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:20190719T085754Z
LOCATION:HG F 30
DTSTART;TZID=Europe/Stockholm:20190614T080000
DTEND;TZID=Europe/Stockholm:20190614T084500
UID:submissions.pasc-conference.org_PASC19_sess177_key104@linklings.com
SUMMARY:SK02 - Large-Scale Optimization Strategies for Typical HPC Workloa
 ds
DESCRIPTION:Keynote, Plenary\n\n\nSK02 - Large-Scale Optimization Strategi
 es for Typical HPC Workloads\n\nLiu\n\nEnsuring performance of application
 s running on large-scale clusters is one of the primary focuses in HPC res
 earch. In this talk, we will show our strategies on performance analysis a
 nd optimization for applications in different fields of research using lar
 ge-scale HPC clusters. Our strategies are designed to comprehensively anal
 yze runtime features of applications, parallel mode of the physical model,
  algorithm implementation and other technical details. This three levels o
 f strategy covers platform optimization, technological innovation, and mod
 el innovation, and targeted optimization based on these features. State-of
 -the-art CPU instructions, network communication and other modules, and in
 novative parallel mode of some applications have been optimized. After opt
 imization, it is expected that these applications will outperform their no
 n-optimized counterparts with obvious increase in performance.<br /><br />
 Video Recording: https://www.video.ethz.ch/conferences/2019/pasc19/c923f8d
 0-93a5-47f2-8780-ab18a10f4d18.html
END:VEVENT
END:VCALENDAR