Intel’s Silvermont Architecture Revealed: Getting Serious About Mobile
by Anand Lal Shimpi on May 6, 2013 1:00 PM EST- Posted in
- CPUs
- Intel
- Silvermont
- SoCs
Final Words
Silvermont really is Intel’s Conroe for the mobile market, but not in the sense that many have been expecting. Given that success in mobile is so closely tied to device wins, Silvermont alone isn’t enough. Unlike Conroe, a very competitive Silvermont won’t change the world overnight. What Silvermont does however is offer a great foundation for Intel going forward. Conroe lead to Penryn, Nehalem, Westmere, Sandy Bridge, Ivy Bridge and soon, Haswell. It was the platform that Intel could build on regularly by executing on tick-tock. Conroe paved the way for the insane advantage Intel has held onto for the past few years. Silvermont is like Conroe in that it provides that same foundation.
The mobile market is far more competitive than the PC industry was back when Conroe hit. There isn’t just one AMD but many competitors in the SoC space that are already very lean and fast moving. There’s also the fact that Intel doesn’t have tremendous marketshare in ultra mobile. Silvermont may feel a lot like Conroe, but the market it’s competing in is very different. That’s not to say that Intel can’t be successful here; it’s just not going to be easy.
Architecturally Silvermont is very conservative, and that’s not a bad thing. A side effect of not wanting to make Haswell irrelevant by a far lower cost part is the benefit of maintaining power efficiency. Intel joins the ranks of Apple and Qualcomm in intelligently scaling performance while respecting power consumption. Intel’s 22nm process should give Silvermont a lot of runway to use. If it can quickly follow up with 14nm, Silvermont’s power advantage could end up being akin to Conroe’s performance advantage in the mid-2000s.
Even so, Silvermont is long overdue. It’s the first mobile architecture where Intel really prioritized smartphones and tablets, and on paper, it looks very good. Now it’s up to Intel to turn a great architecture into great design wins. From what I’m hearing, we may actually see that happen.
Facebook
Twitter
RSS
174 Comments
View All Comments
Ortanon - Monday, May 6, 2013 - link
This.jamesb2147 - Monday, May 6, 2013 - link
That's not an excuse for subjective fluff. Don't get me wrong, I particularly liked the Bulldozer performance reviews and analysis. The reason I liked them was the hard data used to develop ideas about possible use-case scenarios for the CPU's. This article is full of "IT'S GONNA BE AWESUMMMMMM!!!!!1!!!" and not so much nuanced, objective reporting on actual news. It has plenty of analysis, but without concrete evidence, it reads like one of those all-too-familiar forum rants from HardForum or the like, full of people with too much time and not enough to do.If Anandtech is evolving into one of those news outlets that has to keep writing articles to keep people engaged, then I'm not interested. And it's not just my loss, it's the readership's.
wsw1982 - Tuesday, May 7, 2013 - link
if the clover trail+ already has similar performance as the best ARM offer, and the silvermont is said to be 2 times better than clover trail+. What should be the most logic sentiment in your opinion?phoenix_rizzen - Tuesday, May 7, 2013 - link
Well, you're comparing some future Intel SoC that no one has been allowed to actually touch/test (using only Intel's internal "benchmarking") against currently available ARM SoCs. Who knows what the performance will be like for ARM SoCs in 8-12 months, when these Intel SoCs are actually, physically able to be benchmarked.Cautious optimism is warranted. Not flat-out "OMG, THIS IS THE BESTEST EVAR!" fluff like this article spouts.
Spunjji - Wednesday, May 8, 2013 - link
Restrained optimism and a desire for further evidence. I can only assume Anand has already seen more than us, as his attitude is somewhat more positive than that. If he hasn't, well, I have expressed the opinion before that I find he treats Intel press releases rather lightly.cjb110 - Tuesday, May 7, 2013 - link
tbh that's an OTT response, AnandTech have done a piece based on the info they have and their previous experience. Everything mentioned is reasoned out in a logical progression. You might not always agree with the reasoning but its most certainly isn't 'fluff'. There will be a data based analysis later, as always.Krysto - Monday, May 6, 2013 - link
But not entirely unbiased. Making a detailed analysis and being biased aren't mutually exclusive.Krysto - Monday, May 6, 2013 - link
See asymco.com (apple fanboi doing "indepth analysis" about Android and other competitors.. Guess what? They usually favor Apple).Homeles - Monday, May 6, 2013 - link
I doubt there's a single human being on the face of the planet that is unbiased. What's your point?Thrill92 - Tuesday, May 7, 2013 - link
Oh no, your going to have to do some critical thinking about the data and conclusions in media. What ever will you do?