The topic is "Advancing Computing Systems from the Data-Cloud Point-of-View". More information can be found here.
Dr. Xian-He Sun and former SCS member, Prof. Yong Chen, serverd as program co-chair. The workshop attracted more than one hundred attendees. More information of the workshop can be found at here.
Mr. Jibing Li received his MS degree in 2011. After working in Chicago for a short time, he joined Sugon in Beijing, China as a Software Engineer in August, 2012.
Dr. Xian-He Sun delivered a keynote speech at the 7th IEEE International Conference on Networking, Architecture, and Storage (NAS 2012). The topic is "Memory System for Extreme-Scale Computing". More information can be found here.
Dr. Hui Jin moved to Orcale in Redwood, CA. At Orcale, he is a Member of Technical Staff working at the parallel execution group. Before that, he was a student member at our SCS Lab between 2006 and 2012, and received his Ph.D. in Computer Science in May 2012. His homepage is here.
From May 2012 to Aug 2013, Jun He will be work with Dr. John Bent at Los Alamos National Laboratory. He will be working on the PLFS (Parallel Log-structured File System) project as a Graduate Research Assistant. He will study the I/O behaviors of important applications over PLFS. He also will design and implement pattern structures to describe and compress log in PLFS. His homepage is here.
Dr. Surendra Byna moved to Lawrence Berkeley National Laboratory (LBNL) in Berkeley, CA. He was a researcher at NEC Laboratories America in Princeton, NJ. At LBNL, he is a member of the Scientific Data Management group in the Computational Research Division. He was a student member and later a faculty member at our SCS Lab between 2000 and 2009. More information about his new coordinates and his research at LBNL. His homepage is here.
After two highly productive years as a post doctoral research at the SCS Lab., Dr. Huaiming Song returned to China in September, 2011. He is now the R&D Manager of Cloud Storage Group of Sugon's R&D Center.
This is his new homepage.
The Catalyst is emailed to ca. 400 key individuals across the country in business, economic development, science and research whose organizations are already here or are considering relocation/expansion to Chicago/Illinois. The purpose is to showcase Illinois' strength in science research and how that research can be monetized--thus retaining and attracting these businesses. Of course, the ISTC Catalyst is also posted online for a much larger audience to access.
College of Science and Letters Dean Russell Betts announced last Thursday that Professor Xian-He Sun has been appointed the new Chair of the Computer Science Department in the College of Science and Letters. Professor Sun will assume his duties at the start of the 2009-2010 academic year.
The search process was coordinated by a committee chaired by Professor Fred Hickernell AM, comprised of Professors Agam, Hood, Li and Wan from CS and Professor Shahidehpour from ECE in the Armour College.
Betts also expressed appreciation for Professor Bogdan Korel, for his outstanding service as interim chair for the past several years.
Sun received his Ph.D. in computer science from Michigan State University in 1990. He joined IIT in the fall of 1999 as an associate professor of computer science and in 2002 was promoted to the rank of professor. He is an authority in the area of high performance computing and is highly regarded in his field. He has authored more than 150 publications and has been recognized with professional society awards and frequent invitations to speak at national and international meetings. Sun also serves on the editorial board of five professional journals, and has organized more than 20 professional conferences and workshops, including the flagship conference in supercomputing, IEEE SuperComputing.
Xian-He Sun, professor of computer science and director of IIT's Scalable Computing Software Laboratory, gave the keynote speech Reevaluating Amdahl's Law in the Multicore Era at INFOSCALE09 on June 10 in Hong Kong.
Multicore architecture, or architecture having a processing system with two or more cores or CPUs, is now the norm. But there are questions about if and when we should scale up the number of cores to hundreds or more and enter the "many-core" era. In his speech Dr. Sun noted that major vendors are reluctant to do this so far because of Amdahl's law - having to do with what maximum improvements can be expected to a whole system when part of it is improved -- and the "memory wall," i.e., the gap between CPU speed and memory outside of the CPU chip.
Sun used the same hardware cost model of multicore chips used by Mark Hill and Michael Marty, who developed the multicore Amdahl's law theory, to introduce two performance models from the scalable computing point of view. He found that there is no inherent, immovable upper bound on the scalability of multicore architecture. Sun concluded with proposed solutions to the memory-wall problem to make the potential scalability of multicore reachable in practice.
INFOSCALE is the International Conference on Scalable Information Systems, held by the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering (ICTS), a global research society.
Dr. Sun also is a guest faculty member in the Mathematics and Computer Science Division and Computing Division at Argonne and Fermi laboratories. Before joining IIT in 1999, he worked at the U.S. Department of Energy's Ames Laboratory at Iowa State University; the Institute for Computer Applications in Science and Engineering (ICASE) at NASA Langley Research Center; and Louisiana State University, Baton Rouge; and he was an American Society For Engineering Education (ASEE) fellow at Navy Research Laboratories. Dr. Sun's research interests include parallel and distributed processing, high-end computing, software systems, and performance evaluation.
Dr. Sun has published over 150 research articles and has 10 granted and pending U.S. and international patents, and his research is supported by NSF and other U.S. government agencies. He is a senior member of IEEE and ACM, a member of Phi Kappa Phi, an editor of five international professional journals, president of the Society of Chinese-American Professors & Scientists, and more.
(left to right) Junior faculty Sigma Xi winner Xiaoping Qian, student winner Paritosh Mokhasi, and senior faculty winner Xian-He Sun
2009 Sigma Xi Research Awards
The Graduate College is pleased to announce the recipients of the 2009 Sigma Xi Research Awards. The Sigma Xi Research Awards recognize exemplary accomplishments in research, scholarship, and creative activity by faculty members and graduate students at IIT. The faculty awards were presented at the Faculty Awards reception, held on April 22, and the student award was presented at IIT Research Day, held on April 28.
Senior Faculty Division Xian-He Sun, Computer Science Xian-He Sun is a renowned scientist who has made remarkable contributions to the field of computer science, especially in the field of high performance computing and communication. He is an authority on scalable computing, where computing power can be scaled up to meet a users demand by harnessing computing resources on the network.
Sun has authored or co-authored more than 120 publications, and much of his work has had lasting impact. For instance, he was one of the first researchers to provide a theoretical treatment of data implication, where one date query may imply another query. After more than 15 years, this work is still relevant and applicable to fields where memory is limited and many of the data requests must be served off-line via query implication. These fields include databases, information retrieval, and even cell phone design.
Sun was one of the first researchers to identify the "memory wall," the disparity between advancement of computing and memory technologies. CPU performance has doubled every eighteen months, but memory performance has only improved at an average rate of nine percent per year for the last twenty years. Thus, data access performance is the new bottleneck to sustained system performance rather than computing power. Sun has presented a formulation to describe the memory impact on performance, and his work is well recognized in the computer science community.
Sun received a Ph.D. in computer science from Michigan State University in 1990. He joined IIT in the fall of 1999 as an associate professor of computer science and in 2002 was promoted to the rank of professor. During his career, Sun has received more than 25 grants, two patents, and has been actively involved in educating IIT students. He has supervised 12 Ph.D. students, more than 20 masters students, and several undergraduate students. Sun also serves on the editorial board of five professional journals, and has organized more than 20 professional conferences and workshops, including the flagship conference in supercomputing, IEEE SuperComputing.
Junior Faculty Division Xiaoping Qian, Mechanical, Materials, and Aerospace Engineering Xiaoping Qian researches in the area of computational design and manufacturing. He specifically focuses on 3D sensing and modeling and its application in product design and manufacturing; and tip-based nano-imaging and nano-manipulation. Qians work in heterogeneous object modeling has been widely cited, and he has been invited to many institutions to speak on this topic. Due to his pioneering work in direct product design and manufacturing from acquired-point cloud data, he was invited to guest edit a special issue on Point-based Computational Techniques in Computer-Aided Design, a flagship journal in the CAD/CAM area.
Qian joined IIT in the fall of 2004 as an assistant professor of mechanical and aerospace engineering. He received a Ph.D. in mechanical engineering from University of Michigan in 2001. After graduating from University of Michigan, Qian worked as a research scientist for General Electric in its Global Research Center in Niskayuna, New York.
In his short time at IIT, Qian has received more than $1.8 million in external research funding from both government and private sources. He has also supervised four Ph.D. students, five Masters students, and created two new courses in the MMAE department. Qian is also an Associate editor of SME Journal of Manufacturing Systems and has assisted in organizing several conferences.
Student Division Paritosh Mokhasi, Mechanical, Materials, and Aerospace Engineering Paritosh Mokhasi received a B.E. in mechanical engineering from College of Engineering and Technology in Karnataka, India in 2000. In 2004, he received a Master of Science in mechanical and aerospace engineering from IIT. His masters thesis focused on the development of low-dimensional models for the simulation of contaminant dispersion. Among the key features of the types of models that he developed is the ability to predict the evolution of a contaminant plume, both forwards and backward in time, based on data acquired from a minimal number of flow sensors.
Mokhasi will receive his Ph.D. in mechanical and aerospace engineering in May 2009. He has authored or co-authored six journal articles and has given a number of tutorials in MATLAB to undergraduate students. His Ph.D. thesis continues the work of his masters thesis in the area of low-dimensional models for turbulent flows in complex geometries. During his research, Mokhasi re-discovered a variant of the method of proper orthogonal decomposition. Through an extension of this method, he was able to extract characteristic modes of turbulent flows that describe the spatio-temporal evolution of the flow within so-called "episodes." Additionally, Mokhasi has developed a series of increasingly sophisticated models for the dynamics of complex flows, which can accurately model the dynamics of such systems based on time series analysis, non-linear systems prediction, and an innovative application of radial basis function methods.
Ziming Zheng won the Cray Log Analysis contest held during the USENIX (Advanced Computing Technical Association) Workshop on the Analysis of System Logs (WASL), December 8 - 10 in San Diego, CA. WASL was co-located with the 8th USENIX Symposium on Operating Systems Design and Implementation. Zheng's research focuses on discovering and forecasting incipient faults in large-scale systems, as well as fast failure recovery.
Also in December, Wei Tang was awarded a $15,000 Starr Research Fellowship for 2009 from IIT Graduate College. The fellowship allows students to conduct research, develop their skills, and build a portfolio that will demonstrate their capabilities at a national level. Wei's interests are fault tolerance in high-performance computing, resource management in large-scale systems, and related areas.
Computer science Ph.D. candidate Yong Chen has been selected as one of three ACM/IEEE CS High Performance Computing Fellows for 2008, the inaugural year for the fellowship, awarded by the Association for Computing Machinery (ACM), IEEE Computer Society, ACM Special Interest Group on Computer Architecture (SIGARCH), and the SC (Supercomputing) Conference Series. Yong will receive $5,000 for education expenses, $1,600 for travel expenses to the SC08 and/or SC09 conferences, and a certificate documenting the award
Yong Chen won Chinese Government Award for Outstanding Self-financed Students Aboard with a $5,000 stipend. This award is granted to selected Chinese students studying aboard from all disciplines. Yong was one of twelve awarded students from nine Midwest states including Michigan, Indiana, Wisconsin, Illinois, Minnesota, Iowa, Missouri, Kansas and Colorado.
Chen was awarded Fieldhouse Research Fellowship from IIT Graduate College with $7,500 stipend. The fellowship allows students to conduct research, develop their skills, and build a portfolio that will demonstrate their capabilities at a national level. Yong was awarded this fellowship for his proposed research on hiding I/O access latency with pre-execution prefetching, collaborating with Mathematics and Computer Science Division of Argonne National Laboratory.
Computer Science Ph.D. candidate Yong Chen will receive the ACM/IEEE High Performance Computing Fellows Honorable Mention Award at SC07 on Nov. 16, in Reno, NV. SC07 is considered the flagship conference of high-end computing, with 8,000-plus attendees from around the world.Chen's adviser is Professor Xian-He Sun. And Chen's paper published in SC07 is Data Access History Cache and Associated Data Prefetching Mechanisms
Computer Science Professor Xian-He Sun won one of the two awards for excellence in research. "He has been an unbelievably prolific scholar all through his career, and last year was no exception," said McMorris. Sun's scholarly content is matched only by his skill at securing grants, including, most recently, a $650,000 National Science Foundation grant for his research in "push architecture."
The IPRO team 357 myWay+gWay: Touring the High-Tech-Way team won the first place of Tracks 6 and 7 and Top Business Plan.
For her paper, "MPI-Mitten: Enabling Migration Technology in MPI," lead author and CS Ph.D Candidate Cong Du was awarded an Honorable Mention at the Virginia Tech High-End Computing Challenge. Cong Du is completing her dissertation under Prof. Xian-He Sun, who collaborated with her on the winning paper. The VTHECC's purpose is to, "promote the involvement of graduate and undergraduate students in research to improve high-end systems and applications," through, "original, innovative approaches that increase efficiency and reduce the time to solution of real parallel applications on real high-end computing systems."
Virginia Tech Computing Challenge Winners Announced
In the early days of computing, machines were used for scientific applications that required computing power for number crunching. Today the uses of computers have grown exponentially, including business applications such as email, multimedia, data mining, and others which require intensive data retrieval. CPU speed has increased in accordance with Moore's law, or double every 18 months, while at the same time memory access speed has only been improved an average of 9% per year over the past 20 years. Peak CPU speed is no longer matched by the deliverable performance of your application, thus data-access has become the bottleneck of computing, especially for data-centric business applications. CS Professor Xian-He Sun has proposed a novel data access architecture, called server push architecture, to solve the data-access bottleneck. National Science Foundation grant to develop this architecture.
In addition, Prof. Sun is a co-investigator for a five-year project entitled "National Computational Infrastructure for Lattice Gauge Theory," for the Department of Energy, in which he is responsible for the workflow development. These two projects started in August and September of 2006, respectively.
The IPRO305 team, Leaded by Prof. Xian-He Sun and with student leader Mr. Alexander Pope, wins the overall 1st place for Web Design and is the winner of Track 2 (Information Technology) program in Spring 2006