21–23 Mar 2023
LaBRI
Europe/Paris timezone

HomE: Enabling Homomorphic Encryption of DL, a (recently started) ERC Consolidator Grant

22 Mar 2023, 14:10
10m
LaBRI Amphi (LaBRI)

LaBRI Amphi

LaBRI

Short talk Advanced architectures Short Talks on Advanced Architectures

Speaker

ANTONIO PENA (Barcelona Supercomputing Center (BSC))

Description

Deep learning (DL) is widely used to solve classification problems previously unchallenged, such as face recognition, and presents clear use cases for privacy requirements. Homomorphic encryption (HE) enables operations upon encrypted data, at the expense of vast data size increase. RAM sizes currently limit the use of HE on DL to severely reduced use cases. Recently emerged persistentmemory technology (PMEM) offers larger-than-ever RAM spaces, but its performance is far from that of customary DRAMtechnologies.

This project aims to spark a new class of system architectures for encrypted DL workloads, by eliminating or dramatically reducing data movements across memory/storage hierarchies and network, supported by PMEM technology, overcoming its current severe performance limitations. HomE proposes a holistic approach yielding highly impactful outcomes that include novel comprehensive performance characterisation, innovative optimisations upon current technology, and pioneering hardware proposals.

Primary author

ANTONIO PENA (Barcelona Supercomputing Center (BSC))

Presentation materials

There are no materials yet.