1st Workshop on Complex Problems over High Performance Computing Architectures (CPHPCA’15)

Focus topic “High Performance Computing Programming” in conjunction with ARCS 2015.

Porto, Portugal, March 24th – 27th, 2015



The main proposal of CPHPCA is to provide a scenario to discuss how problems with important challenges and high computational requirements can be mapped over current and upcoming high performance architectures. CPHPCA will be a part (in conjunction) of the 28th GI/ITG International Conference on Architecture of Computing Systems (ARCS'15).


The importance of high performance computing is continually rising and has emerged as one of the foremost fields of research. This brings up many issues, in form of new network topologies and technologies (fast accessing data), new low-consumption architectures, new programming models, etc. It forces us to adapt our codes or create new ones to take advantages of the latest computational features.


This workshop focuses on the challenges of how to adapt/implement complex and big problems on platforms composed by a high number of cores, dealing with communication, programming, heterogeneous architectures, load balancing, benchmarking, etc. Today, the difficulty of the problems to be implemented is increasing considerably, large data and computational requirements, dynamic behavior, numerical simulations, automatic models, are just a few examples of this kind of problems. Our target is to bridge the gap between the theory of complex problems (computational fluid dynamics, bioinformatics, lineal algebra, big data computing, ...) and high performance computing platforms by proposing advances in programming.



Authors are invited to submit manuscripts that present original and unpublished research in all areas related with programming of complex problems via parallel and distributed processing. Works focusing on emerging architectures and big computing challenges are specially welcome.


Relevant topics include, but are not limited to:


·     New strategies to improve performance.

·     Code adapting to take advantages of lastest features.

·     Numerical modeling and numerical accuracy analysis for complex problems.

·     Communication, synchronization, load balancing.

·     Benchmarking, performance and scalability of algorithms, data structures, tools, programming models ...

·     Analysis and proposing of new programming models.

·     Adaptive self-tuning computing systems.

·     High level abstraction tools ...


Keynote speakers

Manuel Ujaldón (CUDA Fellow): Emerging trends in GPU computing

Since its inception in early 2007, CUDA has transformed the way we understand High Performance Computing through a constant process of innovations and architectural enhancements. Sustainable performance has been based on three basic pillars: Scalable number of cores, memory access and low power. In this talk, we will review these three aspects and analyze what the future will bring us from commercial platforms: Maxwell for cores, Pascal for memory and Tegra for low power devices. The final part will unveil its preliminary potential from the programming perspective of HPC applications.

Luis Miguel Pinho: Challenges for predictable high-performance: the P-SOCRATES approach

The recent technological advancements and market trends are causing an interesting phenomenon towards the convergence of High-Performance Computing and Embedded Computing domains. On one side, new kinds of high-performance applications are being required by markets needing huge amounts of information to be processed within a bounded amount of time. On the other side, embedded systems are increasingly concerned with providing higher performance in real-time, challenging the performance capabilities of current architectures. This convergence, however, raises the challenge about how to guarantee predictably requirements in presence of parallel execution. This talk will address how the P-SOCRATES project is bringing together next-generation many-core accelerators from the embedded computing domain the programming models and techniques from the high-performance computing domain, and real-time methodologies to provide timing predictability.c

Pedro Valero-Lara: PGAS (Unified Parallel C) Model. Case Study: Lattice-Boltzmann Method (LBM-HPC framework)

The main motivation of this talk is the evaluation of the Unified Parallel C (UPC) model. UPC is one of the current models into the so-called Partitioned Global Address Space (PGAS) paradigm. This paradigm attempts to increase the simplicity of codes and achieve a better efficiency and scalability. In particular, we study the lattice-Boltzmann method for fluid simulations (LBM-HPC open-source framework). This method presents several advantages for parallel computing, and so, it is a very appropriate scenario for comparing the fundamental features of UPC model in comparison with classical parallel programming models, such as the hybrid MPI-OpenMP model.


13:30-13:40            Welcome

13:40-14:10            First Keynote: Emerging trends in GPU computing

14:10-14:35            Second Keynote: P-SOCRATES project

14:35-15:00            Break

15:00-15:30            Full-Overlapped Concurrent Kernels (Pedro Valero-Lara, BCAM)

15:30-16:00            Perfomance Optimizations for an Automatic Target Generation Process in Hyperspectral Analysis (Fernando Sierra-Pajuelo, CETA-CIEMAT)

16:00-16:30            Third Keynote: PGAS (Unified Parallel C) Model. Case Study: Lattice-Boltzmann Method

16:30-17:00            Open Discussion, Future Directions, and Closing Remarks

Guidelines for submission of contributions to workshops:

ARCS 2015 Workshop Proceedings will be published through VDE Verlag on CD and online by the IEEE Computer Society through the IEEE Xplore Digital Library. Workshop papers should not exceed 8 pages (full papers) or 4 pages (short papers) in IEEE format A4, templates can be found [here].

By submitting a paper, the authors accept the copyright form.

After the conference, selected papers will be invited for a special issue of the journal Scalable Computing: Practice and Experience.


Important Dates:

Submission:      January 10, 2014 (strict deadline)

               to:      https://easychair.org/conferences/?conf=cphpca15

Notification:     February 5, 2014

Camera-ready:  February 10, 2015

Workshop:        March 24, 2015


Workshop Chairs

P. Valero-Lara, Basque Center for Applied Mathematics, Spain.

F. L. Pelayo, Univ. of Castilla-La Mancha, Spain.

Johan Jansson, Basque Center for Applied Mathematics, Spain. KTH, Royal Institute of Technology, Sweden.


Program Committee

Manuel Ujaldón, Univ. of Málaga, Spain, Univ. of Newcastle, Australia.

Julien Favier, Univ. of Aix-Marseille, France.

José Ignacio Aliaga Estellés, Jaume I Univ., Spain.

J. Daniel García, Carlos III Univ., Spain.

Alistair Revell, Univ. of Manchester, U.K.

Mark Mawson, Science & Technology Facilities Council (STFC), U.K.

Javier García Blas, Carlos III Univ., Spain.

Marco Danelutto, Univ. of Pissa, Italy.

Francisco Igual Peña, Complutense Univ. of Madrid, Spain.

Manuel Prieto Matías, Complutense Univ. of Madrid, Spain.

Miguel Cárdenas, Reseach Center of Environment, Energy and Technology (CIEMAT), Spain.

Abel Francisco Paz Gallardo, CETA-CIEMAT, Spain.

José Luis Sánchez García, Univ. of Castilla-La Mancha, Spain.

Enrique Arias Antuñez, Univ. of Castilla-La Mancha, Spain.

Roberto Uribe-Paredes, Univ. of Magallanes, Chile.

Ricardo J. Barrientos, Center for Modelling and Scientific Computing (CEMCC), Univ. of La Frontera, Chile.