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:20181221T160731Z
LOCATION:D171/173
DTSTART;TZID=America/Chicago:20181116T083000
DTEND;TZID=America/Chicago:20181116T084000
UID:submissions.supercomputing.org_SC18_sess145_wksp109@linklings.com
SUMMARY:Introduction - International Workshop on Performance, Portability,
  and Productivity in HPC (P3HPC)
DESCRIPTION:Workshop\nHeterogeneous Systems, Performance, Workshop Reg Pas
 s\n\nIntroduction - International Workshop on Performance, Portability, an
 d Productivity in HPC (P3HPC)\n\nDoerfler, Neely, Pennycook, O'Brien\n\nTh
 e ability for applications to achieve both portability and high performanc
 e across computer architectures remains an open challenge.  It is often un
 realistic or undesirable for developers to maintain separate implementatio
 ns for each target architecture, yet in many cases, achieving high perform
 ance and fully utilizing an architecture’s underlying features requires th
 e use of specialized language constructs and libraries. Likewise, abstract
 ions and standards that promise portability cannot necessarily deliver hig
 h performance without additional algorithmic considerations, and performan
 ce compromises are often made to remain portable.  Application developers,
  who strive to work productively while balancing these concerns, often fin
 d the goal to be elusive. \n\nThere is a clear need to develop ways of man
 aging the complexity that arises from system diversity that balance the ne
 ed for performant specializations with the economy of appropriate and effi
 cient abstractions.  Despite growth in the number of available architectur
 es, there are similarities that represent general trends in current and em
 erging HPC hardware: increased thread parallelism; wider vector units; and
  deep, complex, memory hierarchies.  This in turn offers some hope for com
 mon programming techniques and language support as community experience ma
 tures.\n\nThe purpose of this workshop is to provide an opportunity for at
 tendees to share ideas, practical experiences, and methodologies for tackl
 ing the challenge of achieving performance portability and developer produ
 ctivity across current and future homogeneous and heterogeneous computer a
 rchitectures.
URL:https://sc18.supercomputing.org/presentation/?id=wksp109&sess=sess145
END:VEVENT
END:VCALENDAR