BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230124T171525Z
LOCATION:C155
DTSTART;TZID=America/Chicago:20221113T141500
DTEND;TZID=America/Chicago:20221113T143800
UID:submissions.supercomputing.org_SC22_sess428_ws_p3hpc115@linklings.com
SUMMARY:From Task-Based GPU Work Aggregation to Stellar Mergers: Turning F
 ine-Grained CPU Tasks into Portable GPU Kernels
DESCRIPTION:Workshop\n\nFrom Task-Based GPU Work Aggregation to Stellar Me
 rgers: Turning Fine-Grained CPU Tasks into Portable GPU Kernels\n\nDaiß, D
 iehl, Marcello, Kheirkhahan, Kaiser...\n\nMeeting both scalability and per
 formance portability requirements is a challenge for any HPC application, 
 especially for adaptively refined ones. In Octo-Tiger, an astrophysics app
 lication for the simulation of stellar mergers, we approach this with exis
 ting solutions: We employ HPX to obtain fine-grained tasks to easily distr
 ibute work and finely overlap communication and computation. For the compu
 tations themselves, we use Kokkos to turn these tasks into compute kernels
  capable of running on hardware ranging from a few CPU cores to powerful a
 ccelerators. There is a missing link, however: while the fine-grained para
 llelism exposed by HPX is useful for scalability, it can hinder GPU perfor
 mance when the tasks become too small to saturate the device, causing low 
 resource utilization. To bridge this gap, we investigate multiple differen
 t GPU work aggregation strategies within Octo-Tiger, adding one new strate
 gy, and evaluate the node-level performance impact on recent AMD and NVIDI
 A GPUs, achieving noticeable speedups.\n\nSession Format: Recorded\n\nTag:
  Performance Portability\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR