A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL

© 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/

Bibliographic Details
Authors: Jaksic, Zoran, Cadenelli, Nicola, Buchaca Prats, David, Polo Bardés, Jordà, Berral García, Josep Lluís|||0000-0003-3037-3580, Carrera Pérez, David|||0000-0003-4898-3424
Format: article
Publication Date:2020
Country:España
Institution:Universitat Politècnica de Catalunya (UPC)
Repository:UPCommons. Portal del coneixement obert de la UPC
Language:English
OAI Identifier:oai:upcommons.upc.edu:2117/186484
Online Access:https://hdl.handle.net/2117/186484
https://dx.doi.org/10.1016/j.future.2019.10.025
Access Level:Open access
Keyword:Machine learning
Computer systems
CRBM
FPGA
OpenCL
Time-series
ANN
GEMM
Aprenentatge automàtic
Sistemes informàtics
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
id ES_26477deadb3daa2bc1ddd0baeafb698a
oai_identifier_str oai:upcommons.upc.edu:2117/186484
network_acronym_str ES
network_name_str España
repository_id_str
spelling A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCLJaksic, ZoranCadenelli, NicolaBuchaca Prats, DavidPolo Bardés, JordàBerral García, Josep Lluís|||0000-0003-3037-3580Carrera Pérez, David|||0000-0003-4898-3424Machine learningComputer systemsCRBMFPGAOpenCLTime-seriesANNGEMMAprenentatge automàticSistemes informàticsÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic© 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/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.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, UnitedStatesPeer ReviewedElsevier20202020-03-0120202020-05-06journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/186484https://dx.doi.org/10.1016/j.future.2019.10.025reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengEuropean Commission http://doi.org/10.13039/100010661 Horizon 2020 Framework Programme 639595 Holistic Integration of Emerging Supercomputing TechnologiesMinisterio de Economía y Competitividad http://doi.org/10.13039/501100003329 SEV-2015-0493 BARCELONA SUPERCOMPUTING CENTER - CENTRO. NACIONAL DE SUPERCOMPUTACIONopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttps://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/1864842026-05-27T15:37:01Z
dc.title.none.fl_str_mv A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL
title A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL
spellingShingle A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL
Jaksic, Zoran
Machine learning
Computer systems
CRBM
FPGA
OpenCL
Time-series
ANN
GEMM
Aprenentatge automàtic
Sistemes informàtics
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
title_short A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL
title_full A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL
title_fullStr A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL
title_full_unstemmed A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL
title_sort A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL
dc.creator.none.fl_str_mv Jaksic, Zoran
Cadenelli, Nicola
Buchaca Prats, David
Polo Bardés, Jordà
Berral García, Josep Lluís|||0000-0003-3037-3580
Carrera Pérez, David|||0000-0003-4898-3424
author Jaksic, Zoran
author_facet Jaksic, Zoran
Cadenelli, Nicola
Buchaca Prats, David
Polo Bardés, Jordà
Berral García, Josep Lluís|||0000-0003-3037-3580
Carrera Pérez, David|||0000-0003-4898-3424
author_role author
author2 Cadenelli, Nicola
Buchaca Prats, David
Polo Bardés, Jordà
Berral García, Josep Lluís|||0000-0003-3037-3580
Carrera Pérez, David|||0000-0003-4898-3424
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Machine learning
Computer systems
CRBM
FPGA
OpenCL
Time-series
ANN
GEMM
Aprenentatge automàtic
Sistemes informàtics
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
topic Machine learning
Computer systems
CRBM
FPGA
OpenCL
Time-series
ANN
GEMM
Aprenentatge automàtic
Sistemes informàtics
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
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/
publishDate 2020
dc.date.none.fl_str_mv 2020
2020-03-01
2020
2020-05-06
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/186484
https://dx.doi.org/10.1016/j.future.2019.10.025
url https://hdl.handle.net/2117/186484
https://dx.doi.org/10.1016/j.future.2019.10.025
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv European Commission http://doi.org/10.13039/100010661 Horizon 2020 Framework Programme 639595 Holistic Integration of Emerging Supercomputing Technologies
Ministerio de Economía y Competitividad http://doi.org/10.13039/501100003329 SEV-2015-0493 BARCELONA SUPERCOMPUTING CENTER - CENTRO. NACIONAL DE SUPERCOMPUTACION
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
https://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869404812397772800
score 15,300719

Similar Items