Calxeda gears up for server ARM race
'We need a new clock'
SC10 The secretive ARM server startup formerly known as Smooth-Stone and now called Calxeda is coming out a bit today at the SC10 supercomputer trade show in New Orleans. But don't get too excited. The company is not talking about specific chip or server designs based on the ARM RISC architecture, but rather giving potential customers in the HPC world and in the general purpose server racket the design goals it has set for its initial products.
Calxeda is a fake name, and one that Barry Evans, the founder of Smooth-Stone had to change because someone else owns that name. The "smooth stone" in the company's original name refers to the round rock (not to be confused with Dell) that David slew Goliath with using his slingshot. It is pronounced "cal-zay-duh," not "cal-zon-ee," and the X in there is an intentional tweak on the x86 and x64 used to designate Intel and compatible processors.
Evans founded what is now called Calxeda in January 2008 with Larry Wikelius, who was at Opteron server maker Newisys, which sparked to life and generated $450m in server revenues before going the way of all flesh, and David Borland, who has been in charge of chip designs at Marvell, Intel, and AMD. Evans ran Intel's low-power x86 and Xscale ARM chip businesses.
Intel acquired the StrongARM RISC processor business from failing Digital Equipment Corp in 1998, and in 2006, it sold off that XScale business to chip maker Marvell for $600m - a move it may eventually regret with Marvell  and others like Calxeda working on multicore ARM chips aimed squarely at server workloads. Evans is the chief executive officer at Calxeda, while Wikelius is vice president of software engineering and Borland is vice president of hardware engineering.
Back in August, Calxeda raked in  $48m in funding from tech partners ARM Holdings, Advanced Technology Investment Company, Texas Instruments as well as venture capitalists Battery Ventures, Flybridge Capital Partners, and Highland Capital Partners. ARM Holdings is the holding company that licenses the ARM chip architecture that has myriad designs (used on mobile phones and other portable computing devices where battery power drives the design).
ATIC is the investment arm of the Abu Dhabi government that bought the foundry business from Intel nemesis Advanced Micro Devices last year, creating GlobalFoundries. TI is an ARM chip maker in its own right already and is getting out of the fab business (which is why Taiwan Semiconductor Manufacturing Corp is making Oracle's latest Sparc T3 chips and not TI, which fabbed Sparc chips for Sun Microsystems for decades).
Now that Calxeda has some cash, it has a new office in Austin, Texas, and it's hiring more engineers as well as an executive team to help it make and push its products once they are ready for market. To that end, Calxeda has hired Steve Beatty to be vice president of manufacturing at the chip startup; he was previously reponsible for production at chip maker SigmaTel up through its initial public offering in 2003 and up through its acquisition by Freescale Semiconductor in 2008.
Bob Baughman has been hired by Calxeda to be vice president of business development and sales. Baughman was previously vice president of product management for the $700m video solutions group at Ploycom and managed the company's partnership with Microsoft; he also held positions at Marvell and Intel, and came to Intel when the chip giant bought Dialogic in 1999 (the media and signaling chip maker was spun back out of Intel in 2006).
The final new member to the executive team is Karl Fruend, who cut his teeth on the Hewlett-Packard workstation business, did marketing for Cray Research before that company was sold to a prior incarnation of Silicon Graphics. Freund is vice president of marketing for Calxeda, and has spent the past ten years working at IBM, first in charge of marketing for its Tivoli systems management software, then its AIX servers, and most recently its System z mainframes.
'New clock, not just tick or tock'
"The industry needs a new clock, not just another tick or tock," Freund said with a laugh in an interview with El Reg at SC10. Whatever Calxeda is working on specifically, Freund will not say. But he was willing to confirm that Calxeda is working on ARM processors specifically for servers, and that the company will not be launching servers itself but rather working with OEM partners to put its chips inside of their boxes.
Freund was also willing to talk about the design goals that Calxeda has set for itself, making it clear that these goals did not constitute a specific processor roadmap as we are accustomed to seeing from Intel, AMD, IBM, and Oracle. The "server on a chip" design that Calxeda is cooking up will offer the same performance at the system level (with more chips per system) as an equivalent x64-based machine, with the resulting ARM server being half the cost, using one-tenth the energy, and occupying one-tenth the space.
"The baggage of compatibility takes up too much real estate on the chip," says Freund in talking about x64 chips from both Intel and AMD. Which is why chip startup Tilera is making system-on-a-chip designs based (everyone conjectures) on the MIPS architecture that can pack 64 cores and everything it needs onto a single chip and is working on future variants that will do 100 and then 200 cores. (See here  for details on the latest Tilera chips, which offer very good integer performance but which do not have floating point math.) Tilera's future "Stratton" chips will allow server makers to cram up to 40,000 cores into a server rack by 2013, if all goes well; half that will be possible by the end of 2011 using the 100-core TileGx-100 SoCs.
So why come into this dense, low-power server racket when Tilera has such a big lead and not very much business as yet? (Not enough to dent Intel, at least.)
"We think the ARM chips have the ecosystem of developers and tools that the MIPS chips do not," says Freund. And more importantly, ARM chips have the force of history on their side.
Setting aside the issues of memory addressing for the moment, which are an issue for both Tilera and for anyone making ARM processors for servers, owing to the 32-bitness of the designs, Calxeda and Marvell agree that there is a place for 32-bit servers in the data centers (and maybe the living rooms) of the world. (The future "Eagle" Cortex-A15 reference chips from ARM Holdings, the chips have a funky virtualized 40-bit mode  and do not go all the way up to 64 bits.) Calxeda knows that it is going to take some time for ARM to go all the way to 64 bits and is nonetheless convinced that it can make creditable server chips using the ARM architecture.
For a lot of hyperscale data center customers, power draw is as important an issue as processor throughput, and for workloads that can be parallelized on tiny machines, a swarm of low-powered ARM chips with a clean, lean, and mean implementation of Linux might be a better answer than running Linux on x64 chips. "We believe there are plenty of workloads that can work fine with 32-bit processors," Freund says.
This will not be the first time that hoards of cheap machines have assaulted the data center and knocked an incumbent off its tiles excepting the most pesky legacy applications. Mainframes owned the data center for a decade and a half until proprietary minicomputers surrounded them, attacking from the bottom and eventually pulling applications off the mainframe and, more importantly, getting new applications that would have otherwise gone onto the mainframe. Unix-based RISC servers came in, again growing up from workstations, to attack the bottom of the mainframe and minicomputer markets and growing to respresent half of the server racket at the height of the dot-com boom. And then the x86 desktop chip grew up in the 1990s to become the dominant server platform, chewing into the bottom of the RISC/Unix and proprietary mini base and expanding to essentially take over.
Now, it will be the turn of the ARM-based cell phone chip, which Calxeda is going to help grow into a bottom dwelling shark that eats its way into the heart of the server space.
"It has always been a lot easier to scale up a new technology up to take on an established one than it has been to scale that established technology down to meet a new threat," explains Freund, and considering that he was the chief cheerleader for IBM RISC/Unix and mainframe platforms for the past decade, that's a stunning admission. ®