HPC in the Cloud


Dedicated to covering high-end cloud computing
in science, industry and the datacenter

Language Flags

A Busy Week for United Devices


United Devices (UD) has been pretty busy in the last couple of weeks, announcing within a week of each other the first in a series of roundtable events and the release of a new solution.

In the latter, the Austin, Texas-based UD announced its Virtual Cluster solution, which allows non-dedicated nodes to be added to existing clusters. UD, said CEO Ben Rouse, had six beta customers -- consisting of oil & gas and pharma companies, as well as universities -- for the solution, and one thing they found out was that the ratio is somewhere between 2:1 and 3:1 in terms of the number of undedicated machines (desktops, servers, etc.) needed to equal one dedicated node. For a company or government agency that has a lot of existing clusters, as well as a lot of available outside machines, Rouse believes the ease of use and the price tag of $150,000 will make a lot of sense.

However, there also is a bigger picture to look at here, aside from the ROI on all those PCs and file servers, and the TCO on those dedicated clusters. "UD is really a grid management company," said Rouse. "We have our own native workload scheduler for the cluster, and we have companies that use that, but 95 percent of our focus is on the management layer that sits on top of a heterogeneous environment."

What Virtual Cluster could mean to UD is that its users are on their way to Grid infrastructures, where UD's bread truly is buttered. Rouse believes the solution addresses a number of issues that have prevented further adoption of Grid computing, among them the need for an accurate assumption of available capacity. Many companies consider Grid to be based around cycle scavenging, he said, and because of Virtual Cluster's use of UD's Grid MP platform, as well as the presence of a dedicated cluster, availability is not as much of an issue.

Another issue that Rouse sees as an inhibitor to Grid adoption is more cultural -- that being the fear of a new computing paradigm. "One of the barriers to [Grid adoption]," said Rouse, "is it's viewed as a very large, monolithic platform that spans departments ... so individual departmental cluster owners feel like they have to give up control, and there's typically a new paradigm in terms of what the job submission layer is; there is disruption that's caused."

Rouse said UD has found that many companies would like to take the first step toward Grid at a departmental level, and because Virtual Cluster manages the non-dedicated machines underneath the existing workload scheduler (Platform LSF, Sun Grid Engine, Altair PBS Professional, etc.), users don't have to touch the job submission script. In essence, he said, Virtual Cluster can be viewed as a low-risk step toward a shared infrastucture. Users can take the next step(s) when they are ready.

As for the roundtable, which will be taking place Thursday in Princeton, N.J., I was able to get some more details on the event from UD's CTO, Jikku Venkat.   For starters, Venkat noted that Grid computing has already been proven for compute-intensive applications, so this roundtable will focus on more on business applications. In fact, he said, most of UD's work with British Telecommunications (BT) has been around business applications -- an area toward which Venkat said the company has been seeing a shift.

At the roundtable, Venkat expects BT to describe its plans around its Grid- based managed services offering and the motivation for this. Johnson & Johnson, he said, also will discuss potential opportunites around business applications and managed services, as well as their overall successes with Grid thus far.

The roundtable, however, will not focus solely on BT's and Johnson & Johnson's plans around and experiences with Grid, but also will hit upon a variety of topics important to the user community as a whole. Among the topics to be discussed is "preferred pricing models," which has a fairly broad scope and (I would assume) includes both vendor and ISV pricing models.

When asked about ISV pricing, Venkat said, "We believe that ISVs are starting to refine their pricing models to accomodate grids. Large enterprises such as BT and [Johnson & Johnson] have strong relationships with the ISVs and can bring some influence to bear on this issue."

As for the future of these rountable events, Venkat said they were inspired in part by customer demand, and that -- along with the success of the first meeting -- will continue to play a role in the scheduling of subsequent events.

Most Read Blogs

Aspen

Short Takes

Running Computational Fluid Dynamics in the Cloud

May 16, 2013 | When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
Read more...

In Support of Cloud-based Rendering

May 10, 2013 | Australian visual effects company, Animal Logic, is considering a move to the public cloud.
Read more...

Internet2 Awards Program Seeks Innovative Applications

May 10, 2013 | Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
Read more...

Sponsored Whitepapers

Best Practices in Big Data Storage

05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.

Exploring the Potential of Heterogeneous Computing

04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.

Sponsored Multimedias

Newsletters

Stay informed! Subscribe to HPC in the Cloud email Newsletters.

HPC in the Cloud Update
HPCwire Weekly Update
Digital Manufacturing Report
Datanami
HPCwire Conferences & Events
Job Bank
HPCwire Product Showcases



HPC Job Bank


Featured Events



  • June 16, 2013 - June 20, 2013
    ISC'13
    Leipzig,
    Germany

  • June 17, 2013 - June 18, 2013
    Forecast 2013
    San Francisco, CA
    United States




HPC in the Cloud Conferences & Events