CGPA: Coarse-Grained Pruning of Activations for Energy-Efficient RNN Inference

Riera Villanueva, Marc; Arnau Montañés, José María; González Colás, Antonio María

doi:10.1109/MM.2019.2929742

View/Open

Artículo Postprint (2,961Mb)

View Usage Statistics

Cita com:

Show full item record

Riera Villanueva, Marc

Arnau Montañés, José María

González Colás, Antonio María

Document typeArticle

Defense date2019-09-01

Rights accessOpen Access

European Commission's projectCoCoUnit - CoCoUnit: An Energy-Efficient Processing Unit for Cognitive Computing (EC-H2020-833057)

Abstract

Recurrent neural networks (RNNs) perform element-wise multiplications across the activations of gates. We show that a significant percentage of activations are saturated and propose coarse-grained pruning of activations (CGPA) to avoid the computation of entire neurons, based on the activation values of the gates. We show that CGPA can be easily implemented on top of a TPU-like architecture with negligible area overhead, resulting in 12% speedup and 12% energy savings on average for a set of widely used RNNs.

Description

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

CitationRiera, M.; Arnau, J.; Gonzalez, A. CGPA: Coarse-Grained Pruning of Activations for Energy-Efficient RNN Inference. "IEEE micro", 1 Setembre 2019, vol. 39, núm. 5, p. 36-45.

URIhttp://hdl.handle.net/2117/171871

DOI10.1109/MM.2019.2929742

ISSN0272-1732

Publisher versionhttps://ieeexplore.ieee.org/document/8771118

Collections

View Usage Statistics

Show full item record

Files	Description	Size	Format	View
MicroSI-2019-04-0037.R1_Riera Villanueva.pdf	Artículo Postprint	2,961Mb	PDF	View/Open

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder

UPCommons. Global access to UPC knowledge

CGPA: Coarse-Grained Pruning of Activations for Energy-Efficient RNN Inference

View/Open

Browse