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:20260522T150115Z
LOCATION:D171/173
DTSTART;TZID=America/Chicago:20181116T111500
DTEND;TZID=America/Chicago:20181116T113000
UID:submissions.supercomputing.org_SC18_sess145_ws_p3hpc112@linklings.com
SUMMARY:Heterogeneous CPU-GPU Execution of Stencil Applications
DESCRIPTION:Balint Siklosi and Istvan Reguly (Pázmány Péter Catholic Unive
 rsity, Hungary) and Gihan Mudalige (University of Warwick)\n\nHeterogeneou
 s computer architectures are now ubiquitous in high performance computing;
  the top 7 supercomputers are all built with CPUs and accelerators. Portab
 ility across different CPUs and GPUs is becoming paramount, and heterogene
 ous scheduling of computations is also of increasing interest to make full
  use of these systems. In this paper, we present research on the hybrid CP
 U-GPU execution of an important class of applications: structured mesh ste
 ncil codes. Our work broadens the performance portability capabilities of 
 the Oxford Parallel library for Structured meshes (OPS), which allows a sc
 ience code written once at a high level to be automatically parallelised f
 or a range of different architectures. We explore the traditional per-loop
  load balancing approach used by others, and highlighting its shortcomings
 , we develop an algorithm that relies on polyhedral analysis and transform
 ations in OPS to allow load balancing on the level of larger computational
  stages, reducing data transfer requirements and synchronisation points.\n
 \nWe evaluate our algorithms on a simple heat equation benchmark, as well 
 as a substantially more complex code, the CloverLeaf hydrodynamics mini-ap
 p. To demonstrate performance portability, we study Intel and IBM systems 
 equipped with NVIDIA Kepler, Pascal, and Volta GPUs, evaluating CPU-only, 
 GPU-only and hybrid CPU-GPU performance. We demonstrate a 1.05-1.2x speedu
 p on CloverLeaf. Our results highlight the ability of the OPS domain speci
 fic language to deliver effortless performance portability for its users a
 cross a number of platforms.\n\nTag: Heterogeneous Systems, Performance\n\
 nRegistration Category: Workshop Reg Pass\n\nSession Chair: Rob Neely (Law
 rence Livermore National Laboratory)\n\n
END:VEVENT
END:VCALENDAR