Back in 1993 -- in an interview with Computerworld ("Sharing Software Ekes More Life Out of Older Unix Boxes") -- Platform President Songnian Zhou introduced his company's Load Sharing Facility (LSF) breakthrough as "a network operating system that makes it easier to share compute resources across a heterogeneous Unix network." Today, Platform's LSF has become the most widely used job scheduler in enterprise Grid production (Linux and Unix) environments.

And the company has received zero dollars in venture funding through the years -- every dollar has been derived from customer sales, according to Zhou, who sees a number of factors today that indicate a quickly maturing Grid industry.

"The killer app for grid is not the components of applications - ERP, CRM - but the connection of all of these components of enterprise applications to form business processes," said Zhou. "Industry analysts are consistently saying that in order to support SOA as the architecture for applications, you need a service oriented infrastructure. So how do you provide this service-oriented infrastructure to deliver resources where and when needed, based on cost and demand rather than just fixed assets? The Grid provides a very solid set of core technologies for SOI."

Zhou points out that from the bottom up, today's trends in the vendor community are all coming together to the benefit of the emerging enterprise Grid market. After ten-plus years with R3, SAP is component-izing their product, and working towards open integration with third-party software so that applications become more of a building-block approach that can be deployed in Grid environments (and we're seeing similar activity from leading business intelligence provider SAS). On the storage side, companies like NetApp and EMC are focused on the convergence of virtualized storage directions that can make storage participant in a service oriented infrastructure. Meanwhile, networking vendors like Cisco now have the capability to do basic provisioning not just of switch capacity, but as the servers themselves.

As Platform has grown its customer base through the years, the company has also worked closely with the Globus Toolkit.

"By and large, the two [Platform and Globus] server technologies are very complementary," said Zhou. "For example, we don't do security, and Globus has some good security capabilities that a number of our customers find very important. We don't do the directory service, and Globus does that. So there are a number of functionalities in Globus that are very complementary to our product, and that's why we've partnered and integrated and provided support. Platform isn't just looking at making a lot of money selling support for Globus, but really to enable adoption of Grid computing for the many customers who find the capabilities in Globus useful."

Platform has its own Platform Globus Toolkit built on GT3 -- and the company is working on a new version for GT4. Platform also contributed a Community Scheduler Framework that introduced new meta-scheduling concepts, with some scheduling policies and scalability on top of Globus... Meanwhile, Platform continues to extend its customer roster to include major enterprises like Peugeot. Zhou believes that "product lifecycle management" requirements in manufacturing and automotive industries will be a huge growth area for Grid in the near term.

"When you are going through the design process, you need to test a part, see whether structure is good, whether aerodynamics are going to work," said Zhou. "So as you're seeing how different parts fit together, you're doing this virtual assembly to see how your car or airplane -- or whatever the case may be -- will interact with things like aerodynamics and weather. You need to study the manufacturability as part of the design, so that manufacturing is easy and cost-effective. And you also have to take into consideration maintenance issues downstream. So the whole flow, the business process, is called product lifecycle management. And that business process really over time is going to be one of the biggest applications for Grid."

Increasingly, the industry is acknowledging that with so much of the actual manufacturing of products going to 3rd world countries -- some of the biggest margins and values can be derived in the product lifecycle process. And according to Zhou, companies need enterprise Grids that can provide a stable platform for the integration of all the heterogeneous resources -- because more and more, this entire PLM process is based on computing resources, based on programmable machine tools, easily configurable assembly lines, and IT-driven services and maintenance.

Platform wrapped up '05 with the release of the Enterprise Grid Orchestrator -- a new platform for the integration and management of heterogeneous resources in a Grid environment. 2006 should be a very interesting year for the Toronto-based company, which partnered with Microsoft for LSF to offer some key functionality in the Windows Compute Cluster Server release next year.

close window