Skip navigation
Calxeda Outlines Ambitious ARM Roadmap, Penguin Partnership
The HP Redstone server — the Moonshot initiative’s first ARM server prototype — featuring Calxeda SoCs on display at GigaOm Structure in 2012 (Photo: Colleen Miller)

Calxeda Outlines Ambitious ARM Roadmap, Penguin Partnership

ARM processor specialist Calxeda, which recently raised $55 million, this week unveiled its product roadmap along with a new partner in Penguin Computing.

Calxeda technology was on display at the GigaOm Structure conference earlier this year. Calxeda's ARM-based servers are now available through Penguin Computing. (Photo: Colleen Miller)

ARM processor specialist Calxeda, which recently raised $55 million, this week unveiled its product roadmap along with a new partner in Penguin Computing.

Calxeda specializes in ultra-low power servers to cut down data center power usage and increase density. It leverages ARM-based processors for low power server chips instead of Intel x86 architecture, which is currently ubiquitous in the market. While x86 is dominant, ARM is being looked at as a potential alternative due to its energy saving benefits and the accompanying reduction in capital and operating expenses this brings. Calxeda is thinking big, focused not only on power savings, but also prepping itself to handle the world of cloud and parallel workloads.

Of course, this is all pending actual adoption of its ARM technology by the marketplace. The $55 million in funding, in addition to bringing in capital, was also a vote of confidence from investors, and it indirectly increased the confidence of the market.  At least seven server vendors are working with Calxeda technology, including HP and Boston Limited, which is also very promising. Now a roadmap that sees the company enabling warehouse-sized data center situations by 2014 lets us know where it’s going.

So far, Calxeda EnergyCore ECX-1000, has shipped thousands of early EnergyCore SoCs to OEM customers and end users, and has been providing free access to the technology on the OpenStack Trystack.org cloud. Although this is all test-and-dev rather than production, it told Data Center Knowledge early this month that it expects server vendors to launch the first production-ready servers based on its technology by year-end.

First an Appliance, Then a Fleet

The roadmap released today fleshes out the plan a little further, and is quite an ambitious one.  The long term goal is to get its low power 64-bit ARM servers into the data center by 2014. First up on the roadmap is 32-bit technology.

The roadmap indicates a two-pronged strategy to reach additional markets. The first is public and private cloud, the second is massive warehouse-scale data centers.  “We are taking it two steps further to reinvent the server, first into a rack-based cloud appliance, and then extending into an integrated fleet of computing resources, spanning many thousands of efficient servers,” said Calxeda founder and CEO, Barry Evans. “It’s all about finding the right balance of I/O, storage, networking, management, memory and computational elements for each target market segment.

“This is the beauty of an ARM-based SoC approach: each platform can be tailored to add more value by addressing the unique needs of a specific workload,” added Evans.

The second generation platform is code-named “Midway”, and the company hopes it will open up new markets, specifically dynamic web hosting and more computationally intensive Big Data analytics. The second generation increases performance, memory and hardware virtualization support using standard CortexA15 ARM cores. The second generation fabric will support new features such as dynamic power and routing optimization for public and private clouds.  This will be available in volume in 2013.

The third generation platform is code-named “Logo”; this is Calxeda’s platform for the warehouse-scale datacenter. This is further away, expected in 2014. It’s built on 64-bit ARM V8 architecture and features Calxeda’s third-generation scaling features, Calxeda Fleet Services, for automation and optimization of common operations at massive scale. It will also be able to connect hundreds of thousands of nodes with quality of service features and resource control and allocation through an enhanced fabric.

“Lago will be in the first wave of 64-bit complete systems and application stacks on ARM in 2014, and we are collaborating with key partners to ensure that customers can ramp quickly with production-quality software and OS support for both Midway and Lago,” said Evans in the announcement.

Partnership With Penguin

The new Partner is Penguin Computing, which is throwing its hat into the low-power ARM microserver ring through partnering with Calxeda. Its Ultimate Data X1 system is the first server platform offered by a North American system vendor built on the EnergyCore SoC from Calxeda. The system is ideal for I/O bound workloads, including “Big Data” applications, scalable analytics, and cloud storage.

“A new generation of power efficient high density servers is required to run these workloads efficiently," said Charles Wuischpard, CEO of Penguin Computing. "With the incredibly low power envelope and the extremely high density Calxeda’s EnergyCore SoCs offer, the UDX1 is the ideal platform for running these types of workloads.”

The new offering is meant to reduce Total Cost of Ownership for high density, low power computing environments. Other key stats:

  • 5 Watt power envelope per server
  • Has a  modular architecture that can be configured with up to 48 Calxeda EnergyCore server nodes, with four cores per node
  • Includes an internal 10 Gigabit Ethernet switch fabric for node-to-node connectivity and provides up to 144TB of hard drive capacity

Penguin Computing will be showing a live demo of Hadoop running on the UDX1 at the upcoming Strata Conference + HadoopWorld on October 24-25 in New York.

Hide comments

Comments

  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
Publish