SCA Awards

The Supercomputing Frontiers (SCF)/National Supercomputing Centre (NSCC) Singapore awards were inaugurated in 2017, at the 3rd annual SCF High Performance Computing (HPC) conference in Singapore. Organised by NSCC, SCF provided a platform for thought leaders from both academia and industry to interact and discuss visionary ideas, important global trends and novel innovations in supercomputing.

Riding on the success of the SCF conference series, from 2018, NSCC will be expanding SCF’s scope by embarking on SupercomputingAsia 2018 (SCA18) as a new annual conference that will encompass an umbrella of notable supercomputing and allied events in Asia. SCA18’s key objective is to promote a vibrant and shared HPC ecosystem in Asia, where the most exciting HPC developments are taking place.

During this SCA18 conference, the SCF/NSCC awards will be rebranded as the SCA awards. The aim is to promote excellence in HPC, networking, storage and visualisation in the areas of Asia’s research, innovation, education and enterprise.

The candidates for the SCA awards were nominated and selected by a committee of distinguished international panelists and HPC luminaries who sit as members in the SCA Steering Committee. The award categories are as follows:

SupercomputingAsia 2018 – Asia HPC Leadership Award

Recognises an outstanding individual with excellence in leadership within the HPC community.

SupercomputingAsia 2018 – Asia HPC Outstanding Innovation Award

Recognises an individual or an organisation with outstanding contribution towards innovation within the global HPC community.

SupercomputingAsia 2018 – Singapore Distinguished Service Award

Recognises an individual with long-service and contribution within the local HPC community.

SupercomputingAsia 2018 – Singapore Visionary Award

Recognises an outstanding individual who has demonstrated great vision in the future of HPC for Singapore.

SupercomputingAsia 2018 – Outstanding Technical Paper Award

Recognises an outstanding individual/team deemed as the best research technical paper presented at the conference.

Satoshi Sekiguchi, Ph.D. is currently a Vice President of the National Institute of Advanced Industrial Science and Technology (AIST) in Japan, and is appointed the Director General of the Department of Information Technology and Human Factors, which is engaged to perform a research on developing a sound society by specifically addressing the mutual interaction of informatics and ergonomics. He has continued to drive major developments in high performance computing widely from its system architecture to applications. His expertise also includes applying IT-based solutions to many of society’s problems related to global climate change, environmental management and resource efficiency.

He received his BSc. from the University of Tokyo, M.Eng. from University of Tsukuba, and Ph.D. in Information Science and Technology from the University of Tokyo, respectively. He joined the Electrotechnical Laboratory (ETL) where he started his professional carrier as research scientist in 1984. In 2002-2008 he served as the founding director of Grid Technology Research Center, followed by the Director of Information Technology Research Institute, AIST in 2008-2012, and the Deputy Director-General of the Directorate for Information Technology and Electronics in 2012-2014. He is a member of the Science Council Japan, IEEE CS and ACM, and IPSJ fellow.

In his multi-decade involvement as a pioneer of HPC and advanced network computing in Asia, he has demonstrated outstanding leadership and pioneering spirit. In the early 2000s, he worked with international partners from the US, Asia and Europe to build HPC Meta Computing network connecting a several supercomputers allocated by the partners. In the mid 2000s, he helped to establish the National Research Grid Initiative NAREGI, a major Japanese national IT project led by MEXT as one of the co-PIs. He took strong leadership in founding and directing the Centre for Grid Research and Development which intended to deploy key software packages for consisting a grid computing platform on Japan’s SuperSINET and other International links. Also, he was appointed as co-PI of the Business Grid Computing Project led by METI, which aimed to develop software for making better utilisation of the resources in Data Centres.

He developed core technologies for establishing high performance parallel computing environment on grid computing i.e. Grid RPC. He organised a team of Ninf network based information library for global world-wide computing infrastructure in 1997 and achieved stable network flow with high performance communication in high bandwidth-delay product networks. The software was registered as a part of NSF Grid Middleware.

He funded the Gfarm project, a network storage system with high scalability of total I/o bandwidth, which his team achieved a record-breaking near Terabps transfer speeds over a transpacific testbed as early as 2003. He has been involved in leadership roles in many projects including the AIST SOA Service oriented architecture, Green IT computing project supported by NEDO in 2008-2012.

In the late 80s and early 1990s, he pioneered SIGMA-1, a data flow supercomputer for scientific computation using instruction level parallel processing in charge of developing programming language and application for such an innovative machine. Since 2002, he was one of the leading Asian pioneers who co-founded the Pacific Rim Applications and Grid Middleware Assembly. He has served a decade as member of the PRAGMA Steering Committee. In recent years, he is well known for his key project, the GEO (Global Earth Observation) Grid.

In addition to the above research activities, he also served as a member for several international committees of global standards in API for HPC and Data, including Global Grid Forum and Research Data Alliance. He is also involved in the project initiated in Japan to build the world’s fastest supercomputer for artificial intelligence research, also known as the AI Bridging Cloud Infrastructure (ABCI).

Professor Lam Khin Yong is the Vice President (Research) at Nanyang Technological University (NTU) since 2014 and is responsible for guiding the University’s research enterprise across all disciplines and fostering close research collaboration between industry and academia. His long service to NTU extends from 2006, when he was first appointed as Chair of the School of Mechanical & Aerospace Engineering (2006-2008). He was subsequently appointed Associate Provost for Graduate Education & Special Projects (2008-2011), Chief of Staff (2011-2017), Acting CEO of NTU Innovation (2012-2013) and NTU’s Acting Provost (March-December 2017).

Professor Lam has received international recognition for his success in initiating research partnerships, including collaborations involving high performance computation. He is the recipient of numerous honours and awards including the French Legion of Honour, one of the highest decorations awarded by the French Government, which was conferred to him in 2017 for his track record of cultivating academic and industry collaborations between Singapore and France. He has also received Honorary Professorships from the Lomonosov Moscow State University (Russia) and Asia University (Taiwan) in recognition of his achievements to promote deeper industry-academia cooperation, which extend from his early career efforts to bolster the usage of high performance computing by industry partners.

A strong advocate of the triple helix research collaboration model in which industry, academia and public agencies work together to deliver research outcomes with societal impact, he remains firmly committed to bridging the gap between fundamental research and innovation.

Professor Lam’s dedication to high performance computing was evident early in his career where he first played a pivotal role in establishing Singapore’s capabilities in High Performance Computing at the Centre for Computational Mechanics as its Founding Director in 1994. Recognising the value of computational simulation and modelling in fast-tracking solutions to solve scientific challenges, he strove to champion the use of high-performance computing resources from a user’s
perspective to develop novel approaches and models for a host of industry and engineering applications. In particular, he focused on building closer links with the industry to facilitate stronger collaboration and greater industry use of the centre’s computational resources. His work in computational mechanics, simulation and modelling extended to enhancing Singapore’s defence capabilities following his appointment as Director of the NUS-MINDEF Underwater Shock Laboratory in 1991. The research team helmed by Professor Lam, received the Defence Technology Prize from MINDEF in 1998 for their significant research contributions to underwater shock technology. Under his strong leadership, the steady stream of industry income eventually led to the merger with the National Supercomputing Research Centre. Insert the word “National” and its subsequent expansion into the Institute of High Performance Computing (IHPC) in 1998.

In his role as Founding Executive Director of IHPC, he continued to be an instrumental figure in the development and transformation of Singapore’s high-performance computing programs and infrastructure. He led active efforts at IHPC to bridge the academia and industry divide by promoting the use of high
performance computational resources for industrial related research including virtual product design. His concerted approach to boost industry linkages subsequently led to many successful partnerships between IHPC and industry, including a major virtual product design project in Robust Pager Design with Motorola. He also spurred larger-scale industry adoption of high performance computing in his concurrent roles as Programme Director of the MCAE Techniques for Robust Design (from 1997-2000) and Computational Mechanics Industry Programme (from 1995-1998) funded by the National Science & Technology Board (the present day A*STAR). Between 1995 and 2007, Professor Lam continued to secure a series of competitive research grants for computational mechanics research from both companies and organisations, as well as establish the first CAVE visualisation facility in Singapore. The CAVE visualisation facility played a crucial role in paving the way to greater industry participation through the easy visualisation of data sets to create greater analytic capabilities.

In his current role, Professor Lam continues to garner research funding for the university while strengthening the high performance computing capabilities in Singapore. This is reflected in the university’s successful award of the flagship S$75m Rolls-Royce Corporate Lab, which features a research component requiring
computational resources. More recently, his involvement in year-long talks has culminated in the successful signing of a multi-million dollar research collaboration in Artificial Intelligence with Chinese e-commerce and retail giant, Alibaba and NTU. The joint research institute, a first for Alibaba outside China, will deploy AI solutions
across a range of public and private settings.

Since 1991, his pioneering contributions and efforts in his various capacities at the Underwater Shock Laboratory, Centre of Computational Mechanics, the Institute of High Performance Computing and NTU, have undoubtedly expanded Singapore’s now thriving research capabilities in high performance computing. This in turn ensures the country remains an attractive R&D destination and research partner of choice for global industry leaders. Today, Professor Lam continues to be an active
advocate of aligning fundamental research with industry application, including the use of high performance computation for modelling and simulation.

For his distinguished contributions towards shaping the HPC landscape in Singapore, he is conferred the Singapore HPC Distinguished Service Award, SupercomputingAsia ’18.

Dr. Goh is a veteran of the High Performance Computing (HPC) industry of nearly three decades. He joined SGI (founded as Silicon Graphics Computer Systems in 1981) in its early years as a Silicon Valley startup IPO in 1989. He rose up the ranks to become its Chief Scientist at the turn of the millennium, 17 years of which he played a pioneering role as its CTO. As one of the biggest names in HPC, SGI is now within the fold of HPE, and Dr Goh has since become HPE’s VP and CTO of HPC & AI.

Hailed not just by HPCwire as one of the leading HPC visionaries of our time, Dr. Goh has been the driving force behind SGI’s technical computing program for nearly two decades. In Singapore, he is known as the Singaporean who put a supercomputer in space, having initiated and implemented the one-year HPC experiment aboard the International Space Station (ISS) in a NASA effort to study HPC hardware for long duration space travel.

As a strong proponent of AI and machine learning, he is constantly thinking about how HPC can accelerate innovation and improve humanity. In 2017, his team co-designed the Tsubame 3.0 AI supercomputer at the Tokyo Institute of Technology (TiTech). With 47 Petaflops of 16-bit AI computational power, they achieved the world’s largest scalable learning AI system. Moreover, this supercomputer is also one of the world’s most energy efficient, listed at the top of the June 2017 Green500 list.

He has won numerous awards and widespread recognition for his achievements, from “HPCwire Readers’ Choice Top Supercomputing Award 2017” to the “Hyperion Research HPC Innovation Excellence Award 2017”. In 2007, he was named a “Champion 2.0” of the industry by Bio-IT World magazine, and received the “HPC Community Recognition Award” from HPCwire. He is one of the few to be included in HPCwire list of “People to Watch” twice, once in 2005 and again in 2015, as well as InfoWorld’s “Top CTO Award” in 2005.

He has 6 US patents granted with 3 others pending as he is still actively inventing and coming up with visionary ideas and getting them implemented in his new and enlarged role in HPE where he is tasked to develop the next generation computer architectures. His current research interest is in the progression from data intensive computing to analytics, inductive machine learning, deductive reasoning and artificial intelligence, from specific to general intelligence.

Dr. Goh is a popular industry speaker and he continues in various forums, to discuss and shape thinking about innovative technologies and their applications. Moving into more academic realms, by early 2012, he and his wife were invited by the late Stephen Hawking to his 70th birthday symposium and introduced the speaker, Physics Nobel Laureate, Saul Perlmutter. In 2014, he co-presented with NASA at the inaugural 1st plenary of the Supercomputing 2014 Conference to an audience of thousands. Last year, Dr. Goh was appointed to the Scientific Advisory Board of the National Research Foundation, Prime Minister’s Office, Singapore. Today, he is delivering the keynote of the SupercomputingAsia 2018 inaugural conference in Singapore.

For all his achievements, Dr. Goh continues to be grateful to Shell for the Cambridge University scholarship that supported his PhD program.

Next up for Dr. Goh, is HPC-enabled human missions to the Moon, Mars and beyond!

SupercomputingAsia 2018
Outstanding Technical Paper Award

AWARD WINNER

Kesheng Wu, Junmin Gu, Scott Klasky, Norbert Podhorszki & Ji Qiang 

(Lawrence Berkeley National Laboratory, USA)

Title:

#036 Querying Large Scientific Data Sets with Adaptable IO System ADIOS

Abstract:

When working with a large dataset, a relatively small fraction of data records are of interest in each analysis operation. For example, while examining a billion-particle dataset from an accelerator model, the scientists might focus on a few thousand fastest particles, or on the particle farthest from the beam center. In general, this type of selective data access is challenging because the selected data records could be anywhere in the dataset and require a significant amount of time to locate and retrieve. In this paper, we report our experience of addressing this data access challenge with the Adaptable IO System ADIOS. More specifically, we design a query interface for ADIOS to allow arbitrary combinations of range conditions on known variables, implement a number of different mechanisms for resolving these selection conditions, and devise strategies to reduce the time needed to retrieve the scattered data records. In many cases, the query mechanism can retrieve the selected data records orders of magnitude faster than the brute-force approach.

Our work relies heavily on the in situ data processing feature of ADIOS to allow user functions to be executed in the data transport pipeline. This feature allows us to build indexes for efficient query processing, and to perform other intricate analyses while the data is in memory.

To download the paper in PDF, click here

Other shortlisted candidates for the award:

#028: DETOUR: A Large-Scale Non-Blocking Optical Data Center Fabric by Jinzhen Bao, Dezun Dong, Baokang Zhao (click to view PDF)
#045: On the Performance of Spark on HPC Systems: Towards a Complete Picture by Orcun Yildiz, Shadi Ibrahim (click to view PDF)