starpu-max/doc/chapters/advanced-api.texi

@node FXT Support
@section FXT Support

@deftypefun void starpu_fxt_start_profiling (void)
Start recording the trace. The trace is by default started from
@code{starpu_init()} call, but can be paused by using
@code{starpu_fxt_stop_profiling}, in which case
@code{starpu_fxt_start_profiling} should be called to specify when to resume
recording events.
@end deftypefun

@deftypefun void starpu_fxt_stop_profiling (void)
Stop recording the trace. The trace is by default stopped at
@code{starpu_shutdown()} call. @code{starpu_fxt_stop_profiling} can however be
used to stop it earlier. @code{starpu_fxt_start_profiling} can then be called to
start recording it again, etc.
@end deftypefun


@node MPI
@section MPI

@menu
* Initialisation::
* Communication::
* Communication cache::
@end menu

@node Initialisation
@subsection Initialisation

@deftypefun int starpu_mpi_init (int *@var{argc}, char ***@var{argv}, int initialize_mpi)
Initializes the starpumpi library. @code{initialize_mpi} indicates if
MPI should be initialized or not by StarPU. If the value is not @code{0},
MPI will be initialized by calling @code{MPI_Init_Thread(argc, argv,
MPI_THREAD_SERIALIZED, ...)}.
@end deftypefun

@deftypefun int starpu_mpi_initialize (void)
This function has been made deprecated. One should use instead the
function @code{starpu_mpi_init()} defined above.
This function does not call @code{MPI_Init}, it should be called beforehand.
@end deftypefun

@deftypefun int starpu_mpi_initialize_extended (int *@var{rank}, int *@var{world_size})
This function has been made deprecated. One should use instead the
function @code{starpu_mpi_init()} defined above.
MPI will be initialized by starpumpi by calling @code{MPI_Init_Thread(argc, argv,
MPI_THREAD_SERIALIZED, ...)}.
@end deftypefun

@deftypefun int starpu_mpi_shutdown (void)
Cleans the starpumpi library. This must be called between calling
@code{starpu_mpi} functions and @code{starpu_shutdown()}.
@code{MPI_Finalize()} will be called if StarPU-MPI has been initialized
by @code{starpu_mpi_init()}.
@end deftypefun

@deftypefun void starpu_mpi_comm_amounts_retrieve (size_t *@var{comm_amounts})
Retrieve the current amount of communications from the current node in
the array @code{comm_amounts} which must have a size greater or equal
to the world size. Communications statistics must be enabled
(@pxref{STARPU_COMM_STATS}).
@end deftypefun

@node Communication
@subsection Communication

@deftypefun int starpu_mpi_send (starpu_data_handle_t @var{data_handle}, int @var{dest}, int @var{mpi_tag}, MPI_Comm @var{comm})
Performs a standard-mode, blocking send of @var{data_handle} to the
node @var{dest} using the message tag @code{mpi_tag} within the
communicator @var{comm}.
@end deftypefun

@deftypefun int starpu_mpi_recv (starpu_data_handle_t @var{data_handle}, int @var{source}, int @var{mpi_tag}, MPI_Comm @var{comm}, MPI_Status *@var{status})
Performs a standard-mode, blocking receive in @var{data_handle} from the
node @var{source} using the message tag @code{mpi_tag} within the
communicator @var{comm}.
@end deftypefun

@deftypefun int starpu_mpi_isend (starpu_data_handle_t @var{data_handle}, starpu_mpi_req *@var{req}, int @var{dest}, int @var{mpi_tag}, MPI_Comm @var{comm})
Posts a standard-mode, non blocking send of @var{data_handle} to the
node @var{dest} using the message tag @code{mpi_tag} within the
communicator @var{comm}. After the call, the pointer to the request
@var{req} can be used to test or to wait for the completion of the communication.
@end deftypefun

@deftypefun int starpu_mpi_irecv (starpu_data_handle_t @var{data_handle}, starpu_mpi_req *@var{req}, int @var{source}, int @var{mpi_tag}, MPI_Comm @var{comm})
Posts a nonblocking receive in @var{data_handle} from the
node @var{source} using the message tag @code{mpi_tag} within the
communicator @var{comm}. After the call, the pointer to the request
@var{req} can be used to test or to wait for the completion of the communication.
@end deftypefun

@deftypefun int starpu_mpi_isend_detached (starpu_data_handle_t @var{data_handle}, int @var{dest}, int @var{mpi_tag}, MPI_Comm @var{comm}, void (*@var{callback})(void *), void *@var{arg})
Posts a standard-mode, non blocking send of @var{data_handle} to the
node @var{dest} using the message tag @code{mpi_tag} within the
communicator @var{comm}. On completion, the @var{callback} function is
called with the argument @var{arg}. Similarly to the pthread detached
functionality, when a detached communication completes, its resources
are automatically released back to the system, there is no need to
test or to wait for the completion of the request.
@end deftypefun

@deftypefun int starpu_mpi_irecv_detached (starpu_data_handle_t @var{data_handle}, int @var{source}, int @var{mpi_tag}, MPI_Comm @var{comm}, void (*@var{callback})(void *), void *@var{arg})
Posts a nonblocking receive in @var{data_handle} from the
node @var{source} using the message tag @code{mpi_tag} within the
communicator @var{comm}. On completion, the @var{callback} function is
called with the argument @var{arg}. Similarly to the pthread detached
functionality, when a detached communication completes, its resources
are automatically released back to the system, there is no need to
test or to wait for the completion of the request.
@end deftypefun

@deftypefun int starpu_mpi_wait (starpu_mpi_req *@var{req}, MPI_Status *@var{status})
Returns when the operation identified by request @var{req} is complete.
@end deftypefun

@deftypefun int starpu_mpi_test (starpu_mpi_req *@var{req}, int *@var{flag}, MPI_Status *@var{status})
If the operation identified by @var{req} is complete, set @var{flag}
to 1. The @var{status} object is set to contain information on the
completed operation.
@end deftypefun

@deftypefun int starpu_mpi_barrier (MPI_Comm @var{comm})
Blocks the caller until all group members of the communicator
@var{comm} have called it.
@end deftypefun

@deftypefun int starpu_mpi_isend_detached_unlock_tag (starpu_data_handle_t @var{data_handle}, int @var{dest}, int @var{mpi_tag}, MPI_Comm @var{comm}, starpu_tag_t @var{tag})
Posts a standard-mode, non blocking send of @var{data_handle} to the
node @var{dest} using the message tag @code{mpi_tag} within the
communicator @var{comm}. On completion, @var{tag} is unlocked.
@end deftypefun

@deftypefun int starpu_mpi_irecv_detached_unlock_tag (starpu_data_handle_t @var{data_handle}, int @var{source}, int @var{mpi_tag}, MPI_Comm @var{comm}, starpu_tag_t @var{tag})
Posts a nonblocking receive in @var{data_handle} from the
node @var{source} using the message tag @code{mpi_tag} within the
communicator @var{comm}. On completion, @var{tag} is unlocked.
@end deftypefun

@deftypefun int starpu_mpi_isend_array_detached_unlock_tag (unsigned @var{array_size}, starpu_data_handle_t *@var{data_handle}, int *@var{dest}, int *@var{mpi_tag}, MPI_Comm *@var{comm}, starpu_tag_t @var{tag})
Posts @var{array_size} standard-mode, non blocking send. Each post
sends the n-th data of the array @var{data_handle} to the n-th node of
the array @var{dest}
using the n-th message tag of the array @code{mpi_tag} within the n-th
communicator of the array
@var{comm}. On completion of the all the requests, @var{tag} is unlocked.
@end deftypefun

@deftypefun int starpu_mpi_irecv_array_detached_unlock_tag (unsigned @var{array_size}, starpu_data_handle_t *@var{data_handle}, int *@var{source}, int *@var{mpi_tag}, MPI_Comm *@var{comm}, starpu_tag_t @var{tag})
Posts @var{array_size} nonblocking receive. Each post receives in the
n-th data of the array @var{data_handle} from the n-th
node of the array @var{source} using the n-th message tag of the array
@code{mpi_tag} within the n-th communicator of the array @var{comm}.
On completion of the all the requests, @var{tag} is unlocked.
@end deftypefun

@node Communication cache
@subsection Communication cache

@deftypefun void starpu_mpi_cache_flush (MPI_Comm @var{comm}, starpu_data_handle_t @var{data_handle})
Clear the send and receive communication cache for the data
@var{data_handle}. The function has to be called synchronously by all
the MPI nodes.
The function does nothing if the cache mechanism is disabled (@pxref{STARPU_MPI_CACHE}).
@end deftypefun

@deftypefun void starpu_mpi_cache_flush_all_data (MPI_Comm @var{comm})
Clear the send and receive communication cache for all data. The
function has to be called synchronously by all the MPI nodes.
The function does nothing if the cache mechanism is disabled (@pxref{STARPU_MPI_CACHE}).
@end deftypefun


@node Task Bundles
@section Task Bundles

@deftp {Data Type} {starpu_task_bundle_t}
Opaque structure describing a list of tasks that should be scheduled
on the same worker whenever it's possible. It must be considered as a
hint given to the scheduler as there is no guarantee that they will be
executed on the same worker.
@end deftp

@deftypefun void starpu_task_bundle_create ({starpu_task_bundle_t *}@var{bundle})
Factory function creating and initializing @var{bundle}, when the call returns, memory needed is allocated and @var{bundle} is ready to use.
@end deftypefun

@deftypefun int starpu_task_bundle_insert (starpu_task_bundle_t @var{bundle}, {struct starpu_task *}@var{task})
Insert @var{task} in @var{bundle}. Until @var{task} is removed from @var{bundle} its expected length and data transfer time will be considered along those of the other tasks of @var{bundle}.
This function mustn't be called if @var{bundle} is already closed and/or @var{task} is already submitted.
@end deftypefun

@deftypefun int starpu_task_bundle_remove (starpu_task_bundle_t @var{bundle}, {struct starpu_task *}@var{task})
Remove @var{task} from @var{bundle}.
Of course @var{task} must have been previously inserted @var{bundle}.
This function mustn't be called if @var{bundle} is already closed and/or @var{task} is already submitted. Doing so would result in undefined behaviour.
@end deftypefun

@deftypefun void starpu_task_bundle_close (starpu_task_bundle_t @var{bundle})
Inform the runtime that the user won't modify @var{bundle} anymore, it means no more inserting or removing task. Thus the runtime can destroy it when possible.
@end deftypefun

@deftypefun double starpu_task_bundle_expected_length (starpu_task_bundle_t @var{bundle}, {enum starpu_perf_archtype} @var{arch}, unsigned @var{nimpl})
Return the expected duration of the entire task bundle in µs.
@end deftypefun

@deftypefun double starpu_task_bundle_expected_power (starpu_task_bundle_t @var{bundle}, enum starpu_perf_archtype @var{arch}, unsigned @var{nimpl})
Return the expected power consumption of the entire task bundle in J.
@end deftypefun

@deftypefun double starpu_task_bundle_expected_data_transfer_time (starpu_task_bundle_t @var{bundle}, unsigned @var{memory_node})
Return the time (in µs) expected to transfer all data used within the bundle.
@end deftypefun

@node Task Lists
@section Task Lists

@deftp {Data Type} {struct starpu_task_list}
Stores a double-chained list of tasks
@end deftp

@deftypefun void starpu_task_list_init ({struct starpu_task_list *}@var{list})
Initialize a list structure
@end deftypefun

@deftypefun void starpu_task_list_push_front ({struct starpu_task_list *}@var{list}, {struct starpu_task *}@var{task})
Push a task at the front of a list
@end deftypefun

@deftypefun void starpu_task_list_push_back ({struct starpu_task_list *}@var{list}, {struct starpu_task *}@var{task})
Push a task at the back of a list
@end deftypefun

@deftypefun {struct starpu_task *} starpu_task_list_front ({struct starpu_task_list *}@var{list})
Get the front of the list (without removing it)
@end deftypefun

@deftypefun {struct starpu_task *} starpu_task_list_back ({struct starpu_task_list *}@var{list})
Get the back of the list (without removing it)
@end deftypefun

@deftypefun int starpu_task_list_empty ({struct starpu_task_list *}@var{list})
Test if a list is empty
@end deftypefun

@deftypefun void starpu_task_list_erase ({struct starpu_task_list *}@var{list}, {struct starpu_task *}@var{task})
Remove an element from the list
@end deftypefun

@deftypefun {struct starpu_task *} starpu_task_list_pop_front ({struct starpu_task_list *}@var{list})
Remove the element at the front of the list
@end deftypefun

@deftypefun {struct starpu_task *} starpu_task_list_pop_back ({struct starpu_task_list *}@var{list})
Remove the element at the back of the list
@end deftypefun

@deftypefun {struct starpu_task *} starpu_task_list_begin ({struct starpu_task_list *}@var{list})
Get the first task of the list.
@end deftypefun

@deftypefun {struct starpu_task *} starpu_task_list_end ({struct starpu_task_list *}@var{list})
Get the end of the list.
@end deftypefun

@deftypefun {struct starpu_task *} starpu_task_list_next ({struct starpu_task *}@var{task})
Get the next task of the list. This is not erase-safe.
@end deftypefun

@node Using Parallel Tasks
@section Using Parallel Tasks

These are used by parallel tasks:

@deftypefun int starpu_combined_worker_get_size (void)
Return the size of the current combined worker, i.e. the total number of cpus
running the same task in the case of SPMD parallel tasks, or the total number
of threads that the task is allowed to start in the case of FORKJOIN parallel
tasks.
@end deftypefun

@deftypefun int starpu_combined_worker_get_rank (void)
Return the rank of the current thread within the combined worker. Can only be
used in FORKJOIN parallel tasks, to know which part of the task to work on.
@end deftypefun

Most of these are used for schedulers which support parallel tasks.

@deftypefun unsigned starpu_combined_worker_get_count (void)
Return the number of different combined workers.
@end deftypefun

@deftypefun int starpu_combined_worker_get_id (void)
Return the identifier of the current combined worker.
@end deftypefun

@deftypefun int starpu_combined_worker_assign_workerid (int @var{nworkers}, int @var{workerid_array}[])
Register a new combined worker and get its identifier
@end deftypefun

@deftypefun int starpu_combined_worker_get_description (int @var{workerid}, {int *}@var{worker_size}, {int **}@var{combined_workerid})
Get the description of a combined worker
@end deftypefun

@deftypefun int starpu_combined_worker_can_execute_task (unsigned @var{workerid}, {struct starpu_task *}@var{task}, unsigned @var{nimpl})
Variant of starpu_worker_can_execute_task compatible with combined workers
@end deftypefun

@deftp {Data Type} {struct starpu_machine_topology}
@table @asis
@item @code{unsigned nworkers}
Total number of workers.

@item @code{unsigned ncombinedworkers}
Total number of combined workers.

@item @code{hwloc_topology_t hwtopology}
Topology as detected by hwloc.

To maintain ABI compatibility when hwloc is not available, the field
is replaced with @code{void *dummy}

@item @code{unsigned nhwcpus}
Total number of CPUs, as detected by the topology code. May be different from
the actual number of CPU workers.

@item @code{unsigned nhwcudagpus}
Total number of CUDA devices, as detected. May be different from the actual
number of CUDA workers.

@item @code{unsigned nhwopenclgpus}
Total number of OpenCL devices, as detected. May be different from the actual
number of CUDA workers.

@item @code{unsigned ncpus}
Actual number of CPU workers used by StarPU.

@item @code{unsigned ncudagpus}
Actual number of CUDA workers used by StarPU.

@item @code{unsigned nopenclgpus}
Actual number of OpenCL workers used by StarPU.

@item @code{unsigned workers_bindid[STARPU_NMAXWORKERS]}
Indicates the successive cpu identifier that should be used to bind the
workers. It is either filled according to the user's explicit
parameters (from starpu_conf) or according to the STARPU_WORKERS_CPUID env.
variable. Otherwise, a round-robin policy is used to distributed the workers
over the cpus.

@item @code{unsigned workers_cuda_gpuid[STARPU_NMAXWORKERS]}
Indicates the successive cpu identifier that should be used by the CUDA
driver.  It is either filled according to the user's explicit parameters (from
starpu_conf) or according to the STARPU_WORKERS_CUDAID env. variable. Otherwise,
they are taken in ID order.

@item @code{unsigned workers_opencl_gpuid[STARPU_NMAXWORKERS]}
Indicates the successive cpu identifier that should be used by the OpenCL
driver.  It is either filled according to the user's explicit parameters (from
starpu_conf) or according to the STARPU_WORKERS_OPENCLID env. variable. Otherwise,
they are taken in ID order.

@end table
@end deftp

@node Scheduling Contexts
@section Scheduling Contexts
StarPU permits on one hand grouping workers in combined workers in order to execute a parallel task and on the other hand grouping tasks in bundles that will be executed by a single specified worker.
In contrast when we group workers in scheduling contexts we submit starpu tasks to them and we schedule them with the policy assigned to the context.
Scheduling contexts can be created, deleted and modified dynamically.

@deftypefun unsigned starpu_sched_ctx_create (const char *@var{policy_name}, int *@var{workerids_ctx}, int @var{nworkers_ctx}, const char *@var{sched_ctx_name})
This function creates a scheduling context which uses the scheduling policy indicated in the first argument and assigns the workers indicated in the second argument to execute the tasks submitted to it.
The return value represents the identifier of the context that has just been created. It will be further used to indicate the context the tasks will be submitted to. The return value should be at most @code{STARPU_NMAX_SCHED_CTXS}.
@end deftypefun

@deftypefun void starpu_sched_ctx_delete (unsigned @var{sched_ctx_id})
Delete scheduling context @var{sched_ctx_id} and transfer remaining workers to the inheritor scheduling context.
@end deftypefun

@deftypefun void starpu_sched_ctx_add_workers ({int *}@var{workerids_ctx}, int @var{nworkers_ctx}, unsigned @var{sched_ctx_id})
This function adds dynamically the workers indicated in the first argument to the context indicated in the last argument. The last argument cannot be greater than  @code{STARPU_NMAX_SCHED_CTXS}.
@end deftypefun

@deftypefun void starpu_sched_ctx_remove_workers ({int *}@var{workerids_ctx}, int @var{nworkers_ctx}, unsigned @var{sched_ctx_id})
This function removes the workers indicated in the first argument from the context indicated in the last argument. The last argument cannot be greater than  @code{STARPU_NMAX_SCHED_CTXS}.
@end deftypefun

A scheduling context manages a collection of workers that can be memorized using different data structures. Thus, a generic structure is available in order to simplify the choice of its type.
Only the list data structure is available but further data structures(like tree) implementations are foreseen.

@deftp {Data Type} {struct starpu_worker_collection}
@table @asis
@item @code{void *workerids}
The workerids managed by the collection
@item @code{unsigned nworkers}
The number of workerids
@item @code{pthread_key_t cursor_key} (optional)
The cursor needed to iterate the collection (depending on the data structure)
@item @code{int type}
The type of structure (currently STARPU_WORKER_LIST is the only one available)
@item @code{unsigned (*has_next)(struct starpu_worker_collection *workers)}
Checks if there is a next worker
@item @code{int (*get_next)(struct starpu_worker_collection *workers)}
Gets the next worker
@item @code{int (*add)(struct starpu_worker_collection *workers, int worker)}
Adds a worker to the collection
@item @code{int (*remove)(struct starpu_worker_collection *workers, int worker)}
Removes a worker from the collection
@item @code{void* (*init)(struct starpu_worker_collection *workers)}
Initialize the collection
@item @code{void (*deinit)(struct starpu_worker_collection *workers)}
Deinitialize the colection
@item @code{void (*init_cursor)(struct starpu_worker_collection *workers)} (optional)
Initialize the cursor if there is one
@item @code{void (*deinit_cursor)(struct starpu_worker_collection *workers)} (optional)
Deinitialize the cursor if there is one

@end table
@end deftp

@deftypefun struct starpu_worker_collection* starpu_sched_ctx_create_worker_collection (unsigned @var{sched_ctx_id}, int @var{type})
Create a worker collection of the type indicated by the last parameter for the context specified through the first parameter.
@end deftypefun

@deftypefun void starpu_sched_ctx_delete_worker_collection (unsigned @var{sched_ctx_id})
Delete the worker collection of the specified scheduling context
@end deftypefun

@deftypefun struct starpu_worker_collection* starpu_sched_ctx_get_worker_collection (unsigned @var{sched_ctx_id})
Return the worker collection managed by the indicated context
@end deftypefun

@deftypefun pthread_mutex_t* starpu_sched_ctx_get_changing_ctx_mutex (unsigned @var{sched_ctx_id})
TODO
@end deftypefun

@deftypefun void starpu_sched_ctx_set_context (unsigned *@var{sched_ctx_id})
Set the scheduling context the subsequent tasks will be submitted to
@end deftypefun

@deftypefun unsigned starpu_sched_ctx_get_context (void)
Return the scheduling context the tasks are currently submitted to
@end deftypefun

@deftypefun unsigned starpu_sched_ctx_get_nworkers (unsigned @var{sched_ctx_id})
Return the number of workers managed by the specified contexts
(Usually needed to verify if it manages any workers or if it should be blocked)
@end deftypefun

@deftypefun unsigned starpu_sched_ctx_get_nshared_workers (unsigned @var{sched_ctx_id}, unsigned @var{sched_ctx_id2})
Return the number of workers shared by two contexts
@end deftypefun

@node Scheduling Policy
@section Scheduling Policy

TODO

While StarPU comes with a variety of scheduling policies (@pxref{Task
scheduling policy}), 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.

@deftp {Data Type} {struct starpu_sched_policy}
This structure contains all the methods that implement a scheduling policy.  An
application may specify which scheduling strategy in the @code{sched_policy}
field of the @code{starpu_conf} structure passed to the @code{starpu_init}
function. The different fields are:

@table @asis
@item @code{void (*init_sched)(unsigned sched_ctx_id)}
Initialize the scheduling policy.

@item @code{void (*deinit_sched)(unsigned sched_ctx_id)}
Cleanup the scheduling policy.

@item @code{int (*push_task)(struct starpu_task *)}
Insert a task into the scheduler.

@item @code{void (*push_task_notify)(struct starpu_task *, int workerid)}
Notify the scheduler that a task was pushed on a given worker. This method is
called when a task that was explicitely assigned to a worker becomes ready and
is about to be executed by the worker. This method therefore permits to keep
the state of of the scheduler coherent even when StarPU bypasses the scheduling
strategy.

@item @code{struct starpu_task *(*pop_task)(unsigned sched_ctx_id)} (optional)
Get a task from the scheduler. The mutex associated to the worker is already
taken when this method is called. If this method is defined as @code{NULL}, the
worker will only execute tasks from its local queue. In this case, the
@code{push_task} method should use the @code{starpu_push_local_task} method to
assign tasks to the different workers.

@item @code{struct starpu_task *(*pop_every_task)(unsigned sched_ctx_id)}
Remove all available tasks from the scheduler (tasks are chained by the means
of the prev and next fields of the starpu_task structure). The mutex associated
to the worker is already taken when this method is called. This is currently
not used.

@item @code{void (*pre_exec_hook)(struct starpu_task *)} (optional)
This method is called every time a task is starting.

@item @code{void (*post_exec_hook)(struct starpu_task *)} (optional)
This method is called every time a task has been executed.

@item @code{void (*add_workers)(unsigned sched_ctx_id, int *workerids, unsigned nworkers)}
Initialize scheduling structures corresponding to each worker used by the policy.

@item @code{void (*remove_workers)(unsigned sched_ctx_id, int *workerids, unsigned nworkers)}
Deinitialize scheduling structures corresponding to each worker used by the policy.

@item @code{const char *policy_name} (optional)
Name of the policy.

@item @code{const char *policy_description} (optional)
Description of the policy.
@end table
@end deftp

@deftypefun {struct starpu_sched_policy **} starpu_sched_get_predefined_policies ()
Return an NULL-terminated array of all the predefined scheduling policies.
@end deftypefun

@deftypefun void starpu_sched_ctx_set_policy_data (unsigned @var{sched_ctx_id}, {void *} @var{policy_data})
Each scheduling policy uses some specific data (queues, variables, additional condition variables).
It is memorize through a local structure. This function assigns it to a scheduling context.
@end deftypefun

@deftypefun void* starpu_sched_ctx_get_policy_data (unsigned @var{sched_ctx_id})
Returns the policy data previously assigned to a context
@end deftypefun

@deftypefun void starpu_task_set_min_priority (int @var{min_prio})
Defines 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
@code{starpu_task_get_min_priority} function. This function should only be
called from the initialization method of the scheduling policy, and should not
be used directly from the application.
@end deftypefun

@deftypefun void starpu_task_set_max_priority (int @var{max_prio})
Defines 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 @code{starpu_task_get_max_priority} function. This function should
only be called from the initialization method of the scheduling policy, and
should not be used directly from the application.
@end deftypefun

@deftypefun int starpu_task_get_min_priority (void)
Returns the current minimum priority level supported by the
scheduling policy
@end deftypefun

@deftypefun int starpu_task_get_max_priority (void)
Returns the current maximum priority level supported by the
scheduling policy
@end deftypefun

@deftypefun int starpu_push_local_task (int @var{workerid}, {struct starpu_task} *@var{task}, int @var{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 @var{back} not null, @var{task} is put at the back of the queue
where the worker will pop tasks first. Setting @var{back} to 0 therefore ensures
a FIFO ordering.
@end deftypefun

@deftypefun int starpu_push_task_end ({struct starpu_task} *@var{task})
This function must be called by a scheduler to notify that the given
task has just been pushed.
@end deftypefun

@deftypefun int starpu_worker_can_execute_task (unsigned @var{workerid}, {struct starpu_task *}@var{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.
@end deftypefun

@deftypefun double starpu_timing_now (void)
Return the current date in µs
@end deftypefun

@deftypefun uint32_t starpu_task_footprint ({struct starpu_perfmodel *}@var{model}, {struct starpu_task *} @var{task}, {enum starpu_perf_archtype} @var{arch}, unsigned @var{nimpl})
Returns the footprint for a given task
@end deftypefun

@deftypefun double starpu_task_expected_length ({struct starpu_task *}@var{task}, {enum starpu_perf_archtype} @var{arch}, unsigned @var{nimpl})
Returns expected task duration in µs
@end deftypefun

@deftypefun double starpu_worker_get_relative_speedup ({enum starpu_perf_archtype} @var{perf_archtype})
Returns an estimated speedup factor relative to CPU speed
@end deftypefun

@deftypefun double starpu_task_expected_data_transfer_time (unsigned @var{memory_node}, {struct starpu_task *}@var{task})
Returns expected data transfer time in µs
@end deftypefun

@deftypefun double starpu_data_expected_transfer_time (starpu_data_handle_t @var{handle}, unsigned @var{memory_node}, {enum starpu_access_mode} @var{mode})
Predict the transfer time (in µs) to move a handle to a memory node
@end deftypefun

@deftypefun double starpu_task_expected_power ({struct starpu_task *}@var{task}, {enum starpu_perf_archtype} @var{arch}, unsigned @var{nimpl})
Returns expected power consumption in J
@end deftypefun

@deftypefun double starpu_task_expected_conversion_time ({struct starpu_task *}@var{task}, {enum starpu_perf_archtype} @var{arch}, unsigned {nimpl})
Returns expected conversion time in ms (multiformat interface only)
@end deftypefun

@node Running drivers
@section Running drivers

@deftypefun int starpu_driver_run ({struct starpu_driver *}@var{d})
Initialize the given driver, run it until it receives a request to terminate,
deinitialize it and return 0 on success. It returns -EINVAL if @code{d->type}
is not a valid StarPU device type (STARPU_CPU_WORKER, STARPU_CUDA_WORKER or
STARPU_OPENCL_WORKER). This is the same as using the following
functions: calling @code{starpu_driver_init()}, then calling
@code{starpu_driver_run_once()} in a loop, and eventually
@code{starpu_driver_deinit()}.
@end deftypefun

@deftypefun int starpu_driver_init (struct starpu_driver *@var{d})
Initialize the given driver. Returns 0 on success, -EINVAL if
@code{d->type} is not a valid StarPU device type (STARPU_CPU_WORKER,
STARPU_CUDA_WORKER or STARPU_OPENCL_WORKER).
@end deftypefun

@deftypefun int starpu_driver_run_once (struct starpu_driver *@var{d})
Run the driver once, then returns 0 on success, -EINVAL if
@code{d->type} is not a valid StarPU device type (STARPU_CPU_WORKER,
STARPU_CUDA_WORKER or STARPU_OPENCL_WORKER).
@end deftypefun

@deftypefun int starpu_driver_deinit (struct starpu_driver *@var{d})
Deinitialize the given driver. Returns 0 on success, -EINVAL if
@code{d->type} is not a valid StarPU device type (STARPU_CPU_WORKER,
STARPU_CUDA_WORKER or STARPU_OPENCL_WORKER).
@end deftypefun

@deftypefun void starpu_drivers_request_termination (void)
Notify all running drivers they should terminate.
@end deftypefun

@node Expert mode
@section Expert mode

@deftypefun void starpu_wake_all_blocked_workers (void)
Wake all the workers, so they can inspect data requests and task submissions
again.
@end deftypefun

@deftypefun int starpu_progression_hook_register (unsigned (*@var{func})(void *arg), void *@var{arg})
Register a progression hook, to be called when workers are idle.
@end deftypefun

@deftypefun void starpu_progression_hook_deregister (int @var{hook_id})
Unregister a given progression hook.
@end deftypefun