Prof. Houssain Kettani
Dakota State University, USA
Biography: Dr. Houssain Kettani received the Bachelor's degree in Electrical and Electronic Engineering from Eastern Mediterranean University, Cyprus in 1998, and Master’s and Doctorate degrees both in Electrical Engineering from the University of Wisconsin at Madison in 2000 and 2002, respectively. Dr. Kettani served as faculty member at the University of South Alabama (2002-2003), Jackson State University (2003-2007), Polytechnic University of Puerto Rico (2007-2012), Fort Hays State University (2012-2016), Florida Polytechnic University (2016-2018) and Dakota State University since 2018. Dr. Kettani has served as Staff Research Assistant at Los Alamos National Laboratory in summer of 2000, Visiting Research Professor at Oak Ridge National Laboratory in summers of 2005 to 2011, Visiting Research Professor at the Arctic Region Supercomputing Center at the University of Alaska in summer of 2008 and Visiting Professor at the Joint Institute for Computational Sciences at the University of Tennessee at Knoxville in summer of 2010. Dr. Kettani’s research interests include algorithms, cyber security, machine learning and population studies. He presented his research in over sixty refereed conference and journal publications and his work received over 500 citations by researchers all over the world. He chaired over hundred international conferences throughout the world and successfully secured external funding in millions of dollars for research and education from US federal agencies such as NSF, DOE, DOD, and NRC.
Title of Speech: Towards Exascale Computing
Abstract: In 1985, the fastest computer in the world reached 1 Gigaflop/s, or one billion (10^9) calculation per second. By 1996, the speed reached 1 TeraFlop/s or one trillion (10^12), then 1 PetaFlop/s or one quadrillion (10^15) by 2008. In 2016, the fastest computer in the world performs 100 PetaFlop/s and many hand-held devices including smart phones are faster than the fastest supercomputer in the 1980s. The 1 ExaFlop/s mark, or one quintillion (10^18) is expected to be reached in 2020. Currently, the fastest supercomputer has close to eleven million cores and consumes over 15 MW (Mega or million Watts). It is like 150,000 light bulbs of 100W on at the same time. It is more than a million times faster than a personal computer. So, one second of computing using the fastest supercomputer is equivalent to almost two weeks using a PC, while one hour is equivalent to over a century on a PC! These fast computers allowed humans to solve problems that were impossible to solve few years before, including weather (earth and space) forecast, gene permutations, Hurricane tracking, asteroids/comets tracking, spying, etc. However, such humongous machines present huge complexity in operation, maintenance, protection, etc. This remains an active area of interdisciplinary research for continuous improvement in speed, efficiency, hardware and software development as well as algorithms design and analysis to advance the state of the art of parallel computing.