EGA Reference Model: A Closer Look

By By Derrick Harris, Editor

May 16, 2005

Fresh off last week's Reference Model for enterprise Grids release, Paul Strong, chairman of the EGA technical steering committee and systems architect at Sun Microsystems, spoke with GRIDtoday editor Derrick Harris about what people can expect to find within its pages, how it will help clear up confusion among those in the Grid space and how the alliance's first deliverable will “serve as proof of the intent and value of the EGA.”



GRIDtoday:
What, exactly, is the Reference Model? How can interested parties go about viewing it?

PAUL STRONG: The Reference Model is the Enterprise Grid Alliance's (EGA) first technical output, and as such it forms the foundation for the work being undertaken by our other working groups and serves as a basis for collaboration with other stakeholders in the enterprise Grid space, such as enterprise users, other standards bodies, vendors and systems integrators. It is composed of a glossary, a simple model and a set of use cases that capture the requirements for enterprise Grid computing. Like the EGA, the Reference Model is both vendor-neutral and technology agnostic. It is a living document that will evolve as the enterprise Grid technology landscape does, continuing to deliver relevant information to the enterprise Grid community. Anyone can download a copy from the EGA's Web site which can be found at www.gridalliance.org.

Gt: Can you describe, in some detail, the three main components (lexicon, model, use cases) and give some examples of what can be found in each?

STRONG: The glossary provides a small reference of terms that ensures there is a common understanding of enterprise Grid computing terminology. We defined terms such as “enterprise Grid computing,” “Grid component,” “utility computing,” “virtualization” and “scale out,” etc., and related them to each other to help alleviate the confusion surrounding them. In general, we seek to define only what needs defining. We tried not to define terms that are already well-used and clearly understood.

The model, a significant portion of the document, serves as a resource to help describe enterprise Grids. It consists of a small set of simple objects, relationships and verbs/actions that allow the complexity inherent in enterprise Grids to be easily represented and categorized. For example, rather than define the enterprise Grid in terms of services and resources, we define it in terms of a unit of an object of management, the Grid component. The Grid component could be something as concrete as a server or disk, or as abstract as a CRM or ERP application. Grid components have a life cycle, they get provisioned, managed, monitored and finally decommissioned. The model is technology agnostic in that it does not assume a great deal about the technology that is used in building an enterprise Grid. Thus, it can be used to describe existing data centers, as well as current and future enterprise Grids. The model itself then provides a context for the use cases, as well as for comparing various Grid technologies, products and implementations.

Lastly, the use cases illustrate a few generic and specific scenarios within an enterprise Grid. The goal of the EGA is to drive the adoption and deployment of Grid technologies in the enterprise. In order to achieve this, the various standards and products delivered in this space must address a common set of data center requirements and inhibitors to adoption. Use cases are how we do this, and this collection represents the first phase of our work in this area. These serve as a feedback mechanism for enterprise users to ensure that vendors and standards bodies understand their needs.

Gt: How badly was the Grid market in need of this Reference Model?

STRONG: Clearing up the confusion around terminology and providing a simple model that allows the comparison of value delivered by Grid products and solutions is key to driving the adoption of Grid in the enterprise data center. If people don't understand Grid, Grid architectures and Grid technologies within the context of their own data centers and data center processes, such as ITIL or eTOM, then they're unlikely to adopt them. The Reference Model addresses this, or at least it starts to, and, thus, we feel that it fills a big gap for the industry, as well as complementing the valuable work being undertaken in other bodies, especially the Global Grid Forum, the DMTF and SNIA. It is more sharply focused on the data center than other Grid architectural work has been to date, yet it captures more of the abstract components and their life cycles than perhaps some of the component centric information models do today.

Actually, if we continue the previous thread on focus, another area where we felt this work was needed was in driving the needs and requirements of enterprise data centers into the Grid community. Some of the needs of an enterprise are significantly different to those within the community where Grid had its origins. Specifically, a focus on guarantees for mission-critical applications and on leveraging the Grid for a variety of workloads, including traditional mixed transactional (OLTP) and batch workloads, Web services and Service Oriented Architectures (SOAs), as well as compute intensive workloads. Enterprises find the potential economies of scale and agility offered by Grid architectures and Grid technologies (e.g., virtualization, abstraction and automation) very compelling. The Reference Model use cases allow us to articulate those needs and to share them with the Grid community at large and the various standards bodies specifically, so that our collective output realizes that potential.

Gt: How will it help to define enterprise Grid standards?

STRONG: Although the Reference Model was not developed to define enterprise Grid standards per se, we hope that it will help drive a consistent set of standards that meet the needs of enterprise users and drive the adoption of Grid technologies. This is the specific purpose of the use cases. Standards are clearly critical to enabling interoperability and thus extracting the maximum value from the inherently heterogeneous data centers we see today.

Gt: How does the Reference Model address Web services — an issue that has sparked some confusion among various parties involved with Grid computing?

STRONG: As it stands, the Reference Model makes no assumptions about how an enterprise Grid will be implemented. It allows the abstract representation of an enterprise Grid. Indeed, it can be used when describing a non-Grid data center infrastructure as well. This is particularly useful in that it provides a context for understanding the potential value of a chosen means of implementation, such as Web services, without presuming it. Obviously, it is likely that Web services are going to play a major part in realizing enterprise Grids, but the model is a model, not a prescriptive architecture. Other EGA working groups will no doubt focus more on this issue when addressing the key areas of adoption or inhibitors to adoption.

Gt: Personally, and for the EGA as a whole, how does it feel to finally have concrete evidence of the work being done by EGA members in the various working groups?

STRONG: I have to say that we are very pleased with being able to make the first of our deliverables available. This work reflects the consensus and contributions of 20 individuals representing the various EGA member organizations. A real team effort. As our first deliverable, the Reference Model in some ways sets the standard for the work that will follow, and which is already underway, from the other EGA working groups.

Gt: Does the announcement of the Reference Model help to legitimize the EGA to any skeptics?

STRONG: I think the Reference Model will serve as proof of the intent and value of the EGA. We bring a clear focus on the issues around deploying Grid in enterprise data centers and we seek to resolve those through collaboration. The EGA is in many ways not a traditional standards body. Only as a last resort do we expect to develop our own standards. In the general case, we will seek to encourage the development and adoption of appropriate existing standards, and if these do not exist, we will in the first instance seek to find a body whose natural role it is. The work being undertaken in other EGA working groups, using and building on the reference model will continue this approach.

Gt: Is the EGA working with the Globus Consortium in any capacity? If so, how?

STRONG: We are constantly communicating with other Grid stakeholder organizations, like the Globus Consortium, to build relationships and establish a framework for collaboration to ensure that their output meets the needs of the enterprise. Univa, the company formed by a number of the key luminaries in the Grid field with the express purpose of using Globus open source software to transform enterprise IT infrastructures, is a member of the EGA and is highly aligned with our goals. I think that this is indicative of the inclusive and collaborative nature of what the EGA is doing. Expect to see more announcements on collaboration as we move forward.

Gt: Back to the Reference Model — what kind of effect will it have on Grid adoption? Will it directly or indirectly affect the EGA's goals?

STRONG: The Reference Model serves as both an aid to Grid adoption today and as the foundation for much of the EGA's work going forward. So it directly impacts our ability to meet our goals — in a very positive way of course.

The Reference Model provides a clear context and understanding of this space enabling enterprise users to determine the applicability of Grid architectures and technologies, while helping them compare products and solutions. This is key to driving adoption today. Sharing the requirements enumerated in the Reference Model serves the EGA and enterprise Grid stakeholders in the medium to long term by driving consistent and relevant standards and products. Again, something that clearly meets our goals.

Gt: Finally, what else is going on with the EGA? Can we expect to see results emerging from other working groups in the near future? If so, what kind of announcements can we expect?

STRONG: All of our working groups are working hard to address specific areas where technology is evolving or where there are known obstacles. Specifically, we have two groups looking at server and data provisioning. We have a group looking at security in enterprise Grids, exploring what is different in terms of requirements versus those of a more traditional data center. Grids will have a very dynamic nature, since resources are shared. For example, when two application components share an operating system or when a resource is repurposed over time, there are important ramifications with respect to security. Finally, we have a group looking into utility accounting. In many cases, the services that enterprise Grids will host or deliver will almost certainly be offered in a pay per use or value basis. Both of these needs set requirements for telemetry, billing and accounting. The Reference Model serves as the foundation for all of these working groups, plus others we may create in the near future.  e expect to announce additional deliverables from these groups in the next 9-12 months.

Gt: Anything to add?

STRONG: Nothing, other than to thank you for affording me the opportunity to talk about the EGA Reference Model, and to encourage folks to get their organizations to join the EGA and help us in our cause.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire