

Type of Document Master's Thesis Author McFarland, Daniel James Author's Email Address dmcfarl@vt.edu URN etd-06292011-130247 Title Exploiting Malleable Parallelism on Multicore Systems Degree Master of Science Department Computer Science Advisory Committee
Advisor Name Title Ribbens, Calvin J. Committee Chair Back, Godmar V. Committee Member Butt, Ali R. A. Committee Member Keywords
- Malleable
- Resizable
- Rigid
- Thread
Date of Defense 2011-06-16 Availability unrestricted Abstract As shared memory platforms continue to grow in core counts, the need for context-awarescheduling continues to grow. Context-aware scheduling takes into account characteristics of
the system and application performance when making decisions. Traditionally applications
run on a static thread count that is set at compile-time or at job start time, without taking
into account the dynamic context of the system, other running applications, and potentially
the performance of the application itself. However, many shared memory applications can
easily be converted to malleable applications, that is, applications that can run with an
arbitrary number of threads and can change thread counts during execution. Many new
and intelligent scheduling decisions can be made when applications become context-aware,
including expanding to ll an empty system or shrinking to accommodate a more parallelizable
job. This thesis describes a prototype system called Resizing for Shared Memory
(RSM), which supports OpenMP applications on shared memory platforms. RSM includes a
main daemon that records performance information and makes resizing decisions as well as a
communication library to allow applications to contact the RSM daemon and enact resizing
decisions. Experimental results show that RSM can improve turn-around time and system
utilization even using very simple heuristics and resizing policies.
Files
Filename Size Approximate Download Time (Hours:Minutes:Seconds)
28.8 Modem 56K Modem ISDN (64 Kb) ISDN (128 Kb) Higher-speed Access McFarland_DJ_T_2011.pdf 5.83 Mb 00:26:58 00:13:52 00:12:08 00:06:04 00:00:31
If you have questions or technical problems, please Contact DLA.