat_b[NUM_ROW][NUM_COL]; 
float mat_c[NUM_ROW][NUM_COL]; 
int main(void) 
{
  int i,j;
  for (i=0; i<NUM_ROW; i++)
     for (j=0; j<NUM_COL; j++)
        mat_c[i][j] = mat_a[i][j] + mat_b[i][j];
  return 0; 
}

alf_handle_t alf_handle; 
unsigned int nodes; 

/* initializes the runtime environment for ALF */ 
alf_init(&config_parms, &alf_handle); 

/* get the number of SPE accelerators available for from the Opteron */ 
rc = alf_query_system_info(alf_handle, ALF_QUERY_NUM_ACCEL, ALF_ACCEL_TYPE_SPE, &nodes); 

/* set the total number of accelerator instances (in this case, SPE) */ 
/* the ALF runtime will have during its lifetime */ 
rc = alf_num_instances_set (alf_handle, nodes);

/* variable declarations */ 
alf_task_desc_handle_t task_desc_handle; 
alf_task_handle_t task_handle; 
const char* spe_image_name; 
const char* library_path_name; 
const char* comp_kernel_name; 

/* describing a task that's executable on the SPE*/ 
alf_task_desc_create(alf_handle, ALF_ACCEL_TYPE_SPE, &task_desc_handle); 
alf_task_desc_set_int32(task_desc_handle, ALF_TASK_DESC_TSK_CTX_SIZE, 0); 
alf_task_desc_set_int32(task_desc_handle, ALF_TASK_DESC_WB_PARM_CTX_BUF_SIZE,
 sizeof(add_parms_t)); 
alf_task_desc_set_int32(task_desc_handle, ALF_TASK_DESC_WB_IN_BUF_SIZE,
 H * V * 2 sizeof(float)); 
alf_task_desc_set_int32(task_desc_handle, ALF_TASK_DESC_WB_OUT_BUF_SIZE,
 H * V * sizeof(float)); 
alf_task_desc_set_int32(task_desc_handle, ALF_TASK_DESC_NUM_DTL_ENTRIES, 8); 
alf_task_desc_set_int32(task_desc_handle, ALF_TASK_DESC_MAX_STACK_SIZE, 4096); 

/* providing the SPE executable name */ 
alf_task_desc_set_int64(task_desc_handle,
 ALF_TASK_DESC_ACCEL_IMAGE_REF_L,(unsigned long long) spe_image_name); 
alf_task_desc_set_int64(task_desc_handle,
 ALF_TASK_DESC_ACCEL_LIBRARY_REF_L,(unsigned long) library_path_name); 
alf_task_desc_set_int64(task_desc_handle,
 ALF_TASK_DESC_ACCEL_KERNEL_REF_L,(unsigned long) comp_kernel_name);

alf_wb_handle_t wb_handle; 
add_parms_t parm __attribute__((aligned(128))); 
parm.h = H; /* horizontal size of the block */ 
parm.v = V; /* vertical size of the block */ 

/* creating work blocks and adding parameter & io buffer */ 
for (i = 0; i < NUM_ROW; i += H) { 
     alf_wb_create(task_handle, ALF_WB_SINGLE, 0,&wb_handle); 

     /* begins a new Data Transfer List for INPUT */ 
     alf_wb_dtl_set_begin(wb_handle, ALF_BUF_IN, 0); 

     /* Add H*V element of mat_a as Input */ 
     alf_wb_dtl_set_entry_add(wb_handle, &matrix_a[i][0], H * V, ALF_DATA_FLOAT); 

     /* Add H*V element of mat_b as Input */ 
     alf_wb_dtl_set_entry_add(wb_handle, &matrix_b[i][0], H * V, ALF_DATA_FLOAT); 
     alf_wb_dtl_set_end(wb_handle); 

     /* begins a new Data Transfer List OUTPUT */ 
     alf_wb_dtl_set_begin(wb_handle, ALF_BUF_OUT, 0); 

     /* Add H*V element of mat_c as Output */ 
     alf_wb_dtl_set_entry_add(wb_handle, &matrix_c[i][0], H * V, ALF_DATA_FLOAT); 
     alf_wb_dtl_set_end(wb_handle); 

     /* pass parameters H and V to spu */ 
     alf_wb_parm_add(wb_handle, (void *) (&parm), sizeof(parm), ALF_DATA_BYTE, 0); 

     /* enqueuing work block */ 
     alf_wb_enqueue(wb_handle); 
} 
alf_task_finalize(task_handle);

/* waiting for all work blocks to be done*/ 
alf_task_wait(task_handle, -1); 
/* exit ALF runtime */ 
alf_exit(alf_handle, ALF_EXIT_WAIT, -1);

int alf_accel_comp_kernel(void *p_task_context, 
            void *p_parm_context, 
            void *p_input_buffer, 
            void *p_output_buffer, 
            void *p_inout_buffer, 
            unsigned int current_count, 
            unsigned int total_count) 
{
 unsigned int i, cnt;
  vector float *sa, *sb, *sc;
  add_parms_t *p_parm = (add_parms_t *)p_parm_context;
  cnt = p_parm->h * p_parm->v / 4;
  sa = (vector float *) p_input_buffer;
  sb = sa + cnt;
  sc = (vector float *) p_output_buffer;
  for (i = 0; i < cnt; i += 4) { 
      sc[i] = spu_add(sa[i], sb[i]);
      sc[i + 1] = spu_add(sa[i + 1], sb[i + 1]);
      sc[i + 2] = spu_add(sa[i + 2], sb[i + 2]);
      sc[i + 3] = spu_add(sa[i + 3], sb[i + 3]);
     }
  return 0;
}