Process-in-process: techniques for practical address-space sharing

A Hori, M Si, B Gerofi, M Takagi, J Dayal… - Proceedings of the 27th …, 2018 - dl.acm.org
The two most common parallel execution models for many-core CPUs today are
multiprocess (eg, MPI) and multithread (eg, OpenMP). The multiprocess model allows each …

Communication-aware task scheduling strategy in hybrid MPI+ OpenMP applications

R Pereira, A Roussel, P Carribault, T Gautier - OpenMP: Enabling Massive …, 2021 - Springer
While task-based programming, such as OpenMP, is a promising solution to exploit large
HPC compute nodes, it has to be mixed with data communications like MPI. However …

Improving MPI communication overlap with collaborative polling

S Didelot, P Carribault, M Pérache, W Jalby - Computing, 2014 - Springer
With the rise of parallel applications complexity, the needs in term of computational power
are continually growing. Recent trends in High-Performance Computing (HPC) have shown …

Modeling, prediction and optimization of energy consumption of MPI applications using SimGrid

F Heinrich - 2019 - theses.hal.science
The High-Performance Computing (HPC) community is currently undergoingdisruptive
technology changes in almost all fields, including a switch towardsmassive parallelism with …

Hierarchical local storage: Exploiting flexible user-data sharing between mpi tasks

M Tchiboukdjian, P Carribault… - 2012 IEEE 26th …, 2012 - ieeexplore.ieee.org
With the advent of the multicore era, the number of cores per computational node is
increasing faster than the amount of memory. This diminishing memory to core ratio …

Real-time control optimization of water distribution system with storage

M Sunela - 2017 - researchportal.tuni.fi
Real-Time Control Optimization of Water Distribution System with Storage Page 1 THESIS
ON CIVIL ENGINEERING F69 Real-Time Control Optimization of Water Distribution System …

Static/Dynamic Analyses for Validation and Improvements of Multi-Model HPC Applications.

E Saillard - 2015 - theses.hal.science
Supercomputing plays an important role in several innovative fields, speeding up
prototyping or validating scientific theories. However, supercomputers are evolving rapidly …

Efficient Use of Task-based Parallelism in HPC Parallel Applications

R Pereira - 2023 - theses.hal.science
Numerical simulations are a powerful tool for scientific research and the industry, considered
as the third pillar of science by scientists. High-Performance Computing (HPC) is the science …

Implementaçao de openmp para o sistema operacional nanvix em risc-v

RA Souza Filho - 2022 - bdtd.ibict.br
Programar sistemas embarcados com múltiplos núcleos de processamento não é uma
tarefa trivial pois, em muitos casos, esses sistemas não têm suporte a interfaces de …

MATE, a Unified Model for Communication-Tolerant Scientific Applications

SM Martin, SB Baden - … Workshop on Languages and Compilers for …, 2018 - Springer
We present MATE, a model for developing communication-tolerant scientific applications.
MATE employs a combination of mechanisms to reduce or hide the cost of network and intra …