BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250822T115804Z
LOCATION:Room 5.0A52
DTSTART;TZID=Europe/Stockholm:20250617T150000
DTEND;TZID=Europe/Stockholm:20250617T170000
UID:submissions.pasc-conference.org_PASC25_sess119@linklings.com
SUMMARY:MS4A - Empowering Interdisciplinary Collaboration through Reproduc
 ible Benchmarking
DESCRIPTION:Porting and tuning the performance of scientific applications 
 on heterogeneous and increasingly complex supercomputer architectures is c
 urrently a manual and arduous task. Therefore, benchmarks are crucial for 
 evaluating and improving the performance of applications on these systems.
  Benchmarks can be used as a proxy of the execution behaviors of scientifi
 c applications in a controlled and simpler environment, which provides an 
 opportunity to extrapolate performance gains across new hardware, algorith
 m changes, and software updates. This mini symposium brings together inter
 disciplinary communities, who are using supercomputers, to discuss the cha
 llenges and opportunities in tracking, analyzing, and tuning application p
 erformance through the use of reproducible benchmarks. Specifically, we wi
 ll address these critical topics: defining benchmarks to accurately captur
 e scientific application behaviors; broadening performance metrics beyond 
 time to solution, to reflect the impact of optimizations; modernizing the 
 process of running benchmarks and analyzing their performance on different
  hardware architectures; proposing a standard for the definition of new be
 nchmarks to improve reproducibility; identifying opportunities for softwar
 e/hardware co-design across scientific applications and domains; and how t
 o encourage contributions from the community through open-source benchmark
  implementations.\n\nBenchmarking and Co-Design at System and Processor Le
 vel\n\nBenchmarking provides insight into the behaviour of application cod
 es and their kernels on HPC systems. This is useful for identifying bottle
 necks and performance tuning on the application side, as well as for under
 standing how specific hardware features can impact (positively or negative
 ly) the per...\n\n\nEstela Suarez (Forschungszentrum Jülich, University of
  Bonn)\n---------------------\nCollaborative Continuous Benchmarking for H
 PC Applications\n\nBenchmarking is integral to procurement of HPC systems,
  communicating HPC center workloads to HPC vendors, and verifying performa
 nce of the delivered HPC systems. Currently, HPC benchmarking is manual an
 d challenging at every step, posing a high barrier to entry, and hampering
  reproducibility of the...\n\n\nOlga Pearce (Lawrence Livermore National L
 aboratory, Texas A&M University)\n---------------------\nBenchmarking the 
 Three Ps: Performance, Portability, and Productivity\n\nOur high-performan
 ce applications must be written to embrace the full ecosystem of supercomp
 uter design. They need to take advantage of the hierarchy of concurrency o
 n offer, and utilise the whole processor. And writing these applications m
 ust be productive because HPC software outlives any one syst...\n\n\nTom D
 eakin (University of Bristol)\n---------------------\nPanel: Reproducible 
 Benchmarking in Scientific Applications - Challenges and Opportunities\n\n
 What are the current research challenges and opportunities with reproducib
 le benchmarking for scientific applications? Join an interactive panel wit
 h the three speakers Dr. Olga Pearce (LLNL, Texas A&M), Dr. Tom Deakin (Un
 iversity of Bristol), Dr. Estela Suarez (Juelich Supercomputing Center, Un
 iver...\n\n\nJens Domke (RIKEN) and Olga Pearce (Lawrence Livermore Nation
 al Laboratory)\n\nDomain: Engineering, Physics, Computational Methods and 
 Applied Mathematics\n\nSession Chair: Olga Pearce (Lawrence Livermore Nati
 onal Laboratory, TAMU)
END:VEVENT
END:VCALENDAR