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:20181221T160903Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181115T083000
DTEND;TZID=America/Chicago:20181115T170000
UID:submissions.supercomputing.org_SC18_sess324_post189@linklings.com
SUMMARY:Boosting the Scalability of Car-Parrinello Molecular Dynamics Simu
 lations for Multi- and Manycore Architectures
DESCRIPTION:Poster\nTech Program Reg Pass, Exhibits Reg Pass\n\nBoosting t
 he Scalability of Car-Parrinello Molecular Dynamics Simulations for Multi-
  and Manycore Architectures\n\nKlöffel, Meyer, Mathias\n\nWe present our r
 ecent optimizations of the ultra-soft pseudo-potential (USPP) code path of
  the ab inito molecular dynamics program CPMD (www.cpmd.org). Following th
 e internal instrumentation of CPMD, all relevant USPP routines have been r
 evised to fully support hybrid MPI+OpenMP parallelization. For two time-cr
 itical routines, namely the multiple distributed 3D FFTs of the electronic
  states and a key distributed matrix-matrix multiplication, we have implem
 ented hybrid parallel algorithms with overlapping computation and communic
 ation. The achievements in performance and scalability are demonstrated on
  a small reference system of 128 water molecules and further systems of in
 creasing size. Performance evaluation shows gains of up to one order of ma
 gnitude and around 50% peak performance for simulation systems readily use
 d in production.
URL:https://sc18.supercomputing.org/presentation/?id=post189&sess=sess324
END:VEVENT
END:VCALENDAR