Re: [lng-odp] [API-NEXT PATCH v2 4/5] linux-gen: sched: new ordered queue implementation

/* @@ -658,9 +768,21 @@ static int do_schedule(odp_queue_t *out_queue, odp_event_t out_ev[], ret = copy_events(out_ev, max_num); This update doesn't modify the preceding code: ordered = sched_cb_queue_is_ordered(qi); /* Do not cache ordered events locally to improve *

Re: [lng-odp] [API-NEXT PATCH v2 4/5] linux-gen: sched: new ordered queue implementation

On Wed, Nov 30, 2016 at 7:56 AM, Matias Elo wrote: > Add new implementation for ordered queues. Compared to the old > implementation this is much simpler and improves performance ~1-4x > depending on the test case. > > The implementation is based on an atomic ordered

[lng-odp] [API-NEXT PATCH v2 4/5] linux-gen: sched: new ordered queue implementation

Add new implementation for ordered queues. Compared to the old implementation this is much simpler and improves performance ~1-4x depending on the test case. The implementation is based on an atomic ordered context, which only a single thread may possess at a time. Only the thread owning the