SUMMARY
|
|
John completed the requirements for the degree of Doctor of Philosophy in Electrical and Computer Engineering in January 2013.
His experience has encompassed teaching programming and optimization principles to scientists and engineers, software infrastructure development, program optimization for parallel platforms, and the study of parallel programming optimization patterns.
His 16 conference papers, journal and magazine articles, and technical reports focus on the performance, portability, and scalability of data-parallel programming models across a variety of platforms, including multicore CPUs, GPUs, and FPGAs.
|
EDUCATION
|
|
Ph.D., Electrical and Computer Engineering, Universiity of Illinois, deposition January 2013, degree date May 2013
Certificate in Foundations of Teaching: Center for Teaching Excellence, University of Illinois, 2012
M.S., Electrical and Computer Engineering, University of Illinois, 2009
Strategic Technology Management Certificate: Illinois Technology Entrepreneur Center, University of Illinois, 2008
B.S. with Highest Honors, Computer Engineering, University of Illinois, 2006
|
BIOGRAPHY
|
John attended the University of Illinois as an undergraduate from 2002 to 2006, with several semesters of experience as an undergraduate classroom teaching assistant. He received recognition by the department and other bodies for his leadership in teaching even before entering graduate school.
In graduate school, John invested in many areas of teaching and research. He was a part of the founding teaching team of the now-permanent course ECE408/CS482 Applied Parallel Programming, the first university course in the world to teach GPU programming with the CUDA language. His master’s project (MCUDA) was the first system capable of executing code written in the CUDA programming model on a multicore CPU architecture. He has led the continued development of the Parboil accelerator benchmark suite and benchmarking infrastructure, which has been submitted to SPEC as candidates for the SPEC HPG accelerator benchmark suite.
His Ph.D. dissertation topic is exploring whether reasonable performance portability is possible for parallel architectures, and if so, what programming practices, libraries, and tools are required to achieve it.
Some of the technology components resulting from that exploration are currently being commercialized as the Multicore cross-Platform Architecture (MxPA) product from MulticoreWare Inc, where John also currently holds the position of Senior Architect.
John currently holds a lecturing position in Electrical and Computer Engineering, teaching the Spring 2013 offerring of ECE 391: Computer Systems Engineering. He is searching for a full-time tenure-track faculty position and industry contacts to continue making contributions in technology and engineering education. Resume and Curriculum Vitae are available on request.
|
NOTABLE EXPERIENCE AND POSITIONS
|
Education experience
- Lecturer, ECE 391: Computer Systems Engineering, Spring 2013
- Graduate Teaching Assistant and Course Administrator for several semesters of introductory and advanced GPU computing courses.
- Instructor, Virtual School of Computational Science and Engineering, several multi-institution summer workshops on GPU computing for scientists and engineers
|
Key research projects
- Lead developer of the Multicore cross-Platform Architecture (MxPA) compiler and runtime for performance portability
- Lead developer of the Parboil benchmark suite
- Lead developer of the MCUDA compiler and runtime targeting the CUDA language to CPU architectures (no longer supported)
|
Industry impact
- Senior Architect at MulticoreWare, and lead developer of the production version of MxPA.
- SPEC High-Performange Group Representative, advocate and developer for a SPEC Accelerator benchmark suite, with an anticipated release some time this year.
|
AWARDS AND HONORS
|
- Most Valuable Entrpreneurial Leadership in a Startup, University of Illinois Research Park Intern Award: 2012
- Mavis Future Faculty Fellows Program Participant: 2011-2012
- E. A. Reid Fellowship Recipient: 2011-2012
- FCCM 2011 Best Paper award for "Multilevel Granularity Parallelism Synthesis on FPGAs," written with Alexandros Papakonstantinou et al.
- SASP 2009 Best Paper award for "FCUDA: Enabling Efficient Compilation of CUDA Kernels onto FPGAs," written with Alexandros Papakonstantinou et al.
- Dan Vivoli Endowed Fellowship Recipient: 2008-2009 and 2009-2010 (recognizing outstanding research in GPU computing)
- Timothy N. Trick Leadership Award Recipient: 2006
- Accenture Outstanding Student Award Recipient: 2003-2004
|
PUBLICATIONS
|
|
A Scalable, Numerically Stable, High-performance Tridiagonal Solver Using GPUs
[PDF]
|
|
Li-Wen Chang, John A. Stratton, Hee-Seok Kim, Wen-mei W. Hwu
|
| High-Performance Computing, Networking, Storage and Analysis (SC 2012), November 2012
|
Algorithm and Data Optimization Techniques for Scaling to Massively Threaded Systems
[PDF]
|
|
John A. Stratton, Christopher Rodrigues, I-Jui Sung, Li-Wen Chang, Nasser Anssari, Geng Daniel Liu, Wen-mei W. Hwu, Nady Obeid
|
| Computer, Vol. 45, No. 8, August 2012
|
Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing
[PDF]
|
|
John A. Stratton, Christopher Rodrigues, I-Jui Sung, Nady Obeid,
Li-Wen Chang, Nasser Anssari, Geng Daniel Liu, Wen-mei W. Hwu
|
| IMPACT Technical Report, IMPACT-12-01, University of Illinois at Urbana-Champaign
Center for Reliable and High-Performance Computing
March 2, 2012
|
Optimization and Architecure Effects on GPU Computing Workload Performance
[PDF ] |
|
Anssari, Nasser; Chang, Li-Wen; Stratton, John; Obeid, Nady; Hwu, Wen-mei; Liu, Daniel; Rodrigues, Christopher I.; Sung, Ray
|
|
​Proceedings of the IEEE Conference on Innovative Parallel Computing, May 2012 |
Multilevel Granularity Parallelism Synthesis on FPGAs
(Best Paper Award)
[PDF] |
|
Alexandros Papakonstantinou, Yun Liang, John A. Stratton, Karthik Gururaj,
Deming Chen, Wen-Mei W. Hwu, Jason Cong |
|
Proceedings of IEEE International Symposium on Field-Programmable Custom Computing Machines, May 2011 |
Data Layout Transformation Exploiting Memory-Level Parallelism in Structured Grid Many-Core Applications
[PDF] |
| Sung, Ray; Stratton, John; Hwu, Wen-mei |
| Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques (PACT) 2010, Vienna, Austria, September 11-15, 2010 |
Efficient Compilation of Fine-grained SPMD-threaded Programs for Multicore CPUs
[PDF]
|
|
John A. Stratton, Vinod Grover, Jaydeep Marathe, Bastiaan Aarts, Mike Murphy, Ziang Hu, and Wen-mei W. Hwu |
| Proceedings of the International Symposium on Code Generation and Optimization, April 2010. |
FCUDA: Enabling Efficient Compilation of CUDA Kernels onto FPGAs
(Best Paper Award)
[PDF]
(Copyright IEEE 2009. For personal use only.) |
| Alexander Papakonstantinou, Karthik Gururaj,
John A. Stratton, Deming Chen, Jason Cong and Wen-mei W. Hwu |
| Symposium on Application Specific Processors, July 2009. |
Compute Unified Device Architecture Application Suitability
[PDF]
|
| Wen-Mei W. Hwu, Christopher Rodrigues,
Shane Ryoo, and John A. Stratton |
|
Computing in Science and Engineering Vol. 11 No. 3, May 2009.
|
MCUDA: An Efficient Implementation of CUDA Kernels for Multi-Core CPUs
[PDF]
(Copyright Springer LNCS 2008. For personal use only.) |
|
John A. Stratton, Sam S. Stone and Wen-mei W. Hwu
|
|
21st International Workshop on Languages and Compilers
for Parallel Computing, LNCS 5335, pp. 16-30, 2008.
|
Program Optimization Carving for GPU Computing
[ PDF ]
|
| Shane Ryoo, Christopher I. Rodrigues,
Sam S. Stone, John A. Stratton, Sain-Zee Ueng, Sara S. Baghsorkhi,
and Wen-mei W. Hwu |
|
The Special Issue of the Journal of Parallel and Distributed
Computing on General Purpose Parallel Processing Using GPUs, 2008.
|
Program Optimization Space Pruning for a Multithreaded GPU
[PDF] (Copyright ACM 2008. For personal use only.)
|
| Shane Ryoo, Christopher I. Rodrigues, Sam S. Stone,
Sara S. Baghsorkhi, Sain-Zee Ueng, John A. Stratton, and Wen-mei W. Hwu
|
|
Proceedings of the 2008 International Symposium on Code
Generation and Optimization, April 2008.
|
MCUDA: An Efficient Implementation of CUDA Kernels on Multi-cores
[PDF]
|
|
John A. Stratton, Sam S. Stone, Wen-mei W. Hwu |
|
IMPACT Technical Report, IMPACT-08-01, University of Illinois, Urbana, IL 2008.
|
Performance Insights on Executing Non-Graphics Applications on CUDA on the
NVIDIA GeForce 8800 GTX
[PDF]
|
|
Wen-mei Hwu, David Kirk, Shane Ryoo, Christopher Rodrigues, John Stratton,
and Kuangwei Hwang |
|
Presentation at Hot Chips 19, August 2007.
|