Intel Silvermont Architecture: Does This Atom Change It All?

Intel’s Atom was once the Rodney Dangerfield of the processor world. It just didn't get no respect. The first Silverthorne-based Atoms were little single-core affairs that dipped into sub-1 W territory, but required a System Controller Hub that took platform power closer to 5 W. More capable versions from the Diamondville family bumped consumption higher still—all the way to the strange pairing of Atom and the 945GC chipset, which used more than 22 W on its own.

Not surprisingly, then, we haven’t published a lot of flattering coverage on Atom (I think the last time I even bothered with an Atom-based desktop was for Intel’s Atom D510 And NM10 Express: Down The Pine Trail With D510MO in 2009). Even today, five years after expressing its intentions to compete against ARM-based SoCs, the industry continues questioning Intel’s ability to deliver ample performance at power targets low enough to facilitate compelling tablets and smartphones.

Methodical progress compelled us to reconsider Intel’s efforts last year, though. Sixteen months ago, one of our writers went underground and made the bold prediction that Intel will overtake Qualcomm in three years. And that was when Intel didn’t have a single phone design win. The analysis was predicated on Intel’s ability to deliver a performance-competitive CPU based on 32 nm manufacturing and in-order execution, knowledge of the company’s manufacturing roadmap, and anticipation of a forthcoming out-of-order architecture.

Well, the details of that design, already known as Silvermont, become public today. And if the Atom processors based on Silvermont can do everything Intel says they can, then we won’t even need granular measurements like the ones we collected for ARM Vs. x86: The Secret Behind Intel Atom's Efficiency to quantify the company’s efficiency story compared to its ARM-based competition.

If you’ve followed the Atom family’s evolution, then you know that Intel hasn’t modified its fundamental microarchitecture in five years. Yes, it made a shift from 45 to 32 nm manufacturing. But the cores themselves—code-named Saltwell at 32 nm, but based on the original Bonnell design—continue to employ in-order execution, clearly favoring low power use at the expense of performance.  

With Silvermont, that changes. We’re now looking at a more complex out-of-order execution engine largely enabled by a transition to 22 nm manufacturing. This isn’t a “see you again in five years” introduction, either. Intel is committing significant resources to dramatically accelerating development of its “light” architecture, promising yearly refreshes (the first of which will be Airmont at 14 nm, extending Intel's manufacturing advantage beyond the lead it enjoys at 22 nm).

In fact, Intel files all of the changes made to Atom into three categories: those that improve performance, others intended to achieve better power efficiency, and specific optimizations to the company’s process technology.

Create a new thread in the UK Article comments forum about this subject
This thread is closed for comments
Comment from the forums
    Your comment
  • Cazalan
    The competition is heating up. Should get really interesting in 2014 when it's 14nm vs 20nm.
  • aahjnnot
    The original prediction, made in Jan 2012, was that Intel would take overtake Qualcomm in sales terms within three years. I just don't see that. These parts aren't yet shipping and, when they do, phone and tablet manufacturers will almost certainly be very cautious before they award design wins to Intel. Mobile devices are typically on the market for 12-18 months, so much of the product that will be sold in Jan 2015 is already under active development. Jan 2017 is a more realistic time horizon for commercial success.
    But even 2017 presupposes that Intel's as-yet unproven technical superiority will yield more sales, which ain't necessarily so. For the mass market, current mid-range ARM-based tablets and phones are good enough and are improving as rapidly as the Android software infrastructure requires, so, unless Intel can offer a price advantage over the ARM ecosystem, the non-geek buying public are unlikely to be impressed. Many device manufacturers will continue to prefer the additional supply-chain options provided by ARM SOCs, and other manufacturers - including Samsung and Apple who dominate the market - will continue to see strategic benefit in vertical integration and will not move to Intel processors.
    Finally, most of the Intel vs ARM tests that I've ever seen have involved Windows, which has long been optimised for x86 and AMD64. The few tests based on Android and Chrome have been much more favourable to ARM devices. I don't believe that Intel will have anything like the real-world technological lead that this article suggests.
    So I'll pitch my amateur prediction against the Toms Harware pundits. By Jan 2015, we'll see a number of Windows tablets and Windows phones that use Intel processors. These will sell in small numbers and will hold no more than 10% of the total worldwide market for tablets and phones. We'll also see a smattering of Intel processors in Android phones and tablets, but these will have no more than 10% of the total worldwide Android market share. Apple will stay with ARM-based processors for its phones and tablets. Overall Intel worldwide smartphone and tablet market penetration will be around 15%.
    I'll bookmark this comment. We'll see who's right.
  • Michael Robinson
    The article reads like a high pressure technical sales talk. Full of keywords that are never explained and missing anything that allows me to judge how much better the chips are. I believe the article stated that they've moved to a 14nm design, it's faster, it can have more cores and it uses less power. Was there anything else? Does anyone look over the articles just to make sure they don't read like gibberish?
  • Blazer1985
    Can't really see any gibberish here.
    It's a comparison between two architectures and, since the new one isn't commercially available yet, the writer couldn't use any benchmark to show you performance gains but tried to estimate the benefits with a thorough analysis of the architectures.
    Anyway Intel did not move to 14nm, they will move asap though, to maintain a manufacturing advantage over the competitors.
  • Michael Robinson
    "At the same time, Intel’s engineers incremented its instruction set architecture to the 2010 Westmere class (?)—up four years from the original Atom design’s Merom-compatible ISA(?). SSE4.1, SSE4.2, and POPCNT (?)(which operates on integer registers) are part of this ISA package(?) update, augmenting the Atom’s performance picture. AES-NI acceleration (?) and Secure Key (?) (including the RDRAND instruction and Digital Random Number Generator) also make it in. "
    I just picked a paragraph with lots of techno talk and no explanation. I'm pretty sure I could of picked almost anything though. The (?) are mine. I assume these guys go down to some talk, are given a sales brochure and are then told why all the these things are good. I just feel like I've read the brochure but missed the explanations. I guess I expected more from Tom's.