Intel's Medfield & Atom Z2460 Arrive for Smartphones: It's Finally Here
by Anand Lal Shimpi on January 10, 2012 8:00 PM ESTThe GPU
The PowerVR SGX 540 in Medfield is no different from what you'd get in an OMAP 4460, with the exception that it's clocked a bit higher at 400MHz.
The SGX 540 here is a remnant of Intel's earlier strategy to have Medfield out far sooner than it actually is going to show up on the market. Thankfully Intel has plans to introduce a PowerVR SGX 543MP2 based Medfield successor also before the end of the year.
Video Decode/Encode Support, Silicon Hive ISP
Intel relies on two more IP blocks from Imagination Technologies: the VDX385 and VDE285 for 1080p video decode and encode. Intel claims support for hardware accelerated 1080p30 decode, High Profile. Maximum supported bitrate is apparently up to 50Mbps, although Intel only demonstrated a 20Mbps High Profile stream:
Intel also claims support for 1080p30 video encode.
Medfield's ISP is provided by Intel owned Silicon Hive. The ISP supports cameras ranging from 5MP to 16MP (primary sensor), with the reference design standardizing on an 8MP sensor. Medfield supports burst capture at up to 15 fps (8MP).
The Process
Intel bifurcated its process technology a few years ago, offering both low power and high performance versions of each of its process nodes. Today those process nodes are staggered (45nm LP after high perf 32nm, 32nm LP debuts after high performance 22nm, etc...) however Intel plans on bringing both in lockstep.
Medfield debuts on Intel's 32nm LP process. The only details we have from Intel are that leakage is 10x lower than the lowest on 45nm. Compared to Moorestown, Medfield boasts 43% lower dynamic power or 37% higher frequency at the same power level.
The bigger and more valid comparison is to TSMC's 28nm process, which is what companies like Qualcomm will be using for their next-generation SoCs. It's unclear (and very difficult) to compare different architectures on different processes, but it's likely that Intel's 32nm LP process is more comparable to TSMC's 28nm LP process than it would be to any 4x-nm node.
It is important to note that Intel seems very willing to sacrifice transistor density in order to achieve lower power consumption where possible. I don't believe Intel will have the absolute smallest die sizes in the market, but I also don't believe it's clear what the sweet spot is for mobile SoCs at this point. It's quite likely that Apple's ~120mm^2 target is likely where everyone will eventually end up in the near term.
The Roadmap
Although Medfield is already posting competitive performance numbers, its current competition is roughly a year old. Within the next two quarters we'll see smartphones and tablets shipping based on Qualcomm's Krait. The next-generation Snapdragon platform should be Cortex A15-like in its performance level
Today we have Medfield, a single core Atom paired with a PowerVR SGX 540 built on Intel's 32nm LP process. Before the end of the year we'll see a dual-core Atom based Medfield with some form of a GPU upgrade. I wouldn't be too surprised to see something like a PowerVR SGX 543MP2 at that point either. In tandem Intel will eventually release an entry level SoC designed to go after the more value market. Finally we'll see an Intel Atom based SoC with integrated Intel baseband from its Infineon acquisition - my guess is that'll happen sometime in 2013.
Facebook
Twitter
RSS
164 Comments
View All Comments
reenie49 - Wednesday, January 11, 2012 - link
The numbers from Medfield seem competitive with current Arm A9 SOC's , but these are Intel numbers and until the phones are out then we just don t really know , Intel has promised before . In a few months A15 chips at 28 nm will be out and they "should" post higher performance and/or lower power than A9 so will be infront again . But performance is only half the battle , what about cost ? Is Medfield as cheap as Arm ? Intel likes big profit margins and cripples the low end to protect the high end , It is used to charging 60 dollars plus per chip not sub 20 dollars, does Intel really want to be in an arms race with samsung etc ? Will phone manufactures be happy to be tied to one chip producer and pay more for the privilege ? With Arm , they have a choice of 3 or 4 different SOC's or can build there own . So as it has been said before, Intel will have to be alot better to be a reason to ditch Arm . Think it will be another 2 to 3 years before we see a winner in top end smartphones and tablets . I think Arm will still dominate the low end phones with A7 etc, can t see Intel wanting to be in the sub 10 dollar chip market . Has Arm announced its successor to A15 ?ThomasS31 - Wednesday, January 11, 2012 - link
The real deal here is x86 compatibility with Windows 8 coming you can run all you apps from your phones, tablets or high and PCs... it will all work on the intel ecosystem. Evey your old apps.That is a hugh deal vs the ARM ecosystem. You will have Windows 8 ofc, but some old apps simply won't work.
And on 22nm very soon, this will be a killer design in my opinion.
french toast - Wednesday, January 11, 2012 - link
Thankyou for posting this insight into Medfield, you always give the best in depth analysis on the internet, usually without all the biased, speculatory fud.However i have noticed that you have a slight bias towards Intel, nothing major but you seem to give them more benefit of the doubt than they can prove.
You stated thus;
'' Even today it appears to deliver better CPU performance than anything on the market, despite only having a single core''
Nonsense.
This in no way proves that Medfield is a faster chip than say Exynos 4210 from last year.
In fact as you state that Atom is the same architecture, i would say evidence says that even tegra 2 is faster according to these benchmarks ;
http://www.phoronix.com/scan.php?page=article&...
The 2 Intel sourced benchmarks that you sourced do not give the complete picture to go drawing such conclusions, either about the platform or the architecture.
The cortex A9 is at minimum the same performance clock for clock according to more complete benchmarks i linked above, Multi threading which does have uses in Android and even webrowsing/games will be superior on 2 A9s, also if you put both on the same process the A9s will be substantially smaller and consume substantially less power.
Other web site that i have read said that the Medfield reference phone was slightly choppy/laggy when scrolling the home sreen, which they noted doesn't happen on Exynos.
Which is clocked lower and will be 18months older by the time Medfiled releases.
Some else pointed out about which gingerbread update is it running? ove at xda forum they report ICS gains in performance on 2.3.7 for example....
Whilst it is interesting to put up this Intel promotion, it does not conclude that this would have dominated android last year at all, it seems at first glance that it would have been COMPETITIVE last year. there is no proof that an Atom is even on par with A9/same clock speed let alone Krait.
After all the excellant articles i have read on this site, i expected a little better too be honest.
BSMonitor - Wednesday, January 11, 2012 - link
Are you completely mental?? You are comparing miniITX platforms running Ubuntu to SoC's running Android. Your benchmarks are completely meaningless.french toast - Wednesday, January 11, 2012 - link
No there not, they are the only comparable benchmarks that put both architectures through their paces, if you level the clocks the A9s smoke the Atoms...Anand says him self that the Achitecture remains the same.There certainly more comparable than this Intel marketing blitz.
The power point slides above say that Medfield will have substantially more gpu performance than a iphone 4s,samsung galaxy s2..as we know its a sgx540@400 i highly doubt it somehow.
My point is the tests are provided by intel, or run on limited benchmarks that dont test cpu LOAD scenarios, that are not multithreaded, not standardised software, and the atoms are running at a higher clock rate.
No real world power consumption tests were done, yet bizarly, Anand draws the conclusion that it is the superior architecture and would have 'dominated' android last year... i dont see it that way myself.
guilmon19 - Wednesday, January 11, 2012 - link
why is it meaningless? in the intel benchmark they were comparing android 4.0 to 2.3, and from what iv'e read they're very different. While all the miniITX platforms in the other benchmark use a consistent base for all of the hardware by using the same OS. Plus a miniITX is pretty similar to a SoC. The only difference is that SoC are usually smaller and more integrated, but other then that they use very similar hardwarefrench toast - Thursday, January 12, 2012 - link
I agree, the medfields were running on android 2.3.7 which is heavilly optimised compared to the software that some of the others were running on, that alone makes it void.One of the websites ran a quadrant score on the reference platform and got an impressive 3791 how ever the galaxy note, which runs a 1.4ghz exynos and has a core idle. gets 4300+..so that puts it into perspective.
Anand has got a very good reputation for cutting out all the crap and just looking at things in a very objective/logical/technical way, with out jumping the gun and making false assumptions, i hope this continues and we dont see this Intel spin anymore.
halcyon - Wednesday, January 11, 2012 - link
Why don't you benchmark it against Qualcomm S4 A15 Quad?Or the next gen Samsung A15 quads?
Both of those will ship *BEFORE* Medfield devices actually ship.
And they will have lower LTE (not just 3G) idle, highe GPU speeds, and equal/higher perf clock-for-clock.
It looks like Intel *almost* made it this year, but not quite.
Oh well, perhaps the next revision...
BSMonitor - Wednesday, January 11, 2012 - link
Because there is no A15 Quad fully functioning reference phone. Weird.Lucian Armasu - Wednesday, January 11, 2012 - link
Does Atom stand a chance? You say it will be out by the end of the year. We should have at least 2, if not 3 chips based on Cortex A15 by then, one by Samsung at 2 Ghz each core, one by TI (OMAP 5 at 2.5 Ghz), and possibly another one by Samsung that also uses big.Little together with Cortex A7, for even lower power consumption.How will this single core Atom processor be competitive with one of those dual-core processors?
And that's without even counting the dual-core/quad-core Krait chips, which if I'm not mistaken, you've already said they should be more powerful than Atom.