dc.contributor
Universitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors
dc.contributor
Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.contributor
Universitat Politècnica de Catalunya. ARCO - Microarquitectura i Compiladors
dc.contributor.author
Riera Villanueva, Marc
dc.contributor.author
Arnau Montañés, José María
dc.contributor.author
González Colás, Antonio María
dc.date.issued
2019-09-01
dc.identifier
Riera, 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.
dc.identifier
https://hdl.handle.net/2117/171871
dc.identifier
10.1109/MM.2019.2929742
dc.description.abstract
© 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.
dc.description.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.
dc.description.abstract
Peer Reviewed
dc.description.abstract
Postprint (author's final draft)
dc.format
application/pdf
dc.relation
https://ieeexplore.ieee.org/document/8771118
dc.relation
info:eu-repo/grantAgreement/EC/H2020/833057/EU/CoCoUnit: An Energy-Efficient Processing Unit for Cognitive Computing/CoCoUnit
dc.relation
info:eu-repo/grantAgreement/MINECO/1PE/TIN2016-75344-R
dc.subject
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subject
Machine learning
dc.subject
Machine learning
dc.subject
Aprenentatge automàtic
dc.title
CGPA: Coarse-Grained Pruning of Activations for Energy-Efficient RNN Inference
