|
News Feed
|
 LinuxHPC.org.org has an RSS/RDF feed if you wish to include it on your website.
|
 |
|
Linux Cluster RFQ Form
Reach Multiple Vendors With One Linux Cluster RFQ Form. Save time and effort, let LinuxHPC.org do all the leg work for you free of charge. Request A Quote...
|
|
|
LinuxHPC.org is Looking for Interns - If you have experience with Linux clusters and/or cluster applications and you're interested in helping out with LinuxHPC.org let me know. I can promise the experience will be rewarding and educational, plus it'll make good resume fodder. You'll work with vendors and cluster users from around the world. We're also looking for writers and people to do hardware/software reviews. Contact Ken Farmer.
|
|
|
HP Itanium Team Moves to Intel
|
Wednesday December 15 2004 @ 07:59PM EST views: 176
Several related articles...
- E Commerce Times: HP Itanium chip team sold to Intel, more reports
- Yahoo: HP shifts last of Itanium work to Intel
- The Register: HP sends Itanic boat people to Intel
- News.com: HP, Intel End Itanium Partnership
- The Inquirer: Intel To Take Over HP's Itanium Chip Team of 300
[...]
|
|
SysAdmin to SysAdmin: Parallel I/O for clusters using PVFS
|
Wednesday December 15 2004 @ 09:19AM EST views: 205
Linux.com: When you're trying to share files and perform I/O-intensive operations across 100+ nodes of a Beowulf cluster, the old model of a central NFS file server handling every client request begins to break horribly. What many cluster admins do instead is limit NFS to distributing home directories across the cluster, and using some form of parallel I/O model for doing "real work."
[...]
|
|
Industry’s First Grid Computing Resource Guide Announced
|
Friday December 10 2004 @ 04:24PM EST views: 214
Grid Strategies, Inc., a leading provider of strategic marketing, market relations and business development services in the HPC and Grid computing markets, has announced a milestone document to support wider spread development and adoption of Grid computing: the first comprehensive Grid Computing Resource Guide (www.gridresourceguide.com), published in both hard copy and online versions and available in the spring of 2005.
[...]
|
|
Event: The role of switch fabrics in High Performance Linux Clusters
|
Friday December 10 2004 @ 02:27PM EST views: 228
Mr. Wes Medley Federal Systems Engineer with Foundry Networks and Donald Becker CTO and Founder of Scyld. Foundry Networks and Inmon Corporation will provide a technology brief on sFlow – a new network monitoring technology. Donald Becker will provide the current state of switch fabrics and network drivers for Linux HPC
[...]
|
|
HP revamps midrange storage line
|
Friday December 10 2004 @ 11:59AM EST views: 189
ComputerWorld: Hewlett-Packard Co. yesterday announced several upgrades to its midrange storage products, including disk-to-disk or disk-to-tape backup functionality with its StorageWorks Data Protector software and its first array that can use both SCSI and Serial ATA disk.
[...]
|
|
Penguin Computing's Cluster-in-a-Box
|
Friday December 10 2004 @ 11:48AM EST views: 234
Penguin Computing BladeRunner Cluster-in-a-Box server system integrates blade servers, Ethernet switches, storage sub-systems, management software, and cluster operating system software in a single 4U chassis. It greatly simplifies cluster usage with easy to install, easy to manage, and easy to run cluster solutions. BladeRunner Cluster-in-a-Box is a ready-to-go cluster pre-installed with Scyld Beowulf, a full Linux distribution optimized for cluster management providing a single point of installation, login, and administration.
[...]
|
|
Linux clusters for HPC: Why and why not?
|
Thursday December 09 2004 @ 11:09PM EST views: 238
Search Enterprise Linux: If your organization has IT money to burn and doesn't mind being locked into a proprietary system, then buy a supercomputer for your high-performance computing (HPC) applications. If you're not living in that kind of IT ivory tower, you should join the crowd that's checking out the new capabilities of HPC Linux clusters, says Len Rosenthal, co-founder and marketing vice president for PathScale Inc., a provider of hardware and software clustering systems based in Sunnyvale, Calif. In this interview, he points out the strengths and weaknesses in HPC of Linux clusters and the top two processors.
[...]
|
|
AMD Opteron Powers Supercomputer for for Sauber Petronas F1 Team
|
Thursday December 09 2004 @ 10:43AM EST views: 362
F1Live.com: Only nine months after the launch of its ultra-modern wind tunnel, the Sauber Petronas today presented a new supercomputer for Computational Fluid Dynamics (CFD) calculations to international media representatives at its headquarters in Hinwil. 'Albert', as the machine has been christened, is one of the most powerful in Formula One as well as the automotive industry as a whole. The supercomputer was built by the Swiss company Dalco and has a total of 530 AMD Opteron processors installed in High-Density Cooling Enclosures supplied by American Power Conversion (APC). The software is provided by Fluent. Sauber has established technology partnership agreements with all four companies.
[...]
|
|
AMD's Weber predicts eight core Opterons
|
Thursday December 09 2004 @ 10:32AM EST views: 177
The Inquirer: THE CHIEF technology officer of AMD spoke at a Lehman Brothers conference yesterday. Fred Weber said AMD had started working on 64-bit technology five years ago and that it had to extend previous X86 architecture.
[...]
|
|
Absoft Announces General Availability of HPC SDK for IBM Linux on Power Clusters and Servers
|
Thursday December 09 2004 @ 10:11AM EST views: 194
The Absoft High Performance Computing Software Development Kit (HPC SDK) for Linux on Power is the premier Software Develpers’ Kit for building and running High Performance Computing Applications on IBM Linux on Power™. Absoft’s HPC SDK consists of pre-configured tools that help you immediately to Compile, Debug, Run, and Optimize High Performance Computing Applications.
[...]
|
|
Geographically dispersed grid, Part 2
|
Tuesday December 07 2004 @ 10:39AM EST views: 135
In any grid computing environment, you have data nodes and computation nodes. Performance is important. How do you choose technologies to support the computational role of the grid? How to choose technologies for the data virtualisation layer? The author provides high-level decision criteria, and discusses
[...]
|
|
Opteron gets power management
|
Tuesday December 07 2004 @ 09:40AM EST views: 160
NWF: In an effort to help enterprise users get a handle on power and heat issues associated with new server designs that pack more processing punch in smaller spaces, Advanced Micro Devices Monday announced that systems built with its 32/64-bit Opteron processor will include power management technology by the middle of the year.
[...]
|
|
HP expands InfiniBand partnership
|
Tuesday December 07 2004 @ 09:01AM EST views: 175
News.com: Hewlett-Packard has expanded a partnership to integrate its servers with TopSpin equipment for the InfiniBand high-speed networking technology, the companies said Monday. TopSpin sells InfiniBand network adapters and switches, while HP sells TopSpin products under its own name.
[...]
|
|
HP Selects S2io's Xframe 10GbE Adapter For Its Server Lineup
|
Tuesday December 07 2004 @ 02:15AM EST views: 207
S2io Inc., a market-share leader in 10 Gigabit Ethernet Adapter solutions for server and storage environments, announced that its Xframer product has been selected by Hewlett Packard for its Enterprise Server lines.
[...]
|
|
Westinghouse Selects PolyServe NAS Cluster Solution
|
Tuesday December 07 2004 @ 01:32AM EST views: 314
Westinghouse's Nuclear Fuel Business has selected the PolyServe NAS Cluster solution to enable a high-performance, fault-tolerant and cost-effective Linux file-serving cluster, PolyServe, Inc. announced. Westinghouse Electric Sweden, which has been running the PolyServe NAS Cluster in production for more than 10 months, uses the solution to support core analysis and reactor safety calculations crucial to the business of Westinghouse in the market of boiling water reactors.
[...]
|
|
Interview with Rajesh Kota, the lead designer of Newisys’ HORUS chipset for the K8
|
Monday December 06 2004 @ 03:10PM EST views: 193
Real World Tech: We held a real-time online chat with Rajesh Kota, the lead designer of Newisys’ HORUS chipset for the K8. HORUS is the first chipset for the K8 that scales to a 32 way SMP; it was explicitly designed to complement the K8’s scalability and extend it to 32 and 64 way systems. We have just posted the transcript from this interview at:
[...]
|
|
AMD works to chill out Opteron
|
Monday December 06 2004 @ 02:34PM EST views: 171
News.com: Advanced Micro Devices announced on Monday technology that will help its server processors run cooler when idle, a feature that could help customers grapple with electricity and air-conditioning costs.
[...]
|
|
Pogo Linux to Ship First Commercial 8-Way Opteron Server
|
Monday December 06 2004 @ 01:22PM EST views: 248
ITJungle: In December, Linux server and storage specialist Pogo Linux will become the first server maker to stop messing around and actually deliver an eight-way server based on the Opteron 800 series processors. Pogo Linux, which is cheekily based down the street from Microsoft in Redmond, Washington, has adopted motherboard technology from Taiwanese motherboard maker Iwill for its PerformanceWare 5864 server.
[...]
|
|
Don Becker to Speak at BWBUG Meeting Dec 14 in Greenbelt Maryland
|
Monday December 06 2004 @ 01:12PM EST views: 183
Don Becker will give a brief review of the Interconnect and Switch Fabric Market. Don is one of the world experts on Network Drivers for Linux and creator of the first Commerical Cluster Management Software, SCYLD. Wes Medley Fedreal Systems Engineer with Foundry Networks will also speak
[...]
|
|
|
|
SpyderByte:
