Star-P is an interactive parallel computing platform that lets scientists, engineers and analysts create algorithms and models on their desktops using familiar mathematical tools - such as MATLAB and Python - and then run them instantly and interactively on parallel computers with little to no modification. It eliminates the need to re-program applications to run on parallel systems, making problem-solving faster and users more productive.

The new version of Star-P adds support for Platform Computing's LSF workload management software for accelerating batch workload processing for HPC applications. Platform LSF support gives Star-P users an intelligent scheduling tool for their parallelized applications to solve large, complex problems while maximizing available computing resources. Star-P with Platform LSF is ideal for supercomputing centres and other large research organisations where computing resources are scheduled among many users. It ensures the right HPC resources are automatically allocated to the right users for maximum efficiency.

"Together, Platform LSF and Interactive Supercomputing's Star-P, let users manage their compute resources more efficiently. By sending work to the most capable available servers among compute resources managed by Platform LSF, users can deliver more results, faster", stated Simon Lonsdale, director of strategic alliances, Platform Computing. "The pairing of the two technologies not only brings scale-out HPC performance to the desktop but is also compatible with the customer's existing systems management and infrastructure practices. This enables more efficient and cost-effective parallel computing solutions for researchers."

With Star-P's new SGI Altix ICE support, customers can now take advantage of SGI's ultra-dense, liquid-cooled blade server architecture to reap both peak computational performance and user productivity. The SGI Altix ICE is a new kind of blade server - part cluster, part massively parallel processing (MPP) - that minimizes demands on a data centre's space and power. A single SGI Altix rack can be powered by as many as 512 Intel Xeon processors and deliver six teraflops of performance.

SGI Altix ICE support extends the longstanding relationship ISC has built with SGI selling Intel Itanium-based products. Adding ICE gives SGI customers more HPC platform options for solving computationally challenge problems.

"Star-P running on SGI Altix ICE blade servers enables scientists and engineers to easily scale their applications to thousands of nodes to address the most challenging compute problems, without the programming complexities of parallel computing", stated Bill Mannel, SGI senior director of marketing. "In raw computing power, this equates to adding six teraflops per rack. Star-P users can start small, testing and refining their algorithms on their desktops, and easily add computing resources as the application demands."