Dr. Steven A. Guccione is Vice President at Bank of America Merrill Lynch. His interests are in high performance computing, in particular software and tools for parallel computing. Dr. Guccione received his Bachelor of Science degree in Electrical and Computer Engineering from Boston University, his Master of Science degree in Electrical Engineering from the University of Minnesota and his Ph.D. degree in Electrical Engineering from the University of Texas at Austin. He has previously held engineering positions at Xilinx, Advanced Micro Devices, Motorola/MCC, Texas Instruments and several companies.

Financial firms have long been users of large compute resources. While some of the compute infrastructure in banking and finance is used for traditional business activities, supercomputer style installations are increasingly used to perform tasks such as trading support and risk analysis. These computations consume large amounts of compute resources and have requirements not found in traditional supercomputing. While the application area is different from the scientific explorations of traditional supercomputing, the underlying computations are very similar. Both are large scale simulations involving the solving of complex systems of equations, often by numerical techniques such as Monte Carlo. As in other areas, the desire for improved performance and reduced cost has led to the use of compute accelerators or coprocessors. Today, these accelerators primarily take the form of discrete GPUs. It is expected, however, that a variety of forces will lead to increased use of accelerators of differing architectures for financial applications. The classification of accelerators into ‘horizontal’ and ‘vertical’ architectures is proposed and some future directions for accelerator architectures explored.

Dr. Khaled Benkrid is currently the head of ARM Worldwide University Programme for ARM Ltd. He was a Senior Lecturer in Electronic Engineering at the University of Edinburgh, Scotland. His interests are in high performance efficient computing and electronic design automation. He also has a keen interest in the development of new pedagogical approaches to teaching computer science and engineering to students worldwide. He holds a PhD in Computer Science, an MEng in Electronics Engineering, and an executive MBA. He is a UK Charted Engineer and Senior Member of IEEE.

Modern computing is characterized by increasingly heterogeneous and distributed architectures brought about by increasingly stringent and dynamic requirements. The Internet of Things (IoT) is a manifestation of this evolution and promises to change the world we live in. This talk will explore the various technologies involved in IoT and present various architectures, opportunities and challenges. In particular, the ARM's eco-system contribution to this evolution is presented. Finally, the talk will attempt to speculate on what the future might hold for us with IoT.