 |
 |
|
program
Dec. 1st
 |
Cristophe Bisciglia
Founder & Chief Strategy Officer
 |
Lowering Data Management Costs with Cloud Computing and Hadoop
Data volumes everywhere are growing. A TB used to be a lot of data, but today, any number of sensors, users and data feeds can generate as much in a day. All areas of science and industry are feeling the crunch. Working with big data is no longer a niche, and as such, new tools are emerging to enable this at drastically lower costs. Hear how Hadoop and MapReduce can leverage the power of Cloud Computing to drastically reduce costs for data management and enable deeper analysis than ever before.
 |
Paul Strong
Distinguished Research Scientist, eBay
 |
 |
Simone Brunozzi
Web Services Evangelist,
Amazon Web Services
 |
 |
Dr. Owen O'Malley
Hadoop Architect and Apache VP for Hadoop
  |
 |
Kevin L. Jackson
Director, Business Development
Enterprise Solutions, Dataline, LLC.
|
Cloud Computing: The View from Government Customers
Federal government organizations have been viewed as cautious adopters of new technologies. This is typically due to time delays caused by bureaucratic acquisition processes and a low risk approach to change. Cloud computing, however, has captured the attention of many government IT decision makers. The U.S. Defense Department’s Defense Information System Agency is, in fact, already fielding a cloud computing infrastructure. To better understand this relatively fast adoption, Military Information Technology magazine is investigating the government cloud computing marketplace. Through on-line surveys and in-depth interviews customer requirements and concerns will be explored. Information on current cloud computing offerings targeted for government customers will also be collected. In cooperation with “Cloud Musings”, a blog focused on the government cloud computing market, interactive Web 2.0 technologies will also be used to enhance the public dialog. Insights, opportunities and important marketplace trends are expected to be uncovered during this process. The proposed presentation will use insight gained from this project to enlighten the audience on important marketplace questions, such as:
- What quality of service levels are expected from these mission oriented customers?
- How important is cloud interoperability to a government customer?
- What concerns do government IT professional have with interfacing their infrastructures with cloud computing service providers?
- How fast will government organization adopt cloud computing capabilities?
- Will governments use public cloud services or are they more likely to opt for developing their own “private” clouds?
 |
Doron Caspin
Architect Evangelist
Developer & Platform evangelism group
 |
A window to the cloud" - Embracing Microsoft Azure cloud services
The Azure Services Platform (Azure) is an internet-scale cloud services platform hosted in Microsoft data centers, which provides an operating system and a set of developer services that can be used individually or together.
Azure’s flexible and interoperable platform can be used to build new applications to run from the cloud or enhance existing applications with cloud-based capabilities.
Its open architecture gives developers the choice to build web applications, applications running on connected devices, PCs, servers, or hybrid solutions offering the best of online and on-premises.
This session will walk you through the Azure platform, Windows Azure , Live Services, Microsoft SQL Services, Microsoft .NET Services, show you what it is, and how you can benefit from Microsoft cloud services.
 |
Dr. Yaron Wolfsthal
Senior Manager, System Technologies
IBM Research Lab in Haifa (HRL)
 |
The RESERVOIR project - advanced Cloud Computing infrastructure
In early 2008, IBM announced that it undertook to lead a large-scale project called RESERVOIR -- Resources and Services Virtualization without Barriers -- heading a consortium of 13 companies and universities. The RESERVOIR project aims to develop an advanced cloud computing infrastructure that will provide a scalable, flexible and dependable framework for delivering services as utilities. To implement this vision, the project will deeply integrate technologies from the domains of grid, virtualization and business service management. A key part of the project will demonstrate SaaS scenarios from project partners, e.g. SAP and Telefonica, running atop the Reservoir infrastructure. This presentation will describe the motivation, challenges and open research problems faced by the project.
 |
Steve Rubinow
CIO, NYSE Euronext,
The largest exchange in the world.
 |
CIO challenges
There is no end in sight to algorithmic trading. The more demand we're able to satisfy, the more [transactions] they send us. The infrastructure, network and throughput needs are all growing dramatically, and we have to be in a position to supply it. There is a huge increase in volume, revenue and transactions. That trend shows no sign of abating.
 |
Nati Shalom
Founder & CTO, GigaSpaces
 |
Getting Ready for the Cloud
Cloud computing has the potential to revolutionize the way we build and deploy applications - with it, we don't need to worry about provisioning of hardware resources, and it provides economic flexibility when it comes to setting up a working environment. Cloud computing also provides an easy path to growth exactly when it is needed.
Different providers like Amazon, Google, HP, are already providing different levels of software-as-a-service platforms using that model.
Having said that, the cloud is still in its early stages; many of the existing cloud environments are still evolving and there's a perception of risk as a result.
In this session we will introduce a Scale-out Application Server that will enable us to abstract our application from the specific cloud environment. Using this model we could scale our application in our internal data center (a private cloud) in the same way as any other cloud environment without changing our applications. Thisenables us to minimize the risk of making a strategic decision toward a specific platform in early adoption, and gives us the flexibility to choose the *right* platform when it's time to implement in production - without a high transition cost.
In this session, you will learn:
- How to design and deploy enterprise applications in a cloud, or a grid computing platform;
- How to use OpenSpaces, a Spring-based development framework from GigaSpaces, to develop, test and deploy applications on the cloud;
- What to take into account while developing or deploying applications on the cloud
 |
Peter Nickolov
President, COO and CTO, 3Tera
 |
Solutions for instant disaster recovery in the Cloud Computing Environment
Achieving an effective disaster recovery solution has always been difficult and expensive. Often companies backup and/or mirror their data and software only to find that when forced to run them on hardware and network configurations altered by disaster, they don't always work. Moving applications, data and infrastructure in the cloud can actually make disaster recovery easier and much more affordable. This talk will present some of the challenges to achieving disaster recovery and how to effectively deal with issues as data replication, connectivity, monitoring and management appliances that can provide disaster recovery to any online application.
 |
Russ Daniels
Vice-President & CTO
HP Cloud Services Strategy
 |
Designing the Cloud: Services that anticipate our needs
Today, information technology reaches a small fraction of people and delivers a small fraction of the potential value for those it does reach. In this presentation Russ discusses how cloud computing lays the foundation for dynamic services that anticipate and respond to individual and business needs. These services will allow organizations to address millions of customers, understanding and interacting with each individually, factoring in knowledge of their location, situation, and preferences in real time. Russ will describe the required business, social, and technical innovations needed to capitalize on this opportunity.
 |
Craig Balding
Craig is a security practitioner for a Fortune 500 with assets of 200 Billion USD. He has a decade hands on IT Security experience and is co-author of "Maximum Security".
CISSP and Creator of CloudSecurity.org
|
Cloud Computing: The Need for a Security Conversation
There is huge buzz around Cloud Computing. Commentators frequently cite security as potential barrier to adoption however there is very little published on the subject. What are the security implications of this set of technologies referred to as Cloud Computing? This presentation will give both providers and adopters a solid introduction to the security of: current virtualization technologies, SAN/NAS and Cloud Storage, SaaS and strategies for driving 'trust' in the Cloud.
 |
Eyal Waldman
President, Chairman and CEO,
Mellanox (NASDAQ:MLNX)
 |
Virtual Protocol Interconnect (VPI) - The Key to Solving Data Center Connectivity Challenges
The demands on data center I/O connectivity continue to increase with the deployment of multi-core CPUs, virtualization, networked storage, clustered databases, and low-latency applications in financial services, health services, Web 2.0, and the commercial high performance computing sector. Multiple interconnect protocols and fabrics exist to provide the best-of-breed connectivity for certain applications, but the ideal solution is a flexible I/O adapter solution that can address all workloads. In addition, data centers are driving to replace multiple slower speed adapters with one higher speed adapter to save power, cost, cabling and complexity while not compromising lost functionality and performance.
VPI enables I/O infrastructure flexibility and future-proofing for data centers and high-performance computing environments. Mellanox VPI-enabled adapters facilitate any standard networking, clustering, storage, and management protocol to operate over any converged network (InfiniBand, Ethernet, Data Center Ethernet) with the same software solution. Utilizing proven networking, clustering, storage, virtualization and RDMA acceleration engines, VPI optimizes application performance, power consumption, workload agility, and total system efficiency while future-proofing IT infrastructure.”
Cloud Computing in Practice: Fast Application Development and Delivery on Force.com
Several years ago, salesforce.com opened up their infrastructure and made it available to anyone to build a business application and run it on their servers using their platform called Force.com. Force.com is the most proven platform for building enterprise applications that run in the Cloud. It runs all of the salesforce.com apps, over 800 ISV apps and over 80,000 custom apps.
Force.com has been successful because it's the fastest way to get from idea to app. What used to take months can now be done in days or weeks. Force.com allows thousands of companies to free themselves of complex infrastructure so they can focus on building quality apps that deliver value to the business. It’s not just software as a service, it’s a platform as a service, and this presentation will give you a look at what it’s like to develop and deploy in the cloud on Force.com.
 |
Stevie Clifton
Co-Founder and CTO, Animoto
 |
A vivid example of cloud power comes from Animoto, an 18-month-old start-up in New York that lets customers upload images and music and automatically creates customized Web-based video presentations from them; many people then share them with friends. Animoto gives a free video presentation to anyone who signs up for its service, and earlier this spring about 5,000 people a day were trying it.
Then, in mid-April, Facebook users went into a small frenzy over the application, and Animoto had nearly 750,000 people sign up in three days. At the peak, almost 25,000 people tried Animoto in a single hour.
To satisfy that leap in demand with servers, the company would have needed to multiply its server capacity nearly 100-fold, says Stevie Clifton, 30, a co-founder of Animoto and the chief technology officer. But Mr. Clifton and the other co-founders had neither the money to build significant server capacity nor the skills — and interest — to manage it.
Click here for more information
 |
Richard Zippel
Vice President of Technology in the Chief Technologist's Office, Sun Microsystems
 |
 |
William Fellows
Research, The 451 Group
 |
Cloud computing: Cloud 9 or Terra Firma?
 |
Alexis Richardson
Managing Director, Business Development, CohesiveFT
 |
Cohesive Financial Technologies, LLC provides automation solutions. The company provides Elastic Server On-Demand, an automation solution, which simplifies the process of creating application stacks for use in virtual environments. Cohesive Financial Technologies, LLC was founded in 2006 and is based in Chicago, Illinois with additional offices in Palo Alto and London.
 |
Jason A. Stowe
CEO, Cycle Computing, LLC
 |
Computation on the Cloud
The game is changing. Cloud Computing is reshaping how computation and applications are consumed with lower up-front costs and flexible access to servers. Companies that normally purchased servers for peak rather than median usage, along with start-ups/SMBs that couldn't access large compute clusters, can now flexibly get tremendous computational power very quickly.
Access to hundreds or thousands of CPUs is potentially very powerful, but it leads to the question "How do I use them?" How do you manage CPUs, easily run computation, set priorities/scheduling/budget, execute workflows with dependencies, and monitor usage/uptime?
We have solved these problems with CycleCloud (http://www.cyclecloud.com), the leading system for creating production-quality grids in minutes using cloud resources. For over a year, CycleCloud has run computation on Condor-based grid infrastructure with monitoring, usage reporting, and job management functionality. Cloud Computing offers time to market advantages to those who can use it effectively. CycleCloud has made this easy.
And it's not still in development, it's already working. Use cases have included design simulation for hardware/equipment companies, statistical analysis and monte carlos for finance, and bioinformatics calculations for big pharma. CycleCloud gives any company access to the same production-level Condor grids our Fortune 100 clients use in-house.
CycleCloud takes the delays, configuration, administration, and sunken hardware costs out of Grid Computing allowing you to focus on running your jobs.
 |
Wolfgang Gentzsch
DEISA Project, and member of the Board of Directors of the Open Grid Forum
 |
Will HPC become a Cloud Service ?
- The DEISA Experience-
Cloud computing services, as offered by companies like Sun, IBM, Amazon, Google, IBM, Salesforce, Sun, and others, is on its way to become an important and standard component of enterprise IT, adding a new, ‘external’ dimension of flexibility by enhancing one’s ‘home’ resource capacity when needed, where needed. The question still remains how suitable the Cloud services model will be for the capability computing demands of the HPC community, in research and industry.
While grids and virtualization provide the ‘plumbing’ to enable seamless access to distributed resources, clouds denote services on a pay-per-use basis. Grids stand out because of their flexible, dynamic, feature-rich resources and thus are complex by their very nature. Cloud applications will likely follow similar strategies as grid-enabling ones. Just as challenging, though, are the cultural, mental, legal, and political aspects of clouds. Building trust and reputation among the users and the providers will help in some simple scenarios. But it is still a challenge to imagine users easily entrusting their corporate assets and sensitive data to cloud service providers.
One promising example of an HPC grid on its way potentially to a cloud service might be the Distributed European Infrastructure for Supercomputing Applications, or DEISA. DEISA Extreme Computing Initiative (DECI) is successfully offering millions of supercomputing hours to the European e-Science community, at finger tip, and helping scientists gain new scientific insights. Why is DECI so successful? Several reasons, in my opinion: because it has a very targeted focus on specific, long-running, supercomputing applications; many of the applications just run on one single system; it has user-friendly access to resources through DESHL and UNICORE; its coordinating function gives consortium partners full autonomy; and because there is an application task force (ATASKF) that helps users port their applications to the supercomputing infrastructure. If all this were here to stay, DEISA would have a good chance to exist for a long time. And then, we might end up with a DEISA Cloud which will become an external HPC node within your grid application workflow.
Thus, the aim of my talk will be to elaborate on the main differences between grids and clouds, with the aid of the DEISA experience, and discuss what grids can learn from clouds such that they become more user-friendly, or even become a Cloud.
 |
Moshe Kaplan
Co-Founder and CEO, RockeTier
 |
 |
Ayal Baron
Co-Founder and CTO, RockeTier
|
Real Life Cloud Computing: From Field Experience to Strategic Aspects
Cloud computing is the next step in the hosting arena, and many vendors provide platforms as well as services. How can this technology help you meet your business goals? What are the pros and cons of each platform and service? Who already implemented their services and systems on these platforms? What are the challenges? What is the Return On Investment (ROI) and Total Cost Ownership (TCO)? Should you invest in this trend?
Join Ayal and Moshe, and learn from our clients' field experience, how this technology affects the market, how start up take advantage of cloud computing, and what the enterprise sectors think about it. This presentation is based on: 1) RockeTier field experience, 2) evaluation of the existing platforms and services, 3) major consulting and analyst firms: Strauss Strategy that specialize in the IT strategic consulting, Current Analysis that specialize in the telecom sector, Ideas International that specialize in IT infrastructure and Nucleus Research that specialize in ROI and TCO analysis; 5) survey of the finance, telecom and Web 2.0 sectors, including leading product companies, institutes and services companies and 6) survey of early adapters such as start up companies
 |
Nikita Ivanov
Founder and President, GridGain Systems
 |
“GridGain – Java Gateway to Cloud Computing”
The topic of this presentation is about fastest growing open source Java grid computing framework called GridGain and how it is ideally suited for emerging cloud computing. This presentation will outline the current state of the cloud computing, its challenges as well as speaker's vision on where this technology will evolve. It will also emphasize the state of the GridGain project along the same lines and will make a case for a GridGain to be the best Java gateway to cloud computing today.
 |
Jeffrey Birnbaum
Managing Director and Chief Technology Architect, Merrill Lynch.
|
 |
Assaf Marrron
Corporate Architect, CTO Office, BMC Software
 |
An overview of the implications that dynamic and distributed computing as represented by Cloud Computing has upon an Enterprises’ ability to manage its computing environment.
 |
Building Cloud Services Catalog
 |
The world of cloud computing enables the dynamic provisioning of services. Cloud services providers like Amazon, Google, eBay, etc., offer various services over the web, easily accessed. Different needs and new combination of services can be offered based on different service providers.
All this endorse the need for accurate independent information service, containing the services and the way to use them. Obviously such service has to be dynamic, up-to-date and help the automatic provisioning of business process.
This lecture will present the need upon a true example from the Tel Aviv University, and suggest powerful tools from VeNotion technologies allowing the creation of this new dynamic cloud services catalog.
IGT2008 – World Summit of Cloud Computing, Panels:
Panel 1 - EC2 Case Studies
 |
Zvi Schreiber
CEO, G.ho.st No walls
|
Virtual Computer over Amazon Web Services
G.ho.st, ("Ghost" - the Global Hosted Operating SysTem at http://G.ho.st) aggregages web services such as Google Docs, Zoho, Zimbra, ILoveIM, together with a Web desktop and web file system, into a free Virtual Computer service which is provided to consumers. The G.ho.st system itself is hosted on Amazon Web Services utilizing S3, SimpleDB, EC2 and other services. In this talk Zvi will explain briefly the concept of a Web OS, the technologies involved in aggregating third-party web services, and his experience using Amazon cloud computing services.
|
Nati Shalom
Founder & CTO, GigaSpaces
|
Easily Scale Your Apps on Amazon’s Elastic Compute Cloud (EC2)
The Amazon Elastic Compute Cloud (EC2) service allows adding and removing compute resources on-demand, with the benefit of only paying for the hardware capacity needed, when it is needed. But there is a gap: with traditional middleware stacks, such as J2EE and LAMP, developing and deploying reliable transactional and data-intensive applications on the EC2 cloud is complex and time-consuming.
GigaSpaces XAP, the scale-out application server, bridges the gap between on-demand hardware scalability and on-demand application scalability.
|
Simone Brunozzi
Web Services Evangelist, Amazon Web Services
|
Panel 2 - Cloud Security Panel
 |
Professor Barton P. Miller
|
|
Craig Balding
Craig is a security practitioner for a Fortune 500 with assets of 200 Billion USD. He has a decade hands on IT Security experience and is co-author of "Maximum Security". CISSP and Creator of cloudsecurity.org
|
Dec. 2nd
IGT2008 – World Summit of Cloud Computing Workshops:
Cloudera and Yahoo! MapReduce & Hadoop workshop
The goal of this half-day workshop is to expose current software engineers to Hadoop, an open source implementation of the MapReduce and GFS systems developed by Google. Attendees will listen to talks describing the Hadoop technology, and practice working with the Hadoop environment to familiarize themselves with the system. The workshop will last four hours.
http://hadoop.apache.org/core/?SearchParam=hadoop
 |
Aaron Kimball
|
Aaron has been working with Hadoop since early 2007. Aaron has worked with the NSF and several other universities nationally and internationally to advance education in the field of large-scale data-intensive computing. He helped create and deliver academic course materials first used at the University of Washington, which were later adopted by many other academic institutions, as well as Hadoop training materials used by several industry partners. Aaron has also worked as an independent consultant focusing on Hadoop and Amazon EC2-based systems. Aaron holds a B.S. in Computer Science from Cornell University, and an M.S. in Computer Science and Engineering from the University of Washington.
Outline:
Hadoop at Yahoo: (1:00)
- Owen O'Malley, Yahoo, Inc.
- High-level overview of how Hadoop is used at Yahoo
Hadoop Technology Review: (1:30)
- Aaron Kimball, Spinnaker Labs, Inc.
- What is Hadoop
- MapReduce
- Functional programming principles
- Map and Reduce functions
- System design principles
- HDFS / GFS
- File system design
- Hadoop implementation
- Major class hierarchy
- Program flow
- Important interfaces
- Configuring a Hadoop cluster
Lab Activity 1: Setup (0:20)
- Configure Eclipse
- Connect to Hadoop in the Cloud
- Load data into distributed file system
Lab Activity 2: Develop MapReduce program (1:00)
- Create an inverted index over a document set
Wrap Up (0:10)
- Review lab activities / final questions
GigaSpaces
- OpenSpaces: http://www.gigaspaces.com/wiki/display/GS6/OpenSpaces+Overview
|
|
|
|
|
