DynaSprint: Microarchitectural sprints with dynamic utility and thermal management

Conference Paper

Sprinting is a class of mechanisms that provides a short but significant performance boost while temporarily exceeding the thermal design point. We propose DynaSprint, a software runtime that manages sprints by dynamically predicting utility and modeling thermal headroom. Moreover, we propose a new sprint mechanism for caches, increasing capacity briefly for enhanced performance. For a system that extends last-level cache capacity from 2MB to 4MB per core and can absorb 10J of heat, DynaSprint-guided cache sprints improve performance by 17% on average and by up to 40% over a non-sprinting system. These performance outcomes, within 95% of an oracular policy, are possible because DynaSprint accurately predicts phase behavior and sprint utility.

Full Text

Duke Authors

Cited Authors

  • Huang, Z; Joao, JA; Rico, A; Hilton, AD; Lee, BC

Published Date

  • October 12, 2019

Published In

Start / End Page

  • 426 - 439

International Standard Serial Number (ISSN)

  • 1072-4451

International Standard Book Number 13 (ISBN-13)

  • 9781450369381

Digital Object Identifier (DOI)

  • 10.1145/3352460.3358301

Citation Source

  • Scopus