SEARCH
ISTC-CC NEWSLETTER
RESEARCH HIGHLIGHTS
Ling Liu's SC13 paper "Large Graph Processing Without the Overhead" featured by HPCwire.
ISTC-CC provides a listing of useful benchmarks for cloud computing.
Another list highlighting Open Source Software Releases.
Second GraphLab workshop should be even bigger than the first! GraphLab is a new programming framework for graph-style data analytics.
ISTC–CC Q2 2012 Status Report
Summary:
A great quarter for publications with 33 papers published, including 6 papers in HotCloud’12, 5 papers in EuroSys’12, 3 papers in NSDI’12, and 3 papers in ISCA’12!Another 25 papers were accepted. A great quarter, too, for awards and honors, including:
- Ling Liu (George Tech) awarded the IEEE's 2012 Technical Achievement Award "for pioneering contributions to novel internet data management and decentralized trust management"
- Garth Gibson (CMU) and Randy Katz (UC Berkeley), with Dave Patterson, awarded the Jean-Claude Laprie Award in Dependable Computing for their early RAID work
- Ion Stoica (UC Berkeley) and co-authors’ SPARK paper named best paper at NSDI’12
- Onur Mutlu (CMU) and co-authors’ paper is nominated for the best paper award at NOCS’12
- Margaret Martonosi (Princeton) appointed the Hugh Trumbull Adams '35 Professor of Computer Science
- Babu Pillai (Intel Labs) led Intel/CMU team to 3 JouleSort wins.
The GraphLab project has been making tremendous progress, highlighted by (i) 4000 downloads of the code, (ii) a Big Learning workshop to be held July 9 with 300 participants from 60 companies expected, (iii) a new version, GraphLab 2, that scales to billions of nodes and vertices in the Cloud, and (iv) significant Intel Labs engagement/collaboration. Please plan to attend the UCO Showcase June 27th in SC12.All 12 ISTCs and ICRIs will be present.
Details:
ISTC Mission: Four inter-related research pillars (themes) architected to create a strong foundation for cloud computing of the future
The research agenda of the ISTC-CC is composed of the following four themes
- Specialization: Explores specialization as a primary means for order of magnitude improvements in efficiency (e.g., energy), including use of emerging technologies like non-volatile memory and specialized cores.
- Automation: Addresses cloud’s particular automation challenges, focusing on order of magnitude efficiency gains from smart resource allocation/scheduling and greatly improved problem diagnosis capabilities.
- Big Data: Addresses the critical need for cloud computing to extend beyond traditional big data usage (primarily, search) to efficiently and effectively support Big Data analytics, including the continuous ingest, integration, and exploitation of live data feeds (e.g., video or twitter).
- To theEdge: Explores new frameworks for edge/cloud cooperation that can efficiently and effectively exploit billions of context-aware clients and enable cloud-assisted client applications whose execution spans client devices, edge-local cloud resources, and core cloud resources.
Participants
Academic PI: Greg Ganger(CMU)
Executive Sponsor: Wen Hann Wang (CSR)
Managing Sponsor: Rich Uhlig (CSR-SAL)
Program Director: Jeff Parkhurst (APR)
Intel PI: Phil Gibbons
Intel Researchers:Michael Kiminsky, Mike Kozuch, Babu Pillai
AcademicPartners: Dave Andersen, Guy Blelloch, Garth Gibson, Carlos Guestrin, Mor Harchol-Balter, Todd Mowry, Onur Mutlu, Priya Narasimhan, M. Satyanarayanan, and Dan Siewiorek (CMU); Mike Freedman, Kai Li, and Margaret Martonosi (Princeton); Anthony Joseph, Randy Katz, and Ion Stoica (UC Berkeley); Ada Gavrilovska, Ling Liu, Calton Pu, Karsten Schwan, and Sudha Yalamanchili (GA Tech).
Technical highlights
- [Resilient Distributed Datasets] The SPARK paper entitled “Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing,” by Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael J Franklin, Scott Shenker, and Ion Stoica, won the best paper award at NSDI’12. The paper presents Resilient Distributed Datasets (RDDs), a distributed memory abstraction that lets programmers perform in-memory computations on large clusters in a fault-tolerant manner. RDDs are motivated by two types of applications that current computing frameworks handle inefficiently: iterative algorithms and interactive data mining tools. To achieve fault tolerance efficiently, RDDs provide a restricted form of shared memory, based on coarse-grained transformations rather than fine-grained updates to shared state. The paper can be downloaded from https://www.usenix.org/system/files/conference/nsdi12/nsdi12-final138.pdf
- [GraphLab] Carlos Guestrin’s (CMU) GraphLab project has been making tremendous progress! GraphLab’s user base has continued to increase with more than 4000 downloads. A GraphLab Workshop on Big Learning (http://graphlab.org/workshop2012/) will be held July 7 in San Francisco, with around 300 participants from over 60 companies expected. In terms of research goals, the team has pushed forward on two fronts: a new version of GraphLab that addresses natural graphs with high degree vertices. At the core of this version is a modification to the abstraction that factors update functions, further exposing parallelism. This version, GraphLab 2, scales to billions of nodes and vertices on the Cloud, and compares favorably to other existing systems. The team has also been developing GraphChi, a version of GraphLab that works on a machine with reduced processing power and memory through a novel disk-based parallel sliding windows data structure. GraphChi is also able to handle dynamic graphs, forming the first step towards real-time GraphLab. GraphChi is able to solve web-scale problems on a Mac Mini in time comparable to other systems on a large computer cluster.
- [JouleSort wins] Babu Pillai, Michael Kaminsky, Mike Kozuch (Intel Labs), and Dave Andersen (CMU) won 3 categories of the 2012 JouleSort competition, setting new records for fewest joules needed to sort 10^8, 10^9, and 10^10 records.The team used an Intel Core i7-2700K desktop processor, coupled to 2 RAID cards and 16 Intel 710 Series SSDs to beat existing energy efficiency records in the 10GB, 100GB, and 1TB categories by 2.6% (their record from last year), 33%, and 729%, respectively. They also had competitive results using an Atom-based system for the 100GB category, demonstrating energy-efficient systems from different points in the performance-power design space.See http://sortbenchmark.org/ for further details.
- [Energy-efficient on-chip interconnect] The paper entitled "MinBD: Minimally-Buffered Deflection Routing for Energy-Efficient Interconnect," by Chris Fallin, Greg Nazario, Xiangyao Yu, Kevin Chang, Rachata Ausavarungnirun, and Onur Mutlu, was one of five papers nominated for the best paper award at the 6th ACM/IEEE International Symposium on Networks on Chip (NOCS’12), May 2012.
- [Client-Cloud] Kiryong Ha (CMU grad student) and Babu Pillai (Intel Labs) have devised a system to demonstrate the operation and benefits of cloudlets.The demo runs an interactive, compute-intensive fluid simulation application in the backend, and displays current state on a frontend running on an Android phone.The simulated fluid moves in response to accelerometer readings from the phone, allowing the user to interact with the simulation.The backend can be switched from the cloud (one of four Amazon EC2 datacenters) and a local cloudlet (represented by a fast laptop). This system demonstrates response times and higher frame rate for cloudlet-based computation offload over cloud-based services.
- [noSQL open source DB] Accumulo, the NSA-sponsored open-source rewrite of BigTable with extra attention to security and server-side processing, and the "new" noSQL database evaluated in Garth Gibson (CMU) and co-authors’ YCSB++ paper presented at SOCC’11, was promoted out of the incubator to be an Apache "top level project".
- [Open Cirrus] Mike Kozuch (Intel Labs) is serving as the co-lead (with Rick McGeer) for the testbed team of the IEEE Computer Society future technologies effort around cloud computing.Initial discussions around connecting the Open Cirrus effort to GENI are quite promising, and the ultimate goal of the effort is to provide a general mechanism for collaboration between cloud computing testbed efforts.
- Publications summary for the past quarter:
- 27+ papers submitted: including 7 papers to OSDI’12 and at least 3 to SOCC’12
- 25 papers accepted: including to Cloud’12 (3 papers), PACT ’12 (3 papers), SPAA’12 (3 papers), ICAC’12 (2 papers),SCC’12 (2 papers), Sigcomm’12, PODC’12, KDD’12, ICS’12, HPCC’12, AstroHPC’12, and ICME’12
- 33 paper published: in HotCloud’12 (6 papers), EuroSys’12 (5 papers), NSDI’12 (3 papers),ISCA’12 (3 papers),Usenix ATC’12 (2 papers), ISPASS’12 (2 papers), IGCC’12 (2 papers), IEEE CAL, PerCom’12 , IEEE TASE, Sigmod PhD Symp’12, NOCS’12, CCGrid’12, IEEE Micro, ICMR’12, Usenix login;, and Greenmetrics’12 (see List of Publications below)
Schedule of upcoming events and milestones
- June 21-22: Open Cirrus Summit will be held in Beijing.
- June 26: ISTC research to be highlighted at Research@Intel day in San Francisco.
- June 27: Intel’s University Collaboration Office “Showcase” in Santa Clara.This event will run 8am to 6 pm and gather IL researchers, faculty, and students from each of the ISTCs and each of the Intel Collaborative Research Institutes for a day of presentations, demos, posters, and brainstorming.All Intel employees are invited to attend.
- June 28: NSF Workshop on Research Directions in the Principles of Parallel Computing will be held in Pittsburgh, PA. For more details see http://www.cs.cmu.edu/~guyb/spaa/2012/workshop.html.
- July 9: GraphLab Workshop on Big Learning will be held in San Francisco. For more details see http://graphlab.org/workshop2012/.
- August 16: ISTC-CC BOA Annual Review in Pittsburgh
- Oct 25-26: 2nd Annual ISTC-CC Retreat in Pittsburgh
Sponsor group interaction highlights
- [GraphLab] Ted Willke's (SAL) group is very dedicated to GraphLab: they are contributing a new graph ingress system to GraphLab, they are highly involved in the GraphLab workshop (we are doing a joint demo), and one of Carlos Guestrin’s (CMU) students, Jay Gu, is doing an internship with Ted this summer. In addition, Carlos is in active discussions with Ravi's group about starting a collaboration in the intersection between GraphLab and Computer Vision; Dhruv is part of this effort. Finally, one of the Intel core groups is using GraphChi to benchmark the performance of some experimental architecture.
- Karsten Schwan (GA Tech) visited Intel Portland April 18 to discuss joint research and efforts with: Rob Knauerhase, Vishakha Gupta, Paul Brett, Sanjay Kumar, Dulloor Rao, Paul Steinberg, Jeff Jackson, Ganapati Srinivasa, Steve Bennett, Wilfred Pinfold, Rajesh, Jeff, George Cox, Ivan Ganev, Balasubramanian Seshasayee, Josh Fryman, and Romain Cledat. Joint publications are planned with the first five names on this list.
- Alex Merritt (GA Tech grad student) is interning with SAL this summer, working on computation offloading.
- [Joulesort] Babu Pillai (Intel Labs) gave several talks highlighting the approach, results, and take-aways of the Joulesort efforts to various groups at Intel, including SAL, Steve Pawlowski’s staff, Doug Carmean’s group, RAID folks (Robert Stoddard’s group), and IT folks (Jim Brayton’s team, Elwood Coslett’s team, and Ed Goldman’s team).Several good discussions on future system designs and tradeoffs ensued.He also met with Eugene Gorbatov, Nilesh Jain and Kushal Datta (SAL).Babu Pillai, Michael Kaminsky and Mike Kozuch (Intel Labs) spoke to Sean Koehl (Intel) about the Joulesort win.Sean helped the team advertise the win via a blog post and other social media outlets.
- [Sprout] Babu Pillai (Intel Labs) continues to collaborate with Greg Regnier and Diana Hu (SAL) on Sprout. They discussed plans going forward once Diana’s rotation ends in July, identifying three alternative paths that vary in the research content and amount of effort needed.They hope to get additional folks interested and find someone (student or intern) to continue the work over the next 6 months. Babu also had discussions with Ashok Sunder Rajan (Dan Dahle’s team) and Christian Maciocco (SAL) on a potential project using Sprout.
- [Intel IT] Michael Kaminsky (Intel Labs) met with Greg Touretsky of Intel IT to discuss some of the challenges they face sharing data across multiple Intel sites.Michael told Greg about the COPS work and forwarded him pointers to papers/slides, and the two discussed some other ideas around this problem.
- [Client-Cloud] Jeff met with Mahadev Satyanarayanan(Satya) to discuss his research in the “To The Edge” Pillar of the center which focuses on methods of mitigating Client to Cloud BW demands and on sending VMs with apps to local cloudlets. This project is well connected to Intel through Babu Pillai. Contact Jeff or Babu for more information. Publications are located at http://elijah.cs.cmu.edu/ . This project has garnered interest from AT&T with their BW mitigation research and also Bosch which is looking at the potential of using the automobile as a local cloudlet.
- Intel visitors for PDL Visit Day on May 11: Ted Willke, Guangdeng Liao, Richard Olha plus all four ISTC-CC Intel folks.(Also, 30 other industry visitors from 20 companies.)Much ISTC-CC research was shared during this event.
- Mike Kozuch (Intel Labs) presented an update on the AMPlab research agenda and results to the DCSG Cloud Core team on May 23.
- Michael Kaminsky will be on sabbatical June 12–August 6.
- Mike Kozuch will be on sabbatical June 19—August 13.
Other ISTC highlights
- UCO Showcase final planning is in full swing. Looks like there will be 60 posters (~10 from Cloud) and 15 demos(3 from cloud) with all 12 ISTCs/ICRIs represented. The UCO showcase runs from 8 am to 6 pm in SC12 and we encourage everyone to attend.
- Ling Liu (GA Tech) is awarded the IEEE's 2012 Technical Achievement Award "for pioneering contributions to novel internet data management and decentralized trust management.”
- Garth Gibson (CMU) and Randy Katz (UC Berkeley), with David Patterson, received the 2012 Jean-Claude Laprie Award in Dependable Computing Industrial/Commercial Product Impact Category, by the IFIP Working Group 10.4 on Dependable Computing and Fault Tolerance, for outstanding papers published at least 10 years ago that have significantly influenced the theory and/or practice of dependable computing (http://www.dependability.org/articles/laprie/laprie2012.html). Awarded at the 42nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN 2012), June, 2012, Boston, MA.
- Margaret Martonosi (Princeton) is appointed the Hugh Trumbull Adams '35 Professor of Computer Science.
- Program Committees (a partial list):
- Guy Blelloch (CMU): SPAA’12 general chair
- Greg Ganger (CMU): SOCC’12
- Phil Gibbons (Intel Labs): ICALP’12, Middleware’12, DaMoN’12, VLDB’12, IC2E’13, PPoPP’13, Sigmod’13 area-chair
- Garth Gibson (CMU): SC’12, MBDS’12, IC2E’13, Fast’13
- Mor Harchol-Balter (CMU): Sigmetrics’13 general chair
- Anthony Joseph (UC Berkeley): Middleware’12
- Michael Kaminsky (Intel Labs): SOSP’13 general chair
- Mike Kozuch (Intel Labs): HotCloud’12, MBDS’12
- Kai Li (Princeton): MBDS’12
- Ling Liu (GA Tech): VLDB’12 co-chair, ICDCS’12
- Onur Mutlu (CMU): Micro’12 chair
- Priya Narasimhan (CMU): Middleware’12 co-chair
- Calton Pu (GA Tech): SCC’12, ICWS’12
- Karsten Schwan (GA Tech): MBDS’12 co-chair, Middleware’12, ICAC’12, SOCC’12
- Dan Siewiorek (CMU): Middleware’12
- Ion Stoica (UC Berkeley): SOCC’12, OSDI’12
- [Amplifying Funding] New funding secured in Q2 (partial list):
- Onur Mutlu (CMU) awarded an NSF grant on Rearchitecting the Memory Hierarchy
- Timothy Zhu (CMU grad student) awarded the NSF Graduate Fellowship, a 3-year fellowship
- Karsten Schwan and Ada Gavrilovska (GA Tech), ``Software Platform for Heterogeneous Multicore Platforms: from End Devices to Clouds'', Samsung Electronics, $157,100, Sept. 2011 - Aug. 2012 (now fully funded)
- Chengwei Wang (GA Tech grad student) received a Yahoo student award of $5,000
List of publications
[List of the publications that were PUBLISHED by center researchers during the month. This does not include submissions or acceptances, just publications.]
- "Enabling Efficient and Scalable Hybrid Memories Using Fine-Granularity DRAM Cache Management," Justin Meza, Jichuan Chang, HanBin Yoon, Onur Mutlu, and Parthasarathy Ranganathan, IEEE Computer Architecture Letters (CAL), March 2012
- “How Close is Close Enough? Understanding the Role of Cloudlets in Supporting Display Appropriation by Mobile Users”, Sarah Clinch, Jan Harkes, Adrian Friday, Nigel Davies, and Mahadev Satyanarayanan, 2012 IEEE International Conference on Pervasive Computing and Communications (PerCom 2012)
- "Jettison: Efficient Idle Desktop Consolidation with Partial VM Migration,” Nilton Bila, Eyal de Lara, Kaustubh Joshi, H. Andres Lagar-Cavilla, Matti Hiltunen, and M. Satyanarayanan, EuroSys’12, April 2012
- "LazyBase: Trading freshness for performance in a scalable database,” Jim Cipar, Gregory R. Ganger, Kimberly Keeton, Charles B. Morrey III, Craig A. N. Soules, and Alistair Veitch, EuroSys’12, April 2012
- “Energy Efficiency for Large-Scale MapReduce Workloads with Significant Interactive Analysis,” Y. Chen, S. Alspaugh, D. Borthakur, and R. H. Katz, EuroSys’12, April 2012
- “Kineograph: Taking the Pulse of a Fast-Changing and Connected World”, Raymond Cheng, Ji Hong , Aapo Kyrola, Youshan Miao, Xuetian Weng, Ming Wu, Fan Yang, Lidong Zhou, Feng Zhao, and Enhong Chen, EuroSys’12, April 2012
- “BWS: Balanced Work Stealing for Time-Sharing Multicores,” Kaibo Wang, Xiaoning Ding, Phillip B. Gibbons, and Xiaodong Zhang, EuroSys’12, April 2012
- "Stargazer: Automated Regression-Based GPU Design Space Exploration," Wenhao Jia, Kelly A. Shaw, Margaret Martonosi, Proceedings of 2012 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS’12), April 2012
- “Lynx: A Dynamic Instrumentation System for Data-Parallel Applications on GPGPU Architectures,'' Naila Farooqui, Andrew Kerr, Greg Eisenhauer, Karsten Schwan, and Sudhakar Yalamanchili, 2012 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS’12), April 2012
- “Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing,” Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael J Franklin, Scott Shenker, and Ion Stoica, NSDI ’12, April 2012
- “PACMan: Coordinated Memory Caching for Parallel Jobs,” Ganesh Anantharanayanan, Ali Ghodsi, Andrew Wang, Dhruba Borthakur, Srikanth Kandula, Scott Shenker, and Ion Stoica, NSDI ‘12, April 2012
- “Reoptimizing Data Parallel Computing,” Sameer Agarwal, Srikanth Kandula, Nico Bruno, Ming-Chuan Wu, Ion Stoica, and Jingren Zhou, NSDI ’12, April 2012
- "A Petri Net Approach to Mediation-aided Composition of Web Services," YanHua Du, Xitong Li, Pengcheng Xiong, IEEE Transactions on Automation Science and Engineering (TASE), 9(2), April 2012
- "MinBD: Minimally-Buffered Deflection Routing for Energy-Efficient Interconnect," Chris Fallin, Greg Nazario, Xiangyao Yu, Kevin Chang, Rachata Ausavarungnirun, and Onur Mutlu, Proceedings of the 6th ACM/IEEE International Symposium on Networks on Chip (NOCS’12), May 2012
- “Interactive Use of Cloud Services: Amazon SQS and S3”, Hobin Yoon, Jim Donahue, Ada Gavrilovska, Karsten Schwan, 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid’12), May 2012
- "Dynamic Management of Resources and Workloads for RDBMS in Cloud: a Control-theoretic Approach" Pengcheng Xiong, Proc. of ACM SIGMOD/PODS PhD Symposium, May 2012
- "Kilo-NOC: A Heterogeneous Network-on-Chip Architecture for Scalability and Service Guarantees," Boris Grot, Joel Hestness, Stephen W. Keckler, and Onur Mutlu, IEEE Micro, Special Issue: Micro's Top Picks from 2011 Computer Architecture Conferences, May-June 2012
- “Saving Cash by Using Less Cache,” Anshul Gandhi, Timothy Zhu, Mor Harchol-Balter, Michael Kozuch, HotCloud’12, June 2012
- “A Case for Performance-Centric Network Allocation,” Gautam Kumar, Mosharaf Chowdhury, Sylvia Ratnasamy, and Ion Stoica, HotCloud’12, June 2012
- “Discretized Streams: An Efficient and Fault-Tolerant Model for Stream Processing on Large Clusters,” Matei Zaharia, Tathagata Das, Haoyuan Li, Scott Shenker, and Ion Stoica, HotCloud’12, June 2012
- “Sweet Storage SLOs with Frosting,” Andrew Wang, Shivaram Venkataraman, Sara Alspaugh, Ion Stoica, and Randy Katz, HotCloud’12, June 2012
- “Why Let Resources Idle? Aggressive Cloning of Jobs with Dolly,” Ganesh Ananthanarayanan, Ali Ghodsi, Scott Shenker, and Ion Stoica, HotCloud’12, June 2012
- “Automated Diagnosis without Predictability is a Recipe for Failure,” Raja R. Sambasivan and Gregory R. Ganger, HotCloud’12, June 2012
- “A Scalable Server for 3D Metaverses,” Ewen Cheslack-Postava, Tahir Azim, Behram F.T. Mistree, Daniel Reiter Horn, Jeff Terrace, Philip Levis, and Michael J. Freedman, Usenix ATC’12, June 2012
- “The Forgotten ‘Uncore’: On the Energy-Efficiency of Heterogeneous Cores,” Vishal Gupta, Paul Brett, David Koufaty, Dheeraj Reddy, Scott Hahn, Karsten Schwan, Ganapati Srinivasa, Usenix ATC’12, June 2012
- "RAIDR: Retention-Aware Intelligent DRAM Refresh,” Jamie Liu, Benjamin Jaiyen, Richard Veras, and Onur Mutlu, Proceedings of the 39th International Symposium on Computer Architecture (ISCA’12), June 2012
- “A Case for Exploiting Subarray-Level Parallelism (SALP) in DRAM," Yoongu Kim, Vivek Seshadri, Donghyuk Lee, Jamie Liu, and Onur Mutlu, Proceedings of the 39th International Symposium on Computer Architecture (ISCA’12), June 2012
- "Staged Memory Scheduling: Achieving High Performance and Scalability in Heterogeneous Systems," Rachata Ausavarungnirun, Gabriel Loh, Kevin Chang, Lavanya Subramanian, and Onur Mutlu, Proceedings of the 39th International Symposium on Computer Architecture (ISCA’12), June 2012
- “Are sleep states effective in data centers?,” Anshul Gandhi, Michael Kozuch, and Mor Harchol-Balter, Proceedings of the International Green Computing Conference (IGCC’12), June 2012
- “A Cyber-Physical Integrated System for Application Performance and Energy Management in Data Centers,” Hui Chen, Pengcheng Xiong, Ada Gavrilovska, Karsten Schwan and Chengzhong Xu, Third International Green Computing Conference (IGCC'12), June 2012
- "High-Confidence Near-Duplicate Image Detection," Wei Dong, Zhe Wang, and Kai Li. ACM International Conference on Multimedia Retrieval (ICMR’12), June 2012
- “Understanding TCP Incast and Its Implications for Big Data Workloads,” Y. Chen, R. Griffith, D. Zats, A. D. Joseph, and R. H. Katz, USENIX ;login;, 37(3), June 2012
- “Evaluating the Need for Complexity in Energy-Aware Management for Cloud Platforms,” Pooja Ghumre, Junwei Li, Mukil Kesavan, Ada Gavrilovska, and Karsten Schwan, Greenmetrics'12, in conjunction with Sigmetrics, June 2012
List of presentations
In addition to the 29 conference presentations associated with each of the 29 published conference papers listed above, we had the following presentations:
- M. Satyanarayanan (CMU) gave a distinguished lecture in the Computer Science Department at the University of Illinois at Urbana-Champaign on April 2
- Ling Liu (GA Tech) presented “Social Influence based Data Analytics” at University of Tokyo, June 5
- Ling Liu (GA Tech) presented “Connecting Big Data with Big Data Analytics” at FIRST Organization Japan, June 6
- Carlos Guestrin (CMU) gave GraphLab presentations at MIT, UW, Penn, and Sony.