2022 Program

SELSE 2022 technical program

N.B. all timeslots are in PDT time

Change Timezone
Change Timezone
Collapse/Expand all sessions
Thursday May 19, 2022
Collapse/Expand day's sessions

07:00

Welcome session

Welcome message from the chairsStefano Di Carlo, Paolo Rech, Peter Hochschild, Marcello Traiola

07:10

Session 1: "Silent data corruption detection and prevention at-scale"

Moderator: Peter Hochschild, Google
  • SiliFuzz: Fuzzing CPUs by proxy
    Kostya Serebryany, Maxim Lifantsev, Konstantin Shtoyk, Doug Kwan and Peter Hochschild
  • Detection and Prevention of Silent Data Corruption in an Exabyte-scale Database System
    David Bacon
  • Detecting silent data corruptions in the wild
    Harish Dattatraya Dixit, Laura Boyle, Gautham Vunnam, Sneha Pendharkar, Matt Beadon and Sriram Sankar

08:10

Keynote 1

Moderator: Paolo Rech, University of Trento
Title Building Quantum System Software for Unreliable Quantum ComputersDevesh Tiwari, Northeastern University, USA

Abstract: The field of quantum computing has enjoyed extraordinary advances in the last two decades, including the physical implementation and experimental demonstration of medium-scale quantum computers. While these advances continue to be celebrated widely, computational scientists continue to struggle to make meaningful use of existing quantum computers - aka Noisy Intermediate-Scale Quantum (NISQ) machines. This is because NISQ devices are highly error-prone and produce output that can be far from the correct output of the quantum algorithms. If you ever wrote a quantum program and found that your quantum program produced output was not what you had excepted, you are the perfect audience for this talk. In this talk, I will primarily discuss the role of quantum system software in making erroneous quantum devices more usable and meaningful. If you have not written a quantum program yet and you love detecting & correcting errors, I’ll show you that there is a whole exciting universe of quantum computers waiting for you!

Author's bio: Professor Devesh Tiwari is a researcher and educator at Northeastern University where he directs the Goodwill Computing Lab. His group innovates new solutions to make large-scale classical computing systems and quantum computing systems more efficient, reliable, and cost-effective. Before joining the Northeastern faculty, Devesh was a staff scientist at the United States Department of Energy (DOE) Oak Ridge National Laboratory.For his teaching and mentoring contributions, he was awarded the Professor of the Year by the Northeastern University chapter of the IEEE Eta Kappa Nu honor society. His research group, led by his excellent PhD students, has lowered the barrier to entry and accelerated the R&D efforts in multiple emerging computer systems areas including quantum system software, serverless computing, and AI-driven data center optimizations, via open-sourcing novel software artifacts and datasets. He has introduced several novel peer-review elements in the computer systems community in his role as the program co-chair/track co-chair for ICDCS, IISWC, IPDPS, and ICCD. Most recently, he was the Technical Program Committee Co-Chair for HPDC’22 and is slated to be the overall Technical Program Committee Co-Chair for IPDPS’23. He is an Associate Editor for Transactions of Parallel & Distributed Computing (TPDS), Transactions of Storage (ToS), and Journal of Parallel & Distributed Computing (JPDC). He was recognized with the TPDS Editorial Excellence Award for his exceptional contributions to the TPDS journal as an editor. Devesh's webpage

08:50

Break

09:05

Session 2: "Reliability assessment, from platforms to memory"

Moderator: Angeliki Kritikakou, University of Rennes, IRISA
  • Understanding GPU Application Vulnerability Across Program Lifetime
    Hao Qiu, Semiu Olowogemo, Bor-Tyng Lin, Daniel Limbrick and William Robinson
  • Reliability of Google’s Tensor Processing Units for Convolutional Neural Networks
    Rubens Luiz Rech Junior and Paolo Rech
  • Effects of High Energy Protons on a Self-Refresh DRAM
    Lucas Matana Luza, Carolina Imianosky, André Martins Pio de Mattos, Douglas Almeida dos Santos, Daniel Söderström and Luigi Dilillo
Friday May 20, 2022
Collapse/Expand day's sessions

07:00

Session 3: "The blurred boundaries between reliability and security"

Moderator: Marcello Traiola - Inria Rennes, IRISA
  • Towards the Integration of Reliability and Security Mechanisms to Enhance the Fault Resilience of Neural Networks
    Nikolaos Deligiannis, Riccardo Cantoro, Matteo Sonza Reorda, Marcello Traiola and Emanuele Valea
  • CAN-MM: Multiplexed Message Authentication Code for Controller Area Network message authentication in road vehicles
    Franco Oberti, Alessandro Savino, Ernesto Sanchez, Filippo Parisi, Stefano Di Carlo and Paolo Casasso
  • Using analog scrambling circuits for automotive sensor integrity and authenticity
    Cristiano Chenet, Alessandro Savino and Stefano Di Carlo

08:00

Keynote 2

Moderator: Stefano Di Carlo, Politecnico di Torino
Title - "Hot Topic at Semiconductor Research Corporation (SRC): Real-Time Anomaly Detection and Mitigation to Improve Hardware Security and Robustness"John Oakley, Science Director, Semiconductor Research Corporation (SRC), USA

Abstract: Artificial Intelligence (AI) is a major workload in many of today’s systems. Anomaly detection to promote functional safety is a critical requirement of many AI powered systems. Machine Learning (ML) systems are trained by very large data sets which could never be exhaustive. Small perturbations to an image can sway neural network models into a wrong conclusions. Research has shown that a well-placed sticker can change the perception of a stop sign to a Speed Limit sign. There is an implicit trust assumption for object detection in autonomous vehicles. Anomaly detection can also be used to identify security attacks or employ feature analysis for contextual authentication. Detecting these anomalies in real-time is just the first step, systems will need to be mitigate these to maintain security and robust operations over the life of the system. Robust AI/ML models and reasoning methods will be used to predict attacks and guide defense mechanisms. Semiconductor Research Corporation (SRC) research in anomaly detection and mitigation which spans AI hardware, automotive electronics, functional safety, and hardware security. As detailed in the Decadal Plan for Semiconductors, improving the trustworthiness and robustness of systems are daunting challenges which needs significant research for years and decades to come.

Author's bio: John Oakley, a Science Director at SRC, is focused on leading Hardware Security (HWS), Packaging (PKG), Automotive Electronics (Auto), AI Hardware and Intelligent Cognitive Assistant (ICA) research. John works closely with government, industry, and university partners to advance these research topics. John was formerly a RF Control Architect at Intel Corporation, has over 20 years of successful digital design experience at Motorola, Freescale, Fujitsu, and Intel. His willingness to help and mentor, in addition to his deep technical expertise, make him a key member of Intel’s technical team. John has 14 issued patents and has developed more than 55 successful integrated devices, several of which have shipped in high volumes. He has worked in numerous digital system spaces, and is presently in the transceiver and modem fields focusing on the control planes of cellular platforms. An expert in 3GPP standards and their application to real world devices, John was Vice Chairman of the MIPI Working Group RFFE and a member of the MIPI Working groups RIO and TSG. Beyond the work environment, John is a Ruby Life Master at Bridge and is avid player of strategy and role playing games. John's webpage

08:40

Break

08:55

Session 4: "Overhead reduction: from neural networks data to OS and NoC hardening"

Moderator: Bastien Deveautour, INL, CPE Lyon
  • Spiking Neural Network Data Reduction via Interval Arithmetic
    Sepide Saeedi, Alessio Carpegna, Alessandro Savino and Stefano Di Carlo
  • Tolerating Errors in NoC: A Lightweight Region-Based Fault-Mitigation Method
    Romain Mercier, Cédric Killian, Angeliki Kritikakou, Youri Helen and Daniel Chillet
  • Reliability assessment of Real-time Operating System in Embedded Systems
    Alberto Bosio, Maurizio Rebaudengo and Alessandro Savino

09:55

Closing session

Closing remarks from the chairsStefano Di Carlo, Paolo Rech, Peter Hochschild, Marcello Traiola

N.B. all timeslots are in PDT time - Change Timezone at the top of the page