BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000713Z
LOCATION:405
DTSTART;TZID=America/Denver:20231113T083000
DTEND;TZID=America/Denver:20231113T170000
UID:submissions.supercomputing.org_SC23_sess242_tut140@linklings.com
SUMMARY:Efficient Distributed GPU Programming for Exascale
DESCRIPTION:Andreas Herten (Forschungszentrum Jülich; Jülich Supercomputin
 g Centre (JSC), Institute for Advanced Simulation); Simon Garcia de Gonzal
 o (Sandia National Laboratories); Jiri Kraus and Markus Hrywniak (NVIDIA C
 orporation); and Chelsea Maria John (Forschungzentrum Jülich, Jülich Super
 computing Centre)\n\nOver the past decade, GPUs became ubiquitous in HPC i
 nstallations around the world, delivering the majority of performance of s
 ome of the largest supercomputers (e.g. Summit, Sierra, JUWELS Booster). T
 his trend continues in the recently deployed and upcoming Pre-Exascale and
  Exascale systems (JUPITER, LUMI, Leonardo; El Capitan, Frontier, Perlmutt
 er): GPUs are chosen as the core computing devices to enter this next era 
 of HPC.  To take advantage of future GPU-accelerated systems with tens of 
 thousands of devices, application developers need to have the proper skill
 s and tools to understand, manage, and optimize distributed GPU applicatio
 ns.\n\nIn this tutorial, participants will learn techniques to efficiently
  program large-scale multi-GPU systems. While programming multiple GPUs wi
 th MPI is explained in detail, also advanced tuning techniques and complem
 enting programming models like NCCL and NVSHMEM are presented. Tools for a
 nalysis are shown and used to motivate and implement performance optimizat
 ions. The tutorial teaches fundamental concepts that apply to GPU-accelera
 ted systems in general, taking the NVIDIA platform as an example. It is a 
 combination of lectures and hands-on exercises, using one of Europe’s fast
 est supercomputers, JUWELS Booster, for interactive learning and discovery
 .\n\nTag: Accelerators, Exascale, Heterogeneous Computing, Performance Opt
 imization\n\nRegistration Category: Tutorial Reg Pass\n\n
END:VEVENT
END:VCALENDAR