Wachovia Banks On Grid Expansion
Charlotte-based Wachovia will be getting super-computer style processing from its expanded grid
May 27, 2004
![Network Computing logo Network Computing logo](https://eu-images.contentstack.com/v3/assets/bltde8121fc52c5c8f3/blt3f3d0318f746b1c2/65a530e4187606040a1d8b8c/placeholder.png?width=1280&auto=webp&quality=95&format=jpg&disable=upscale)
Wachovia Securities Inc.is planning to expand its grid strategy to speed up risk assessments, seeking to avoid the expense of investing in a supercomputer.
Speaking at the Gt04 conference in Philadelphia, Wachovia IT architect Brad Shea explained that the company’s grid infrastructure currently consists of about 250 nodes, encompassing desktops and a mixture of Intel Corp. (Nasdaq: INTC) and Sun Microsystems Inc. (Nasdaq: SUNW) Solaris servers.
The grid is used within the firm’s fixed income group for financial calculations and risk assessments. But, like all financial firms, speed is of the essence when completing these calculations, and the Charlotte, N.C.-based bank is planning to boost its processing capacity. This will involve expanding the grid infrastructure to 800 nodes during the course of this year.
Wachovia’s existing grid infrastructure has already enabled the bank to slash the time taken to complete many risk assessments from 15 hours to 15 minutes. But the next stage is to cut these times even further, with “near real-time” risk assessments now the goal, according to Shea.
He says, “I think that it’s very likely that we can do considerably faster risk assessments than we do today, because of the scale of the grid that we are planning.”Although he was unwilling to provide specific details on the financial benefits, Shea admitted one of the big attractions of grid computing is that it helps avoid the cost of investing in a supercomputer. “That’s one of the ways that we look at the ROI calculation."
This certainly makes sense: Grid computing is a way for companies to harness their existing CPU resources without having to face either the financial burden or implementation hassles of deploying a supercomputer. These do not come cheap. In 2002, for example, the U.S. Department of Energy awarded IBM Corp. (NYSE: IBM) a contract worth up to $267 million to build two supercomputers.
But there is more to Wachovia’s grid than sheer processing horsepower. Specialist software from DataSynapse, for example, plays a key role. By using the vendor's GridServer software, Wachovia has been able to convert applications that were previously running on dedicated servers into Web services that can be run across the entire grid infrastructure.
Rather than relying on a specific server for processing power, the application instead uses whatever resources are available on the grid. There was a significant amount of interest in this type of technology at Gt’04, as increasing numbers of firms look to harness the computing power offered by the grid (see Paremus Plays Its Hand).
Wachovia is planning to open up its expanded grid infrastructure to an increasing number of applications. Shea says, “I am not limiting this to risk assessment -- that’s the low-hanging fruit. Our goal is to do general purpose computing within the grid.“For any other application that we are running in-house, there’s the potential that we could run it on the grid."
— James "Low-Hanging" Rogers, Site Editor, Next-gen Data Center Forum
You May Also Like
Maximizing cloud potential: Building and operating an effective Cloud Center of Excellence (CCoE)
September 10, 2024Radical Automation of ITSM
September 19, 2024Maximizing Manufacturing Efficiency with Real-Time Production Monitoring
September 25, 2024