◆ id
unsigned _starpu_sched_ctx::id |
id of the context used in user mode
◆ do_schedule
unsigned _starpu_sched_ctx::do_schedule |
boolean indicating whether the scheduling_ctx will be considered for scheduling (1) or not (0)
◆ name
const char* _starpu_sched_ctx::name |
◆ sched_policy
struct starpu_sched_policy* _starpu_sched_ctx::sched_policy |
◆ policy_data
void* _starpu_sched_ctx::policy_data |
data necessary for the policy
◆ user_data
void* _starpu_sched_ctx::user_data |
pointer for application use
◆ is_initial_sched
unsigned _starpu_sched_ctx::is_initial_sched |
we keep an initial sched which we never delete
◆ tasks_barrier
wait for the tasks submitted to the context to be executed
◆ ready_tasks_barrier
wait for the tasks ready of the context to be executed
◆ ready_flops
double _starpu_sched_ctx::ready_flops |
amount of ready flops in a context
◆ iterations
long _starpu_sched_ctx::iterations[2] |
Iteration number, as advertised by application
◆ min_ncpus
int _starpu_sched_ctx::min_ncpus |
◆ max_ncpus
int _starpu_sched_ctx::max_ncpus |
◆ min_ngpus
int _starpu_sched_ctx::min_ngpus |
◆ max_ngpus
int _starpu_sched_ctx::max_ngpus |
◆ inheritor
unsigned _starpu_sched_ctx::inheritor |
in case we delete the context leave resources to the inheritor
◆ finished_submit
unsigned _starpu_sched_ctx::finished_submit |
indicates whether the application finished submitting tasks to this context
◆ min_priority
int _starpu_sched_ctx::min_priority |
By default we have a binary type of priority: either a task is a priority task (level 1) or it is not (level 0).
◆ hwloc_workers_set
hwloc_bitmap_t _starpu_sched_ctx::hwloc_workers_set |
hwloc tree structure of workers
◆ perf_counters
struct starpu_sched_ctx_performance_counters* _starpu_sched_ctx::perf_counters |
a structure containing a series of performance counters determining the resize procedure
◆ close_callback
void(* _starpu_sched_ctx::close_callback) (unsigned sched_ctx_id, void *args) |
callback called when the context finished executed its submitted tasks
◆ hierarchy_level
unsigned _starpu_sched_ctx::hierarchy_level |
value placing the contexts in their hierarchy
◆ main_master
int _starpu_sched_ctx::main_master |
if we execute non-StarPU code inside the context we have a single master worker that stays awake, if not master is -1
◆ nesting_sched_ctx
unsigned _starpu_sched_ctx::nesting_sched_ctx |
ctx nesting the current ctx
◆ perf_arch
struct starpu_perfmodel_arch _starpu_sched_ctx::perf_arch |
perf model for the device comb of the ctx
◆ parallel_view
unsigned _starpu_sched_ctx::parallel_view |
For parallel workers, say whether it is viewed as sequential or not. This is a helper for the prologue code.
◆ awake_workers
unsigned _starpu_sched_ctx::awake_workers |
for ctxs without policy: flag to indicate that we want to get the threads to sleep in order to replace them with other threads or leave them awake & use them in the parallel code
◆ init_sched
void(* _starpu_sched_ctx::init_sched) (unsigned) |
function called when initializing the scheduler
◆ nsms
int _starpu_sched_ctx::nsms |
nr of SMs assigned to this ctx if we partition gpus
The documentation for this struct was generated from the following file: