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:20260522T150116Z
LOCATION:D175
DTSTART;TZID=America/Chicago:20181111T105100
DTEND;TZID=America/Chicago:20181111T111500
UID:submissions.supercomputing.org_SC18_sess155_ws_waccpd104@linklings.com
SUMMARY:OpenMP Target Offloading: Splitting GPU Kernels, Pipelining Commun
 ication and Computation, and Selecting Better Grid Geometries
DESCRIPTION:Artem Chikin, Tyler Gobran, and Jose N. Amaral (University of 
 Alberta)\n\nThis paper presents three ideas that focus on improving the ex
 ecution of high-level parallel code in GPUs. The first addresses programs 
 that include multiple parallel blocks within a single region of GPU code. 
 A proposed compiler transformation can split such regions into multiple, l
 eading to the launching of multiple kernels, one for each parallel region.
  Advantages include the opportunity to tailor grid geometry of each kernel
  to the parallel region that it executes and the elimination of the overhe
 ads imposed by a code-generation scheme meant to handle multiple nested pa
 rallel regions.  Second, is a code transformation that sets up a pipeline 
 of kernel execution and asynchronous data transfer. This transformation en
 ables the overlap of communication and computation. Intricate technical de
 tails that are required for this transformation are described. The third i
 dea is that the selection of a grid geometry for the execution of a parall
 el region must balance the GPU occupancy with the potential saturation of 
 the memory throughput in the GPU.  Adding this additional parameter to the
  geometry selection heuristic can often yield better performance at lower 
 occupancy levels.\n\nTag: Accelerators, Heterogeneous Systems, Parallel Pr
 ogramming Languages, Libraries, and Models\n\nRegistration Category: Works
 hop Reg Pass\n\nSession Chairs: Sunita Chandrasekaran (University of Delaw
 are); Guido Juckeland (Helmholtz-Zentrum Dresden-Rossendorf (HZDR), TUD Dr
 esden University of Technology); and Sandra Wienke (RWTH Aachen University
 )\n\n
END:VEVENT
END:VCALENDAR