BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:0-79@lisn.upsaclay.fr
DTSTART;TZID=Europe/Paris:20221213T153000
DTEND;TZID=Europe/Paris:20221213T173000
DTSTAMP:20221206T094647Z
URL:https://www.lisn.upsaclay.fr/evenements/some-experiences-in-machine-le
 arning-and-data-science-for-high-performance-computing-resource-management
 /
SUMMARY:Some experiences in Machine Learning and Data Science for High-Perf
 ormance Computing resource management
DESCRIPTION:High-Performance Computing (HPC) platforms are growing in size 
 and complexity. In an adversarial manner\, the power demand of such platfo
 rms rapidly grows as well\, and current top supercomputers require power a
 t the scale of an entire power plant. To make a more responsible usage of 
 such power\, researchers are devoting a significant amount of effort to de
 vise algorithms and techniques to improve different aspects of performance
 \, such as scheduling and resource management.In this seminar\, I will pre
 sent some experiences using Machine Learning and Data Science techniques f
 or efficient HPC resource management. I will show a method that exploits H
 PC simulation and regression to create novel HPC scheduling policies. I wi
 ll show our current work on combining multiple data sources to classify an
 d predict the energy behavior of HPC applications. Then I will finish by s
 howing some foreseeable ways to extend these experiences to other computin
 g platforms and other dimensions of the problem.
CATEGORIES:Science responsable
LOCATION:LISN Site Belvédère\, Rue du Belvédère  Campus universitaire b
 ât 507 91405 Orsay\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Rue du Belvédère  Campus 
 universitaire bât 507 91405 Orsay\, France;X-APPLE-RADIUS=100;X-TITLE=LIS
 N Site Belvédère:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20221030T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR