GCASR 2016‎ > ‎

Presentations



 

Opening Remarks

8:00 am - 8:10 am

 

History and Mission of GCASR 

 Andrew A. Chien (University of Chicago)

   
Opening Remarks by GCASR 2015 Co-Chairs

 Shan L(University of Chicago)

Fabián E. Bustamante (Northwestern University)


 

Keynote I

8:10 am - 9:10 am

(Session Chair: Andrew Chien, University of Chicago)

https://dl.dropboxusercontent.com/u/8950924/MJF2013HS.jpg




Emerging Trends in Big Data Software and the Berkeley Data Analytics Stack

Michael Franklin (UC Berkeley / University of Chicago)


AbstractBig Data software has created quite a stir, largely driven by open source environments such as Hadoop and Spark.   In this talk, I’ll begin by giving an overview of one such environment, the Berkeley Data Analytics Stack (BDAS) which has been built over the past 6 years by the students and researchers at the UC Berkeley AMPLab.  BDAS has served as the launching platform for Spark, Mesos, Tachyon, GraphX, MLlib and other popular systems.  I’ll describe BDAS and say a bit about how the organization of the AMPLab enabled us to have significant and fairly immediate impact on industrial practice as an academic project.   I will then survey some of the more recent extensions to BDAS including some or all of the following: real-time analytics, machine learning model serving, machine learning pipeline optimization,  and human-in-the-loop analytics.   This is an extended version of a short keynote presented at the recent Strata big data industry conference.

Bio: Michael Franklin recently joined the Department of Computer Science at the University of Chicago after seventeen years on the faculty at UC Berkeley, where he still serves as Director of the Algorithms, Machines, and People Laboratory (AMPLab), an NSF CISE Expedition in Computing center.   He is an ACM Fellow, a two-time winner of the ACM SIGMOD “Test of Time” award, has several recent “Best Paper” awards and two recent CACM Research Highlights selections, and is recipient of the outstanding Advisor Award from the Computer Science Graduate Student Association at Berkeley. 
 

Keynote II

5:00 pm - 6:00 pm

(Session Chair: Andrew Chien, University of Chicago)

Bill Dally



Efficiency and Programmability: The Challenges of Future Computing

William Dally (NVIDIA)


Abstract: The computing demands of mobile devices, data centers, and HPC are increasing exponentially.  At the same time, the end of Dennard scaling has slowed the rate of improvement and made all computing power limited.  With improvements in semiconductor process technology offering little increase in efficiency, innovations in architecture and circuits are required to maintain the expected performance scaling.   Specialized hardware gives excellent efficiency but at the expense of generality and programmability. 

To compensate for slower scaling, emerging computer systems have heterogenous processors, deep memory hierarchies, and large-scale parallelism - making them challenging to program.  Target-independent programming has the potential to greatly simplify the programming of these machines.  The programmer expresses all of the parallelism and abstract representations of locality.   Mapping tools adapt the program to the characteristics of a particular target machine. 

This talk will discuss these challenges of efficiency and programmability in more detail and introduce some of the technologies being developed to address them.

Bio
Bill is Chief Scientist and Senior Vice President of Research at NVIDIA Corporation and a Professor (Research) and former chair of Computer Science at Stanford University. Bill and his group have developed system architecture, network architecture, signaling, routing, and synchronization technology that can be found in most large parallel computers today. While at Bell Labs Bill contributed to the BELLMAC32 microprocessor and designed the MARS hardware accelerator. At Caltech he designed the MOSSIM Simulation Engine and the Torus Routing Chip which pioneered wormhole routing and virtual-channel flow control. At the Massachusetts Institute of Technology his group built the J-Machine and the M-Machine, experimental parallel computer systems that pioneered the separation of mechanisms from programming models and demonstrated very low overhead synchronization and communication mechanisms.  At Stanford University his group has developed the Imagine processor, which introduced the concepts of stream processing and partitioned register organizations, the Merrimac supercomputer, which led to GPU computing, and the ELM low-power processor.  Bill is a Member of the National Academy of Engineering, a Fellow of the IEEE, a Fellow of the ACM, and a Fellow of the American Academy of Arts and Sciences.  He has received the ACM Eckert-Mauchly Award, the IEEE Seymour Cray Award, the ACM Maurice Wilkes award, and the  IPSJ FUNAI Achievement Award.  He currently leads projects on computer architecture, network architecture, circuit design, and programming systems. He has published over 200 papers in these areas, holds over 100 issued patents, and is an author of the textbooks, Digital Design: A Systems Approach, Digital Systems Engineering, and Principles and Practices of Interconnection Networks.


Session 1: Security & Reliability

9:30 am - 11:30 pm (1st floor)

(Session Chair: Venkat Venkatakrishnan, University of Illinois at Chicago)




 

Trustworthy Systems through Information-Flow Analysis

Fred Chong (University of Chicago)



Bio: Fred Chong is the Seymour Goodman Professor of Computer Architecture in the Department of Computer Science at the University of Chicago. Chong received his Ph.D. from MIT in 1996 and was a faculty member and Chancellor's fellow at UC Davis from 1997-2005. He was also a Professor of Computer Science, Director of Computer Engineering, and Director of the Greenscale Center for Energy-Efficient Computing at UCSB from 2005-2015. His research interests include computer security, emerging technologies for computing, multicore and embedded architectures, and sustainable computing. 




 Lather, Rinse, Repeat: Opportunities in High Performance Software Development

Paul Petersen (Intel)


Bio: Paul Petersen is a Sr. Principal Engineer in the Software and Solutions Group (SSG) at Intel leading a team in defining next generation features for parallel runtimes and software analysis tools.   He received a Ph.D. degree in Computer Science from the University of Illinois in 1993.   After UIUC, he was employed at Kuck and Associates, Inc. (KAI) working on auto-parallelizing compiler (KAP), and was involved in the early definition and implementations of OpenMP.   While at KAI, he developed the Assure line of parallelization/correctness products, for Fortran, C++ and Java.   In 2000, Intel Corporation acquired KAI, and he joined the software tools group creating the Thread Checker products, which evolved into the Inspector and Advisor components of the Intel® Parallel Studio.  Inspector uses dynamic binary instrumentation to detect memory and concurrency bugs, and Advisor uses similar techniques along with performance measurement and modeling to assist developers in transforming existing serial applications to be ready for parallel execution. 


Yanjing Li


 

Cross-Layer Resilience

Yanjing Li (University of Chicago)



Bio: Yanjing Li is an assistant professor in the Department of Computer Science (Systems Group), University of Chicago. She received her Ph.D. in Electrical Engineering from Stanford University. Prior to joining University of Chicago, she was a senior research scientist at Intel Labs. Dr. Li's research interests lie broadly in the area of computer architecture and systems, which include robust system design, energy-efficient systems, and emerging technologies. Dr. Li’s awards and honors include the European Design and Automation Association Outstanding Dissertation Award, the IEEE International Test Conference Best Student Paper Award, the IEEE VLSI Test Symposium Best Paper Award, and multiple Intel Divisional Recognition Awards. 




Jason Flinn

Learning from the Past: Fast, On-Demand Analysis of Prior Executions with Eidetic Systems

Jason Flinn (University of Michigan)


Bio: Jason Flinn is a Professor of Computer Science and Engineering at the University of Michigan, Ann Arbor.  His research interests include operating systems, distributed systems, and mobile computing.  He is currently the director of the Software Systems Laboratory at the University of Michigan.  His research has been recognized with an NSF CAREER award and 8 best paper awards at SOSP, OSDI, ASPLOS, FAST, and MobiSys.

 





 

Discovering and Rendering In-memory Forensics Information with Confidence

Dongyan Xu (Purdue University)


Bio: Dongyan Xu is a professor of computer science and a University Faculty Scholar at Purdue University. He is also affiliated with the Center for Education and Research in Information Assurance and Security (CERIAS). He has been on Purdue faculty since 2001, when he received his Ph.D. in computer science from the University of Illinois at Urbana-Champaign. His research efforts span computer systems security and forensics, cloud computing, and virtualization, with projects sponsored by both government agencies and industry. He is the co-author of six award-winning papers at major conferences in security and cloud computing.
 

Session 2: GPU & Parallel Systems

9:30 am - 11:30 am (9th floor)

(Session Chair: Nikos Hardavellas, Northwestern University)




 

Argo NodeOS: Node-level Hardware Resource Management for an Exascale Operating System

Judicael A. Zounmevo (Argonne National Lab)




Bio: Judicael Zounmevo is a postdoc in the Mathematics and Computer Science division of Argonne National Laboratory. His research covers operating systems concerns for HPC, parallel and distributed computing at extreme scale, MPI and RDMA.






Application-Oriented Network Traffic Analysis based on GPUs

Wenji Wu (Fermi Lab)


Bio: Dr. Wenji Wu is a Principal Network Research Investigator at Core Computing Division, Fermilab, where he has worked on high-speed networking, and bulk data transfer. His research focus is to utilize multicore and manycore to address performance challenges in high-speed networks. Dr. Wu is now responsible for two DOE network research projects, the MDTM project (http://mdtm.fnal.gov) and the BigData Express project (http://bigdataexpress.fnal.gov). He is also working on the WireCAP project (http://wirecap.fnal.gov). Dr. Wu earned his PhD in computer engineering from University of Arizona. 



Parallelization in the Multicore Era

Simone Campanoni (Northwestern University)


Bio: Simone Campanoni is a tenure-track assistant professor at the Electrical Engineering and Computer Science department of Northwestern University. Simone addresses research challenges through vertical specialization of the hardware/software stack. Simone's main research areas are compilers and virtual machines, with special interest in computer architecture, runtime systems, operating systems, and programming languages. Simone started the HELIX research project at Harvard University in 2010 as a post-doc working with Profs. David Brooks and Gu-Yeon Wei. HELIX uses static and dynamic compilation, run-time optimization, and architecture specialization to extract coarse-grained parallelism for many-core architectures from complex "sequential" code. Simone received his Ph.D. degree with highest honors from Politecnico di Milano University in 2009. His dissertation discusses theoretical and practical performance implications of thread level parallelism. To this end, Simone designed and built a bytecode virtual machine optimized for commodity multicore platforms. Simone is the author of ILDJIT, a parallel compilation framework that includes static and dynamic compilers as well as a bytecode virtual machine. ILDJIT has been used in several academic and industrial research projects, including HELIX.



 

Vulkan: A Next Generation Graphics API for Android

Michael Lentine (Google)


Bio: Michael Lentine is a software engineer at Google where he has primarily focused on the Android graphics platform. He received his Ph.D. from Stanford University in 2012 where he focused on computer graphics and physically based simulation. He also has extensive experience working in graphics for both game and visual effects companies.





 

Socio-Cultural and Dynamic Information in Social Networks

Eunice Santos (Illinois Institute of Technology)

Bio: Eunice E. Santos is the Ron Hochsprung Endowed Chair and Professor at the Illinois Institute of Technology. She is also the Department Chair of Computer Science. She was a professor at Virginia Tech, Lehigh University, and UTEP, and was a Senior Research Fellow for the Department of Defense Center for Technology and National Security Policy. She has served as the Director of the National Center for Border Security and Immigration, Director of the Center for Defense Systems Research, and Founding Director of the Institute of Defense & Security at UTEP. She is a recipient of the IEEE Computer Society Technical Achievement Award (for pioneering work in Computational Social Systems). She has also received an NSF Career Award, the Robinson Faculty Award, the Spira Award for Excellence in Teaching, and other awards. She is a past member of the IDA/DARPA Defense Science Study Group.  She is the Founding co-Editor-in-Chief of the new IEEE Transactions on Computational Social Systems. She received her PhD in Computer Science from the University of California, Berkeley. She also has BS and MS degrees in both Mathematics and Computer Science. She is a Fellow of AAAS.

 

Session 3: Data Science

12:50 am - 2:20 pm (1st floor)

(Session Chair: Kamil Iskra, Argonne National Lab)


4CeeD: Real-Time Data Acquisition and Analysis Framework for Materials and Semiconductor Fabrication Cyber-Physical Environments

Klara Nahrstedt (University of Illinois at Urbana-Champaign)

Bio: Klara Nahrstedt is the Ralph and Catherine Fisher Professor in the Computer Science Department, and Director of the Coordinated Science Laboratory in the College of Engineering at the University of Illinois at Urbana-Champaign. Her research interests are directed toward trustworthy power grid, 3D teleimmersive systems, mobile systems, Quality of Service (QoS) and resource management, Quality of Experience in multimedia systems, and real-time security in mission-critical systems. She is the co-author of widely used multimedia books `Multimedia: Computing, Communications and Applications' published by Prentice Hall, and ‘Multimedia Systems’ published by Springer Verlag. She is the recipient of the IEEE Communication Society Leonard Abraham Award for Research Achievements, University Scholar, Humboldt Award, IEEE Computer Society Technical Achievement Award, and the former chair of the ACM Special Interest Group in Multimedia. She was the general chair of ACM Multimedia 2006, general chair of ACM NOSSDAV 2007 and the general chair of IEEE Percom 2009.
Klara Nahrstedt received her Diploma in Mathematics from Humboldt University, Berlin, Germany in numerical analysis in 1985. In 1995 she received her PhD from the University of Pennsylvania in the Department of Computer and Information Science. She is ACM Fellow, IEEE Fellow, and Member of the Leopoldina German National Academy of Sciences.






 

Orthogonal key-value locking

Goetz Graefe  (HP Lab)


Bio: Goetz is currently a HP fellow. Goetz Graefe's contributions to database research and product development include query optimization in the Exodus research effort and in the Tandem SQL/MX product, query execution in the Volcano research prototype, and query processing in Microsoft's SQL Server product. In addition to query processing, his work has covered indexing, in particular novel techniques for b-trees, robust performance in query processing, for example a new integrated join algorithm, and transaction support, for example a new schemes for key-range locking and key-value locking. One of his current work streams focuses on database utilities, for example faster backup, restore, and recovery.

Two of the top three database conferences have recognized his contributions. In 2000, Graefe received the “ten-year test of time award” at the ACM Special Interest Group on Management Of Data ( SIGMOD) International Conference for his 1990 paper on parallel query executionIn 2005, he received the inaugural “influential paper award” at the IEEE International Conference on Data Engineering (ICDE) for a 1993 paper on extensible query optimization.



How Big Data Analytics Improves Wireless Network Operations and Security

Baoling Sheen &  Zhibi Wang (Huawei)


Bio: Baoling Sheen is currently a Sr. Solution Design Architect at FutureWei Technologies. She works in Wireless Data Analytics Research Lab, focusing on Predictive Data Analytics and Statistical Data Modeling. Before that, she worked in Lucent Technologies and University HealthSystem Consortium. Zhibi Wang is currently a Sr Staff Engineer at FutureWei Technologies. He works in Wireless Access Lab, focusing on wireless security. Before that, he worked in Lucent Technologies and Argonne National Lab.
 





 


Technical and Quantitative Challenges in US Equities Market Making

Carson Cook, Colin Clarke and Rob Lopez (KCG Holdings, Inc.)

Bio: Carson Cook has been a developer at KCG since 2011. Colin Clarke is a trader at KCG. Rob Lopez has been a quantitative trader at KCG since 2010. Before joining KCG, Rob worked for McKinsey & Company, Cooperfund, and TD Securities.
 

Session 4: Cloud & Data Center Infrastructure

2:45 pm - 4:35 pm (1st floor)

(Session Chair: Zhiling Lan, Illinois Institute of Technology)

Efficient Virtual Address Translation for Modern Workloads

Michael Swift (University of Wisconsin -- Madison)


Bio: Mike Swift is an associate professor at the University of Wisconsin, Madison. His research focuses on the hardware/operating system boundary, including devices drivers, new processor/memory technologies, and transactional memory. He grew up in Amherst, Massachusetts and received a B.A. from Cornell University in 1992. After college, he worked at Microsoft in the Windows group, where he implemented authentication and access control functionality in Windows Cairo, Windows NT, and Windows 2000. He received a Ph.D. on operating system reliability from the University of Washington in 2005.


Cross-Layer Optimizations between Network and Compute in Online Services

Balajee Vamanan (University of Illinois at Chicago)


Bio: Balajee Vamanan is an assistant professor in the department of computer science at the University of Illinois at Chicago (UIC). He joined UIC after graduating from Purdue University in October 2015. His research straddles networking, systems, and architecture. Specifically, he is interested in the emerging networking-paradigms such as Software-Defined Networking (SDN) and Network Function Virtualization (NFV), and network optimizations for interactive, online services (e.g., Web search, social networks). He has published in top networking and architecture conferences. Before graduate school, he was a hardware designer at NVIDIA where he designed the memory controller for the first unibody MacBook Air.



Taming the Swarm: Scalability in Control and Design of Swarm Robotics

Mike Rubenstein (Northwestern University)


Bio: Michael Rubenstein is currently an assistant professor at Northwestern's McCormick School of Engineering.  There he is working on Kilobot, a robot designed for testing swarm algorithms in a group of over a thousand robots.  He received his Ph.D. from The University of Southern California's School of Computer Science under the supervision of Wei-Min Shen.  His thesis, titled: "Self-Assembly and Self-Healing for Robotic Collectives", details a control algorithm for a simple, simulated multi-robot system which guarantees that it can self-assemble and self-heal any desired connected shape.  Most of his research is centered around the design and control of multi-robot systems.  Additional information can be found at his webpage: http://users.eecs.northwestern.edu/~mrubenst/






Cache in a Flash: Making cost-effective use of flash–based caching

Fred Douglis (EMC)

Bio: Fred Douglis is in the Advanced Development group of EMC Core Technologies Division, in the office of the CTD CTO. He works on systems and storage technologies such as flash memory, deduplication, compression, load balancing, and others.  He holds M.S. and Ph.D. degrees in computer science from U.C. Berkeley and a B.S. in computer science from Yale.  He has worked in industrial applied research throughout his career, including Matsushita, AT&T (Bell) Labs, and IBM Research before joining EMC in 2009. He also has been a visiting professor at VU Amsterdam and Princeton University.  He served as editor in chief of IEEE Internet Computing from 2007-2010 and has been on its editorial board since 1999.  He is a member of the IEEE Computer Society Board of Governors from 2016-2018.




 

Conveyor: Enabling low-friction continuous deployment via containers and dynamic resource scheduling

Jonathan Pliske & Tristan Blease (Groupon)


Bio: Jonathan Pliske is a software engineering lead at Groupon. Since joining in 2010, he has been involved in many of the performance and infrastructure initiatives required to transition what was once a single monolithic Ruby on Rails application into the diverse and scalable architecture Groupon now uses to serve customers around the globe. Previous projects include distributed tracing, web request routing, and full-stack performance debugging and tuning.   Tristan Blease is a senior software engineer at Groupon. He has also been involved in many of the performance and infrastructure initiatives at Groupon required for smashing the monolith, including distributed tracing, web request routing, and full-stack performance debugging and tuning. He currently works with the Project Conveyor team to help design and implement the robust systems needed to ensure the success of the project.