Computational Sprinting: Exceeding Sustainable Power in Thermally Constrained Systems

Loading...
Thumbnail Image
Degree type
Doctor of Philosophy (PhD)
Graduate group
Computer and Information Science
Discipline
Subject
Energy efficient computer architecture
Parallel mobile architecture
Themal-aware computer architecture
Computer Engineering
Computer Sciences
Funder
Grant number
License
Copyright date
2014-08-22T00:00:00-07:00
Distributor
Related resources
Contributor
Abstract

Although process technology trends predict that transistor sizes will continue to shrink for a few more generations, voltage scaling has stalled and thus future chips are projected to be increasingly more power hungry than previous generations. Particularly in mobile devices which are severely cooling constrained, it is estimated that the peak operation of a future chip could generate heat ten times faster than than the device can sustainably vent. However, many mobile applications do not demand sustained performance; rather they comprise short bursts of computation in response to sporadic user activity. To improve responsiveness for such applications, this dissertation proposes computational sprinting, in which a system greatly exceeds sustainable power margins (by up to 10x) to provide up to a few seconds of high-performance computation when a user interacts with the device. Computational sprinting exploits the material property of thermal capacitance to temporarily store the excess heat generated when sprinting. After sprinting, the chip returns to sustainable power levels and dissipates the stored heat when the system is idle. This dissertation: (i) broadly analyzes thermal, electrical, hardware, and software considerations to analyze the feasibility of engineering a system which can provide the responsiveness of a plat- form with 10x higher sustainable power within today's cooling constraints, (ii) leverages existing sources of thermal capacitance to demonstrate sprinting on a real system today, and (iii) identifies the energy-performance characteristics of sprinting operation to determine runtime sprint pacing policies.

Advisor
Milo M. Martin
Date of degree
2013-01-01
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation