Machine Learning to Design an Auto-tuning System for the Best Compressed Format Detection for Parallel Sparse Computations

Autor: Olfa Hamdi-Larbi, Ichrak Mehrez, Thomas Dufaud

Publikováno v: Parallel Processing Letters
Parallel Processing Letters, World Scientific Publishing, 2021, ⟨10.1142/S0129626421500195⟩
Parallel Processing Letters, 2021, 31 (04), pp.2150019. ⟨10.1142/S0129626421500195⟩

International audience; Many applications in scientific computing process very large sparse matrices on parallel architectures. The presented work in this paper is a part of a project where our general aim is to develop an auto-tuner system for the s

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f1cfb5f2f3585dc8aaff7064334497a
https://hal.archives-ouvertes.fr/hal-03429364

MYX: Runtime correctness analysis for multi-level parallel programming paradigms

Autor: Christian Terboven, Matthias S. Müller, Nahid Emad, Taisuke Boku, Joachim Protze, Serge G. Petiton, Thomas Dufaud, Hitoshi Murai, Miwako Tsuji

Publikováno v: Software for Exascale Computing-SPPEXA 2016-2019
Hans-Joachim Bungartz; Severin Reiz; Benjamin Uekermann; Philipp Neumann; Wolfgang E. Nagel. Software for Exascale Computing-SPPEXA 2016-2019, 136, Springer International Publishing, pp.545-567, 2020, Lecture Notes in Computational Science and Engineering, 978-3-030-47956-5 (e-book). ⟨10.1007/978-3-030-47956-5_18⟩
Software for Exascale Computing-SPPEXA 2016-2019 ISBN: 9783030479558
Software for Exascale Computing
Software for Exascale Computing-SPPEXA 2016-2019, 136, Springer International Publishing, pp.545-567, 2020, Lecture Notes in Computational Science and Engineering, ⟨10.1007/978-3-030-47956-5_18⟩

International audience; In recent years the increasing compute power is mainly provided by rapidly increasing concurrency. Therefore, the HPC community is looking for new parallel programming paradigms to make the best use of current and upcoming mac

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2d2c3ba8690eb19aa314ae9f9858e6f
https://hal.science/hal-03429330/document

Size effect on the three state thermal hysteresis of a 2D spin crossover nanoparticles

Autor: Camille Harlé, Thomas Dufaud, Devan Sohier, Salah Eddine Allal, J. Linares, Pierre-Richard Dahoo

Publikováno v: Journal of Physics: Conference Series
Journal of Physics: Conference Series, 2018, 1141, pp.012158. ⟨10.1088/1742-6596/1141/1/012158⟩
Journal of Physics: Conference Series, IOP Publishing, 2018, 1141, pp.012158. ⟨10.1088/1742-6596/1141/1/012158⟩

In this report first we show, in a framework of the Ising-like model, a numerical simulation of a typical two step thermal transition obtained for a square lattice 12x12: a "first-step hysteresis" for a high spin fraction Nhs between 0 - 0,5 and at a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a450729ca52638acb196ca3aacda7abb
https://hal.science/hal-01965090/document

Machine Learning for Optimal Compression Format Prediction on Multiprocessor Platform

Autor: Olfa Hamdi-Larbi, Nahid Emad, Ichrak Mehrez, Thomas Dufaud

Publikováno v: 2018 International Conference on High Performance Computing & Simulation (HPCS)
2018 International Conference on High Performance Computing & Simulation (HPCS), Jul 2018, Orleans, France. ⟨10.1109/HPCS.2018.00047⟩
HPCS

International audience; Many scientific applications handle large size sparse matrices which can be stored using special compression formats to reduce memory space and processing time. The choice of the Optimal Compression Format (OCF) is a critical

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d38fba93689bc22fdbc521dffb858275
https://hal.science/hal-01927621

Understanding the Performances of Sparse Compression Formats Using Data Parallel Programming Model

Autor: Ichrak Mehrez, Olfa Hamdi-Larbi, Nahid Emad, Thomas Dufaud

Publikováno v: 2017 International Conference on High Performance Computing & Simulation (HPCS), Jul 2017, Genoa, France. IEEE
2017 International Conference on High Performance Computing & Simulation (HPCS), Jul 2017, Genoa, France. IEEE, Jul 2017, Genoa, Italy. ⟨10.1109/HPCS.2017.103⟩
HPCS
HPCS 2017-International Conference on High Performance Computing & Simulation
HPCS 2017-International Conference on High Performance Computing & Simulation, Jul 2017, Gênes, Italy. pp.667-674, ⟨10.1109/HPCS.2017.103⟩

International audience; Several applications in numerical scientific computing involve very large sparse matrices with a regular or irregular sparse structure. These matrices can be stored using special compression formats (storing only non-zero elem

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cbace05aad3a77e7745a4785ef4a4531
https://hal.archives-ouvertes.fr/hal-01726654