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
- Intel Corporation
- Stanford University