Using dynamic broadcasts to improve task-based runtime performances

A Denis, E Jeannot, P Swartvagher… - Euro-Par 2020: Parallel …, 2020 - Springer
Task-based runtimes have emerged in the HPC world to take benefit from the computation
power of heterogeneous supercomputers and to achieve scalability. One of the main …

Task-based randomized singular value decomposition and multidimensional scaling

E Agullo, O Coulaud, A Denis, M Faverge, A Franc… - 2022 - inria.hal.science
The multidimensional scaling (MDS) is an important and robust algorithm for representing
individual cases of a dataset out of their respective dissimilarities. However, heuristics …

Providing in-depth performance analysis for heterogeneous task-based applications with starvz

VG Pinto, LL Nesi, MC Miletto… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Task-based parallelism has adequately addressed the coding complexity required to fully
exploit the processing power offered by omnipresent hybrid CPU/GPU supercomputers …

A multithreaded communication engine for multicore architectures

F Trahay, E Brunet, A Denis… - 2008 IEEE International …, 2008 - ieeexplore.ieee.org
The current trend in clusters leads towards an increase of the number of cores per node. As
a result, an increasing number of parallel applications is mixing message passing and …

Interferences between communications and computations in distributed HPC systems

A Denis, E Jeannot, P Swartvagher - Proceedings of the 50th …, 2021 - dl.acm.org
Parallel runtime systems such as MPI or task-based libraries provide models to manage
both computation and communication by allocating cores, scheduling threads, executing …

Scalability of the NewMadeleine communication library for large numbers of MPI point-to-point requests

A Denis - 2019 19th IEEE/ACM International Symposium on …, 2019 - ieeexplore.ieee.org
New kinds of applications with lots of threads or irregular communication patterns which rely
a lot on point-to-point MPI communications have emerged. It stresses the MPI library with …

A design-for-test structure for optimising analogue and mixed signal IC test

AH Bratt, AMD Richardson… - … the European Design …, 1995 - ieeexplore.ieee.org
A new Design-for-Test (DfT) structure based on a configurable operational amplifier, referred
to as a" swap amp" is presented that allows access to embedded analogue blocks. The …

Improving reactivity and communication overlap in MPI using a generic I/O manager

F Trahay, A Denis, O Aumage, R Namyst - Recent Advances in Parallel …, 2007 - Springer
MPI applications may waste thousands of CPU cycles if they do not efficiently overlap
communications and computation. In this paper, we present a generic and portable I/O …

An analysis of the impact of multi-threading on communication performance

F Trahay, É Brunet, A Denis - 2009 IEEE International …, 2009 - ieeexplore.ieee.org
Although processors become massively multicore and therefore new programming models
mix message passing and multi-threading, the effects of threads on communication libraries …

A scalable and generic task scheduling system for communication libraries

F Trahay, A Denis - 2009 IEEE International Conference on …, 2009 - ieeexplore.ieee.org
Since the advent of multi-core processors, the physionomy of typical clusters has
dramatically evolved. This new massively multi-core era is a major change in architecture …