Convolution engine

Abstract

General-purpose processors, while tremendously versatile, pay a huge cost for their flexibility by wasting over 99% of the energy in programmability overheads. We observe that reducing this waste requires tuning data storage and compute structures and their connectivity to the data-flow and data-locality patterns in the algorithms. Hence, by backing off from full programmability and instead targeting key data-flow patterns used in a domain, we can create efficient engines that can be programmed and reused across a wide range of applications within that domain.

Document Details

Document Type
Pub Defense Publication
Publication Date
Mar 23, 2015
Source ID
10.1145/2735841

Entities

People

  • Christos Kozyrakis
  • Mark Horowitz
  • Ofer Shacham
  • Preethi Venkatesan
  • Rehan Hameed
  • Wajahat Qadeer

Organizations

  • Defense Advanced Research Projects Agency
  • Google
  • Intel Corporation
  • Stanford University

Tags

Fields of Study

  • Computer science

Readers

  • Graph Algorithms and Convex Optimization.
  • Nanoscale Plasmonic Nanotechnology
  • Software Engineering.