Adding flags to scheduler allowing to control thread stealing and idle back-off #3768
Conversation
- reduce false sharing in local priority scheduler and thread_queue - reduce false sharing in latch and condition_variable - disable stealing counters by default
- disable exponential idle backoff by default - simplify wait_or_add_new functionality
…::reset - flyby: add warning suppression for MSVC
- flyby: don't use alignment with NVCC
| @@ -822,10 +846,11 @@ namespace hpx { namespace threads { namespace detail | |||
| // if nothing else has to be done either wait or terminate | |||
| else | |||
| { | |||
| ++idle_loop_count; | |||
| --idle_loop_count; | |||
There was a problem hiding this comment.
Does this need to be reversed? Just thinking about naming. Right now it's more like idle_loop_countdown ;) and it's different from the other counts that actually grow.
There was a problem hiding this comment.
I reversed this as it helped me not to carry around the end value to the point where it needed to be reset.
| @@ -247,7 +247,7 @@ namespace hpx { namespace threads { namespace policies | |||
| num_pending_misses += high_priority_queues_[num_thread].data_-> | |||
| get_num_pending_misses(reset); | |||
| } | |||
| if (num_thread == 0) | |||
| if (num_thread == num_queues_-1) | |||
There was a problem hiding this comment.
Does this make a difference?
There was a problem hiding this comment.
There was some inconsistency that we were accessing the low-priority queue from different cores, sometimes it was core zero sometimes the last one. I made it consistent to reduce false sharing on that queue.
hkaiser
force-pushed
the
control_thread_stealing
branch
2 times, most recently
from
044e0e9
to
b1b9e7a
Compare
…e back-off This adds a couple of things: - adding mark_end_of_scheduling hook to execution parameters allowing to be called back after the scheduling phase of the parallel algorithm - added invocation of mark_begin/mark_end scheduling parameters to sequential for_each and for_loop - added flags to scheduling loop that allows to control thread stealing and idle back-off (effective only for schedulers that support it) - changed implementation of static_priority_scheduler to full rely on local_priority_scheduler except that it starts of with stealing disabled - made fast_idle_mode scheduler flag more useful as it now speeds up idle back-off in case of unsuccessful thread stealing (no work available through thread stealing) - set HPX_WITH_THREAD_MANAGER_IDLE_BACKOFF=ON by default (can now be disabled at runtime) - added add_scheduler_mode/remove_scheduler_mode/add_remove_scheduler_mode APIs allowing to control the scheduler mode dynamically - flyby: removed unused arguments for get_next_thread, added argument controlling enable_stealing for wait_or_add_new - modified for_each_scaling test to not measure data initialization also added command line options `--disable_stealing` and `--fast_idle_mode`
hkaiser
force-pushed
the
control_thread_stealing
branch
2 times, most recently
from
ba55402
to
01b43d2
Compare
- flyby: remove obsolete periodic_maintenance
hkaiser
force-pushed
the
control_thread_stealing
branch
from
01b43d2
to
89b45d3
Compare
|
What was the reason the |
|
@msimberg the |
This adds a couple of things:
mark_end_of_schedulinghook to execution parameters allowing to be called back after the scheduling phase of the parallel algorithmHPX_WITH_THREAD_MANAGER_IDLE_BACKOFF=ONby default (can now be disabled at runtime)add_scheduler_mode/remove_scheduler_mode/add_remove_scheduler_modeAPIs allowing to control the scheduler mode dynamically--disable_stealingand--fast_idle_modeThis relies on #3745 being merged first.This subsumes #3745Fixes #3744