28th ASE (Advanced Supercomputing Environment) Seminar

Details
Type | Symposium |
---|---|
Intended for | General public / Enrolled students / International students / Alumni / Companies |
Date(s) | May 22, 2017 17:00 — 18:30 |
Location | Hongo Area Campus |
Venue | 2017 Remote Conference Room (4F 413), Information Technology Center (ITC), ºÚÁϳԹÏÍø |
Capacity | 30 people |
Entrance Fee | No charge |
Registration Method | No advance registration required |
Contact | Masaaki Kondo Advanced Supercomputing Environment (ASE) Seminar ·¡-³¾²¹¾±±ô£º°ì´Ç²Ô»å´Ç£À³ó²¹±ô.¾±±è³¦.¾±.³Ü-³Ù´Ç°ì²â´Ç.²¹³¦.Âá±è |
¡ö±Ê°ù´Ç²µ°ù²¹³¾
17:00-17:05 Masaaki Kondo (ºÚÁϳԹÏÍø) Welcome & Opening
17:05-18:00 Jonathan Eastep (Intel)¡¡Global Extensible Open Power Manager: A Vehicle for HPC Community Collaboration on Co-Designed Energy Management Solutions
The power scaling challenge associated with Exascale systems is a well-known issue. In this talk, we provide an overview of the Global Extensible Open Power Manager (GEOPM). GEOPM is an open source power management runtime framework which is being contributed to the HPC community to foster collaboration on new power management runtime techniques to address Exascale power challenges or enhance performance and power efficiency on today’s systems as well. Through GEOPM’s plug-in extensible architecture, it enables rapid prototyping of new runtime algorithms. This talk will cover GEOPM’s architecture and usages then discuss opportunities for collaboration. For additional information, please visit:
18:00-18:15 Thang Cao (ºÚÁϳԹÏÍø) ¡¡Cooling-Aware Job Scheduling and Node Allocation for Overprovisioned HPC Systems
Limited power budget is becoming one of the most crucial challenges in developing supercomputer systems. Hardware overprovisioning which installs a larger number of nodes beyond the limitations of the power constraint is an attractive way to design future supercomputers. In air-cooled HPC centers, it is said that about half of the total power is consumed by cooling facilities. Reducing cooling power and effectively utilizing power resources for computing nodes are important challenges. In this talk, we present a cooling and node location-aware job scheduling strategy which tries to optimize job-to-node mapping while improving the total system throughput under the constraint of total system (compute nodes and cooling facilities) power consumption.
18:15-18:25 Kengo Nakajima (ºÚÁϳԹÏÍø) Overview of Supercomputing Research Division, Information Technology Center, the University of Tokyo
18:25-18:30 Masaaki Kondo (ºÚÁϳԹÏÍø) Closing