Seventh Workshop on Models, Algorithms and Methodologies

for Hybrid Parallelism in new HPC Systems (MAMHYP-24)

Ostrava, Czech Republic, September 8-11, 2024

jointly with the

15th International Conference on Parallel Processing

and Applied Mathematics PPAM 2022

(https://ppam.edu.pl/)

Background

MAMHYP-24 is the seventh workshop following those held in Torun, Warsaw, Krakow, Lublin, Bialystok and Gdansk in 2011, 2013, 2015, 2017, 2019 and 2022, respectively, in conjunction with the PPAM conferences. Despite the progress made in the field, developing efficient algorithms for HPC systems with multiple forms of parallelism remains a challenging problem.

More precisely, from an architectural perspective, a High-Performance Computing (HPC) system can be characterized by a hybrid multi-level structure: at the highest level, several systems are interconnected by geographic networks (System level); an intermediate level consists of nodes within a single system communicating through dedicated fast networks or high-performance switches (Node level); finally, at the lowest level, there are multiple computing elements, including computing cores and graphic accelerators, sharing resources within a single CPU (Core level).

These architectural levels exhibit distinct features, necessitating different algorithmic development methodologies. Consequently, the development of algorithms and scientific software for these systems requires a judicious combination of methodologies to address the diverse forms of parallelism corresponding to each architectural level. The overarching objective is to develop hybrid and hierarchical algorithms capable of leveraging the underlying platform. Key challenges in this domain include managing extensive degrees of parallelism stemming from numerous computing units, addressing the heterogeneity of these devices, and integrating various forms of parallelism into a single algorithm. These issues are primarily investigated to achieve exascale performance and, on another front, to confront new forms of distributed computing such as cloud computing, edge computing, and their intersection with HPC.

This workshop specifically targets Models, Methodologies, Algorithms, and Environments for harnessing all forms of parallelism and their amalgamation at all levels within emerging HPC systems, aiming to consolidate the current state of knowledge in the field.

The topics include, but are not limited, to:

Hybrid and hierarchical based parallel algorithms
Multi-core and many-core parallel computing, GPU computing
Architecture-aware parallelization on HPC platforms
Auto tuning techniques for heterogeneous and parallel environments
Performance analysis
Techniques for multi-/many-core platforms, NUMA architectures, or accelerator components
Task scheduling and load balancing among computing elements
Synchronization and access to shared resources
Multilevel cache management
Computational kernels for scientific computing and applications
Performance and scalability models
Tools and programming environments supporting efficient usage of multilevel parallelism.
Resources virtualization
High Performance cloud/edge/fog computing
Intra/Infra Virtual machines high performance communications algorithms
Fault tolerant implementation

Paper Submission and Publication

All rules of paper submission of the PPAM conference apply. In particular:

Papers will be refereed and accepted on the basis of their scientific merit and relevance to the
Workshop topics.

Papers presented at the Workshop will be included into the conference proceedings and
published after the conference by Springer in the LNCS series.

Before the Workshop, abstracts of accepted papers will be posted on this site.

Authors should submit papers (PDF files) using the online submission tool

Papers are not to exceed 14 pages (LNCS style)

Final camera-ready versions of accepted papers will be required by October 31, 2024.

Dates

Submission of Papers: May 17, 2024 (extended)
Notification of Acceptance: June 7, 2024
Conference: September 8-11, 2024
Camera-Ready Papers: October 31, 2024

Workshop Organizers

Giuliano Laccetti (Univ. of Naples Federico II, Italy) giuliano.laccetti@unina.it
Marco Lapegna (Univ. of Naples Federico II, Italy) marco.lapegna@unina.it
Valeria Mele (Univ. of Naples Federico II, Italy) valeria.mele@unina.it
Raffaele Montella (Univ. of Naples Parthenope, Italy) raffaele.montella@uniparthenope.it
Diego Romano (National Research Council, Italy) diego.romano@cnr.it

Program committee

- Diana Di Luccio University of Naples Parthenope, Italy

- Javier Garcia Blas, University Carlos III, Madrid Spain

- Fabio Gianpaolo, University of Naples Federico II, Italy

- Sokol Kosta, Aalborg University Copenhagen, Denmark
- Giuliano Laccetti, University of Naples Federico II, Italy, and INFN (Nuclear Physics National Institute), Italy

- Marco Lapegna, University of Naples Federico II, Italy, and INFN (Nuclear Physics National Institute), Italy
- Valeria Mele, University of Naples Federico II, Italy

- Raffaele Montella, University of Naples Parthenope, Italy

- Gloria Ortega, University of Almeria, Spain

- Edoardo Prezioso, University of Naples, Federico II, Italy

- Diego Romano, National Research Council, Italy
- Guido Russo, University of Naples Federico II, Italy

- Lucas Szustak, Polish Academy of Sciences, Poland

- Roman Wyrzykowski, Czestochowa University of Technology, Poland

Special Event

The 2024 edition of the MAMHYP workshop will host a dissemination event of the activities of the University of Naples Federico II Dept. of Mathematics related to the Pnrr National Center �HPC, Big Data and Quantum Computing�, Spoke 1-Future HPC and Big Data (https://www.supercomputing-icsc.it/spoke-1-future-hpc-big-data/). This activity is within the Collaboration Project between CINI/University of Naples Parthenope and University of Naples Federico II Dept. of Mathematics, led respectively by Raffaele Montella and Marco Lapegna.

Special Issue on Scientific Journal

Authors of selected papers from MAMHYP24 will be invited to submit an extended version of their papers to a Special Issue of the journal "Concurrency and Computation: Practice and Experiences." Other high-quality papers that fit the Special Issue topics are also welcome for submission.