In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy
will defend his dissertation
Optimizations for Energy Efficiency within Distributed Memory Programming Models
With the breakdown of Dennard Scaling and Moore's law, power consumption appears to be a primary challenge on the pathway to exascale computing. Extreme Scale Research reports indicate the energy consumption during movement of data off-chip is orders of magnitude higher than within a chip. The direct outcome of this has been a rising concern about the energy and power consumption of large-scale applications that rely on various communication libraries and parallelism constructs for distributed computing. While innovative designs of hardware set the upper bounds for power consumption, there is a need for the software to adapt itself to achieve maximum efficiency at mimimal joules.
This work presents detailed analyses of multiple factors across different layers of the software stack, that affect the energy consumption of large scale distributed memory HPC applications and programming environments. As part of this empirical analyses, we isolate multiple constraints (imposed by the communication, memory, and the execution model) that hinder energy-efficient execution of such applications. We also suggest modifications to a typical SPMD programming model in order to reduce the impact of these constraints. As part of this talk, good programming practice will be presented and empirical evidence of their impact will be discussed.
This defense will also be presented as a webinar session for remote attendees.
-- (Video+audio) URL: www.uberconference.com/sidphddefense
-- (Audio only) Conf. Ph# +1 (832) 930-3750
No PIN needed
Date: Tuesday, November 8, 2016
Time: 3:45 PM (Central Time)
Place: PGH 550
Advisor: Dr. Barbara Chapman, Dr. Edgar Gabriel
Faculty, students, and the general public are invited.