Research Home

Shuaiwen Leon Song 

"Contrary to common belief, performance evaluation is an art." (Raj Jain, 1991)

Senior Staff Scientist and Technical Lead, 
High Performance Computing Group, 
Pacific Northwest National Laboratory (PNNL);
Adjunct Scholar, Computer Science Department,
College of William & Mary      

 I am currently a senior staff scientist and technical lead in High Performance Computing Group at Pacific Northwest National Lab (PNNL). I am also affiliated with College of William & Mary as a courtesy scholar in Computer Science Department. I received my Ph.D. in Computer Science from Virginia Tech in 2013. Prior to joining PNNL HPC group in May 2013, I worked as R&D intern with several government and industrial  labs including Center for Advanced Computing (CASC) at Lawrence Livermore National Lab (LLNL), Performance Analysis Lab (PAL) at Pacific Northwest National Lab (PNNL), and the Architecture Research Division at NEC Research American at Princeton.

I am the recipient of 2017 IEEE TCHPC early career award in high performance computing, 2011 Livermore ISCR scholar, 2011 Paul E. Torgersen Excellent research award and 2016 PNNL PCSD outstanding performance award. I have received two SC best paper nomination and a HiPEAC paper award. I have published in the major HPC-related conferences including ASPLOS, MICRO, HPCA, PPoPP, SC, PACT, CGO, HPDC, ICS, and IPDPS, etc. I serve as organizing committee or PC member for several major HPC venues including ASPLOS, PPoPP, SC, ICS, IPDPS, HPDC, etc. My past and current research are funded by several major government agencies including DOE ASCR, DoD, DoD DARPA and Lab LDRD.  I have continuing collaboration with both academia and industry labs (Microsoft Research, Intel lab, NVIDIA research). I am currently leading big data analytics and deep learning HPC design LDRD at PNNL.  

My research interests lie in several areas of High Performance Computing (HPC):
  • Performance and Energy evaluation and optimization for large-scale HPC systems
  • Software-Architecture Co-design
  • Emerging architectures (e.g., emerging many-core accelerators, complex memory architectures and deep-learning architectures)
  • Approximate Computing
  • Big data analytics and applied deep learning in HPC

Recent Awards and Recognition:
  • 2017 IEEE TCHPC early career award in high performance computing
  • HiPEAC Paper Award
  • Best paper finalist for SC'17
  • Best student paper finalist for SC'15
  • Courtesy Scholar, Computer Science Department, College of William & Mary 
  • DOE Lab Directed Research and Development (LDRD) Award on Machine Learning Initiative (MLI)
  • DOE Lab Directed Research and Development (LDRD) Award on EvoGraph framework.
  • PNNL PCSD Outstanding Performance Award. 
  • Chair, IEEE Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware (IPDRM), in conjunction with IPDPS.
  • Chair, The Twelfth IEEE Workshop on High-Performance Power-Aware Computing (HPPAC), in conjunction with IPDPS'16, Chicago. 
  • PNNL staff research highlight award 2015
  • PNNL research award 2015
  • 2011 Paul E. Torgersen excellent research award
  • 2011 Lawrence Livermore ISCR scholar
Software (release in progress):
  • PowerPack 2.0 [TPDS'10]
  • GraphReduce [SC'15]
  • EvoGraph [ISC'17]
  • CUDAAdvisor--- LLVM-based runtime profiling for modern GPUs [CGO'18]:  https://github. com/sderek/CUDAAdvisor.git
  • CCProf--- Lightweight Detection of Cache Conflicts [CGO'18]:
  • PNNL-GCollect: GPU toolkit (CTA manager, Register manager, Multi-GPU Docker, etc) for Big Data and Machine Learning 
  • ProphetGraph (under development)
  • SuperNeurons [PPoPP'18] (under development)

  • DOE ASCR research highlight on on-package memory impact on scientific applications:
  • Boosting graphics performance through processing in-memory
  • Digital Trends: <
  • Yahoo Tech: <>
  • Bit-Tech: <>
  • PNNL featured research news:
  • PNNL research highlight: Changing the game,
  • PNNL research spotlight: Improving computing system performance,, March 2016. 
  • "Powering Down", article about my work on power management on large-scale system, published on DOE DEIXIS magazine featured article, , written by Monte Basgall. 
  • PNNL Science Research Highlight: Energy Star: Novel models of HPC systems depict the interplay between energy efficiency and resilience", Link: ,2015.
  • PNNL ACMDD staff award and honors: PNNL HPC Staff Take on Energy E.ciency, Resilience at scale", Link:, 2015.
  • PNNL ACMDD staff award and honors: PNNL HPC Staff research: Improving Energy, Performance Efficiency for High Performance Computing", Link:, 2015.
  • PNNL Current Magazine: \HPC system modeling: Depicting interplay between energy efficiency and resilience", June 2015 issue.
  • InsideHPC: "PNNL looks at undervolting to meet exascale goals", written by Rich Bruecker, president of insideHPC:
  • HPC Wire Top Feature Article: "Tackling the Power and Energy wall for Future HPC Systems",, Dec, 2013.
  • 2018/4/10, our paper got accepted to ICS'18 @ Beijing. Congrats Ang !
  • 2018/3/14, our research on on-package memory impact has been featured on DOE ASCR research highlight: 
  • 2018/2/8, I am invited to serve on the review board for Concurrency and Computation, Practice and Experience (CCPE) journal. 
  • 2018/1/24, I am invited to serve as PC for PPoPP'19. 
  • 2018/1/24, I am participating DOE ASCR Heterogeneous workshop to help ASCR draft strategies for beyond exascale computing. I will also be helping Kirk Cameron@VT to lead discussion and power and resilience aspect of heterogeneity research. 
  • 2018/1/13, I had a great meeting with Professor Micheal Taylor at UW for our potential partnership for research on deep learning on ASIC cloud. 
  • 12/12, Our paper on system-level optimizing deep learning memory constraint has been accepted to PPoPP'18. Congrats everyone!
  • 11/15, I did my first remote lecture to graduate students@Duke University on GPU research. 
  • 11/15, I presented our nominated best paper on exploring the real impact of on-package memory on scientific kernels at SC17. It was really fun. 
  • 10/31, paper on runtime approximation on GPU for 3D rendering has been accepted to HPCA-24. Congratulations ~
  • 10/31, two CGO papers are accepted. Good work everyone!~
  • 10/27, I will be visiting Microsoft Research on Nov 3rd to discuss our deep learning collaboration. 
  • 10/27, I will be visiting Intel research to give a talk on 10/30. Very excited.
  • 10/12,  I will be receiving the 2017 IEEE TCHPC early career award at SC'17 award session. Very excited!
  • 10/9, I am funded as PI for the 2nd phase of DOE LDRD award for developing binarized neural network strategy on HPC and embedded GPUs. 
  • 8/15, I am invited to speak at the colloquium at the school of computing at Clemson University on September 22, 2017. 
  • 8/15, I am invited to give a talk at SIAM  PP18 in Tokyo Japan next march. 
  • 8/4, I serve as R&D 100 judge. 
  • 8/3, our paper on CTA clustering receives HiPEAC Paper award. Congratulations everyone!
  • 7/25, I will be the publication chair for ACM ICS'18 in Beijing. Please submit your interesting research!
  • 7/24, I am invited to serve PC for IPDPS'18. 
  • 7/5, I will be affiliated with College of William & Mary as a courtesy scholar, affiliated with Computer Science department. 
  • 7/2, our paper on power-efficient SRAM design for throughput-oriented architectures has been accepted to MICRO-50 (61/327=18.6%). 
  • 6/15, our paper on on-package memory has been nominated for SC'17 best paper ! Awesome. 
  • 4/28, I gave an invited talk at CS department of William and Mary. I was pleased to see many faculty and students there. 
  • 4/18, I am awarded another PI for DOE Lab LDRD on Machine Learning Initiative (MLI) HPC case studies. I am very excited to use deep learning strategies to explore approximate computing impact on HPC applications. 
  • 3/22. a paper is accepted at ICS'17. This work tackles the scalability issues facing the state-of-the-art Finite State Machine parallelization techniques. Congratulations to Junqiao and Zhijia!
  • 22/2/17, I will be giving two invited talks in April. One at Tsinghua University CS department on April 13th . Big Thanks to Professor Jidong Zhai.
  • 3/2, I am invited to serve as program committee the upcoming SC'17. Please submit your best work!
  • 7/1, I am invited to serve as ASPLOS'18 organizing committee (ACM SRC & Poster Co-chair). Please submit your best work to our fantastic conference !  
  • 29/11: My single PI PNNL LDRD has been awarded to fund my proposed research for two years. Exciting!
  • 17/11, I will be serving as PC for ICS'17. Please submit your interesting work!
  • 15/11, I was interviewed by NVIDIA at SC'16 about my research and the video will be released on their website !
  • 10/11, the paper me and my postdoc led has been accepted to ASPLOS-XXII. This work has explored a new type of locality on modern GPUs which may significantly impact future GPU architecture design as well software-level optimizations. This software-based technique is directly deployable to modern GPU hardware  without hardware modifications. We are really thrilled about this work. 
  • 10/12, our paper about utilizing HMC in GPU to processing graphics workload has been accepted to HPCA'17 main conference !
  • 9/19/2016, I will be serving the publicity chair and PC again for HPDC'17, Please submit your best work!
  • 08/20, I am invited to serve PC for IPDPS'17. 
  • 08/15, our paper gets accepted by USENIX Middelware 2016 with 19% acceptance rate. Congratulations to Eddy and Ahri. 
  • 06/30, Our paper got accepted by PACT 2016. Congratulations everyone! It will be interesting to visit Isreal in the fall. 
  • 05/06, I am very excited to be invited to attend 2016 Microsoft Research Summit on July 14~16 in Bellevue, WA. This is really exciting!
  • 03/22/2016: Two ICS papers are accepted today. I am glad that these two very interesting ideas are appreciated by the committee with great positive feedback. 
  • 03/12/2016: Two HPDC full papers are accepted, with an acceptance rate of 15.5% (20/130). This is definitely a great news!
  • 1/30/2016: I will be giving a invited talk to EECS at University of Houston on March 7th. ECE speaker series:
  • 12/19/2015: Our paper has been accepted to IPDPS 2016. Congrats everyone!
  • 11/02/2015: Our papers have been accepted to ACM HiPEAC 2016 and DATE 2016. 
  • 10/21/2015: I am invited to give a talk at UT Austin in November for my energy and resilience research. 
  • 10/20/2015: My research on energy and resilience at large scale will be featured at DOE Computer Science Graduate Fellowship website. 
  • 9/3/2015: Our paper has been accepted to ACM Transactions on Architecture and Code Optimization (TACO). Congrats Tan!
  • 9/1/2015: I am invited to serve on IPDPS'16 and HPDC'16 program committee.
  • 7/1/2015: Our GraphReduce paper is nominated for best student paper at SC'15. 
  • 6/30/2015: Our GraphReduce paper is accepted to appear in SC'15. 
  • 5/30/2015: My research is featured in insideHPC news: "PNNL looks at undervolting to meet exascale goals", article about our work at IPDPS'15, written by Rich Bruecker, president of insideHPC media, Inside HPC News:
  • 4/29/2015: PNNL has featured my two research from last year in research highlight and announcements:;;
  • 3/15/2015: Our paper got accepted to appear in ICS 2015. 
  • 3/12/2015: I am invited to serve as HPDC'16 publicity co-chair. 
  • 2/28/2015: I am invited to serve NSF proposal review panelist. 
  • 12/19/2014: I am invited to be serving the TPC member for performance track in the upcoming SC 15, Austin, Texas. 
  • 12/11/2014: During these couple of months, the following work got accepted: IPDPS'15 (energy&resilience techniques at scale), JPDC'14 (efficient SVM software design for large scale), ICPADS'14 (ACDT framework), ICS'14 (adaptive cross-architecture combination method for graph traversal), PPL'14 (extension to the MIC performance evaluation work).
  • 03/11/2014: I am serving as organizing committee member for DAC'14 SEAK workshop. 
  • 12/23/2013: I am serving as a PC member for IGCC'14. 
  • 12/17/2013: Our research work has been featured on HPC Wire.
  • 12/06/2013: Our MIC-SVM paper has been accepted by IPDPS'14.

Full Publication List:  Google Scholar Link  DBLP

Selected Publication List:

 ICS'18         Warp-Consolidation: A Novel Execution Model for GPUs
                     Ang Li, Weifeng Liu, Linnan Wang, Kevin Barker, Shuaiwen Leon Song
                     to appear in 32nd ACM International Conference on Supercomputing (ICS'18),
                    June, Beijing, China. 

TACO            NUMA-Caffe: NUMA-Aware Deep Learning Neural Networks, 
                     Probir Roy, Shuaiwen Leon Song, SRIRAM KRISHNAMOORTHY, Dipanjan Sengupta, Xu LiuACM                             Transactions on Architecture and Code Optimization (TACO), 2018 issues. 

HPCA-24      Perception-Oriented 3D Rendering Approximation for Modern Graphics Processors
                      Chenhao Xie, Xin Fu, Shuaiwen Leon Song
                      To appear in 24th IEEE International Symposium on High-Performance Computer                                                          Architecture (HPCA),  Vienna, Austria, February 24 – 28, 2018
                      Acceptance rate: 56/260=20%
                      Paper  Talk Bib

PPOPP'18   SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks
                      To appear in 2018 ACM Principles and Practice of Parallel Computing (PPoPP),
                    Vienna, Austria, February 24-28, 2018
                     Acceptance rate: 28/138 = 20%
                     Paper Talk   Bib


CGO'18        CUDAAdvisor: LLVM-based Runtime Profiling for Modern GPUs
                      Du Shen, Shuaiwen Leon Song, Ang Li, Xu Liu 
                      To appear in ACM International Symposium on Code Generation and Optimization, Vienna,                               Austria, Feb 24~28th. 
                     (Artifact Evaluation Stamped)
                       Paper  Talk Bib

CGO'18         Lightweight Detection of Cache Conflicts
                      Probir Roy, Shuaiwen Leon Song, Sriram Krishnamoorthy, Xu Liu 
                      To appear in ACM International Symposium on Code Generation and Optimization, Vinnea,                               Austria, Feb 24~28th. 
                     (Artifact Evaluation Stamped)
                       Paper  Talk Bib

MICRO-50       BVF: Enabling Significant On-Chip Power Savings via Bit-Value-Favor For Throughput                             Processors 
                        Ang Li, Wenfeng Zhao, Shuaiwen Leon Song
                        To appear in the 50th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO-50)
                        Acceptance rate: 61/327=18.6%
                        Paper  Talk Bib

SC'17             Exploring and Analyzing the Real Impact of Modern On-Package Memory on HPC Scientific Kernels
                      Ang Li, Weifeng Liu, Mads Kristensen, Brain Vinter, Hao Wang, Kaixi Hou and Shuaiwen Leon Song
                      29th ACM/IEEE International Conference for High Performance Computing, Networking, Storage and                         Analysis, Denver, Co, 2017
                    Image result for award iconNominated for Best Paper. Acceptance rate: 61/327=18.6%
                       Paper  Talk  Bib            

ICS'17              ScalaFSM: Enabling Scalability-Sensitive Speculative Parallelization for FSM Computations
                        Junqiao Qiu, Zhijia Zhao, Bo Wu, Abhinav Vishnu and Shuaiwen Leon Song
                         To appear in ACM International Conference on Supercomputing,
                         Chicago, U.S., June 13th~16th, 2017
                          Acceptance rate: 28/177=15.8%
                          Paper  Talk  Bib

ASPLOS-XXII   Locality-Aware CTA Clustering For Modern GPUs 
                        Ang Li, Shuaiwen Leon Song, Weifeng Liu, Xu Liu, Akash Kumar, Henk Corporal
                        To appear in ACM International Conference on Architectural Support for Programming Languages
                        and Operating Systems (ASPLOS-XXII), Xi'An, China, April 8~12, 2017
                   HiPEAC Paper Award. Acceptance rate: 56/321=17.4%       
                        Paper  Talk  Bib


HPCA-23         Processing-in-Memory Enabled Graphics Processors for 3D Rendering
                      Chenhao Xie, Shuaiwen Leon Song, Xin Fu
                      In proceedings of 23rd IEEE International Symposium on High-Performance Computer                                             Architecture (HPCA), Austin, Texas, USA, February 4 – 8, 2017
                      Acceptance rate: 50/231=21.6%
                      Paper  Talk  Bib

ISC-17            EvoGraph: On-The-Fly Efficient Mining of Evolving Graphs on GPU
                      Dipanjon Sengupta and Shuaiwen Leon Song
                      To appear in 2017 International Conference on Supercomputing, Frankfurt, Germany, June 22nd, 2017
                      Paper  Talk  Bib

Middleware'16   ORION: A Framework for GPU Occupancy Tuning, Ari B. Hayes, Lingda Li, Daniel Chavarria,                                   Shuaiwen Leon Song, Eddy Z. Zhang, accepted to appear in annual ACM/IFIP/USENIX 
                        Middleware Conference 2016, Trento, Italy. 
                        (Acceptance rate: 21/107=19%)
                        Paper  Talk   Bib

PACT'16         Combating the Reliability Challenge of GPU Register File at Low Supply Voltage
                      Jingweijia Tan, Shuaiwen Leon Song, Kaige Yan, Xin Fu, Andres Marquez, Darren Kerbyson
                      To appear in the 25th ACM/IEEE/IFIP International Conference on Parallel Architectures and                                     Compilation Techniques (PACT), Haifa, Israel, September, 2016. 
                      Acceptance rate: 31/139=22%
                      Paper  Talk  Bib

                             SFU-Driven Transparent Approximation Acceleration on GPUs
                      Ang Li, Shuaiwen Leon Song, Mark Wijtvliet, Akash Kumar, Henk Corporaal
ICS'16            To appear in 30th ACM International Conference on Supercomputing 
                             Istanbul, Turkey, June 2016.
                             Acceptance rate: 43/180=23.8%
                             Paper    Talk  Bib

                             Tag-Split Cache for Efficient GPGPU Cache Utilization
ICS'16            Lingda Li, Ari Hayes, Shuaiwen Leon Song, Eddy Zheng Zhang
                      To appear in 30th ACM International Conference on Supercomputing
                      Istanbul, Turkey, June 2016.
                             Acceptance rate: 43/180=23.8%
                      Paper    Talk  Bib 

                      SMT-Aware Instantaneous Footprint Optimization
                             Probir Roy, Xu Liu, Shuaiwen Leon Song
HPDC'16        To appear 25th ACM international Symposium on High-Performance and Distributed Computing
                      Kyoto, Japan, 2016 
                      Acceptance rate: 20/130=15.5%
                        Paper   Talk   Bib

                       New-Sum: A Novel Online ABFT Scheme For General Iterative Methods  
                       Dingwen Tao, Shuaiwen Leon Song, Sriram Krishnamoorthy, Panruo Wu, Eddy Zheng Zhang, 
                       Zizhong Chen, Darren Kerbyson
HPDC'16             To appear 25th ACM international Symposium on High-Performance and Distributed Computing
                       Kyoto, Japan, 2016 
                       Acceptance rate: 20/130=15.5%
                       Paper   Talk   Bib

                         X: A Comprehensive Analytic Model for Parallel Machines
                         Ang Li, Shuaiwen Leon Song, Akash Kumar, Daniel Chavarria, Henk Corporaal
IPDPS'16          To appear in 30th IEEE International Parallel & Distributed Processing Symposium (IPDPS)
                         Chicago, U.S., 2016
                         Acceptance rate: 114/496=22%
                         Paper   Talk  Bib

                       Scalable Energy Efficiency with Resilience for High Performance Computing Systems: A Quantitative                        Methodology
TACO              Li Tan, Zizhong Chen, Shuaiwen Leon Song
                       ACM Transactions on Architecture and Code Optimization
                         Volume 12 Issue 4, Article No. 35, January 2016 
                       Paper  Bib
                         Critical Point Based Register-Concurrency Autotuning For GPUs
DATE'16          Ang Li, Shuaiwen Leon Song, Akash Kumar, Eddy Z.Zhang, Daniel Chavarrria, and Henk Corporaal
                       Design, Automation & Test In Europe Conference
                               Dresden, Germany, 2016
                        Acceptance rate: 24%
                               Paper   Talk  Bib   

                         Scalable Energy Efficiency with Resilience for High Performance Computing Systems: A Quantitative                        Methodology
HiPEAC'16       Li Tan, Zizhong Chen, Shuaiwen Leon Song
                       11th ACM International Conference on High Performance Embedded Architectures and Compilers 
                       Prague, Czech Republic, 2016  
                       Paper  Talk  Bib  

                      GraphReduce: Processing Large-scale Graphs on Accelerator-based Systems 
SC'15             Dipanjan Sengupta, Shuaiwen Leon Song, Kapil Agarwal, Karsten Schwan 
                      27th ACM/IEEE International Conference for High Performance Computing, Networking, Storage and                         Analysis, Austin, TX, 2016
                    Image result for award iconRunner-Up for Best Student Paper. Acceptance rate: 4/358=1%
                      Paper  Talk  Bib            

                        Locality-Driven Dynamic GPU Cache Bypassing     
ICS'15            Chao Li, Shuaiwen Leon Song, Hongwen Dai, Albert Sidelnik, Siva Hari, Huiyang Zhou
                      29th ACM International Conference on Supercomputing
                      Newport Beach,CA, 2015
                      Acceptance rate: 22%
                      Paper  Talk  Bib  

                       Investigating the Interplay Between Energy Efficiency and Resilience in High Performance Computing
IPDPS'15         Tan Li, Shuaiwen Leon Song, Panruo Du, Zizhong Chen, Rong Ge, Darren Kerbyson
                       29th IEEE International Parallel & Distributed Processing Symposium 
                       Hyderabad, India, 2015
                       Acceptance rate: 21%
                       Paper Talk  Bib

                              Scaling Support Vector Machines On Modern HPC Platforms  
JPDC              Yang You, Haohuan Fu, Shuaiwen Leon Song, Amanda Randles, Darren J. Kerbyson,                                              Andres Marquez, Guangwen Yang, Adolfy Hoisie  
                       Elsevier Journal of Parallel and Distributed Computing 
                              JPDC-14-60R2, 2014
                       Designing A Highly Efficient and Adaptive Cross-Architecture Combination Method for Graph Traversal
                     Yang You, Shuaiwen Leon Song, Darren Kerbyson
ICS'14           28th ACM International Conference on Supercomputing
                     Munich, Germany, June 2014
                     Paper Bib

                     MIC-SVM: Designing A Highly Efficient Support Vector Machine For Advanced Modern Multi-Core and                      Many-Core Architectures                   
IPDPS'14       Yang You, Shuaiwen Leon Song, Haohuan Fu, Andres Marquez, Guangwen Yang, Kevin Barker, Kirk                        Cameron, Maryam Dehanavi, Amanda Peters Randles
                     28th IEEE International Parallel & Distributed Processing Symposium 
                     Phoniex, Arizona, 2014
                     Acceptance rate: 21%
                     Paper  Bib

                              Power, Performance and Energy Models and Systems for Emergent Architectures
PhD Thesis      Shuaiwen Leon Song
                              May 2013, Virginia Tech

                       Unified Performance and Power Modeling of Scientific Workloads
                       Shuaiwen Leon Song, Kevin J.Barker, Darren J.Kerbyson
E2SC'13          International workshop on Energy Efficient Supercomputing (E2SC) In Conjunction with SC'13
                               Denver, Colorado, U.S.
                       Paper Bib

                         Evaluating the Multi-core and Many-core Architectures Through Accelerating the Three-Dimensional                          Lax-Wendroff Correction Stencil
                       Yang You, HaoHuan Fu, Shuaiwen Leon Song, Maryam Mehri Dehnavi, Guangwen Yang
IJHPCA            International Journal of High Performance Computing Applications
                          Paper Bib

                                Exploring Machine Learning Techniques for Dynamic Modeling on Future Exascale Systems
                        Shuaiwen Leon Song, Nathan R. Tallent, Abhinav Vishnu
Modsim'13       DOE annual workshop on modeling and simulation of exascale systems and applications (Modsim)
                        Seattle, Washington, September 2013

                                A Simplified and Accurate Model of Power-Performance Efficiency on Emergent GPU Architectures
                        Shuaiwen Leon Song, Chun-yi Su, Barry Rountree, Kirk W. Cameron
IPDPS'13          27th IEEE International Parallel & Distributed Processing Symposium
                        Boston, U.S., May 2013
                        Acceptance rate: 20%
                        Paper  Bib

                               System-Level Power-Performance Efficiency Modeling for Emergent GPU Architectures
PACT'12          Shuaiwen Leon Song, Kirk W. Cameron
                       21st International Conference on Parallel Architectures and Compilation Techniques 
                       Minneapolis, Minnesota, Sept 2012
                       Paper Bib

                             Iso-energy-efficiency: An approach to power-constrained parallel computation                        
                      Shuaiwen Song, Chun-yi Su, Rong Ge, Vishnu A, Kirk W. Cameron
IPDPS'11        25th IEEE International Parallel & Distributed Processing Symposium
                      Anchorage, Alaska, May 2011
                      Acceptance rate: 19%
                       Paper Bib
                            Designing Energy Efficient Communication Runtime System: A View from PGAS Models
JOS                    Vishnu A, Shuaiwen Leon Song, A Marquez, K.J. Barker, D.J. Kerbyson, Kirk. W. Cameron 
                     Journal of Supercomputing, Springer, 2011
                     Paper Bib
                             Iso-energy-efficiency: An approach to scalable system power-performance optimization
SC'11                Shuaiwen Leon Song
                      Selected Ph.D. Showcase
                             23th ACM/IEEE International Conference for High Performance Computing, Networking, Storage and                         Analysis, Seattle, WA, 2011

                            PowerPack: Energy profiling and analysis of high performance systems and applications
TPDS            Rong Ge, Xizhou Feng, Shuaiwen Leon Song, Hung-Ching Chang, Dong Li, Kirk W. Cameron
                            IEEE Transactions on Parallel and Distributed Systems 
                     Volume 21, Number 5, Page 658, May 2010. 
                            Paper Bib
                        Energy Profiling and Analysis of HPC Challenge Benchmarks
IJHPCA          Shuaiwen Leon Song, Rong Ge, Xizhou Feng, Kirk W. Cameron
                        International Journal of Hi Performance Computing Applications
                      Volume 23, Issue 3, Pages: 265-276, August 2009 
                        Paper Bib

Book Chapter:

Shuaiwen Leon Song and Kirk W. Cameron, "Harnessing Green IT: Principles and Practices", Chapter 2: Green Computer. S. Murugesan and G. Gangadharan (eds), Wiley Press, UK, 2011. 

Professional Activities:
  • PPoPP'19, Program Committee
  • HPDC'18, Program Committee and Publicity Chair
  • ASPLOS'18, organizing committee (ACM SRC & Poster chair) 
  • ICS'18, Publication Chair
  • IPDPS'18, Program Committee (primary) 
  • SC'17, Program Committee for programming system track
  • ICS'17, Program Committee
  • HPDC'17, Publicity chair
  • HPDC'17, PC member
  • IPDPS'17, PC member
  • HPDC'16, session chair
  • IPDPS'16 , session chair for distributed algorithms
  • HPDC'16, PC member
  • IPDPS'16, PC member
  • ISPA'16, PC member
  • ICPADS'16, PC member
  • IGCC'16, PC member
  • chairing IPDPS'16-HPPAC workshop 
  • chairing IPDPS'16-IPDRM workshop
  • HPDC'16, publicity co-chair
  • SC'15, session chair
  • SC'15, PC Committee for performance track
  • ICPP'15, Performance Modeling Track
  • IGCC'15, PC.
  • ISPA'15, PC. 
  • IGCC'15, PC.
  • NSF proposal panelist
  • CCGRID'15 Poster Program Committee
  • ACM CF'15 - Workshop on Analytics Platforms for the Cloud 
  • Publicity chair for IPDPS'15-HPPAC workshop
  • Organizing committee member for HPCC'15 
  • External reviewer for CCGRID'15 
  • IGCC'14- GPCDP workshop 
  • SC'14-E2SC workshop
  • SC'14-E2SC workshop session chair
  • CCGRID'14 session chair for scheduling
  • CCGRID'14 
  • International Workshop on Big Data Analytics, Management and Storage (ASE Big Data Science 2014)
  • DAC-SEAK'14 workshop
  • IGCC'14 
  • IPDPS'14-HPPAC workshop
  • IPDPS'13 session chair for programming framework
  • SC'13-E2SC workshop
  • SC 12 Panelist for BOF "Cooling Supercomputing: Achieving Energy Efficiency At Extreme Scales"

Collaborators And Mentored Ph.D. students:
  • Albert Sidelnik, NVIDIA Research
  • Siva Hari, NVIDIA Research
  • Daniel Wong, UC Riverside
  • Xu Liu, William & Mary
  • Chao Li, NCSU (Ph.D. student. Currently at Qualcomm)
  • Zhen Lin, NCSU (Ph.D. student)
  • Huiyang Zhou, NCSU
  • Tan Li, UC Riverside (Ph.D. student, now at Los Alamos National Lab)
  • Dingwen Tao, UC Riverside (Ph.D. student)
  • Zizhong Chen, UC Riverside
  • Barry Rountree, LLNL
  • You Yang, UC Berkeley (Ph.D. student)
  • Amanda Peters Randles, Duke University
  • Eddy Zhang, Rutgers University
  • Karsten Schwan, Georgia Tech
  • Xin Fu, University of Houston
  • Lizhong Chen, Oregon State University
  • DipanJan Sengupta, Georgia Tech (Ph.D. student)
  • Ang Li, PNNL (postdoc)
  • Jingweijia Tan, University of Houston (Ph.D. student, Ph.D. committee, currently at Qualcomm)
  • Probir Roy, William & Mary (Ph.D. student)
  • Du Shen, William & Mary (Ph.D. student)
  • Zhijia Zhao, UC Riverside 

My Recent CV Upon Request.

Please Contact me at: 

Office: 509-372-4189

Contact Email: