W05 AxC: 4th Workshop on Approximate Computing

Printer-friendly versionPDF version
Location / Room: 
Room 5

Programme Chair

Alberto Bosio, INL, FR (Contact Alberto Bosio)

General Co-Chairs

Mario Barbareschi, University of Naples Federico II, IT (Contact Mario Barbareschi)
Claus Braun, University of Stuttgart, DE (Contact Claus Braun)

Aim of the Workshop:
the investigation of connections between AxC paradigm and the verification, the test and the reliability of digital
circuits from two points of view:
  1. how the approximate computing paradigm impacts the design and manufacturing flow of integrated circuits;
  2. how the verification, testing and reliability disciplines can be exploited in the approximate computing paradigms.
The organizing committee of AxC19 is proud to announce two keynote speeches, which will be given by
  • Prof. Kaushik Roy, title: Re-Engineering Computing with Neuro-Inspired Learning: Devices, Circuits, Systems. and Approximations
  • Dr. Cristiano Malossi, title: Transprecision Computing for Energy-Efficiency
For further details about Workshop program, keynotes and other information, please visit the AxC19 website at: http://embedded.unina.it/AxC19
Submission website is already available: https://easychair.org/conferences/?conf=axc19
For this edition, authors of accepted papers will be invited to submit their work for a special issue on
"Advancing on Approximate Computing: Methodologies, Architectures and Algorithms", planned to be published
onto Future Generation Computer Systems (Q1, IF 4.639, H index 85).
You can find details about AxC19 from the CfP available at http://embedded.unina.it/AxC19/call-for-paper/


07:30W05.1Registration Desk opens
08:30W05.2Opening Session
09:00W05.3Keynote 1

Keynote "Transprecision Computing for Energy-Efficiency" by dr. Cristiano Malossi from IBM Research of Zurich

10:00W05.4Coffee Break
10:30W05.5Technical Session 1

Resilience-based Mapping of Deep Neural Network Operations to Approximate Computing Units
Christoph Schorn (Robert Bosch GmbH), Matthias Roth (Esslingen University of Applied Sciences), Andre Guntoro (Robert Bosch GmbH) and Gerd Ascheid (RWTH Aachen University)

Noise Budgeting in Multiple-Kernel Word-Length Optimization
Van-Phu Ha (University of Rennes 1), Tomofumi Yuki (University of Rennes 1) and Olivier Sentieys (University of Rennes 1)

Reliability Evaluation of Mixed-Precision Architectures
Paolo Rech (UFRGS), Fernando Fernandes dos Santos (UFRGS), and Daniel Oliveira (UFRGS)

Approximate Computing of Transcendental Functions Applied to Artificial Neural Networks
Xin Fan (IDS, RWTH Aachen Univ), Arthur Ruder (IDS, RWTH Aachen Univ), Cecilia Höffler (IDS, RWTH Aachen Univ), and Tobias Gemmeke (IDS, RWTH Aachen Univ)

12:00W05.6Lunch break
13:00W05.7Invited Talk

Approximate Computing in HPC: building from ground up
Alessandro Cilardo (Università degli Studi di Napoli Federico II)

13:30W05.8Keynote 2

Keynote : Re-Engineering Computing with Neuro-Inspired Learning: Devices, Circuits, Systems. and Approximations" by prof. Kaushik Roy from School of Electrical and Computer Engineering of Purdue University.

14:30W05.9Coffee Break
15:00W05.10Technical Session 2

Targeting Approximation through Data Lifetime: A Quest for Optimization Metrics
Alessandro Savino (Politecnico di Torino), Michele Portolan (Univ. Grenoble Alpes, TIMA), Stefano Di Carlo (Politecnico di Torino) and Regis Leveugle (Univ. Grenoble Alpes, TIMA)

Jump Search: A Fast Technique for the Synthesis of Approximate Circuits
Linus Witschen (Paderborn University), Hassan Ghasemzadeh Mohammadi (Paderborn University), Matthias Artmann (Paderborn University) and Marco Platzner (Paderborn University)

An Approximate Communication Technique for Energy Efficient Networks on Chip
Giuseppe Ascia (University of Catania), Vincenzo Catania (University of Catania), John Jose (Indian Institute of Technology Guwahati), Salvatore Monteleone (University of Catania), Maurizio Palesi (University of Catania) and Davide Patti (University of Catania)

Adjustable Precision Computing Using Redundant Arithmetic
Ali Skaf (TIMA), Mona Ezzadeen (TIMA), Mounir Benabdenbi (TIMA) and Laurent Fesquet (TIMA)

Towards One Million Component Library of Approximate Circuits
Lukas Sekanina (Brno University of Technology), Zdenek Vasicek (Brno University of Technology) and Vojtech Mrazek (Brno University of Technology)

Exploiting Approximate Computing to Increase System Lifetime
E. Sanchez (Politecnico di Torino), P. Bernardi (Politecnico di Torino) and W. J. Perez-Holguin (Universidad Pedagógica y Tecnológica de Colombia)

Approximate Computing for Sizing Hidden Layer in CNN
Stefano Marrone (University of Naples Federico II) and Carlo Sansone (University of Naples Federico II)