Publications
Detailed Information
Fast performance estimation and design space exploration of manycore-based neural processors
Cited 0 time in
Web of Science
Cited 2 time in Scopus
- Authors
- Issue Date
- 2019-06
- Publisher
- IEEE
- Citation
- Proceedings - Design Automation Conference
- Abstract
- © 2019 Association for Computing Machinery.In the design of a neural processor, a cycle-accurate simulator is usually built to estimate the performance before hardware implementation. Since using the simulator to perform design space exploration (DSE) of hardware architecture is quite time consuming, we propose a novel method to use a high-level analytical model for fast DSE. In the model, non-deterministic execution delay is modeled with some parameters whose contribution to the performance is estimated statically by simulation. The viability of the proposed methodology is confirmed with two neural processors with different manycore architectures, achieving 2000 times speed-up within 3% accuracy error, compared with simulator-based DSE.
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.