Name: Distributed Computing Laboratory, EPFL
Type: Organization
Bio: We are the Distributed Computing Lab (DCL) @ EPFL. Our research is about the theory and practice of distributed computing.
Location: Lausanne, Switzerland
Blog: http://dcl.epfl.ch
Distributed Computing Laboratory, EPFL's Projects
Byzantine-resilient distributed SGD with TensorFlow.
ASCYLIB (with OPTIK) is a concurrent-search data-structure library with over 40 implementantions of linked lists, hash tables, skip lists, binary search trees, queues, and stacks.
Porting ASCYLIB to C++
An attempt to rewrite ASCYLIB (https://github.com/LPD-EPFL/ASCYLIB) in Go
Distributed Momentum for Byzantine-resilient Stochastic Gradient Descent (ICLR 2021)
The skeleton code for the CA15 class project on the design of a very simple STM
CLHT is a very fast and scalable (lock-based and lock-free) concurrent hash table with cache-line sized buckets.
The official repo of the Distributed Algorithm course (CS451) project - Fall 2023
Concurrent Algorithms Project 2021
Concurrent Algorithms Project 2022
Concurrent Computing Project 2023
Distributed Algorithms, Fall 2015. Code skeleton for the bonus project, Student Simple Storage Service (S4).
Differential Privacy and Byzantine Resilience in SGD: Do They Add Up? (PODC 2021)
DSig: Breaking the Barrier of Signatures in Data Centers
Artifacts for DSig: Breaking the Barrier of Signatures in Data Centers
FeGAN: Scaling Distributed GANs
A persistent LSM key-value store. FloDB is designed to scale with the number of threads and memory size.
System Support for Byzantine Machine Learning
just a pointer saying that Krum's code in the Aggregathor repo to reduce emails
memory management and utilities for concurrent data structures for non-volatile ram
LOCKIN is a locking library with various lock algorithms implemented in header files for ease of use
MCTOP: A Multi-Core Topology Abstraction
memcached using the CLHT hash table
Mu: Microsecond Consensus for Microsecond Applications
Distributed transactions
The Probabilistic Fault Tolerance of Neural Networks in the Continuous Limit, El-Mahdi El-Mhamdi, Rachid Guerraoui, Andrei Kucharavy, Sergei Volodin
jemalloc for non-volatile ram with per-memory-area tracking
lock-free concurrent data structures for non-volatile RAM