Parallel Numerical Methods and Libraries

for Heterogeneous Multi/Many­cores

Platform heterogeneity is emerging as one of the main characteristics of today's parallel environments where different memory hierarchies and kinds of HW accelerators are more and more present.
For Computational Science and Engineering applications, it is essential that there be available efficient and highly scalable numerical libraries and tools capable to exploit such modern heterogeneous computers. These systems are typically characterized by very different software environments which require new level of flexibility in the algorithms and methods used to achieve adequate level of performance.
Traditional parallel algorithms and programming environments, designed for homogeneous parallel systems, are not fully able to utilize the available high­ performance of today's and forthcoming heterogeneous multi/many­cores.
This conference subject aims to provide a forum for researchers and practionists for discussing recent advances in parallel numerical methods and algorithms and their implementations on current heterogeneous parallel architectures. We solicit research works that address algorithmic design, implementation techniques, performance analysis, integration of parallel numerical methods in science and engineering applications as well as theoretical models aimed at efficiently solving problems on heterogeneous platforms.

Important Dates:

Paper submission: 3rd Nov 2017
Acceptance notification: 1st Dic 2017
Camera ready due: 22nd Dic 2017
Conference: 21st - 23rd Mar 2018


We focus on papers covering various topics of interests that include, but are not limited to the following:
  • Parallel algorithms for efficient problem solving on heterogeneous platforms
  • Numerical linear algebra libraries
  • Heterogeneous parallel programming tools
  • Applications of numerical algorithms in science and engineering
  • Iterative methods and solvers
  • Optimization methods
  • Solution methods for non­linear problems
  • Analysis methods for large data sets
  • Hardware accelerators utilization to solve numerical problem
  • Parallel programming languages, compilers, libraries for accelerated computing
  • GPU algorithms for solving differential equations
  • Multi/Many­cores and GPU tools for parallel solution of large­scale problems

Programme Co-chairs:

Salvatore Cuomo, University of Naples Federico II, Italy

Livia Marcellino, University of Naples Parthenope, Italy

Massimo Torquati, University of Pisa, Italy

Programme Committee:

Jing Gong, PDC Center for High Performance Computing, KTH Royal Institute of Technology, Sweden

Paolo Viviani, Conputer Science Department, University of Turin, Italy

Mencagli Gabriele, Computer Science Department, University of Pisa, Italy

Daniela Di Serafino, Università degli Studi della Campania "L. Vanvitelli", Italy

Mario Cannataro, Università degli Studi Magna Grecia, Catanzaro, Italy

Pierangelo Veltri, Università degli Studi Magna Grecia, Catanzaro, Italy

Jan Lemeire, Department of Electronics and Informatics, Vrije Universiteit Brussel, Belgium

Geraldo Toraldo, University of Naples Federico II, Italy

Gang Mei, China University of Geosciences, Beijing, China

Jose Carlos Valeverde, University of Castilla la Mancha, Albacete, Spain

Gwanggil Jeon, Department of Embedded Systems Engineering, Incheon National University, Incheon, South Korea

Awais Ahmad, Kyungpook National University, South Korea