An Era Already Ended
Soon, Hewlett-Packard will no longer have a chip on its shoulder -- its own chip, that is
June 2, 2005
![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)
Soon, Hewlett-Packard will no longer have a chip on its shoulder -- its own chip, that is. This week, HP announced the last iteration of its high-end PA RISC-based servers based on its own RISC design; although it will sell servers based on that system for a number of years and support them well into next decade, it's also rolled out a new line of its Integrity NonStop servers, based on Intel's Itanium processors.
And that's clearly a direction that server manufacturers are taking, save for the obvious RISC-based biggie here -- IBM's Power-based systems. Aside from the Power line, though, basic proprietary RISC is probably an outmoded processor architecture for the server market at this point, and the performance gains and scalability of Itaniums, and of AMD's higher-performance Opterons, is finally tempting a critical mass of IT buyers over to those platforms. It took a while to get Itanium sales into gear, but it finally seems to be happening now. Even Sun is pursuing the AMD path, recognizing perhaps that its own SPARC lines are vulnerable to the processor market's two dedicated large companies.
Really, the end has long been in sight for HP's PA line. The company needs to continue competing at the high end for servers; as new CEO Mark Hurd continues his post-Carly Fiorina remake of the company, servers have to be a linchpin of steadiness for HP. And a proprietary RISC line of servers isn't going to do as a long-term strategy. This move is smart: It serves the installed base and provides a migration path for customers over to Itanium. And HP won't be spending resources on Itanium development, having handed that over completely to Intel; that frees the company to do more work at the systems level to keep advancing its servers' capabilities. This is one decision that's not really sparking any mourning anywhere.
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