NVIDIA has announced their new GPU server from SIGGRAPH today, the Quadro Plex Visual Computing System (VCS) Model S4.
The Quadro Plex Model S4 is an industry standard form factor optimized for large-scale server deployments. Featuring four Quadro GPUs in a high-density 1U chassis for high-performance remote graphics and offline rendering applications, the Quadro Plex Model S4 offers system monitoring, thermal control and fault notification for efficient integration into data centers.
IBM’s BI blade
IBM announced its Information Server Blade from LinuxWorld this week
The new IBM Information Server Blade is a completely integrated offering comprised of IBM blade hardware, the IBM Information Server data integration software platform, and implementation services including financing….
Designed for all types of challenging data integration projects including consolidations, mergers and acquisitions, business intelligence or data warehousing, IBM Information Server Blade leverages the dynamic nature of grid computing with the flexibility of blade computing and virtualization technologies to access and translate large quantities of information stored across an enterprise.
IBM is talking about these things in small clusters for medium- to large-sized businesses
…a major corporation used a cluster of Information Server Blades at a cost around $300,000 running 24 Intel microprocessors to crunch through a massive data warehousing job in 45 minutes. Previously, when the job was run on a $3 million Sun server, the data integration job took them five and a half hours.
(More on this enterprise HPC news item)
IBM announces migration of running apps
IBM has started talking about its new Live Partition Mobility technology, now in beta.
Live Partition Mobility, currently in beta testing with general availability planned later this year, is a continuous availability feature that will enable POWER6-based servers, such as the System p 570, to move live logical partitions — including the entire operating system and all its running applications — from one server to another while the systems are running.
This sounds similar to the functionality that Evergrid is currently working on, some of which is deployed. While I believe that neither offering requires users to change their codes, the IBM solution is supported in hardware. (More on this enterprise HPC news item)