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:20210916T132456Z
LOCATION:
DTSTART;TZID=Europe/Stockholm:20210706T173000
DTEND;TZID=Europe/Stockholm:20210706T190000
UID:submissions.pasc-conference.org_PASC21_sess182_post116@linklings.com
SUMMARY:P06 - Best Practice for Efficient and Scalable Application Perform
 ance
DESCRIPTION:Poster\n\nP06 - Best Practice for Efficient and Scalable Appli
 cation Performance\n\nWylie, Garcia-Gasulla\n\nNowadays, the whole HPC com
 munity is looking forward to the exascale era. On the one hand, computer a
 nd system architects are investing their effort to design the first exasca
 le supercomputer. On the other hand, application developers and scientists
  from different fields relying on HPC struggle to prepare their codes to r
 un efficiently, even on current leadership computer systems. Some of the c
 hallenges they face are well known (e.g., parallelization inefficiencies c
 aused by synchronizations, load imbalance, or communication patterns). Oth
 er constraints/inefficiencies arise from new computing paradigms (e.g., ho
 w to manage input/output when dealing with big data) and the heterogeneity
  of computing resources (e.g., when/how to efficiently exploit an accelera
 tor). <br />After more than 200 assessments, the Performance Optimisation 
 and Productivity (POP) Centre of Excellence (CoE) has a unique view of the
  most common pitfalls and sources of inefficiency that prevent codes from 
 running efficiently and achieving scalability. We present a set of common 
 patterns and share recommendations based on the performance analysis of fl
 agship codes of CoEs addressing a variety of scientific domains (e.g., Hem
 eLB from CompBioMed, SeisSol from ChEESE, and IFS from ESiWACE).
END:VEVENT
END:VCALENDAR