GRIDtoday editor Derrick Harris spoke with Ed Hubbard, founder and chief marketing officer of United Devices, about the company's strategy around SC'05. its recent acquisition of France-based GridXpert (a leader in the manufacturing sector), the issues of Grid standards and Grid adoption, and the differences between Grids and clusters — a topic that arises quite often in the HPC space.
—
GRIDtoday: How's everything going with United Devices? Will you be announcing any news at SC'05?
ED HUBBARD: Business continues to grow with several of our large customers moving their Grids to a central services model and offering them enterprise-wide.
At SC'05, we'll have a number of announcements, three as a matter of fact. We'll have an announcement with HP, Microsoft and an ISV partner.
Gt: What about the news of the past several months? Can you comment on the GridXpert acquisition? How has it affected the company in terms of customers in new markets and geographies?
HUBBARD: Acquiring GridXpert and its best-of-breed meta-scheduling technology has accelerated a number of our deployments by leveling the complexities of multiple, incompatible schedulers/DRMs. Not surprisingly, we've also opened up a number of conversations within our expanded customer base around the products and services offered by UD. Finally, part of our reasoning for this acquisition was to significantly enhance our position in manufacturing and I believe this has been more successful than we projected. The former GridXpert team (now UD, of course) had a fairly large number of evaluations going on that we've been able to add a lot of value to from a services and technology perspective. I anticipate a very good conversion rate on these evaluations.
Gt: Moving on to the Grid industry as a whole, I'm wondering where you see the market heading in terms of widespread adoption? Would it benefit the cause if the community could agree on some quality standards?
HUBBARD: We continue to architect around open Web services standards, which have served us well with customers. In fact, this is one of the areas where we continue to receive a lot of positive feedback — namely the ability of our customers to easily create application services and portals around our infrastructure in environments like Java and C#.
On the topic of standards, I don't think they've held the industry back as they've largely been irrelevant to date (at least in our deployments). Our view is that this is changing but not in the way you might expect. We actually see more divergence, which was another problem we wanted to address with the GridXpert acquisition. By embracing the reality of the market (multiple, incompatible schedulers / DRMs) and providing a solution to eliminate that unnecessary complexity for our customers, we believe we have a superior product set to solve what our customers really face in their everyday production environments.
I don't think this is going to change very quickly since there is a huge gap between public/press perception and commercial reality that needs to be closed with some open conversation:
- There is a perception out there that WSRF/OGSA & Globus are standards.
- The reality is that Globus is merely a Grid software toolkit. In other words, it is an implementation geared toward academic environments where it has been somewhat successful — it is not a standard by any means. OGSA is really WSRF and is currently under review at OASIS and it does not address current enteprise issues around interopability. Most of the requirements addressed in the current document reflect academic needs of running multiple Grid services across different organizations.
We've tried hard to stay out of this debate and just be customer-driven, but this is the core problem of standards for the Grid market that no one seems willing to admit or discuss openly.
Gt: How is it that United Devices is so successful in the Grid space given the somewhat disappointing enterprise adoption rates? Does it have something to do with simply targeting the right customers in the right industries?
HUBBARD: We have 100-plus customers today ranging in size from 20 nodes to 3 million, but this hasn't been an overnight success. We have worked hard and slugged it out with more than a dozen other players that have come and, thankfully, gone. This has left a pretty stable set of solutions that have settled into that age-old competitive triad (UD, DataSynapse and Platform) where there are three quality solutions in the market that all own their respective verticals and compete in the verticals where no player has a clearly dominant position.
I would argue that Grids have already penetrated the majority of the Fortune 500 in some form even if they haven't been adopted as an enterprise-wide service yet. For UD, we chose to focus early-on on life sciences and have been very successful in that vertical market. We've built up a ton of credibility, a high-quality set of references and large, complex deployments that I'd put up against any competitor's reference set. With GridXpert, I hope we've successfully telegraphed that we plan to repeat this same success in the manufacturing and other environments and, in fact, are already well on our way.
Gt: On to Supercomputing … what is it about this show that draws so many attendees and exhibitors? For how long has United Devices been exhibiting at the show?
HUBBARD: I think the show draws well because of the natural progress of technology, e.g. what used to be a highly specialized supercomputing application 10 years ago is now running on a Grid and the results can be visualized and manipulated on a single workstation. The democratization of these engineering analyses has continued unabated and the show where you can go to discuss them across the board remains the SC'XY shows.
UD has either exhibited or attended the show (based on our strategy for the given year) since 2000.
Gt: Seeing as how United Devices operates in both the Grid and cluster markets, which do you tend to focus on at SC events, which seem to focus a more on the cluster/HPC market?
HUBBARD: We typically focus on clusters at the SC'XY shows for both practical/logistics reasons and because we just think its a better fit from an application perspective. If you look across the set of applications in use and demo'd at the SC'XY shows, you'll find a large number of MPI-based applications that really require the speed and low interconnect latency of a cluster to run effectively. A Grid is simply a set of resources — these resources could include clusters. We don't see a Grid market as different from a cluster market. We can effectively manage clusters stand-alone or as part of larger Grid deployments through our Grid MP platform (MPI jobs included).
Gt: Finally, and I'm starting to ask this question a lot because I feel that there is still some confusion out there, can you define, at least from a United Devices perspective, the differences/similarities between clusters and Grids?
HUBBARD: Grids are the superset in our vernacular. A Grid can be made up of any available device that may be useful to the application type(s) the enterprise is trying to accelerate, raise the reliability on, etc. That said, we love starting somewhere on a cluster because we can clearly articulate how this single, little cluster could grow up to be the enterprise's Grid — we call this a “Grid-ready cluster.” Many of our current implementations started out as a cluster and built a Grid of clusters and other resources.
Clusters are, in general, simpler animals. They are typically self contained, built from homogeneous hardware, have dedicated, private-switched networks and storage, are managed carefully by dedicated staff and are often a better path from a price/performance perspective for a number of applications.
Grids, on the other hand, often include a cluster, or multiple clusters. Sometimes running the same underlying scheduler/DRM, but sometimes not. They can also contain servers that are part of “'hot” recovery sites, underutilized machines from, for example, a company's Web farm that do very little at night but which can add significant power to a Grid with high overnight processing demands. Workstations and PCs are also often a part of enterprise Grids and this adds complexity around security requirements, data management and caching, etc., that we've tuned for in our Grid MP platform. Finally, Grids become a much larger, integrated part of the business's core value creation and as such absolutely require a higher level of manageability than a single cluster. This area is one where we have been increasingly focused over the last couple years driven by our customers.
The Grid is fundamentally about removing the current hard, static binding between an application and its execution environment. In the new world, this binding will be soft and very dynamic. The benefits of doing this are very significant for our customers.
Gt: Is there anything else you'd like to add about United Devices, SC'05 or the Grid market in general?
HUBBARD: From both introspection and looking at our competitors, we fully believe that Grids are moving into mainstream adoption. All indications from our current customers and prospects point in this direction.