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
french toast - Thursday, January 12, 2012 - link
Im sorry, although this isnt an area that i have a huge amount of knowlege on, i can say with some certainty that both Qualcomm and ST-E will have on die baseband shipping this year on 28nm, In qualcomms case the s4 processor that is being demoed with the Asus idea pad has one in.I can also say it has 2 main advantages that i know of (and likely many more that i dont)
1) When put on die and using the same process as in qualcomm and ST-E case it vastly improves power effiecency, a big problem with currant 4g.
2) As most of the components are included on die that you have mentioned, that means more space out side of the die, less hastle for the manufacturers and more space inside the device/phone for things like battery/or smaller device.
Regards to Apple, apple bought PA semi, back in 2007/08 and use it to design its A-series chips, whilst it hasn't used a complete custom licence, they have done some soft optimisations, im not privvy to what they are.
Samsung also acquired intrinsity around the same time, and used their custom logic to some minor power improvements to the cortex core..first seen on the hummingbird..as Apple uses samsung to manufacture there chips, you can bet some of that is licenced too.
Qualcomm ,nvidia (not tegra)and Marvel also have full custom license.
aury - Wednesday, January 11, 2012 - link
"We did manage to run SunSpider on the K800 though, which yielded a score of 1,971 -- just a hair faster than the 1,985 that we saw on the Galaxy Nexus."So either your test is off by about 600 points, or Engadget is blind.
Anand Lal Shimpi - Wednesday, January 11, 2012 - link
I haven't played with the K800 that was being shown off but I am not familiar with the state of Lenovo's Android skin at this point, nor the details of how SunSpider was run. Our SunSpider numbers were run on the Medfield reference design which is what the K800 should be based on though.I'll try and do some digging.
Take care,
Anand
paul878 - Wednesday, January 11, 2012 - link
Who is going to hurt more?Intel entering into the Mobile Space or Arm entering the PC Space?
tipoo - Wednesday, January 11, 2012 - link
Well, Intel has plenty of padding to live on should things go sour. Plus they have compatibility on their side. I'd guess Intel will be fine no matter where things go, ARM now has the pressure on to be competitive.name99 - Wednesday, January 11, 2012 - link
"but one stand out issue was the A9 has a great execution core but seems to be more limited on the memory interface. Atom can support far more outstanding misses in L2 than the Cortex A9, which chokes bandwidth to the processor for anything not already in the L2 cache."It will be interesting to see if ARM take this seriously. Memory performance was THE downfall of PPC. It seems that companies and engineers think connecting to memory is not sexy compared to the core CPU; and I'd love to think that ARM are beyond this sort of childishness, but I honestly don't know.
guilmon19 - Wednesday, January 11, 2012 - link
ARM's A15 platform was also designed with servers in mind, and servers address and use the RAM alot more then basic applications so i think they'll, hopefully, have that fixed by A15IceDread - Wednesday, January 11, 2012 - link
I've always said that Intel would gain on ARM and eventually pass ARM. While I believed it would take a year more or two before they were this close on ARM, I'm still right :pThis will be interesting to follow, hopefully Amd gets their thump out and also does something on this market and then we have both Intel and Amd competing with cpu and gpu power for mobile devices.
varunkrish - Wednesday, January 11, 2012 - link
I believe Anand Chandrasekher who was the brain behind Medfield left Intel due to failure of Intel-Nokia partnership. Any insight on that ?Android does seem a good choice for Intel compared to MeeGo as the ecosystem is already present.
stadisticado - Wednesday, January 11, 2012 - link
I'd more characterize him as the brain behind the Nokia tieup, not the silicon. Silicon would have been controlled by the design teams, not the product division GM, which Anand was.