Mostra el registre d'ítem simple
A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL
dc.contributor.author | Jaksic, Zoran |
dc.contributor.author | Cadenelli, Nicola |
dc.contributor.author | Buchaca Prats, David |
dc.contributor.author | Polo Bardés, Jordà |
dc.contributor.author | Berral García, Josep Lluís |
dc.contributor.author | Carrera Pérez, David |
dc.contributor.other | Universitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors |
dc.contributor.other | Barcelona Supercomputing Center |
dc.date.accessioned | 2020-05-06T08:29:50Z |
dc.date.available | 2020-05-06T08:29:50Z |
dc.date.issued | 2020-03-01 |
dc.identifier.citation | Jaksic, Z. [et al.]. A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL. "Future generation computer systems", 1 Març 2020, vol. 104, núm. March 2020, p. 201-211. |
dc.identifier.issn | 0167-739X |
dc.identifier.uri | http://hdl.handle.net/2117/186484 |
dc.description | © 2020 Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/ |
dc.description.abstract | Conditional Restricted Boltzmann Machine (CRBM) is a promising candidate for a multidimensional system modeling that can learn a probability distribution over a set of data. It is a specific type of an artificial neural network with one input (visible) and one output (hidden) layer. Recently published works demonstrate that CRBM is a suitable mechanism for modeling multidimensional time series such as human motion, workload characterization, city traffic analysis. The process of learning and inference of these systems relies on linear algebra functions like matrix–matrix multiplication, and for higher data sets, they are very compute-intensive. In this paper, we present a configurable framework for CRBM based workloads for arbitrary large models. We show how to accelerate the learning process of CRBM with FPGAs and OpenCL, and we conduct an extensive scalability study for different model sizes and system configurations. We show significant improvement in performance/Watt for large models and batch sizes (from 1.51x up to 5.71x depending on the host configuration) when we use FPGA and OpenCL for the acceleration, and limited benefits for small models comparing to the state-of-the-art CPU solution. |
dc.description.sponsorship | This work was supported by the European Research Council(ERC) under the European Union’s Horizon 2020 research andinnovation programme (grant agreements No 639595); the Min-istry of Economy of Spain under contract TIN2015-65316-P andGeneralitat de Catalunya, Spain under contract 2014SGR1051;the ICREA, Spain Academia program; the BSC-CNS Severo Ochoaprogram, Spain (SEV-2015-0493) and Intel Corporation, UnitedStates |
dc.format.extent | 11 p. |
dc.language.iso | eng |
dc.publisher | Elsevier |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International |
dc.rights.uri | https://creativecommons.org/licenses/by-nc-nd/4.0/ |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic |
dc.subject.lcsh | Machine learning |
dc.subject.lcsh | Computer systems |
dc.subject.other | CRBM |
dc.subject.other | FPGA |
dc.subject.other | OpenCL |
dc.subject.other | Time-series |
dc.subject.other | ANN |
dc.subject.other | GEMM |
dc.title | A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL |
dc.type | Article |
dc.subject.lemac | Aprenentatge automàtic |
dc.subject.lemac | Sistemes informàtics |
dc.contributor.group | Universitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions |
dc.identifier.doi | 10.1016/j.future.2019.10.025 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://www.sciencedirect.com/science/article/pii/S0167739X19313676 |
dc.rights.access | Open Access |
local.identifier.drac | 26906540 |
dc.description.version | Postprint (published version) |
dc.relation.projectid | info:eu-repo/grantAgreement/EC/H2020/639595/EU/Holistic Integration of Emerging Supercomputing Technologies/Hi-EST |
dc.relation.projectid | info:eu-repo/grantAgreement/MINECO//SEV-2015-0493/ES/BARCELONA SUPERCOMPUTING CENTER - CENTRO. NACIONAL DE SUPERCOMPUTACION/ |
local.citation.author | Jaksic, Z.; Cadenelli, N.; Buchaca, D.; Polo, J.; Berral, J.; Carrera, D. |
local.citation.publicationName | Future generation computer systems |
local.citation.volume | 104 |
local.citation.number | March 2020 |
local.citation.startingPage | 201 |
local.citation.endingPage | 211 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [318]
-
Articles de revista [1.049]
-
Articles de revista [382]
-
Articles de revista [164]