CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

SWAS: Stealing Work Using Approximate System-Load Information

Stavros Tzilis (Institutionen för data- och informationsteknik, Datorteknik (Chalmers)) ; Miquel Pericàs (Institutionen för data- och informationsteknik, Datorteknik (Chalmers)) ; P. Trancoso ; Ioannis Sourdis (Institutionen för data- och informationsteknik, Datorteknik (Chalmers))
46th International Conference on Parallel Processing Workshops, ICPPW 2017, Bristol, United Kingdom, 14 August 2017 (1530-2016). p. 309-318. (2017)
[Konferensbidrag, refereegranskat]

This paper explores the potential of utilizing approximate system load information to enhance work stealing for dynamic load balancing in hierarchical multicore systems. Maintaining information about the load of a system has not been extensively researched since it is assumed to introduce performance overheads. We propose SWAS, a lightweight approximate scheme for retrieving and using such information, based on compact bit vector structures and lightweight update operations. This approximate information is used to enhance the effectiveness of work stealing decisions. Evaluating SWAS for a number of representative scenarios on a multi-socket multi-core platform showed that work stealing guided by approximate system load information achieves considerable performance improvements: up to 18.5% for dynamic, severely imbalanced workloads; and up to 34.4% for workloads with complex task dependencies, when compared with random work stealing.

Nyckelord: Approximate information , Resource management , Runtime systems , Work stealing

Denna post skapades 2017-10-25.
CPL Pubid: 252772


Läs direkt!

Länk till annan sajt (kan kräva inloggning)

Institutioner (Chalmers)

Institutionen för data- och informationsteknik, Datorteknik (Chalmers)


Datavetenskap (datalogi)

Chalmers infrastruktur