 |
Xipeng Shen(pronounced as [sipeng shen])Visiting Scientist @ CSAIL, MIT Adina Allen Term Distinguished Associate Professor, CS, College of William & Mary |
Academic Genealogy Jacob T. Schwartz (New York U.) with John Cocke(IBM) |__ 1971 Ken Kennedy (Rice U.) |__ 2000 Chen Ding (U. Rochester) |__ 2006 Xipeng Shen |
|---|
Xipeng Shen is a visiting scientist at MIT Computer Science and
Artificial Intelligence Lab, and an Adina Allen Term Distinguished
Associate Professor at the College of William and Mary. He is an IBM
CAS Faculty Fellow, and a winner of the 2011 DOE Early Career Award
and 2010 NSF CAREER Award.
Xipeng Shen's research lies in the broad field of programming systems,
with an emphasis on enabling extreme-scale
data-intensive computing and intelligent portable
computing through innovations in both compilers and
runtime systems. I have been particularly interested in
capturing large-scale program behavior patterns, in both
data accesses and code executions, and exploiting them
for scalable and efficient computing in a heterogeneous,
massively parallel environment.
He leads the WM-CAPS research group.
Awards
- 2011 DOE (Department of Energy) Early Career Award
- 2010 NSF (National Science Foundation) CAREER Award
- 2010, 2011, 2012 IBM CAS Faculty Fellow
- 2010 ACM PPoPP Best Paper Award
Recent Professional Activities
- Program Committees: SC'13, IPDPS'13, SC'12, Micro'12 (ERC), ASPLOS'12, OOPSLA'12, PPOPP'12, ACM Grand SRC'12, ICPP'12, IPDPS'12, InPar'12, PPPJ'12, ISMM'12 (ERC), EXADAPT'12, GPGPU'12, AsHES'12, IISWC'11, MSPC'11, OOPSLA'11 (ERC), SMART'11, GPUScA'11, NPC'11, IPDPS'11, CGO'11, PDCN'11, IISWC'10, NPC'10, GPUScA'10, SMART'10, ISMM'09, iWAPT'09
- Organizing Committees: CGO'13 (Publication Chair), ICPP'12 (Program Vice Co-Chair of Compilers & Runtime track), MSPC'11 (PC Co-Chiar), PPOPP'12 (Workshops & Tutorials Chair), ICS'11 (Workshops & Tutorials Chair), PACT'11 (ACM Student Research Competition Chair), IISWC'10 (Publications Chair), PACT'09 (Posters and ACM Student Research Competition Chair)
- Panelists: DOE'11, NSF ICSE'11, IISWC'10, NSF ICSE'09, NSF ICSE'08
Research Interests
- Extreme-Scale, Data-Intensive Computing
- Accelerator-Based Heterogeneous High Performance Computing (GPU, CELL, etc.)
- Data Locality, Memory Hierarchies, and Memory Management
- Virtual Machines and Just-In-Time Compilation
- Program Dynamic Optimizations and Parallelization
- Program Phase Analysis
- Statistical/Machine Learning
Recent and Selected Publications (full list of publications)
[PPOPP'13] "Complexity Analysis and Algorithm Design for Reorganizing Data to Minimize Non-Coalesced Memory Accesses on GPU", Bo Wu, Zhijia Zhao, Eddy Z. Zhang, Yunlian Jiang, and Xipeng Shen, PPOPP, Shenzhen, China, 2013. (to appear)
[CGO'13] "ProfMig: A Framework for Flexible Migration of Program Profiles Across Software Versions", Mingzhou Zhou, Bo Wu, Yufei Ding, and Xipeng Shen, CGO, Shenzhen, China, 2013. (to appear)
[OOPSLA'12] "Exploiting Inter-Sequence Correlations for Program Behavior Prediction", B. Wu and Z. Zhao and X. Shen and Y. Jiang and Y. Gao and R. Silvera, SPLASH/OOPSLA, Tucson, AZ, 2012. [PDF]
[PACT'12] "Speculative Parallelization Needs Rigor: Probabilistic Analysis for Optimal Speculation of Finite State Machine Applications", Z. Zhao and B. Wu and X. Shen, PACT, Minneapolis, MN, 2012. (2-page poster paper)
[ICS'12] "One Stone Two Birds: Synchronization Relaxation and Redundancy Removal in GPU-CPU Translation", Z. Guo and B. Wu and X. Shen, ACM International Conference on Supercomputing,Venice, Italy, 2012. [PDF]
[PACT'11] "Enhancing Data Locality for Dynamic Simulations through Asynchronous Data Transformations and Adaptive Control", Bo Wu, Eddy Zhang, Xipeng Shen, The Twentieth International Conference on Parallel Architectures and Compilation Techniques, Galveston Island, Texas, USA, Oct, 2011. Acceptance rate: 16% (36/221). [PDF]
[PACT'11] "Correctly Treating Synchronizations in Compiling Fine-Grained SPMD-Threaded Programs for CPU", Ziyu Guo, Eddy Zhang, Xipeng Shen, The Twentieth International Conference on Parallel Architectures and Compilation Techniques, Galveston Island, Texas, USA, Oct, 2011. Acceptance rate: 16% (36/221). [PDF]
[OOPSLA'11] "A Step Towards Transparent Integration of Input-Consciousness into Dynamic Program Optimizations", Kai Tian, Eddy Zhang, Xipeng Shen, 2011 ACM International Conference on Systems, Programming, Languages and Applications, Portland, Oregon, USA, Oct, 2011. Acceptance rate: 37% (61/166). [PDF]
[TPDS'11] "The Significance of CMP Cache Sharing on Contemporary Multithreaded Applications", Eddy Zhang, Yunlian Jiang, Xipeng Shen, IEEE Transactions on Parallel and Distributed Systems. (accepted in March 2011; to appear)
[ASPLOS'11] "On-the-Fly Elimination of Dynamic Irregularities for GPU Computing", Eddy Z. Zhang, Yunlian Jiang, Ziyu Guo, Kai Tian, Xipeng Shen, the Sixteenth International Conference on Architectural Support for Programming Languages and Operating Systems , Newport Beach, California, USA, March, 2011. Acceptance rate: 21% (32/152). [PDF] [Slides]
[OOPSLA'10] "An Input-Centric Paradigm for Program Dynamic Optimizations", Kai Tian, Yunlian Jiang, Eddy Z. Zhang, Xipeng Shen, 2010 ACM International Conference on Systems, Programming, Languages and Applications, Reno, NEVADA, USA, Oct, 2010. Acceptance rate: 27% (45/164). [PDF] [Slides]
[TPDS'10] "The Complexity of Optimal Job Co-Scheduling on Chip Multiprocessors and Heuristics-Based Solutions", Yunlian Jiang, Kai Tian, Xipeng Shen, Jinghe Zhang, Jie Chen, Rahul Tripathi, IEEE Transactions on Parallel and Distributed Systems, 10.1109/TPDS.2010.193, Nov, 2010. [PDF]
[ICS'10] "Streamlining GPU Applications On the Fly", E. Z. Zhang, Y. Jiang, Z. Guo, X. Shen, ACM International Conference on Supercomputing,Tsukuba, Japan, June, 2010. Acceptance rate: 17.8% (32/180). [PDF][Slides]
[CC'10] "Is Reuse Distance Applicable to Data Locality Analysis on Chip Multiprocessors?", Y. Jiang, E. Zhang, K. Tian, X. Shen, International Conference on Compiler Construction,Paphos, Cyprus, March, 2010. Accpetance rate: 28% (15/56). [PDF][Slides]
[CGO'10] "Exploiting Statistical Correlations for Proactive Prediction of Program Behaviors", Y. Jiang, E. Zhang, K. Tian, F. Mao, M. Gethers, X. Shen, Y. Gao, ACM/IEEE International Symposium on Code Generation and Optimization, Toronto, April, 2010. [PDF][Slides]
[PPoPP'10] "Does Cache Sharing on Modern CMP Matter to the Performance of Contemporary Multithreaded Programs?", Eddy Z. Zhang, Yunlian Jiang, Xipeng Shen, the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, Bangalore, India, Jan, 2010. Acceptence rate: 16.7% (29/173). [PDF][Slides] (Best Paper Award)
[HiPEAC'10] "Combining Locality Analysis with Online Proactive Job Co-Scheduling in Chip Multiprocessors", Yunlian Jiang, Kai Tian, and Xipeng Shen, the International Conference on High-Performance Embedded Architectures and Compilers, Pisa, Italy, Jan, 2010. Acceptance rate: 25.5% (24/94). [PDF][Slides]
[IPDPS'09] ``A Cross-Input Adaptive Framework for GPU Programs Optimization", Yixun Liu, Eddy Zheng Zhang, and Xipeng Shen, 2009 IEEE International Parallel & Distributed Processing Symposium, Rome, Italy, May, 2009. Acceptance rate: 23% (100/440). [PDF]
[CF'09] ``A Study on Optimally Co-scheduling Jobs of Different Lengths'', Kai Tian, Yunlian Jiang, Xipeng Shen, The ACM International Conference on Computing Frontiers, Ischia, Italy, May, 2009. Acceptance rate: 23% (26/113).[PDF]
[CGO'09] ``Cross-Input Learning and Discriminative Prediction in Evolvable Virtual Machine'', Feng Mao, and Xipeng Shen, 2009 International Symposium on Code Generation and Optimization, Seattle, Washington, March, 2009. [PDF][Slides]
[VEE'09] ``Influence of Program Inputs on the Selection of Garbage Collectors'', Feng Mao, and Xipeng Shen, The 2009 ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments, Washington, DC, March, 2009. Acceptance rate: 35% (14/40). [PDF][Slides]
[PACT'08] ``Analysis and Approximation of Optimal Co-scheduling on CMP'', Yunlian Jiang, Xipeng Shen, Jie Chen, and Rahul Tripathi, the International Conference on Parallel Architecture and Compilation Techniques, Toronto, Canada, October, 2008. Acceptance rate: 18% (29/159). [PDF]
[PLDI'07]``Software Behavior-oriented Parallelization'', C. Ding, X. Shen, K. Kelsey, C. Tice, R. Huang, C. Zhang, the Conference on Programming Language Design and Implementation, San Diego, CA, June 2007. Acceptance rate: 25% (45/178).[PDF][Slides]
[POPL'07] ``Locality Approximation Using Time'', X. Shen, J. Shaw, B. Meeker, C. Ding, the Symposium on Principles of Programming Languages, Nice, France, January 2007. Acceptance rate: 18% (36/198).[PDF][Slides](7-page short paper)
[ICS'05] ``Lightweight Reference Affinity Analysis'', Xipeng Shen, Yaoqing Gao, Chen Ding, and Roch Archambault, in Proceedings ofthe Ninteenth ACM International Conference on Supercomputing (ICS 2005), Cambridge, MA, USA, June 2005, pages 131--140. Acceptance rate: 28% (42/152).[PDF]
[ASPLOS'04] ``Locality Phase Prediction'', Xipeng Shen, Yutao Zhong, and Chen Ding, in Proceedings of the Eleventh International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS XI), Boston, MA, USA, October 2004, pages 165--176. Acceptance rate: 14% (24/169). [PDF][Slides]
[PLDI'04] ``Array Regrouping and Structure Splitting Using Whole-Program Reference Affinity'', Yutao Zhong, Maksim Orlovich, Xipeng Shen, Chen Ding, in Proceedings of ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2004), Washington DC, USA, June 2004, pages 255--266. Acceptance rate: 20% (25/127).[PDF]
Teaching
- CSC420/520 - Introduction to Machine Learning (Fall 2011)
- CSC420/520 - Computing in the Multicore Era (Fall 2010)
- CSC780 - Programming Systems for Multi-core and GPU (Fall 2009, Fall 2008)
- CSC652 - Advanced Compiler Construction (Spring 2012,Spring 2011,Spring 2010,Spring 2009,Spring 2008, Spring 2007)
- CSC442/542 - Compiler Construction (Fall 2007)
CSC420/520 - Mathematical Foundations of Artificial Intelligence (Fall 2006)
Quick Links: Curriculum Vitae Publications
News :
7/2012 SPLASH'12/OOPSLA'12 accepts a paper on loop sequence prediction.
6/2012 PACT'12 accepts a 2-page poster paper on rigorous speculative parallelization.
3/2012 ICS'12 accepts a paper on optimizing GPU-CPU translation.
10/2011 Zhijia Zhao won 2nd place in the ACM Student Research Competition at PACT'11.
9/2011 LCPC'11 published paper on GPU-CPU translation.
6/2011 PACT'11 accepted two papers, on opt irreg app and gpu compilation respectively.
6/2011 SPLASH/OOPSLA'11 accepted paper on Input-Conscious Dyn. Opt.
5/2011 DOE Early Career Award! (detail)
3/2011 Journal paper accepted by IEEE TPDS.
10/2010 ASPLOS'11 accepted paper on GPU runtime optimizations.
9/2010 Journal paper accepted by IEEE TPDS.
5/2010 SPLASH (OOPSLA) accepted paper on input-centric dynamic optimizations.
4/2010 IBM CAS Canada Research Faculty Fellow. (detail)
3/2010 ACM ICS'10 accepted paper on streamlining GPU applications.
3/2010 NSF CAREER Award! (detail)
1/2010 Best Paper Award from ACM PPoPP'10! (detail)
12/2009 CC'10 accepted paper on multicore locality prediction.
11/2009 ACM/IEEE CGO'10 accepted paper on behavior correlations.
Contact :
- The Stata Center 32-G730
- MIT Computer Science and Artificial Intelligence Laboratory
- 32 Vassar Street
- Cambridge, MA 02139
- 617-253-7768 (voice)