KEYNOTE

Clouds and Observatories: How Infrastructure Clouds Can Change the Way We Do Science

Kate Keahey
Fellow, University of Chicago
Scientist, Argonne National Laboratory

Abstract:

Kate Keahey
The advent of IaaS cloud computing promises acquisition and management of customized on-demand resources. What is the best way to leverage those resources? What new applications are emerging in this context? How will they change our work patterns? What new technical approaches need to be developed to support them? What new opportunities will they lead to?

In this talk, I will describe an emerging trend towards building observatories – a new, powerful, and transformative tool that has the potential to change the nature and revitalize many areas of science. I will outline the challenges that the construction of an observatory faces and describe a potential approach towards solving them in the context of tools that the Nimbus team is developing to address them. I will also give examples of the observatory concept in the context of several scientific projects and discuss the interaction patterns associated with them that are currently driving our approach.


Bio:

Kate Keahey is one of the pioneers of infrastructure cloud computing. She leads the development of Nimbus project which provides an open source Infrastructure-as-a-Service implementation as well as an integrated set of platform-level tools allowing users to build elastic application by combining on-demand commercial and scientific cloud resources. Kate is a Scientist in the Distributed Systems Lab at Argonne National Laboratory and a Fellow at the Computation Institute at the University of Chicago.



KEYNOTE

Cloud Storage Services: A Model of (In)Consistency

Doug Terry
Principal Researcher, Microsoft Research Silicon Valley

Abstract:

Doug Terry
Cloud storage systems invariably replicate data for high availability and low latency access. Application designers, as well as cloud providers, must deal with trade-offs between consistency, performance, and availability. Some cloud services, like Windows Azure, replicate data while providing strong consistency to their clients while others, like Amazon’s S3, have chosen eventual consistency. Recently, systems such as Amazon’s DynamoDB and the Google App Engine Datastore offer a choice of consistency when reading shared data. This talk examines the implications of such a choice and explores a broader class of consistency guarantees that can, and perhaps should, be provided within the cloud.


Bio:

Doug Terry is a Principal Researcher in the Microsoft Research Silicon Valley lab. His research focuses on the design and implementation of novel distributed systems including mobile and cloud services. Prior to joining Microsoft, Doug was the co-founder and CTO of a start-up company named Cogenia, Chief Scientist of the Computer Science Laboratory at Xerox PARC, and an Adjunct Professor in the Computer Science Division at U. C. Berkeley, where he still occasionally teaches a graduate course on distributed systems. Doug has a Ph.D. in Computer Science from U. C. Berkeley. He is an ACM Fellow, past chair of ACM's Special Interest Group on Operating Systems (SIGOPS), and Chair of ACM's Tech Pack Committee on Cloud Computing.



KEYNOTE

Big Data and Big Computing, and the Cloud

Frederica Darema
Director, Mathematics, Information and Life Sciences
Air Force Office of Scientific Research (AFOSR)

Abstract:

Frederica Darema
In recent years there have been transformative changes in the application systems landscape, in that we deal with more complex systems, and often with systems-of-systems, be they natural, engineered, or societal systems. In tandem with this, we have seen the emergence of advanced approaches and infrastructure environments for analysis, understanding and management of such systems. The supporting environments for complex application systems span a wide and heterogeneous range of powerful computational and instrumentation infrastructures, including ubiquitous end-user devices and pervasive sensing and control systems, and networks thereof. Advanced methodologies for analysis and management of the referenced systems include the InfoSymbioticSystems/DDDAS (Dynamic Data Driven Applications Systems) paradigm, whereby the executing models of the system are dynamically coupled with instrumentation aspects of the system in a dynamic feed-back loop. The underlying supporting platforms for such capabilities span from the high-end to the real-time data-acquisition and control, and end-user devices, integrated as a unified computational-instrumentation platform. We use here the term Big Computing to mean this unified, integrated collection of platforms. Furthermore, an increasing big component of Big Data are data from ubiquitous sensing, and the methods referenced here allow dynamic and adaptive management of such heterogeneous resources, to discover data that are essential to improve the analysis of a system, and to exploit these data in intelligent ways and convert them into new capabilities. The presentation will discuss how such aspects of Big Data and Big Computing need to be addressed in future directions of Autonomic Computing and Cloud Computing.


Bio:

Dr. Frederica Darema is with the Air Force Office of Scientific Research (AFOSR). Prior to that, she held executive level positions at NSF, as Senior Science and Technology Advisor, and Senior Science Analyst, in the Computer and Information Science and Engineering Directorate at NSF. Dr. Darema received her BS degree from the School of Physics and Mathematics of the University of Athens - Greece, and MS and Ph. D. degrees in Theoretical Nuclear Physics from the Illinois Institute of Technology and the University of California at Davis, respectively, where she attended as a Fulbright Scholar and a Distinguished Scholar. After Physics Research Associate positions at the University of Pittsburgh and Brookhaven National Lab, she received an APS Industrial Fellowship and became a Technical Staff Member in the Nuclear Sciences Department at Schlumberger-Doll Research. Subsequently, she joined the IBM T. J. Watson Research Center as a Research Staff Member in the Computer Sciences Department, and later-on she established a multidisciplinary research group on parallel applications and became the Research Manager of that group. While at IBM she also served in the IBM Corporate Technical Strategy Group, examining and helping to set corporate-wide strategies. Dr. Darema's interests and technical contributions span the development of parallel applications, parallel algorithms, programming models, environments, and performance methods and tools for the design of applications and of software for parallel and distributed systems. In her career Dr. Darema has developed initiatives and programs that are recognized as having "changed the landscape of Computer Science research"; such initiatives include: the Next Generation Systems Program on novel research directions in systems software, and the DDDAS paradigm which has been characterized as "visionary" and "revolutionary". She has also led initiatives on research at the interface of neurobiology and computing, and other across-NSF and cross-agency initiatives and programs, such as those on: Information Technology Research; Nanotechnology Science and Engineering; Scalable Enterprise Systems; and Sensors. During 1996--1998, she completed a two-year assignment at DARPA where she initiated a new thrust for research on methods and technology for performance engineered systems. Dr. Darema was elected IEEE Fellow for proposing the SPMD (Single-Program-Multiple-Data) computational model that has become the predominant model for programming high-performance parallel and distributed computers. Dr. Darema is also the recipient of the IEEE Technical Achievement Award, for her work in pioneering DDDAS. Dr. Darema has given numerous keynotes and other invited presentations in professional forums.



KEYNOTE

Cloud 3.0: Software Defined Environment

Chung-Sheng Li
Director of the Commercial Systems Department
IBM T.J. Watson Research Center

Abstract:

Chung-Sheng
Two phenomena are happening simultaneously during the past few years: Enterprises are increasingly aggressive in moving mission critical and performance sensitive applications to the cloud. In addition, many new mobile, social and analytics applications are directly developed and operated on the cloud. These two phenomenon drove the shift of the value proposition of cloud computing from cost reduction to simultaneous agility and optimization. These requirements (agility and optimization) drove the recent disruptive trend on software defined computing where the entire computing infrastructure - compute, storage and network - are becoming software defined and dynamically programmable.

Software defined environment originated from the compute environment where the computing resources are virtualized and managed as virtual machines or containers (including bare metal containers). Software defined network (SDN) moves the network control plane away from the switch to the software running on server for improved programmability, efficiency and extensibility. Software define storage, similar to software defined network, separates the control plane from the data plane of a storage and dynamically leverages heterogeneity of storage to respond to changing workload demands. Software defined environment brings together software defined compute, network and storage and unifies the control planes from each individual software defined component. Unified control planes allow rich resource abstractions to enable assembling purpose fit systems and/or providing programmable infrastructures to enable dynamic optimization in response to business requirements. The key elements within software defined environment include capability based resource abstraction, policy based workload abstraction, and outcome based continuous mapping of the workload to the resources. The logical abstraction of the software defined infrastructure (that includes compute, storage, and network) for the available resources in compute, storage and network across one or more data centers. The available resources can be potentially extended by using hybrid cloud (or cloud broker) technologies to include multiple private and public clouds. This logical model of software defined infrastructure includes pools of computing and storage resources interconnected by networking resources. This abstraction of the data center enables the equivalent of Instruction Set Architecture (ISA) at the data center or multi- data center levels.

In this talk, we will discuss the key ingredients of this disruptive trend on software defined computing, and illustrate the potential benefit in the context of mobile, analytics, and managed service environment.


Bio:

Chung-Sheng Li is currently the director of the Commercial Systems Department. He has been with IBM T.J. Watson Research Center since May 1990. His research interests include cloud computing, security and compliance, digital library and multimedia databases, knowledge discovery and data mining, and data center networking. He has authored or coauthored more than 130 journal and conference papers and received the best paper award from IEEE Transactions on Multimedia in 2003. He is both a member of IBM Academy of Technology and a Fellow of the IEEE.

He has initiated and coinitiated several research programs in IBM on fast tunable receiver for all-optical networks, content-based retrieval in the compressed domain for large image/video databases, federated digital libraries, and bio-surveillance.

He received BSEE from National Taiwan University, Taiwan, R.O.C., in 1984, and the MS and PhD degrees in electrical engineering and computer science from the University of California, Berkeley, in 1989 and 1991, respectively.