Predictions that Intel's Atom processor will defeat ARM in the embedded market are premature, writes an analyst in EETimes. Atom may prove to be a little faster, writes Kenton Williston, but ARM chips are cheaper, more power efficient, smaller — and they're here now.

According to the results of LinuxDevices.com's annual reader survey, ARM surpassed X86 in embedded deployments about three years ago, with the gap likely to widen in the years ahead.

Which OSes were/will be in your (company's) embedded designs during the past/next two years?
(Results from 2007 survey. Click to enlarge)

Earlier this week, Intel formally announced its next-generation mobile device chips products, Atom and Centrino Atom, aimed at helping x86 regain its footing in the embedded and device markets. The chips use a new x86-compatible micro-architecture with an in-order pipeline, similar to ARM. Built on 45 nanometer process technology and using “High-K” metal gate transistor technologies, the Atom processor fits onto a 25mm by 25mm die, even with tons of cache. It will use a tenth the power of its mobile Core2 Duo “ULV” chips, Intel says, while scaling to 1.8GHz speeds.

It is likely that the Atom will reach the market only as part of the Intel Centrino Atom chipset, which combines the CPU with a “Poulsbo” companion chip that integrates northbridge and southbridge. Designed to meet the needs of Intel's “Mobile Internet Device” (MID) specification for handheld devices, the Centrino Atom chipset can also optionally include WiFi, WiMax, and other peripheral chips. The chipset will also be available with a penny-sized, 16GB solid state disk called the Z-P140.

ARM's latest offering, meanwhile, is the Cortex-A8 core, which was recently embraced by Texas Instruments (TI) in its OMAP3 applications processors. Incorporating a dual-issue design that can clock up to 1GHz, the Cortex-A8 is claimed to use less than 300mW when implemented using 65nm technology. TI reports that its benchmarks show the Cortex-A8 performing at up to 1200 Dhrystone MIPS (millions of instructions per second).

ARM vs. Atom

There's much to like about the Intel Atom, writes Williston in EETimes. Yet, he suggests, the media and its readers may have been overwhelmed by the hype machine. Williston offers the following responses to typical arguments from the atomic power lobbyists, at times quoting analysts such as Forward Concepts's Will Strauss to back him up:

• Atom will beat ARM because it can run Vista. — No it can't, says Williston. Atom can run Windows CE and Linux, but ARM can do the same.
• Only Atom offers a “real” Internet experience with Flash video, YouTube, etc. — “Wrong,” writes Williston, pointing to ARM Flash players from BSquare, and an ARM-based YouTube decoder from On2. He might also have noted that Nokia's ARM- and Linux-based Internet tablets use a Mozilla-based browser, with plugins for Flash, Windows Media files, and even Microsoft's Flash-like Silverlight technology.
• Intel dominates every market it enters. Here, the writer refers the reader to the history books, especially two years ago when Intel sold its PXA line of embedded processors to Marvell after failing to dominate the market for ARM-based SoCs.
• Atom will win because ARM is proprietary technology. Nope, he writes. ARM chips are available from a number of semiconductor vendors.
• Intel will win on cost. Not likely, he writes. Using a 65nm process, the Cortex-A8 occupies less than 3mm x 3mm, he notes, while the Atom core probably takes up about 9mm x 9mm of Atom's 25mm x 25mm die size, despite its smaller 45nm process. “With such a huge area disadvantage, it's hard to see how Intel will win on cost,” he writes.
• Intel will win on power. Once again, not likely, he argues. Intel quotes a thermal design power (TDP) of 0.6W to 2W for Atom, he writes, but doesn't specify clock speeds. ARM offers only “typical” power measurements, making comparison difficult. But at best, he suggests, Intel matches ARM on power usage, while “in most scenarios, Atom burns more power.”
• Intel will win because it has the most advanced fabs. Perhaps, he writes, but who cares? “Consumers focus on cost, power and speed,” he writes.

In the end, Williston admits that the Intel Atom will likely run faster than ARM chips, especially for applications that exploit Atom's support for dual-threading. He also allows that “the most important versions of Atom are still a year or two away” when the chip will “integrate graphics and a memory controller.” This, however, is a bit of a two-edged sword, as the embedded device market is exploding now, and ARM seems to be everywhere, along with Via and other potential competitors not mentioned in the article.

Perhaps the Atom's biggest advantage is its inherently superior support for PC applications, which could bring more well-tested x86 software to set-top boxes (STBs), automotive infotainment devices, ultra-mobile computers, and devices like the TiVo. The advantage is especially acute with games. “If Intel can leverage the large base of existing PC games it could outflank ARM with mobile gaming devices,” he writes.

Williston's conclusion: “Atom is an important new architecture, and it is likely to be a big success in many markets. Just don't expect it to dethrone ARM in the mobile market segment any time soon.”

The full EETimes story, called “Analysis: Hits and Misses in coverage of Intel's Atom,” is available here.

---

 
This article was originally published on LinuxDevices.com and has been donated to the open source community by QuinStreet Inc. Please visit LinuxToday.com for up-to-date news and articles about Linux and open source.