Filters








27 Hits in 8.3 sec

Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs [article]

Miguel de Prado, Andrew Mundy, Rabia Saeed, Maurizio Denna, Nuria Pazos, Luca Benini
2020 arXiv   pre-print
Thus, we present a set of results for state-of-the-art DNNs on a range of Arm Cortex-A CPU platforms achieving up to 4x improvement in performance and over 2x reduction in memory with negligible loss in  ...  Building on this knowledge, we present an automated exploration framework to ease the deployment of DNNs.  ...  Finally, we present the results from applying the automated design space exploration, introduced in Section V, to optimise deployment of DNNs on Arm Cortex-A CPUs. A.  ... 
arXiv:2006.05181v2 fatcat:bfqm7genmngpxf3lzbpvh6fq3y

How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures [article]

Stylianos I. Venieris and Ioannis Panopoulos and Ilias Leontiadis and Iakovos S. Venieris
2021 arXiv   pre-print
accuracy, together pose critical problems to the deployment of DNNs across the various embedded and mobile devices in the wild.  ...  In this paper, we provide preliminary answers to this potentially game-changing question by presenting an array of design techniques for efficient AI systems.  ...  For instance, flagship smartphones tend to host more powerful CPUs (e.g. the Arm Cortex-X1 core in Samsung S21 Ultra) and GPUs than their mid-(e.g.  ... 
arXiv:2106.15021v1 fatcat:b25jifosajeuba57qxiaockmg4

OODIn: An Optimised On-Device Inference Framework for Heterogeneous Mobile Devices [article]

Stylianos I. Venieris and Ioannis Panopoulos and Iakovos S. Venieris
2021 arXiv   pre-print
This paper proposes OODIn, a framework for the optimised deployment of DL apps across heterogeneous mobile devices.  ...  of a highly parametrised multi-layer design; and (2) perform a principled optimisation of both model- and system-level parameters through a multi-objective formulation, designed for DL inference apps,  ...  2020, October Chipset MediaTek MT6752 Snapdragon 730 Exynos 990 CPU 8× 1.69 GHz ARM Cortex-A53 2× 2.2 GHz Kryo 470 Gold 6× 1.8 GHz Kryo 470 Silver 2× 2.73 GHz Exynos M5 2× 2.5 GHz ARM  ... 
arXiv:2106.04723v1 fatcat:hkw46xsbcnetbdtqohq7kvxqiq

fpgaConvNet: Mapping Regular and Irregular Convolutional Neural Networks on FPGAs

Stylianos I. Venieris, Christos-Savvas Bouganis
2018 IEEE Transactions on Neural Networks and Learning Systems  
This paper presents fpgaConvNet, an end-to-end framework for the optimised mapping of ConvNets on FPGAs.  ...  The proposed framework comprises an automated design methodology based on the Synchronous Dataflow (SDF) paradigm and defines a set of SDF transformation in order to efficiently navigate the architectural  ...  Both platforms are based on the Xilinx Zynq-7000 System-on-Chip which integrates a dual-core ARM Cortex A9 CPU alongside an FPGA fabric on the same chip.  ... 
doi:10.1109/tnnls.2018.2844093 pmid:29994725 fatcat:jp45bvjfhne7te2hi337x7ccne

M2DC – Modular Microserver DataCentre with heterogeneous hardware

Ariel Oleksiak, Michal Kierzynka, Wojciech Piatek, Giovanni Agosta, Alessandro Barenghi, Carlo Brandolese, William Fornaciari, Gerardo Pelosi, Mariano Cecowski, Robert Plestenjak, Justin Činkelj, Mario Porrmann (+19 others)
2017 Microprocessors and microsystems  
In this paper, we focus in particular on the thermal management strategies and on the initial benchmarking of the Aarch64 ARM architecture.  ...  The resulting server architecture will be able to be tailored to meet requirements from a wide range of application domains.  ...  A next-generation system architecture design based on ARMv8 (64-bit) technology is being explored in the Mont-Blanc 2 project.  ... 
doi:10.1016/j.micpro.2017.05.019 fatcat:ds2khzdznvfcninkzvlwhpvos4

D1.1 - State of the Art Analysis

Danilo Ardagna
2021 Zenodo  
It is found that some areas, such as component placement and design space exploration with privacy preservation and performance guarantees, are fairly under-developed, since solutions tailo [...]  ...  We also extensively discuss existing solutions for applications deployment, monitoring, runtime management, and scheduling considering the emerging Function as a Service paradigm.  ...  The ODROID-HC4 board is based on the same ARM CPU as the ODROID-C4.  ... 
doi:10.5281/zenodo.6372377 fatcat:f6ldfuwivbcltew4smiiwphfty

D7.9: Hardware developments V

Alan O'Cais, Christopher Werner, Simon Wong, Padraig Ó Conbhuí, Jony Castagna, Godehard Sutmann
2020 Zenodo  
and detailed feedback to the project software developers; - discussion of project software needs with hardware and software vendors, completion of survey of what is already available for particular hardware  ...  Update on "Hardware Developments IV" (Deliverable 7.7: https://doi.org/10.5281/zenodo.3256137) which covers: - Report on hardware developments that will affect the scientific areas of interest to E-CAM  ...  As a result, an optimisation for one combination of hardware components may not be possible on another, or may indeed be a pessimization.  ... 
doi:10.5281/zenodo.3931510 fatcat:kelxr6ap5vfunpjisfpwiauwue

LIPIcs : an Open-Access Series for International Conference Proceedings

Marc Herbstritt, Wolfgang Thomas
2016 ERCIM News  
To achieve this, however, they are highly-optimised for one specific task, and a huge amount of human effort is usually needed to design a DNN for a new task.  ...  For instance, when a robotic arm tries to reach a point in space, the learning algorithm can perform the movement, then, at the end of the trial, measure the distance to the target.  ...  This calls for approaching security in a holistic manner.  ... 
doi:10.18154/rwth-2018-223393 fatcat:ddo7qz65l5b7peuksw2amaoxai

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  This version of my thesis is typeset for online dissemination to improve readability, whereas the thesis submitted to the University of Warwick in support of my application for the degree of Doctor of  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4598227 fatcat:hm2ksetmsvf37adjjefmmbakvq

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  This version of my thesis is typeset for online dissemination to improve readability, whereas the thesis submitted to the University of Warwick in support of my application for the degree of Doctor of  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4591029 fatcat:zn2hvfyupvdwlnvsscdgswayci

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  This copy of my thesis is typeset for online dissemination to improve readability, whereas the thesis submitted to the University of Warwick in support of my application for the degree of Doctor of Philosophy  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4399748 fatcat:63ggmnviczg6vlnqugbnrexsgy

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  This copy of my thesis is typeset for online dissemination to improve readability, whereas the thesis submitted to the University of Warwick in support of my application for the degree of Doctor of Philosophy  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4413249 fatcat:35qbhenysfhvza2roihx52afuy

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  This copy of my thesis is typeset for online dissemination to improve readability, whereas the thesis submitted to the University of Warwick in support of my application for the degree of Doctor of Philosophy  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4429792 fatcat:qs6yuapx4vdbdmwna7ix7nnwty

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  This copy of my thesis is typeset for online dissemination to improve readability, whereas the thesis submitted to the University of Warwick in support of my application for the degree of Doctor of Philosophy  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4415407 fatcat:6dejwzzpmfegnfuktrld6zgpiq

2022 Roadmap on Neuromorphic Computing and Engineering [article]

Dennis V. Christensen, Regina Dittmann, Bernabé Linares-Barranco, Abu Sebastian, Manuel Le Gallo, Andrea Redaelli, Stefan Slesazeck, Thomas Mikolajick, Sabina Spiga, Stephan Menzel, Ilia Valov, Gianluca Milano (+47 others)
2022 arXiv   pre-print
The aim of this Roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic  ...  Modern computation based on the von Neumann architecture is today a mature cutting-edge science.  ...  concerns are increasingly pressuring our way of life, become an essential component of a sustainable society.  ... 
arXiv:2105.05956v3 fatcat:pqir5infojfpvdzdwgmwdhsdi4
« Previous Showing results 1 — 15 out of 27 results