With the spead of data analytics on the edge, more and more complex machine learning algorithms are being deployed on low power devices. As these algorithms require huge amount of almost non-changing data, the use of non-volatile memories seems to be a solution to the huge leakage induced by SRAM memories.

In this reseach line, we propose to explore the integration of emerging memory technologies in computing architecture and how its affect applications running on such platforms.

Videos






Related Publications

Which Coupled is Best Coupled? An Exploration of AIMC Tile Interfaces and Load Balancing for CNNs
Klein, Joshua Alexander Harrison; Boybat, Irem; Ansaloni, Giovanni; Atienza, David; Marina Zapater Sancho
2024-08-01IEEE Transactions on Parallel and Distributed SystemsPublication funded by Fvllmonti ((FETPROACT))
ALPINE: Analog In-Memory Acceleration with Tight Processor Integration for Deep Learning
Klein, Joshua Alexander Harrison; Boybat, Irem; Qureshi, Yasir Mahmood; Dazzi, Martino; Levisse, Alexandre Sébastien Julien; Ansaloni, Giovanni; Zapater Sancho, Marina; Sebastian, Abu; Atienza Alonso, David
2022-12-09IEEE Transactions on Computers (TC)Publication funded by WiPLASH H2020 (New on-chip wireless communication plane)Publication funded by Compusapien (Next-gen computing systems inspired by the human brain)
Running Efficiently CNNs on the Edge Thanks to Hybrid SRAM-RRAM In-Memory Computing
Rios, Marco Antonio; Ponzina, Flavio; Ansaloni, Giovanni; Levisse, Alexandre Sébastien Julien; Atienza Alonso, David
2021-02-01 DATE 2021 Design, Automation and Test in Europe Conference, Virtual Conference and Exhibition, February 1-5, 2021Publication funded by SNF ML-edge (ML-edge: Enabling Machine-Learning-Based Health Monitoring in Edge Sensors via Architectural Customization)Publication funded by WiPLASH H2020 (New on-chip wireless communication plane)Publication funded by Compusapien (Next-gen computing systems inspired by the human brain)
Write Termination circuits for RRAM : A Holistic Approach From Technology to Application Considerations
Levisse, Alexandre Sébastien Julien; Bocquet, Marc; Rios, Marco Antonio; Alayan, Mouhamad; Moreau, Mathieu; Molas, Gabriel; Vianello, Elisa; Atienza Alonso, David; Portal, Jean-Michel
2020-06-05IEEE AccessPublication funded by Compusapien (Next-gen computing systems inspired by the human brain)Publication funded by WiPLASH H2020 (New on-chip wireless communication plane)
RRAM-VAC: A Variability-Aware Controller for RRAM-based Memory Architectures
Shikhar Tuli, Marco Antonio Rios, Alexandre Sébastien Julien Levisse, David Atienza Alonso
2020-01-13IEEE/ACM Asia and South Pacific Design Automation Conference ASP-DAC 2020Publication funded by Compusapien (Next-gen computing systems inspired by the human brain)
A Hybrid Cache HW/SW Stack for Optimizing Neural Network Runtime, Power and Endurance
Simon, William Andrew; Levisse, Alexandre Sébastien Julien; Zapater Sancho, Marina; Atienza Alonso, David
202028th IFIP/IEEE International Conference on Very Large Scale IntegrationPublication funded by Compusapien (Next-gen computing systems inspired by the human brain)Publication funded by RECIPE H2020 (REliable power and time-ConstraInts-aware Predictive management of heterogeneous Exascale systems)Publication funded by SNF ML-edge (ML-edge: Enabling Machine-Learning-Based Health Monitoring in Edge Sensors via Architectural Customization)Publication funded by WiPLASH H2020 (New on-chip wireless communication plane)
Functionality Enhanced Memories for Edge-AI Embedded Systems
Alexandre Levisse; Marco Rios, William Simon; P-E. Gaillardon, David Atienza
2019-11-25Non-Volatile Memory Technology Symposium 2019Publication funded by Compusapien (Next-gen computing systems inspired by the human brain)
RRAMSpec: A Design Space Exploration Framework for High Density Resistive RAM
Deepak M. Mathew, André Lucas Chinazzo, Christian Weis, Matthias Jung, Bastien Giraud, Pascal Vivet, Alexandre Levisse, Norbert Wehn
2019-08-08 International Conference on Embedded Computer Systems SAMOS 2019: Embedded Computer Systems: Architectures, Modeling, and SimulationPublication funded by Compusapien (Next-gen computing systems inspired by the human brain)
Switching event detection and self-termination programming circuit for energy efficient ReRAM memory arrays
Mouhamad Alayan, Eloi Muhr, Alexandre Levisse, Marc Bocquet, Mathieu Moreau, Etienne Nowak, Gabriel Molas, Elisa Vianello, Jean Michel Portal
2019-04-02IEEE Transactions on Circuits and Systems II 2019Publication funded by Compusapien (Next-gen computing systems inspired by the human brain)
Resistive Switching Memory Architecture Based on Polarity Controllable Selectors
Alexandre Levisse, Pierre-Emmanuel Gaillardon, Bastien Giraud, Ian O'Connor, Jean-Philippe Noel, Mathieu Moreau, Jean-Michel Portal
2018-12-21IEEE Transactions on Nanotechnology 2018Publication funded by Compusapien (Next-gen computing systems inspired by the human brain)