-
Popular Articles
Dell Builds a VIA-Powered Server to Cut Power Costs
HP Finally Boards the Mega Data Center Bandwagon
Future of cloud computing … more clouds. Seriously.
How the Cloud Will Disrupt the IT Status Quo
SeaMicro’s Secret Server Changes Computing Economics
Oracle’s Ellison Rethinks Clouds as Economy Tumbles
If the Data Center Is the Computer the Fight Is on to Control the Ecosystem
-
Recent Pictures
-
-
Don’t call it a wimpy node: SeaMicro rethinks the server for webscale
SeaMicro, the startup that has built a business in the low-power microserver market, said it has now integrated Intel’s workhorse Xeon chip inside its boxes. SeaMicro, which crams hundreds of Intel’s low-power Atom-based chips inside its specialty servers for smaller workloads, has gradually proven to Intel and the rest of the market how strong the demand is for low-power architectures. Intel eventually designed a specialty Atom chip just for SeaMicro that gave it the capabilities that data center customers were looking for. Today it goes further.
(Read Full Article)
IBM builds memory chips one atom at a time
Computer and memory chips usually tend to get smaller over time, but in a paper published Thursday in Science IBM details how it's building memory chips that would be 100 times more dense than today's hard drives by starting with the smallest building blocks--atoms.
(Read Full Article)
SuVolta gets $17.6M to make power sipping chips
Apparently, I’m not the only one who thought SuVolta is a great example of the future of chip tech. Bright Capital, Kleiner Perkins Caufield & Byers, August Capital, New Enterprise Associates, Northgate Capital and DAG Ventures all have contributed to a $17.6 million funding round in the company, which doesn’t exactly design chips but has come up with a novel way to design transistors in a way that makes them use less power.
Chips made using its technique have recently run at full speed but consumed half the power of their counterparts that use traditional transistors. This isn’t just a concern of a crazy startup; Intel recently unveiled a new process technology using 3-D transistors that is designed to save on power by helping chips continue to get smaller.
(Read Full Article)
Comment Mentions: Intel Kleiner Perkins Caufield & Byers
Forget Ethernet, researchers want data centers to go wireless
You know those cabling contests that try to get systems administrators to show off their racks? If this article from the MIT Technology Review is right, those may become a distant memory as researchers from the University of California, Santa Barbara, Intel and IBM have shown how they can send data between servers without those pesky cables using 60 GHz wireless and bouncing those radio signals off the ceiling.
That means rapid data transfers up of to 500 Gigabits per second (current Ethernet cables in data centers are generally 1, 10 or maybe 40 gigabits per second) and less mess with physical cables. Of course, every switch at the top of a rack would have to get a radio card slotted into it, and there’s also the matter of putting reflective panels on the ceiling for the wireless signals to bounce off of. The top of the servers would ...
(Read Full Article)
The cloud shouldn’t be an over the top service
The public Internet and the cloud shouldn’t mix, according to a paper out today from Joe Weinman of HP. Cisco seems to agree, if Tuesday’s announcement of its CloudVerse suite of products is any indication. A growing number of endpoints, the multiple services built within web applications, and the infinite variety of demands made on any web-based service mean the network can’t be trusted to run over the top.
The network is the cloud, so it needs to be agile, smart and billed based on usage.
Instead, the industry will need to move to pay-per-use, dynamic networks where possible to improve the economic benefits of cloud scenarios and deliver defined quality-of-service for applications that will require low latency, argues Weinman. Weinman, who moved over to HP from AT&T last year, is a deep thinker on the economics of cloud computing. He also argues that bandwidth will ...
(Read Full Article)
For science, big data is the microscope of the 21st century
Johns Hopkins is taking a $1.2 million grant from the National Science Foundation to build a 100 gigabit per second network to shuttle data from the campus to other large computing centers at national labs and even at Google. The network will be capable of transferring an amount of data equivalent to 80 million file cabinets filled with text each day.
The head of the project, Dr. Alex Szalay, detailed the plans, which include gear from networking gear from Cisco, Arista and Solarflare, Nvidia GPUs; and 66,000 x86 cores. That’s on top of the actual fiber that will connect a new, 1-megawatt data center inside the physics building to regional Mid-Atlantic Crossroads research and engineering network at the University of Maryland.
(Read Full Article)
Facebook has no plans for a Taiwan data center
“Re: Taiwan, we have no plans to build a datacenter there.” Facebook spokesman, Michael Kirkland’s response to an article stating that Facebook had plans to build a 720,000-square foot data center in the Central Taiwan Science Park. Related research and analysis from GigaOM Pro:Subscriber content. Sign [...]
(Read Full Article)
The data center gets its first 100 Gbps optical chip
Luxtera, which makes a optics chips that has characteristics of a standard silicon chip, has developed a hybrid chip for the data center market that can achieve speeds of more than 100 gigabits per second. Those are the same speeds that telecommunications firms are enabling via long-haul cables to handle the massive demand for bandwidth worldwide, but in this case are designed to handle the next wave of big data and networking-intensive applications inside webscale and cloud data centers.
Luxtera was founded in 2001 and builds chips that allow messages to be sent at the speed of light, but instead of using specialty materials that optics chipmakers such as Infinera use, Luxtera uses traditional silicon chips made using the CMOS process. This cuts down on the cost of the chips and makes it possible to use them for high-volume jobs, such as switching in the data center.
(Read Full Article)
The ARM v. Intel fight just got good
ARM said its next generation architecture will offer cores capable of 64-bit computing. The boost from 32-bits to 64-bits will push ARM-based processors over the last big hurdle keeping the chip IP company outside the enterprise and corporate computing market, and pit it squarely against Intel.
(Read Full Article)
Comment Mentions: Intel Wall Street Journal Nvidia
Apple hires Yahoo’s data center chief
Scott Noteboom, the man who has been in charge of Yahoo’s data center operations since 2005, has now joined Apple as the iconic consumer electronics maker expands into the cloud. This follows Apple's hiring of Microsoft data center guru Kevin Timmons a few months back.
(Read Full Article)
Comment Mentions: Apple Yahoo Kevin Timmons
Does networking need a DevOps movement?
The networking industry is set for a change as the shifts caused by the needs of webscale operators and virtualization bring complexity and costs to moving data around a data center. As networks look more like a cloud, does the field need a DevOps culture?
(Read Full Article)
Will OpenFlow lower your phone bill?
The mobile industry is in trouble. It intelligent networks that are expensive to run, but its retail customers want cheap pipes. At a conference Wednesday, a Verizon executive detailed the problem and explained how he wants to use OpenFlow and software-defined networking to lower his costs.
(Read Full Article)
Comment Mentions: Amazon.com Cisco Deutsche Telecom
How long until clouds adopt extreme computing chips?
Both mobile and high performance computing are placing huge power efficiency and performance demands on chips, but the real $64,000 question is how long until such extreme computing use cases hit the server mainstream. Asked another way, how long till Amazon adopts ARM-based servers?
(Read Full Article)
Comment Mentions: Amazon.com Intel Facebook
Broadband under the sea: Where do those cables go
Want to know how your email packets from Rhode Island make it over to South Africa? Or what about your VoIP call from Hong Kong to Honolulu? Now there’s a map for that, thanks to the folks at Telegeography who have rolled out an interactive tool that shows you the location of various undersea cables. These cables are the links that connect the Internet across oceans and continents, and typically they only get noticed when they go down.
For the truly nerdy, this makes awesome wall art (you can put it next to your spectrum allocation chart!), but if you’re more like the rest of the population, it’s a fun resource to turn to the next time a woman panning for copper cuts a cable, you’re looking for a good place to base a data center, or you want to see how interconnected we are. For ...
(Read Full Article)
Amazon turns back to core audience with new caching service
Amazon has been adding all kinds of features to attract enterprise users to its cloud computing platform, but with it's new caching product, it's returning to web developers. Perhaps with an influx of platforms and Open Stack, Amazon realizes it needs to concentrate on its core.
(Read Full Article)
Comment Mentions: Amazon.com Facebook
Joyent launches a new OS for the cloud
Joyent has open sourced its cloud operating system. Called SmartOS, and already utilized in Joyent's public cloud and SmartDataCenter private-cloud software, it will be available via an open source license much like the Joyent-led Node.js effort is, says Joyent CTO Jason Hoffmann.
(Read Full Article)
Future of cloud computing … more clouds. Seriously.
The next big leap in both technology and business models around sharing elastic compute resources might be bidding for those resources at auction or acquiring them through a broker, according to a report issued Thursday from Forrester. The report argues that while the technologies aren’t here today, a business built on aggregating clouds from public and private networks and delivering capacity and services in an automated, on-demand fashion to companies will emerge by the end of this year, and standards will start appearing in 2012.
(Read Full Article)
Comment Mentions: Forrester Research
Facebook sides with Tilera in the server architecture debate
Facebook engineers have tested a 64-core chip from Tilera and found it ideal for grabbing data quickly from key value stores. This may galvanize the creation of new benchmarks as the debate of which architecture works best for webscale and cloud computing rages.
(Read Full Article)
Dell follows the networking acquisition binge with Force10 buy
Dell said it would buy networking gear-maker company Force10 Networks on Wednesday. The move was expected since Dell’s rivals in the server space have tied up their networking equipment buys after Cisco launched servers that combined computing and networking in one box.
(Read Full Article)
Twitter’s data center mystery deepens
Updated. What’s up with Twitter’s data center strategy? Twitter’s plans are reportedly in disarray according to sources I spoke with yesterday at our Structure 2011 conference in San Francisco. Two people shared that the microblogging service, which announced plans to build a Utah data center back in July 2010, will abandon the site entirely and move its servers to a data center in Sacramento, Calif.
I’ve reached out to Twitter for comment, but if this is true, it wouldn’t come as a surprise to those closely watching Twitter’s infrastructure moves. Update: Twitter spokeswoman Carolyn Penner said via email that Twitter has not abandoned the Utah site and added, “I can also confirm that we have multiple sites, but I won’t go into further detail.”
(Read Full Article)
Comment Mentions: Data Center Knowledge
Question Everything: A New Processor For Big Data
We are moving from the Information Age to the Insight Age, and as part of that shift we need a compute architecture that will handle the storage and processing required all without requiring a power plant hooked up to every data center. What architecture will win?
(Read Full Article)
Comment Mentions: Intel Facebook Department of Defense
IBM Turns Back on Juniper to Buy Blade Networks
Explore Structure Blog (Sep 27 2010)
IBM today said it would buy Blade Networks, a company that makes networking gear that can help vendors combine computing and networking in a box that resembles Cisco’s unified computing system. IBM plans to pay an undisclosed amount for Blade, which is four-and-a-half years old, reported $79 million in revenue for 2009, and planned for revenue in excess of $100 million for its fiscal year, which ends in October. Update: Sources are saying that IBM paid $400 million for Blade.
The deal is also a bit of bad news for Juniper, the networking and switch maker that had a deepening partnership with IBM in the wake of Cisco launching its competitive entry into the server market, thereby alienating its former partners. Since that move, HP has made the somewhat dubious purchase of 3COM, and Dell has signed several partnerships with any networking vendor that has a port, including some ...
(Read Full Article)
Comment Mentions: Cisco Brocade Vikram Mehta
VSS Gets $20M to Keep an Eye on Corporate Networks
VSS Monitoring, a network traffic monitoring company, has taken $20 million in growth equity from Battery Ventures. The funding was the first for the company — founded in 2003 — and it will be used for R&D and to accelerate the company’s expansion. What’s noteworthy is that until this point, VSS had built network monitoring software and hardware and sold it for five years without taking venture capital.
(Read Full Article)
Puppet Labs Gets $5M for Data Center Software
Puppet Labs has raised a $5 million second round of funding led by Kleiner Perkins Caufield & Byers, which brings the total funding for open source configuration management software provider to more than $7 million. The company also announced the latest version of the Puppet software.
(Read Full Article)
Comment Mentions: Kleiner Perkins Caufield & Byers
The Origins of Amazon’s Cloud Computing
The story of Amazon creating a cloud computing business to take advantage of capacity left over from the peak holiday season has settled into the Internet apocrypha, but blogger Carl Brooks claims he’s uncovered the real reason the online bookstore got into the cloud: homesickness.
Brooks interviewed Jesse Robbins, the guy who formerly kept Amazon’s servers running. As he tells it, the project began as a way to keep an engineering talent named Chris Pinkham with Amazon after he wanted to return to his home country of South Africa. From Brooks’ story:
(Read Full Article)
Comment Mentions: Amazon.com
1-25 of 58 // 1 2 3 »
RSS Feeds
Recent Comments
ControlCircle » Gartner: Build your own datacentre rather than hosting
It’s startling that in today’s volatile environment Gartner is prescribing such a high risk strategy. ...
Carbon3IT Ltd » Does efficiency matter when your power is renewable (and affordable)? - By Peter Judge
Peter, do you really think that this is good practice?, as you say its like ...
See all recent comments