Publications associées à Mémoire virtuelle

EdgeAI-Aware Design of In-Memory Computing Architectures

Driven by the demand for real-time processing and the need to minimize latency in AI algorithms, edge computing has experienced remarkable progress. Decision-making AI applications stand out for their heavy reliance on data-centric operations, predominantl ...

EPFL2024

Secure Interface Design Leveraging Hardware/Software Support

Atri Bhattacharyya

Computer systems rely heavily on abstraction to manage the exponential growth of complexity across hardware and software. Due to practical considerations of compatibility between components of these complex systems across generations, developers have favou ...

EPFL2024

Intermediate Address Space: virtual memory optimization of heterogeneous architectures for cache-resident workloads

David Atienza Alonso, Marina Zapater Sancho, Luis Maria Costero Valero, Darong Huang, Qunyou Liu

The increasing demand for computing power and the emergence of heterogeneous computing architectures have driven the exploration of innovative techniques to address current limitations in both the compute and memory subsystems. One such solution is the use ...

2024

Rebooting Virtual Memory with Midgard

Siddharth Gupta

Virtual Memory (VM) is a critical programming abstraction that is widely used in various modern computing platforms. With the rise of datacenter computing and birth of planet-scale online services, the semantic and capacity requirements from memory have ev ...

EPFL2023

One-shot Garbage Collection for In-memory OLTP through Temporality-aware Version Storage

Anastasia Ailamaki, Syed Mohammad Aunn Raza, Periklis Chrysogelos, Angelos Christos Anadiotis

Most modern in-memory online transaction processing (OLTP) engines rely on multi-version concurrency control (MVCC) to provide data consistency guarantees in the presence of conflicting data accesses. MVCC improves concurrency by generating a new version o ...

ACM2023

Bit-Line Computing for CNN Accelerators Co-Design in Edge AI Inference

David Atienza Alonso, Giovanni Ansaloni, Alexandre Sébastien Julien Levisse, Marco Antonio Rios, Flavio Ponzina

By supporting the access of multiple memory words at the same time, Bit-line Computing (BC) architectures allow the parallel execution of bit-wise operations in-memory. At the array periphery, arithmetic operations are then derived with little additional o ...

2023

HPCache: memory-efficient OLAP through proportional caching revisited

Anastasia Ailamaki, Hamish Mcniece Hill Nicholson, Periklis Chrysogelos

Analytical engines rely on in-memory data caching to avoid storage accesses and provide timely responses by keeping the most frequently accessed data in memory. Purely frequency- and time-based caching decisions, however, are a proxy of the expected query ...

Springer2023

When the industry built the city: business archives, memory and community in a contemporary company town

Anna Karla De Almeida Milani

This short essay illustrates the role of the business archive in the transmission and maintenance of contemporary industrial culture, with a focus on the company town of Dalmine. In the context of Dalmine, the business archive managed by the Fondazione Dal ...

EPFL Press English Imprint2023

How to Achieve Large-Area Ultra-Fast Operation of MoS 2 Monolayer Flash Memories?

Aleksandra Radenovic, Andras Kis, Mukesh Kumar Tripathi, Asmund Kjellegaard Ottesen, Yanfei Zhao, Guilherme Migliato Marega, Zhenyu Wang, Hyungoo Ji

Memory devices have returned to the spotlight due to increasing interest in using in-memory computing architectures to make data-driven algorithms more energy-efficient. One of the main advantages of this architecture is the efficient performance of vector ...

2023

Engram cell connectivity as a mechanism for information encoding and memory function

Maurizio Ferdinando Pezzoli

Information derived from experiences is incorporated into the brain as changes to ensembles of cells, termed engram cells, which allow memory storage and recall. The mechanism by which those changes hold specific information is unclear. Here, we test the h ...

Cell Press2023

Leaderless consensus

Rachid Guerraoui, Gauthier Jérôme Timothée Voron, Vincent Gramoli, Mihail Igor Zablotchi, Karolos Antoniadis, Antoine Philippe Matthieu Desjardins

Classic synchronous consensus algorithms are leaderless in that processes exchange proposals, choose the maximum value and decide when they see the same choice across a couple of rounds. Indulgent consensus algorithms are typically leader-based. Although t ...

ACADEMIC PRESS INC ELSEVIER SCIENCE2023

Method for reading and writing unreliable memories and a corresponding memory controller device and memory

Andreas Peter Burg, Reza Ghanaatian Jahromi

A method of accessing a memory space of a memory device with a decoder, the memory space having faults, including the steps of performing a memory access operation by an electronic device to a access a logical memory space of the memory device, and randomi ...

2022

Dynamic Probabilistic Pruning: A General Framework for Hardware-Constrained Pruning at Different Granularities

Alexandre Schmid, Lizeth Gonzalez Carabarin

Unstructured neural network pruning algorithms have achieved impressive compression ratios. However, the resulting-typically irregular-sparse matrices hamper efficient hardware implementations, leading to additional memory usage and complex control logic t ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

AstriFlash: A Flash-Based System for Online Services

Babak Falsafi, Siddharth Gupta, Lei Yan, Mark Johnathon Sutherland, Yunho Oh

Modern datacenters host datasets in DRAM to offer large-scale online services with tight tail-latency requirements. Unfortunately, as DRAM is expensive and increasingly difficult to scale, datacenter operators are forced to consider denser storage technolo ...

2023

Structure-preserving approaches and data-driven closure modeling for model order reduction

Nicolò Ripamonti

In this thesis, we propose model order reduction techniques for high-dimensional PDEs that preserve structures of the original problems and develop a closure modeling framework leveraging the Mori-Zwanzig formalism and recurrent neural networks. Since high ...

EPFL2022

In-Memory Hardware and Architectural Extensions for Workloads Acceleration

William Andrew Simon

Utilization of edge devices has exploded in the last decade, with such use cases as wearable devices, autonomous driving, and smart homes. As their ubiquity grows, so do expectations of their capabilities. Simultaneously, their formfactor and use cases lim ...

EPFL2022

HPCache: Memory-Efficient OLAP Through Proportional Caching

Anastasia Ailamaki, Hamish Mcniece Hill Nicholson, Periklis Chrysogelos

Analytical engines rely on in-memory caching to avoid disk accesses and provide timely responses by keeping the most frequently accessed data in memory. Purely frequency- & time-based caching decisions, however, are a proxy of the expected query execution ...

ACM2022

2022 roadmap on neuromorphic computing and engineering

Srikanth Ramaswamy, Carlo Ricciardi, Elisa Donati, Yihwa Kim, Silvia Tolu, Xuan Li, Abu Sebastian, Emre Neftci, Roberto Galeazzi

Modern computation based on von Neumann architecture is now a mature cutting-edge science. In the von Neumann architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer i ...

IOP Publishing Ltd2022

Tuning paradigm of external stimuli driven electronic, optical and magnetic properties in hybrid perovskites and metalorganic complexes br

Mohammad Khaja Nazeeruddin

We have witnessed a wide range of theoretical as well as experimental investigations to envisage external stimuli induced changes in electronic, optical and magnetic properties in the metal organiccomplexes, while hybrid perovskites have recently joined th ...

ELSEVIER SCI LTD2022

HyperLogLog: Exponentially Bad in Adversarial Settings

Mathilde Aliénor Raynal

Computing the count of distinct elements in large data sets is a common task but naive approaches are memory-expensive. The HyperLogLog (HLL) algorithm (Flajolet et al., 2007) estimates a data set's cardinality while using significantly less memory than a ...

IEEE COMPUTER SOC2022