@c -*-texinfo-*-

@c This file is part of the StarPU Handbook.
@c Copyright (C) 2009--2011  Universit@'e de Bordeaux 1
@c Copyright (C) 2010, 2011  Centre National de la Recherche Scientifique
@c Copyright (C) 2011 Institut National de Recherche en Informatique et Automatique
@c See the file starpu.texi for copying conditions.

@node StarPU Advanced API
@chapter StarPU Advanced API

@menu
* Defining a new data interface::  
* Multiformat Data Interface::  
* Task Bundles::                
* Task Lists::                  
* Defining a new scheduling policy::  
* Expert mode::                 
@end menu

@node Defining a new data interface
@section Defining a new data interface

@menu
* Data Interface API::  Data Interface API
* An example of data interface::        An example of data interface
@end menu

@node Data Interface API
@subsection Data Interface API

@deftp {Data Type} {struct starpu_data_interface_ops}
@anchor{struct starpu_data_interface_ops}
Defines the per-interface methods. TODO describe all the different fields
@end deftp

@deftp {Data Type} {struct starpu_data_copy_methods}
Per-interface data transfer methods. TODO describe all the different fields
@end deftp

@node An example of data interface
@subsection An example of data interface

TODO
See @code{src/datawizard/interfaces/vector_interface.c} for now.

@node Multiformat Data Interface
@section Multiformat Data Interface

@deftp {Data Type} {struct starpu_multiformat_data_interface_ops}
todo. The different fields are:
@table @asis
@item @code{cpu_elemsize} the size of each element on CPUs,
@item @code{opencl_elemsize} the size of each element on OpenCL devices,
@item @code{cuda_elemsize} the size of each element on CUDA devices,
@item @code{cpu_to_opencl_cl} pointer to a codelet which converts from CPU to OpenCL
@item @code{opencl_to_cpu_cl} pointer to a codelet which converts from OpenCL to CPU
@item @code{cpu_to_cuda_cl} pointer to a codelet which converts from CPU to CUDA
@item @code{cuda_to_cpu_cl} pointer to a codelet which converts from CUDA to CPU
@end table
@end deftp

@deftypefun void starpu_multiformat_data_register (starpu_data_handle *@var{handle}, uint32_t @var{home_node}, void *@var{ptr}, uint32_t @var{nobjects}, struct starpu_multiformat_data_interface_ops *@var{format_ops});
Register a piece of data that can be represented in different ways, depending upon
the processing unit that manipulates it. It allows the programmer, for instance, to
use an array of structures when working on a CPU, and a structure of arrays when
working on a GPU.

@var{nobjects} is the number of elements in the data. @var{format_ops} describes
the format.

@example
#define NX 1024
struct point array_of_structs[NX];
starpu_data_handle handle;

/*
 * The conversion of a piece of data is itself a task, though it is created,
 * submitted and destroyed by StarPU internals and not by the user. Therefore,
 * we have to define two codelets.
 * Note that for now the conversion from the CPU format to the GPU format has to
 * be executed on the GPU, and the conversion from the GPU to the CPU has to be
 * executed on the CPU.
 */
#ifdef STARPU_USE_OPENCL
void cpu_to_opencl_opencl_func(void *buffers[], void *args);
starpu_codelet cpu_to_opencl_cl = @{
    .where = STARPU_OPENCL,
    .opencl_func = cpu_to_opencl_opencl_func,
    .nbuffers = 1
@};

void opencl_to_cpu_func(void *buffers[], void *args);
starpu_codelet opencl_to_cpu_cl = @{
    .where = STARPU_CPU,
    .cpu_func = opencl_to_cpu_func,
    .nbuffers = 1
@};
#endif

struct starpu_multiformat_data_interface_ops format_ops = @{
#ifdef STARPU_USE_OPENCL
    .opencl_elemsize = 2 * sizeof(float),
    .cpu_to_opencl_cl = &cpu_to_opencl_cl,
    .opencl_to_cpu_cl = &opencl_to_cpu_cl,
#endif
    .cpu_elemsize = 2 * sizeof(float),
    ...
@};
starpu_multiformat_data_register(handle, 0, &array_of_structs, NX, &format_ops);
@end example
@end deftypefun

@node Task Bundles
@section Task Bundles

@deftp {DataType} {struct starpu_task_bundle}
The task bundle structure describes a list of tasks that should be
scheduled together whenever possible. The different fields are:
@table @asis
@item @code{mutex} Mutex protecting the bundle
@item @code{int previous_workerid} last worker previously assigned a task from the bundle (-1 if none)
@item @code{struct starpu_task_bundle_entry *list} list of tasks
@item @code{int destroy} If this flag is set, the bundle structure is automatically free'd when the bundle is deinitialized.
@item @code{int closed} Is the bundle closed ?
@end table
@end deftp

@deftypefun void starpu_task_bundle_init ({struct starpu_task_bundle *}@var{bundle})
Initialize a task bundle
@end deftypefun

@deftypefun void starpu_task_bundle_deinit ({struct starpu_task_bundle *}@var{bundle})
Deinitialize a bundle. In case the destroy flag is set, the bundle
structure is freed too.
@end deftypefun

@deftypefun int starpu_task_bundle_insert ({struct starpu_task_bundle *}@var{bundle}, {struct starpu_task *}@var{task})
Insert a task into a bundle.
@end deftypefun

@deftypefun int starpu_task_bundle_remove ({struct starpu_task_bundle *}@var{bundle}, {struct starpu_task *}@var{task})
Remove a task from a bundle. This method must be called with
bundle->mutex hold. This function returns 0 if the task was found,
-ENOENT if the element was not found, 1 if the element is found and if
the list was deinitialized because it became empty.
@end deftypefun

@deftypefun void starpu_task_bundle_close ({struct starpu_task_bundle *}@var{bundle});
Close a bundle. No task can be added to a closed bundle. A closed
bundle automatically gets deinitialized when it becomes empty.
@end deftypefun

@deftypefun double starpu_task_bundle_expected_length ({struct starpu_task_bundle *}@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_data_transfer_time ({struct starpu_task_bundle *}@var{bundle}, unsigned {memory_node})
Return the time (in µs) expected to transfer all data used within the bundle
@end deftypefun

@deftypefun double starpu_task_bundle_expected_power ({struct starpu_task_bundle *}@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

@node Task Lists
@section Task Lists

@deftp {Data Type} {struct starpu_task_list}
todo
@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

@node Defining a new scheduling policy
@section Defining a new scheduling policy

TODO

A full example showing how to define a new scheduling policy is available in
the StarPU sources in the directory @code{examples/scheduler/}.

@menu
* Scheduling Policy API:: Scheduling Policy API
* Source code::
@end menu

@node Scheduling Policy API
@subsection Scheduling Policy API

@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{init_sched}
Initialize the scheduling policy.
@item @code{deinit_sched}
Cleanup the scheduling policy.
@item @code{push_task}
Insert a task into the scheduler.
@item @code{push_prio_task}
Insert a priority task into the scheduler.
@item @code{push_prio_notify}
Notify the scheduler that a task was pushed on the worker. This method is
called when a task that was explicitely assigned to a worker is scheduled. This
method therefore permits to keep the state of of the scheduler coherent even
when StarPU bypasses the scheduling strategy.
@item @code{pop_task}
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{pop_every_task}
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.
@item @code{post_exec_hook} (optional)
This method is called every time a task has been executed.
@item @code{policy_name}
Name of the policy (optional).
@item @code{policy_description}
Description of the policy (optionnal).
@end table
@end deftp

@deftypefun void starpu_worker_set_sched_condition (int @var{workerid}, pthread_cond_t *@var{sched_cond}, pthread_mutex_t *@var{sched_mutex})
This function specifies the condition variable associated to a worker
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.
The initialization method of a scheduling strategy (@code{init_sched}) must
call this function once per worker.
@end deftypefun

@deftypefun void starpu_sched_set_min_priority (int @var{min_prio})
Defines the minimum 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_sched_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_sched_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_sched_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_sched_get_min_priority (void)
Returns the current minimum priority level supported by the
scheduling policy
@end deftypefun

@deftypefun int starpu_sched_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_worker_may_execute_task (unsigned @var{workerid}, {struct starpu_task *}@var{task}, unsigned {nimpl})
Check if the worker specified by workerid can execute the codelet.
@end deftypefun

@deftypefun double starpu_timing_now (void)
Return the current date
@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 (uint32_t @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 @var{handle}, unsigned @var{memory_node}, 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 Source code
@subsection Source code

@cartouche
@smallexample
static struct starpu_sched_policy dummy_sched_policy = @{
    .init_sched = init_dummy_sched,
    .deinit_sched = deinit_dummy_sched,
    .push_task = push_task_dummy,
    .push_prio_task = NULL,
    .pop_task = pop_task_dummy,
    .post_exec_hook = NULL,
    .pop_every_task = NULL,
    .policy_name = "dummy",
    .policy_description = "dummy scheduling strategy"
@};
@end smallexample
@end cartouche

@node Expert mode
@section Expert mode

@deftypefun void starpu_wake_all_blocked_workers (void)
todo
@end deftypefun

@deftypefun int starpu_progression_hook_register (unsigned (*@var{func})(void *arg), void *@var{arg})
todo
@end deftypefun

@deftypefun void starpu_progression_hook_deregister (int @var{hook_id})
todo
@end deftypefun