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:20211207T055411Z
LOCATION:Online
DTSTART;TZID=America/Chicago:20211119T083000
DTEND;TZID=America/Chicago:20211119T120000
UID:submissions.supercomputing.org_SC21_sess329@linklings.com
SUMMARY:PAW-ATM 2021: The 4th Annual Parallel Applications Workshop, Alter
 natives To MPI+X
DESCRIPTION:Workshop\n\nPAW-ATM2021:  Introduction\n\nMorris\n\nThe 4th An
 nual Parallel Applications Workshop, Alternatives To MPI+X (PAW-ATM) intro
 duction and opening remarks\n\n---------------------\nEvaluation of Two To
 pology-Aware Heuristics on Level-3 BLAS Library for Multi-GPU Platforms\n\
 nGautier, Ferreira Lima\n\nNowadays GPUs have dominated the market conside
 ring the computing/power metric and numerous research works have provided 
 Basic Linear Algebra Subprograms implementations accelerated on GPUs. Seve
 ral software libraries have been developed for exploiting performance of s
 ystems with accelerators, but t...\n\n---------------------\nToward High P
 roductivity and Performance for Irregular Applications in Chapel\n\nRoling
 er, Craft, Krieger, Sussman\n\nLarge scale irregular applications, such as
  sparse linear algebra and graph analytics, exhibit fine-grained memory ac
 cess patterns and operate on very large data sets. The Partitioned Global 
 Address Space (PGAS) model simplifies the development of distributed-memor
 y irregular applications, as all th...\n\n---------------------\nScaling a
 nd Acceleration of Three-Dimensional Structure Determination for Single-Pa
 rticle Imaging Experiments with SpiniFEL\n\nChang, Slaughter, Mirchandaney
 , Donatelli, Yoon\n\nThe Linac Coherent Light Source is an X-ray free elec
 tron laser facility enabling the study of the structure and dynamics of si
 ngle macromolecules. A major upgrade will bring the repetition rate of the
  X-ray source from 120 to 1 million pulses per second. Exascale computing 
 capabilities will be requ...\n\n---------------------\nDemonstrating UPC++
 /Kokkos Interoperability in a Heat Conduction Simulation\n\nWaters, MacLea
 n, Bonachea, Hargrove\n\nWe describe the replacement of MPI with UPC++ in 
 an existing Kokkos code that simulates heat conduction within a rectangula
 r 3D object, as well as an analysis of the new code's performance on CUDA 
 accelerators. The key challenges were packing the halos in Kokkos data str
 uctures in a way that allowed...\n\n---------------------\nOptimization of
  Asynchronous Communication Operations through Eager Notifications\n\nKami
 l, Bonachea\n\nUPC++ is a C++ library implementing the Asynchronous Partit
 ioned Global Address Space (APGAS) model. We propose an enhancement to the
  completion mechanisms of UPC++ used to synchronize communication operatio
 ns that is designed to reduce overhead for on-node operations. Our enhance
 ment permits eager ...\n\n---------------------\nInvited Talk:  Toward an 
 Efficient Use of ExaScale High-Performance Computing\n\nOrozco\n\nNew gene
 ration Tier-0 computers will cross soon the mythic ExaScale barrier. It is
  however less clear that such massive computers will be used in a fruitful
  manner in complex systems such as the biological one, where individual pr
 oblems rarely  ts the ideal requirements for massively parallel ...\
 n\n---------------------\nPAW-ATM:  Morning Break (10-10:30)\n\n\n\n------
 ---------------\nPAW-ATM 2021:  Panel Discussion\n\nPophale, Chapman, Edel
 man, Laurendeau, Orozco...\n\nDifferent aspects of the workshop and other 
 questions from the moderator and audience will be discussed in the panel.\
 n\n---------------------\nPAW-ATM 2021:  The 4th Annual Parallel Applicati
 ons Workshop, Alternatives to MPI+X\n\nMorris, Badia, Ferguson\n\nSupercom
 puters get faster and more complex every year.  MPI, long the dominant mod
 el for distributed computation, has adapted by combining with models for i
 ntra-node parallelism (e.g. OpenMP, CUDA). These MPI+X hybrids offer perfo
 rmance but demand significant programmer effort to write, debug and tu...\
 n\n\nTag: Online Only, Applications, Extreme Scale Computing, Heterogeneou
 s Systems, Parallel Programming Languages and Models, Software Engineering
 \n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR