TODO. While StarPU comes with a variety of scheduling policies (see Task Scheduling Policies), it may sometimes be desirable to implement custom policies to address specific problems. The API described below allows users to write their own scheduling policy.
More...
|
typedef void(* | starpu_notify_ready_soon_func) (void *data, struct starpu_task *task, double delay) |
|
|
struct starpu_sched_policy ** | starpu_sched_get_predefined_policies () |
|
void | starpu_worker_get_sched_condition (int workerid, starpu_pthread_mutex_t **sched_mutex, starpu_pthread_cond_t **sched_cond) |
|
unsigned long | starpu_task_get_job_id (struct starpu_task *task) |
|
int | starpu_sched_get_min_priority (void) |
|
int | starpu_sched_get_max_priority (void) |
|
int | starpu_sched_set_min_priority (int min_prio) |
|
int | starpu_sched_set_max_priority (int max_prio) |
|
int | starpu_worker_can_execute_task (unsigned workerid, struct starpu_task *task, unsigned nimpl) |
|
int | starpu_worker_can_execute_task_impl (unsigned workerid, struct starpu_task *task, unsigned *impl_mask) |
|
int | starpu_worker_can_execute_task_first_impl (unsigned workerid, struct starpu_task *task, unsigned *nimpl) |
|
int | starpu_push_local_task (int workerid, struct starpu_task *task, int back) |
|
int | starpu_push_task_end (struct starpu_task *task) |
|
int | starpu_get_prefetch_flag (void) |
|
int | starpu_prefetch_task_input_on_node_prio (struct starpu_task *task, unsigned node, int prio) |
|
int | starpu_prefetch_task_input_on_node (struct starpu_task *task, unsigned node) |
|
int | starpu_idle_prefetch_task_input_on_node_prio (struct starpu_task *task, unsigned node, int prio) |
|
int | starpu_idle_prefetch_task_input_on_node (struct starpu_task *task, unsigned node) |
|
int | starpu_prefetch_task_input_for_prio (struct starpu_task *task, unsigned worker, int prio) |
|
int | starpu_prefetch_task_input_for (struct starpu_task *task, unsigned worker) |
|
int | starpu_idle_prefetch_task_input_for_prio (struct starpu_task *task, unsigned worker, int prio) |
|
int | starpu_idle_prefetch_task_input_for (struct starpu_task *task, unsigned worker) |
|
uint32_t | starpu_task_footprint (struct starpu_perfmodel *model, struct starpu_task *task, struct starpu_perfmodel_arch *arch, unsigned nimpl) |
|
uint32_t | starpu_task_data_footprint (struct starpu_task *task) |
|
double | starpu_task_expected_length (struct starpu_task *task, struct starpu_perfmodel_arch *arch, unsigned nimpl) |
|
double | starpu_worker_get_relative_speedup (struct starpu_perfmodel_arch *perf_arch) |
|
double | starpu_task_expected_data_transfer_time (unsigned memory_node, struct starpu_task *task) |
|
double | starpu_task_expected_data_transfer_time_for (struct starpu_task *task, unsigned worker) |
|
double | starpu_data_expected_transfer_time (starpu_data_handle_t handle, unsigned memory_node, enum starpu_data_access_mode mode) |
|
double | starpu_task_expected_energy (struct starpu_task *task, struct starpu_perfmodel_arch *arch, unsigned nimpl) |
|
double | starpu_task_expected_conversion_time (struct starpu_task *task, struct starpu_perfmodel_arch *arch, unsigned nimpl) |
|
void | starpu_task_notify_ready_soon_register (starpu_notify_ready_soon_func f, void *data) |
|
void | starpu_sched_ctx_worker_shares_tasks_lists (int workerid, int sched_ctx_id) |
|
void | starpu_sched_task_break (struct starpu_task *task) |
|
TODO. While StarPU comes with a variety of scheduling policies (see Task Scheduling Policies), it may sometimes be desirable to implement custom policies to address specific problems. The API described below allows users to write their own scheduling policy.
◆ starpu_sched_policy
struct starpu_sched_policy |
Contain all the methods that implement a scheduling policy. An application may specify which scheduling strategy in the field starpu_conf::sched_policy passed to the function starpu_init().
For each task going through the scheduler, the following methods get called in the given order:
For each task not going through the scheduler (because starpu_task::execute_on_a_specific_worker was set), these get called:
◆ init_sched
void(* starpu_sched_policy::init_sched) (unsigned sched_ctx_id) |
Initialize the scheduling policy, called before any other method.
◆ deinit_sched
void(* starpu_sched_policy::deinit_sched) (unsigned sched_ctx_id) |
Cleanup the scheduling policy
◆ push_task
int(* starpu_sched_policy::push_task) (struct starpu_task *) |
Insert a task into the scheduler, called when the task becomes ready for execution. This must call starpu_push_task_end() once it has effectively pushed the task to a queue (to note the time when this was done in the task), but before releasing mutexes (so that the task hasn't been already taken by a worker).
◆ push_task_notify
void(* starpu_sched_policy::push_task_notify) (struct starpu_task *, int workerid, int perf_workerid, unsigned sched_ctx_id) |
Notify the scheduler that a task was pushed on a given worker. This method is called when a task that was explicitly assigned to a worker becomes ready and is about to be executed by the worker. This method therefore permits to keep the state of the scheduler coherent even when StarPU bypasses the scheduling strategy.
◆ pop_task
struct starpu_task*(* starpu_sched_policy::pop_task) (unsigned sched_ctx_id) |
Get a task from the scheduler. If this method returns NULL, the worker will start sleeping. If later on some task are pushed for this worker, starpu_wake_worker() must be called to wake the worker so it can call the pop_task() method again. The mutex associated to the worker is already taken when this method is called. This method may release it (e.g. for scalability reasons when doing work stealing), but it must acquire it again before taking the decision whether to return a task or NULL, so the atomicity of deciding to return NULL and making the worker actually sleep is preserved. Otherwise in simgrid or blocking driver mode the worker might start sleeping while a task has just been pushed for it. If this method is defined as NULL
, the worker will only execute tasks from its local queue. In this case, the push_task method should use the starpu_push_local_task method to assign tasks to the different workers.
◆ pop_every_task
struct starpu_task*(* starpu_sched_policy::pop_every_task) (unsigned sched_ctx_id) |
Remove all available tasks from the scheduler (tasks are chained by the means of the field starpu_task::prev and starpu_task::next). The mutex associated to the worker is already taken when this method is called. This is currently not used and can be discarded.
◆ submit_hook
void(* starpu_sched_policy::submit_hook) (struct starpu_task *task) |
Optional field. This method is called when a task is submitted.
◆ pre_exec_hook
void(* starpu_sched_policy::pre_exec_hook) (struct starpu_task *, unsigned sched_ctx_id) |
Optional field. This method is called every time a task is starting.
◆ post_exec_hook
void(* starpu_sched_policy::post_exec_hook) (struct starpu_task *, unsigned sched_ctx_id) |
Optional field. This method is called every time a task has been executed.
◆ do_schedule
void(* starpu_sched_policy::do_schedule) (unsigned sched_ctx_id) |
Optional field. This method is called when it is a good time to start scheduling tasks. This is notably called when the application calls starpu_task_wait_for_all() or starpu_do_schedule() explicitly.
◆ add_workers
void(* starpu_sched_policy::add_workers) (unsigned sched_ctx_id, int *workerids, unsigned nworkers) |
Initialize scheduling structures corresponding to each worker used by the policy.
◆ remove_workers
void(* starpu_sched_policy::remove_workers) (unsigned sched_ctx_id, int *workerids, unsigned nworkers) |
Deinitialize scheduling structures corresponding to each worker used by the policy.
◆ policy_name
const char* starpu_sched_policy::policy_name |
Optional field. Name of the policy.
◆ policy_description
const char* starpu_sched_policy::policy_description |
Optional field. Human readable description of the policy.
◆ STARPU_NMAX_SCHED_CTXS
#define STARPU_NMAX_SCHED_CTXS |
Define the maximum number of scheduling contexts managed by StarPU. The default value can be modified at configure by using the option --enable-max-sched-ctxs.
◆ STARPU_MAXIMPLEMENTATIONS
#define STARPU_MAXIMPLEMENTATIONS |
Define the maximum number of implementations per architecture. The default value can be modified at configure by using the option --enable-maximplementations.
◆ starpu_sched_get_predefined_policies()
Return an NULL
-terminated array of all the predefined scheduling policies.
◆ starpu_worker_get_sched_condition()
void starpu_worker_get_sched_condition |
( |
int |
workerid, |
|
|
starpu_pthread_mutex_t ** |
sched_mutex, |
|
|
starpu_pthread_cond_t ** |
sched_cond |
|
) |
| |
When there is no available task for a worker, StarPU blocks this worker on a condition variable. This function specifies which condition variable (and the associated mutex) should be used to block (and to wake up) a worker. Note that multiple workers may use the same condition variable. For instance, in the case of a scheduling strategy with a single task queue, the same condition variable would be used to block and wake up all workers.
◆ starpu_sched_get_min_priority()
int starpu_sched_get_min_priority |
( |
void |
| ) |
|
TODO: check if this is correct Return the current minimum priority level supported by the scheduling policy
◆ starpu_sched_get_max_priority()
int starpu_sched_get_max_priority |
( |
void |
| ) |
|
TODO: check if this is correct Return the current maximum priority level supported by the scheduling policy
◆ starpu_sched_set_min_priority()
int starpu_sched_set_min_priority |
( |
int |
min_prio | ) |
|
TODO: check if this is correct Define the minimum task priority level supported by the scheduling policy. The default minimum priority level is the same as the default priority level which is 0 by convention. The application may access that value by calling the function starpu_sched_get_min_priority(). This function should only be called from the initialization method of the scheduling policy, and should not be used directly from the application.
◆ starpu_sched_set_max_priority()
int starpu_sched_set_max_priority |
( |
int |
max_prio | ) |
|
TODO: check if this is correct Define the maximum priority level supported by the scheduling policy. The default maximum priority level is 1. The application may access that value by calling the function starpu_sched_get_max_priority(). This function should only be called from the initialization method of the scheduling policy, and should not be used directly from the application.
◆ starpu_worker_can_execute_task()
int starpu_worker_can_execute_task |
( |
unsigned |
workerid, |
|
|
struct starpu_task * |
task, |
|
|
unsigned |
nimpl |
|
) |
| |
Check if the worker specified by workerid can execute the codelet. Schedulers need to call it before assigning a task to a worker, otherwise the task may fail to execute.
◆ starpu_worker_can_execute_task_impl()
int starpu_worker_can_execute_task_impl |
( |
unsigned |
workerid, |
|
|
struct starpu_task * |
task, |
|
|
unsigned * |
impl_mask |
|
) |
| |
Check if the worker specified by workerid can execute the codelet and return which implementation numbers can be used. Schedulers need to call it before assigning a task to a worker, otherwise the task may fail to execute. This should be preferred rather than calling starpu_worker_can_execute_task() for each and every implementation. It can also be used with impl_mask == NULL
to check for at least one implementation without determining which.
◆ starpu_worker_can_execute_task_first_impl()
int starpu_worker_can_execute_task_first_impl |
( |
unsigned |
workerid, |
|
|
struct starpu_task * |
task, |
|
|
unsigned * |
nimpl |
|
) |
| |
Check if the worker specified by workerid can execute the codelet and return the first implementation which can be used. Schedulers need to call it before assigning a task to a worker, otherwise the task may fail to execute. This should be preferred rather than calling starpu_worker_can_execute_task() for each and every implementation. It can also be used with impl_mask == NULL
to check for at least one implementation without determining which.
◆ starpu_push_local_task()
int starpu_push_local_task |
( |
int |
workerid, |
|
|
struct starpu_task * |
task, |
|
|
int |
back |
|
) |
| |
The scheduling policy may put tasks directly into a worker’s local queue so that it is not always necessary to create its own queue when the local queue is sufficient. If back
is not 0, task
is put at the back of the queue where the worker will pop tasks first. Setting back
to 0 therefore ensures a FIFO ordering.
◆ starpu_push_task_end()
Must be called by a scheduler to notify that the given task has just been pushed.
◆ starpu_get_prefetch_flag()
int starpu_get_prefetch_flag |
( |
void |
| ) |
|
◆ starpu_prefetch_task_input_on_node_prio()
int starpu_prefetch_task_input_on_node_prio |
( |
struct starpu_task * |
task, |
|
|
unsigned |
node, |
|
|
int |
prio |
|
) |
| |
Prefetch data for a given p task on a given p node with a given priority
◆ starpu_prefetch_task_input_on_node()
int starpu_prefetch_task_input_on_node |
( |
struct starpu_task * |
task, |
|
|
unsigned |
node |
|
) |
| |
Prefetch data for a given p task on a given p node
◆ starpu_idle_prefetch_task_input_on_node_prio()
int starpu_idle_prefetch_task_input_on_node_prio |
( |
struct starpu_task * |
task, |
|
|
unsigned |
node, |
|
|
int |
prio |
|
) |
| |
Prefetch data for a given p task on a given p node when the bus is idle with a given priority
◆ starpu_idle_prefetch_task_input_on_node()
int starpu_idle_prefetch_task_input_on_node |
( |
struct starpu_task * |
task, |
|
|
unsigned |
node |
|
) |
| |
Prefetch data for a given p task on a given p node when the bus is idle
◆ starpu_prefetch_task_input_for_prio()
int starpu_prefetch_task_input_for_prio |
( |
struct starpu_task * |
task, |
|
|
unsigned |
worker, |
|
|
int |
prio |
|
) |
| |
Prefetch data for a given p task on a given p worker with a given priority
◆ starpu_prefetch_task_input_for()
int starpu_prefetch_task_input_for |
( |
struct starpu_task * |
task, |
|
|
unsigned |
worker |
|
) |
| |
Prefetch data for a given p task on a given p worker
◆ starpu_idle_prefetch_task_input_for_prio()
int starpu_idle_prefetch_task_input_for_prio |
( |
struct starpu_task * |
task, |
|
|
unsigned |
worker, |
|
|
int |
prio |
|
) |
| |
Prefetch data for a given p task on a given p worker when the bus is idle with a given priority
◆ starpu_idle_prefetch_task_input_for()
int starpu_idle_prefetch_task_input_for |
( |
struct starpu_task * |
task, |
|
|
unsigned |
worker |
|
) |
| |
Prefetch data for a given p task on a given p worker when the bus is idle
◆ starpu_task_footprint()
Return the footprint for a given task, taking into account user-provided perfmodel footprint or size_base functions.
◆ starpu_task_data_footprint()
uint32_t starpu_task_data_footprint |
( |
struct starpu_task * |
task | ) |
|
Return the raw footprint for the data of a given task (without taking into account user-provided functions).
◆ starpu_task_expected_length()
Return expected task duration in micro-seconds.
◆ starpu_worker_get_relative_speedup()
Return an estimated speedup factor relative to CPU speed
◆ starpu_task_expected_data_transfer_time()
double starpu_task_expected_data_transfer_time |
( |
unsigned |
memory_node, |
|
|
struct starpu_task * |
task |
|
) |
| |
◆ starpu_task_expected_data_transfer_time_for()
double starpu_task_expected_data_transfer_time_for |
( |
struct starpu_task * |
task, |
|
|
unsigned |
worker |
|
) |
| |
Return expected data transfer time in micro-seconds for the given worker
.
◆ starpu_data_expected_transfer_time()
Predict the transfer time (in micro-seconds) to move handle
to a memory node
◆ starpu_task_expected_energy()
Return expected energy consumption in J
◆ starpu_task_expected_conversion_time()
Return expected conversion time in ms (multiformat interface only)
◆ starpu_task_notify_ready_soon_register()
void starpu_task_notify_ready_soon_register |
( |
starpu_notify_ready_soon_func |
f, |
|
|
void * |
data |
|
) |
| |
Register a callback to be called when it is determined when a task will be ready an estimated amount of time from now, because its last dependency has just started and we know how long it will take.
◆ starpu_sched_ctx_worker_shares_tasks_lists()
void starpu_sched_ctx_worker_shares_tasks_lists |
( |
int |
workerid, |
|
|
int |
sched_ctx_id |
|
) |
| |
The scheduling policies indicates if the worker may pop tasks from the list of other workers or if there is a central list with task for all the workers
◆ starpu_wake_worker_relax()
int starpu_wake_worker_relax |
( |
int |
workerid | ) |
|
Wake up workerid
while temporarily entering the current worker relax state if needed during the waiting process. Return 1 if workerid
has been woken up or its state_keep_awake flag has been set to 1
, and 0
otherwise (if workerid
was not in the STATE_SLEEPING or in the STATE_SCHEDULING).
◆ starpu_wake_worker_no_relax()
int starpu_wake_worker_no_relax |
( |
int |
workerid | ) |
|
Must be called to wake up a worker that is sleeping on the cond. Return 0 whenever the worker is not in a sleeping state or has the state_keep_awake flag on.
◆ starpu_wake_worker_locked()
int starpu_wake_worker_locked |
( |
int |
workerid | ) |
|
◆ starpu_wake_worker_relax_light()
int starpu_wake_worker_relax_light |
( |
int |
workerid | ) |
|
Light version of starpu_wake_worker_relax() which, when possible, speculatively set keep_awake on the target worker without waiting for the worker to enter the relax state.