Andrew Chien has authored over seventy publications in the areas of
compilers, system software, networks and processor architecture of high-performance
systems. Over the past fifteen years, Andrew Chien has been involved
in numerous parallel computing architecture and software. As a graduate
student at MIT, he participated in Arvind's tagged-token Dataflow Architecture
project, and then Dally's J-Machine project, an early low-overhead message
passing machine. As a faculty member at the University of Illinois,
Andrew pursued a wealth of architecture, networking, and language implementation
projects. Andrew is well known for his work on high speed cluster communication
-- the Fast Messages (FM) and High Performance Virtual Machines (HPVM)
systems which are the basis for a wealth of clustering research and
NCSA's Windows NT Clustering efforts. These systems have also been widely
disseminated around the world to over 500 academic, national laboratory,
and commercial environments.
Andrew's early work on concurrent object-oriented programming systems
began at MIT and continued at Illinois, providing key intellectual input
to the pC++ project and the parallel software efforts of the Japanese
Real World Computing Project (RWC) which led to the HPC++ standard.
His Concert project developed a range of compiler and runtime techniques
for fine-grained concurrent object-oriented languages and foreshadows
aggressive type, cloning, and data structure optimizations which have
yet to appear in commercial compilers for languages such as C++ and
Java.
Selected Professional Activities
Editorial and Program Committees:
Associate Editor, IEEE Transactions on Parallel and Distributed
Computing
Guest Editor, IEEE Computer Special Issue on Network Interfaces,
1998.
Program Chair, ACM Symposium on the Principles and Practice of Parallel
Programming, 1999.
Program Vice Chairman, IEEE International Parallel Processing Symposium,
1995.
Member, numerous program committees in compilers, object-oriented
systems, computer architecture, etc.
Research Interests:
Parallel computer architecture, object-oriented programming, language
implementation (compilers and runtime systems), distributed objects,
operating systems, networks, and reconfigurable computing.
Awards and Honors
National Science Foundation Young Investigator Award 1994; C.
W. Gear Outstanding Junior
Faculty Award, 1995; Senior Xerox Award for Excellence in Research,
1996
SIAM Parallel Processing 2001, USENIX Windows 2000, Cluster 2000, SC'1999,
1999 SIGPLAN PPoPP Symposium, HiPC '98, ADASS '98, NATO Workshop on
HPC 1998, HPCA 1998, DOE Scalable Clusters Workshop 1997, ONR PCRCW
1997, IPPS 1997, SIAM Parallel Processing, 1997, Frontiers 1996, IWPC++
1996, IBM CASCON 1995, IPPS 1995, Frontiers 1995, ONR PCRCW 1994, Hot
Interconnects 1993.
Five Closely Related Publications:
H. Song, X. Liu, D. Jakobsen, X. Zhang, K. Taura, and A. Chien,
The MicroGrid: A Scientific Tool for Modeling Computational Grids,
finalist for Best Paper Award, SC'2000, Dallas, Texas, November 2000.
J. Dolby and Andrew A. Chien, Automatic Inlining Optimization and
its Evaluation}, SIGPLAN Symposium on Programming Language Design
and Implementation, Vancouver, British Columbia, June 2000.
B. Ganguly and Andrew A. Chien, High-Level Parallel Programming
of An Adaptive Mesh Application Using the Illinois Concert System,
in International Symposium on Computing in Object-Oriented Parallel
Environments, Sante Fe, New Mexico, December 8-11, 1998.
V. Karamcheti and Andrew A. Chien, A Hierarchical Load-Balancing
Framework for Dynamic Multithreaded Computations, in SC '98: High
Performance Networking and Computing Conference, November 1998, Orlando,
Florida.
V. Karamcheti, J. Plevyak, and A. A. Chien, Runtime Mechanisms for
Efficient Dynamic Multithreading, in the Journal of Parallel and Distributed
Computing, Volume 37, pgs 21-40.
Five Other Significant Publications:
M. Lauria, S. Pakin, and Andrew A. Chien, Efficient Layering for
High Speed Communication: Fast Messages 2.x, in Proceedings of the
Seventh High Performance Distributed Computing Conference (HPDC'7),
Chicago, Illinois, July, 1998.
J. Dolby and Andrew A. Chien, An Evaluation of Object Inline Allocation
Techniques, in the Proceedings of the 1998 Object-oriented Programming,
Systems, Languages, and Architectures Conference, (OOPSLA '98), October
1998, Vancouver, British Columbia, Canada.
Scott Pakin, Vijay Karamcheti, and Andrew A. Chien, Fast Messages:
Efficient, Portable Communication for Workstation Clusters and Massively-Parallel
Processors, in IEEE Concurrency, 1997.
Mario Lauria and Andrew A. Chien, MPI-FM: A High Performance MPI
on Workstation Clusters, Journal of Parallel and Distributed Computing,
Volume 40, Number 1, January 1997.
Andrew A. Chien, Julian Dolby, Bishwaroop Ganguly, Vijay Karamcheti,
and Xingbin Zhang, Evaluating High Level Parallel Programming Support
for Irregular Applications in ICC++, in International Scientific Computing
in Object-oriented Parallel Environments Conference (ISCOPE), Marina
del Rey, December 1997, Springer-Verlag LNCS.
Other PI's on this proposal, Co-authors of the ``Grids'' book.
Vijay Karamcheti (NYU), Dennis Gannon (Indiana), Reagan Moore (SDSC/UCSD),
David Culler (UC Berkeley), Rajesh Gupta (UCI), Alex Nicolau (UCI),
Nikil Dutt (UCI), Bishwaroop Ganguly (MIT Lincoln Laboratories), William
Weihl (Compaq Research), Matt Buchanan (Compaq Computer), Jae Kim
(Hal Computer). Jane Liu, Wen-mei Hwu, Klara Nahrstedt, David Padua,
and Weng Chew (Illinois)
Graduate and Post Doctoral Advisors:
Ph.D. Thesis Advisor: Professor William J. Dally (MIT => Stanford)
S.M. Thesis Advisor: Arvind (Massachusetts Institute of Technology)
Thesis Advisor and Postgraduate-Scholar Sponsor:
Andrew has supervised 15 Master's students, 6 Ph.D. students, and
4 postdoctoral fellows. These alumni are employed variously as faculty
at research universities, corporate research laboratories, and startup
companies. He currently supervises a group with ten graduate students.