static int base_bcol_basesmuma_setup_ctl (mca_bcol_basesmuma_module_t *sm_bcol_module,
mca_bcol_basesmuma_component_t *cs)
{
const int my_index = sm_bcol_module->super.sbgp_partner_module->my_index;;
bcol_basesmuma_smcm_file_t input_file;
int ret;
/* exchange remote addressing information if it has not already been done */
if (NULL == sm_bcol_module->ctl_backing_files_info) {
input_file.file_name=cs->sm_ctl_structs->map_path;
input_file.size=cs->sm_ctl_structs->map_size;
input_file.size_ctl_structure=0;
input_file.data_seg_alignment=BASESMUMA_CACHE_LINE_SIZE;
input_file.mpool_size=cs->sm_ctl_structs->map_size;
ret = bcol_basesmuma_smcm_allgather_connection(sm_bcol_module,
sm_bcol_module->super.sbgp_partner_module,
&(cs->sm_connections_list),
&(sm_bcol_module->ctl_backing_files_info),
sm_bcol_module->super.sbgp_partner_module->group_comm,
input_file, cs->clt_base_fname,
false);
if (OMPI_SUCCESS != ret) {
return ret;
}
}
/* fill in the pointer to other ranks scartch shared memory */
if (NULL == sm_bcol_module->shared_memory_scratch_space) {
sm_bcol_module->shared_memory_scratch_space =
calloc (sm_bcol_module->super.sbgp_partner_module->group_size, sizeof (void *));
if (!sm_bcol_module->shared_memory_scratch_space) {
opal_output (ompi_bcol_base_framework.framework_output, "Cannot allocate memory for shared_memory_scratch_space.");
return OMPI_ERR_OUT_OF_RESOURCE;
}
for (int i = 0 ; i < sm_bcol_module->super.sbgp_partner_module->group_size ; ++i) {
if (i == my_index) {
/* local file data is not cached in this list */
continue;
}
sm_bcol_module->shared_memory_scratch_space[i] =
(void *)((intptr_t) sm_bcol_module->ctl_backing_files_info[i]->sm_mmap +
cs->scratch_offset_from_base_ctl_file);
}
sm_bcol_module->shared_memory_scratch_space[my_index] =
(void *)((intptr_t) cs->sm_ctl_structs->map_addr + cs->scratch_offset_from_base_ctl_file);
}
return OMPI_SUCCESS;
}
/* New init function used for new control scheme where we put the control
* struct at the top of the payload buffer
*/
int bcol_basesmuma_bank_init_opti(struct mca_bcol_base_memory_block_desc_t *payload_block,
uint32_t data_offset,
mca_bcol_base_module_t *bcol_module,
void *reg_data)
{
/* assumption here is that the block has been registered with
* sm bcol hence has been mapped by each process, need to be
* sure that memory is mapped amongst sm peers
*/
/* local variables */
int ret = OMPI_SUCCESS, i, j;
sm_buffer_mgmt *pload_mgmt;
mca_bcol_basesmuma_component_t *cs = &mca_bcol_basesmuma_component;
bcol_basesmuma_registration_data_t *sm_reg_data =
(bcol_basesmuma_registration_data_t *) reg_data;
mca_bcol_basesmuma_module_t *sm_bcol =
(mca_bcol_basesmuma_module_t *) bcol_module;
mca_bcol_base_memory_block_desc_t *ml_block = payload_block;
size_t malloc_size;
bcol_basesmuma_smcm_file_t input_file;
int leading_dim,loop_limit,buf_id;
unsigned char *base_ptr;
mca_bcol_basesmuma_module_t *sm_bcol_module=
(mca_bcol_basesmuma_module_t *)bcol_module;
int my_idx, array_id;
mca_bcol_basesmuma_header_t *ctl_ptr;
void **results_array, *mem_offset;
mca_bcol_basesmuma_local_mlmem_desc_t *ml_mem = &sm_bcol_module->ml_mem;
/* first, we get a pointer to the payload buffer management struct */
pload_mgmt = &(sm_bcol->colls_with_user_data);
/* go ahead and get the header size that is cached on the payload block
*/
sm_bcol->total_header_size = data_offset;
/* allocate memory for pointers to mine and my peers' payload buffers
* difference here is that now we use our new data struct
*/
malloc_size = ml_block->num_banks*ml_block->num_buffers_per_bank*
pload_mgmt->size_of_group *sizeof(mca_bcol_basesmuma_payload_t);
pload_mgmt->data_buffs = (mca_bcol_basesmuma_payload_t *) malloc(malloc_size);
if( !pload_mgmt->data_buffs) {
ret = OMPI_ERR_OUT_OF_RESOURCE;
goto exit_ERROR;
}
/* allocate some memory to hold the offsets */
results_array = (void **) malloc(pload_mgmt->size_of_group * sizeof (void *));
/* setup the input file for the shared memory connection manager */
input_file.file_name = sm_reg_data->file_name;
input_file.size = sm_reg_data->size;
input_file.size_ctl_structure = 0;
input_file.data_seg_alignment = BASESMUMA_CACHE_LINE_SIZE;
input_file.mpool_size = sm_reg_data->size;
/* call the connection manager and map my shared memory peers' file
*/
ret = bcol_basesmuma_smcm_allgather_connection(
sm_bcol,
sm_bcol->super.sbgp_partner_module,
&(cs->sm_connections_list),
&(sm_bcol->payload_backing_files_info),
sm_bcol->super.sbgp_partner_module->group_comm,
input_file,cs->payload_base_fname,
false);
if( OMPI_SUCCESS != ret ) {
goto exit_ERROR;
}
/* now we exchange offset info - don't assume symmetric virtual memory
*/
mem_offset = (void *) ((uintptr_t) ml_block->block->base_addr -
(uintptr_t) cs->sm_payload_structs->data_addr);
/* call into the exchange offsets function */
ret=comm_allgather_pml(&mem_offset, results_array, sizeof (void *), MPI_BYTE,
sm_bcol_module->super.sbgp_partner_module->my_index,
sm_bcol_module->super.sbgp_partner_module->group_size,
sm_bcol_module->super.sbgp_partner_module->group_list,
sm_bcol_module->super.sbgp_partner_module->group_comm);
if( OMPI_SUCCESS != ret ) {
goto exit_ERROR;
}
/* convert memory offset to virtual address in current rank */
leading_dim = pload_mgmt->size_of_group;
loop_limit = ml_block->num_banks*ml_block->num_buffers_per_bank;
for (i=0;i< sm_bcol_module->super.sbgp_partner_module->group_size;i++) {
/* get the base pointer */
int array_id=SM_ARRAY_INDEX(leading_dim,0,i);
if( i == sm_bcol_module->super.sbgp_partner_module->my_index) {
/* me */
base_ptr=cs->sm_payload_structs->map_addr;
} else {
base_ptr=sm_bcol_module->payload_backing_files_info[i]->
sm_mmap->map_addr;
}
/* first, set the pointer to the control struct */
pload_mgmt->data_buffs[array_id].ctl_struct=(mca_bcol_basesmuma_header_t *)
(uintptr_t)(((uint64_t)(uintptr_t)results_array[array_id])+(uint64_t)(uintptr_t)base_ptr);
/* second, calculate where to set the data pointer */
pload_mgmt->data_buffs[array_id].payload=(void *)
(uintptr_t)((uint64_t)(uintptr_t) pload_mgmt->data_buffs[array_id].ctl_struct +
(uint64_t)(uintptr_t) data_offset);
for( buf_id = 1 ; buf_id < loop_limit ; buf_id++ ) {
int array_id_m1=SM_ARRAY_INDEX(leading_dim,(buf_id-1),i);
array_id=SM_ARRAY_INDEX(leading_dim,buf_id,i);
/* now, play the same game as above
*
* first, set the control struct's position */
pload_mgmt->data_buffs[array_id].ctl_struct=(mca_bcol_basesmuma_header_t *)
(uintptr_t)(((uint64_t)(uintptr_t)(pload_mgmt->data_buffs[array_id_m1].ctl_struct) +
(uint64_t)(uintptr_t)ml_block->size_buffer));
/* second, set the payload pointer */
pload_mgmt->data_buffs[array_id].payload =(void *)
(uintptr_t)((uint64_t)(uintptr_t) pload_mgmt->data_buffs[array_id].ctl_struct +
(uint64_t)(uintptr_t) data_offset);
}
}
/* done with the index array */
free (results_array);
/* initialize my control structures!! */
my_idx = sm_bcol_module->super.sbgp_partner_module->my_index;
leading_dim = sm_bcol_module->super.sbgp_partner_module->group_size;
for( buf_id = 0; buf_id < loop_limit; buf_id++){
array_id = SM_ARRAY_INDEX(leading_dim,buf_id,my_idx);
ctl_ptr = pload_mgmt->data_buffs[array_id].ctl_struct;
/* initialize the data structures */
for( j = 0; j < SM_BCOLS_MAX; j++){
for( i = 0; i < NUM_SIGNAL_FLAGS; i++){
ctl_ptr->flags[i][j] = -1;
}
}
ctl_ptr->sequence_number = -1;
ctl_ptr->src = -1;
}
/* setup the data structures needed for releasing the payload
* buffers back to the ml level
*/
for( i=0 ; i < (int) ml_block->num_banks ; i++ ) {
sm_bcol->colls_with_user_data.
ctl_buffs_mgmt[i].nb_barrier_desc.ml_memory_block_descriptor=
ml_block;
}
ml_mem->num_banks = ml_block->num_banks;
ml_mem->bank_release_counter = calloc(ml_block->num_banks, sizeof(uint32_t));
ml_mem->num_buffers_per_bank = ml_block->num_buffers_per_bank;
ml_mem->size_buffer = ml_block->size_buffer;
/* pointer to ml level descriptor */
ml_mem->ml_mem_desc = ml_block;
if (OMPI_SUCCESS != init_nb_coll_buff_desc(&ml_mem->nb_coll_desc,
ml_block->block->base_addr,
ml_mem->num_banks,
ml_mem->num_buffers_per_bank,
ml_mem->size_buffer,
data_offset,
sm_bcol_module->super.sbgp_partner_module->group_size,
sm_bcol_module->pow_k)) {
BASESMUMA_VERBOSE(10, ("Failed to allocate memory descriptors for storing state of non-blocking collectives\n"));
return OMPI_ERROR;
}
return OMPI_SUCCESS;
exit_ERROR:
return ret;
}
