The two companies aim to give high-performance computers more "mass market" appeal by making them easier to deploy, support and manage. Enhancements will includethat includes custom installation scripts and documentation aimed at making deployment easier. HP said there is now increased scalability of large clusters with the HP Message Passing Interface and InfiniBand drivers offering better performance in applications that require high-speed, low-latency communications.
Customers can "realistically expect to have a 64-node cluster deployed and running within two hours," HP said in a statement.
Earl Joseph, an analyst at IDC, said there will be "continuing strong growth, averaging over 20 percent a year, with (high-performance computing) standards-based clusters growing at even higher rates. End users are looking for easy-to-use systems and will likely go with vendors that can provide an easy transition from their desktop to (high-performance computing) servers," Joseph said.
There has been a range of new products announced this week in advance of the International Supercomputing Conference, which opens Wednesday in Dresden, Germany.
IBM, for instance, announced that, the Blue Gene/P, is capable of processing more that 3 quadrillion operations a second, or three petaflops. Blue Gene/P is designed to continuously operate at more than 1 petaflop in real-world situations.
And, a high-performance computing platform that Sun executives claim will vault the company back into the top ranks of supercomputer manufacturers.
The influential Top 500 list of the world's most powerful supercomputers, which currently has IBM in the top four positions, will be updated at the International Supercomputing Conference this week.
Colin Barker of ZDNet UK reported from London.