HPCS2017 Keynotes

The International Conference on High Performance Computing & Simulation

(HPCS 2017)

The 15th Annual Meeting

July 17 – 21, 2017

The Grand Hotel Savoia

Genoa, Italy

http://hpcs2017.cisedu.info or http://cisedu.us/rp/hpcs17

HPCS 2017 KEYNOTES

Tuesday Keynote: HPC, Cloud and Artificial Intelligence

Bill McColl

Chief Technology Officer, Parallel Computing

Huawei Research, Paris, France

NOTES (See file below. Forthcoming)

Wednesday Keynote: The Effect of Hierarchical Memory on the Design

of Parallel Applications and the Expression of Parallelism

David W. Walker

Cardiff School of Computer Science and Informatics

Cardiff University, U.K.

NOTES (See file below)

Thursday Keynote: Challenges of Exascale Computing

Paul C. Messina

Argonne National Laboratory and ALD Exascale Project Director

Illinois, USA

NOTES (See file below)

HPCS Plenary Talk: Research and Education Networks as an Enabler

for Scientific Computing: The GARR Vision

Federico Ruggieri

Director of Research at the National Institute for Nuclear and Particle Physics (INFN)

and Director of GARR, the Italian Research & Education Network, Rome, Italy

NOTES (See file below)

______________________________________________________________________

Tuesday Keynote: HPC, Cloud and Artificial Intelligence

Bill McColl

Chief Technology Officer, Parallel Computing

Huawei Research, Paris, France

ABSTRACT

High Performance Computing has been extremely successful by focusing on how best to support software developers that have the technical skills required to design highly parallel algorithms, to optimize data partitioning and load balancing, to minimize communications and synchronization, and to do all of the other things necessary to achieve the highest possible performance on large-scale dedicated clusters and supercomputers with CPUs, GPUs, advanced networking, and highly parallel file systems. In HPC, where choices have to be made between, for example, high performance and fault tolerance, the tendency has almost always been to focus on the former.

Big Data, AI and Cloud Computing have also been extremely successful in recent years by focusing on exactly the opposite community, those software developers who do not have the technical skills, or motivation, required for HPC. In Big Data, AI and Cloud Computing, many/most of the key design decisions regarding parallelization, data partitioning, load balancing, communications, synchronization, redundancy and fault tolerance are automated, and the key objective is to enable developers to produce applications with a minimum of effort, applications that will typically be run on low-cost pools of commodity cloud hardware resources, that will often be virtualized or based on containers.

In this talk, I will describe some of the challenges in bringing high performance to big data, AI and cloud computing, and describe some new approaches to this problem. As AI moves to the center of computing, and "AI-as-a-Service" becomes a major new business opportunity, this area will become more and more important. If HPC also moves to a new era in which cost-effective "cloudonomics" matters more, then it will become important there too.

SPEAKER BIOGRAPHY

Wednesday Keynote: The Effect of Hierarchical Memory on the Design

of Parallel Applications and the Expression of Parallelism

David W. Walker

Cardiff School of Computer Science and Informatics

Cardiff University, U.K.

ABSTRACT

Efficient access to hierarchical memory is essential in achieving good performance in both sequential and parallel applications. This presentation will consider the interplay of application design, the expression of parallelism, and data movement across hierarchical memory. The talk will include a brief survey of parallel programming paradigms and algorithms, and will discuss how these might change in the era of exascale computing. Block and tile algorithms will be described as techniques for improving memory performance, and work on the use of space-filling curves to improve locality of reference will be presented.

SPEAKER BIOGRAPHY

______________________________________________________________________

Bill McColl joined Huawei’s Paris Research Center in 2014. Bill was previously Professor of Computer Science at Oxford University, Head of Research in Parallel Computing at Oxford, and Chairman of the Faculty of Computer Science. He also founded and led Oxford Parallel - a major center for research on industrial and business applications of parallel computing at Oxford. In his research, he has worked on many areas of parallel algorithms and software systems. He developed the BSP approach to parallel computing, along with Les Valiant of Harvard. BSP is now used at most of the major global web companies (Google, Facebook, Microsoft,…) for their massively parallel graph computing and analytics. BSP also powers leading-edge massively parallel machine learning algorithms and software. At Huawei he currently leads teams in China and France that are developing new parallel algorithms and software platforms for cloud analytics and AI.

Thursday Keynote: Challenges of Exascale Computing

______________________________________________________________________

David W. Walker is Professor of High Performance Computing in the School of Computer Science and Informatics at Cardiff University. Professor Walker has conducted research into parallel and distributed applications and software environments for the past 30 years and has published over 140 papers on these subjects. Before joining Cardiff University, Professor Walker spent ten years in the United States at the California Institute of Technology, the University of South Carolina, and Oak Ridge National Laboratory. During this time, he was involved in the specification of MPI and the development of the ScaLAPACK software library. Professor Walker is co-editor of Concurrency and Computation: Practice and Experience, a principal editor of Computer Physics Communications, and serves on the editorial boards of the International Journal of High Performance Computing Applications, and the Journal of Computational Science.

Paul C. Messina

Argonne National Laboratory and ALD Exascale Project Director

Illinois, USA

ABSTRACT

The U.S. Department of Energy established in 2016 the Exascale Computing Project (ECP) -- a joint project of the DOE Office of Science (DOE-SC) and the DOE National Nuclear Security Administration (NNSA) -- that will result in a capable exascale ecosystem and prepare mission critical scientific and engineering applications to take advantage of that ecosystem.

This presentation will describe the goals of the ECP initiative, its plans for achieving them, and its current status, with special emphasis on the challenges to be overcome.

SPEAKER BIOGRAPHY

______________________________________________________________________

Dr. Paul Messina is Advisor to the Associate Laboratory Director and Laboratory on Exascale and Argonne Distinguished Fellow at Argonne National Laboratory. His current role is Project Director for the U.S. DOE Exascale Computing Project, a multi-laboratory project. During 2008-2015 he served as Director of Science for the Argonne Leadership Computing Facility and in 2002-2004 as Distinguished Senior Computer Scientist at Argonne and as Advisor to the Director General at CERN (European Organization for Nuclear Research). From 1987-2002, Dr. Messina served as founding Director of California Institute of Technology's (Caltech) Center for Advanced Computing Research, as Assistant Vice President for Scientific Computing, and as Faculty Associate for Scientific Computing, Caltech. During a leave from Caltech in 1999-2000, he led the DOE-NNSA Accelerated Strategic Computing Initiative.

In his first association with Argonne from 1973-1987, he held a number of positions in the Applied Mathematics Division and was the founding Director of the Mathematics and Computer Science Division.

HPCS Plenary Talk: Research and Education Networks as an Enabler

for Scientific Computing: The GARR Vision

Federico Ruggieri

Director of Research at the National Institute for Nuclear and Particle Physics (INFN)

and Director of GARR, the Italian Research & Education Network, Rome, Italy

ABSTRACT

In the last few decades, Moore’s law and the uptake of fibre-optics have changed the way science is done. Nowadays, research groups distributed worldwide are exploiting high capacity networks and unprecedented computing power to process large amounts of data which were simply beyond our possibilities only a few years ago. Problems too complex to be tackled are now approachable, and if your data centre is still not enough, high-capacity networks can be exploited to extend it at the geographical level.

In this talk, the role of National and international Research and Education Networks is highlighted, also thanks to success stories from different scientific domains, from HEP to bioinformatics to culture, and a vision for the future is sketched.

SPEAKER BIOGRAPHY

Federico Ruggieri is the Director of research at the National Institute for Nuclear and Particle Physics (INFN) and Director of Gruppo Armonizzazione Reti della Ricerca, (GARR), the Italian Research & Education Network, Federico Ruggieri has been director of CNAF, one of the major scientific computing centres in Italy, and President of INFN’s National Computing and Network Committee. As professor of data acquisition at the University of Roma Tre, he boasts more than 400 scientific and technological publications. His collaboration with GARR dates back to the nineties, when he was a member of the first GARR Scientific and Technical Committee.