Except that Atom has room for growth. This is just now on 32nm, but 22nm is online and shipping in a month or 2 with Ivy bridge... They can stay one process ahead of the rest and compete.
Dont forget, the last time Intel had any real pressure they answered with the Core2 Duo/Quad. If Intel puts their focus behind this, they will get it.
Except Intel isn't one process ahead. TSMC is already producing 28nm chips for Q1 2012, where as Intel is talking about 32nm chips. And last I checked, I don't ever remember the Atom line ever getting first dibs on Intel's latest fab process. That always goes to their desktop and laptop designs.
Besides, Intel still needs to deal with the biggest problem for switching: in order to beat the competition, you can't just be a little bit better, you have to be an order of magnitude better to get people to switch.
"Except Intel isn't one process ahead. TSMC is already producing 28nm chips for Q1"
Intel is just starting 22nm while TSMC and others are starting 28nm.
" I don't ever remember the Atom line ever getting first dibs on Intel's latest fab process"
They have already announced that that will change in 2012. Atom will be right in front.
"in order to beat the competition, you can't just be a little bit better, you have to be an order of magnitude better to get people to switch"
And that is exactly what I am saying not to count Intel out of. If they put their efforts into a platform, they will get it. They have some of the best chip engineers on earth, and plenty of them. They have unlimited cash reserves, talent, manufacturing experience and industry clout.
As far as switching, they also have the ability to Run Win8 and x86 apps, so that gives more flexibility and opens up the enterprise market to tablets in a way that ARM never will. I am not saying everything will work out perfect for them and go 100% as planned, but If I were to bet on it, my $ is behind Intel getting it done.
Intel is WAAAY behind in the mobile space. It's not that easy to compete with the x86 baggage. There is a limit to what you can do. Throwing more people to a problem doesn't solve the problem faster. Some things just takes time.
Besides, with Apple having their own chip, it's only a matter of time before they create a fully integrated Siri / Gaming solution with their A6-7 chips. With their S/W and H/W all lined up, no amount of Intel intervention can save them.
The problem is not as simple as you make it out to be.
That and x86 isnt "baggage" in the enterprise sector. With Win8 and using x86 apps, companies can actually do real business on tablets instead of these "silly" little apps that are written for ARM tablets. X86 will make tablets a useable work computer.
You're conveniently forgetting that all those 'awesome' legacy x86 are written for mouse and keyboard interaction and are all but useless in touchscreen based tablet. At best, trying to use them will be horrible, at worst, it'll be outright impossible.
x86 alone will NOT make smartphones and tablets into useable work computer. Writing new applications that fully utilize touchscreen useage model will.
x86 is overkill is obsolete in the mobile sector. There is no dependancies of x86 in mobile. You're no going to run a desktop app on a mobile phone.
You'll need to rewrite a mobile app which exploits the mobile phone's capabilities. That is why ARM is such a beast.
Do you really think Intel can compete with RIM in the enterprise sector or Apple in the consumer sector that easily?
Intel's got a LOOONG way to go before I declare them a legitimate challenge. It'll make multiple execution mistakes from either of the companies before Intel has a shot. This is not out of the realm of possibilities, but Intel by itself cannot determine its own destiny in this sector.
"Intel will compete in the mobile market. Like it or not. "
But with WHAT ?. This junk?!. It loses out in the power consumption department like 2W vs 500mw. Its performance is not outstanding. Have you seen the ARM A15 dual core performance ?. Intel will say WTF!.
So this chip is almost the same as the netbook chip and hardly usable in tablet form. In phone formfactor, its battery life is going to be short. Who wants it when you have great choices way better elsewhere.
Wait till Apple sue them like they sue everyone else, then will be game over for Intel Medfield x86 Andoird Phones. Or even worse maybe till Intel manages to release the Medfield in 2012, Apple will already succeeded to ban all Android OS&phones then Intel will have the CPU but no OS to support it or no mobile phone that can integrate it since they will be all banned by Apple. After all that was the dream of Steve Jobs to destroy all Android eco-system phones+OS+processors that means destroying all other mobile phone makers besides Apple, destroying all other mobile OS'es besides iOS and destroying all other processor developers besides Apple, what a wonderful dream of a dead man this was. ROTFL
"Apple will already succeeded to ban all Android OS&phones"
What are you smoking that makes you think Apple will win? They have already lost most of their cases that have come to court becasue they have no merit.
Apple is suing for very vague concepts. If you want to say "Apple is being copied", then take it back to the root. Apple "copied" the whole mobile phone idea, as well as putting and OS and apps on a phone from Palm/Handspring. All companies do this. The entire industry builds off ideas of others. It always has, as all industries always have. Its as if to say, Toyota, GM, BMW and Honda shouldnt be allowed to make cars because they all copy Ford. Specifically Appl's suits are as if Ford sued GM because they have cupholders and mudflaps on their pick up trucks. Petty and irrelevant.
I agree, let's wait and see...Remember when we all first saw a netbook? It was kinda cool, but it turned out to be a failure...and that was a major initiative of Intel's. Dell just stopped making all their minis. But make it or not, another player is going to be good for us consumers. Let's wait and see what happens, worst case is they fail. Best case, we see Intel chipped tablets and phones. And like it or not, the Intel brand sells. Heck, they'll even try to buy their way into products, and it will probably work. It would be nice to see an Android tablet beat the featureless iPad2 in EVERY benchmark. That's my 2 cents.
Intel is still being annoyingly vague with this, current Atom cores draw magnitudes more power (watts vs hundreds of milliwats) than ARM cores, I'd be surprised if it actually drew less power than ARM cores like they are saying here. And graphics performance is as compared to what? A measly 535, a Mali 400, or a SGX543MP2? Or what is performance in general compared to, a single core Cortex A9 or dual core A9 or quad core Tegra 3, etc etc. I'm excited to see some new blood in the SoC market but this tells us almost nothing.
Quite awhile ago, IDF I think, Intel announced that the new 22nm process with the new FinFET 3D transistors has still lower active power and a 20X reduction in standby leakage power over even 32nm products -- that means much improved battery life over Medfield's 32nm. Medfield 32nm gets Intel in the door and in the race. 22nm is the real winner over ARM. While 22nm is indeed a generation ahead of ARM, the 22nm FinFET puts them out even further. No one but Intel has that until at least the 16nm node.
Agreed... Notice no comparable apps power usage. Everything they show for battery life could be done with a idle or near idle core using on-chip task specific dsps etc... Standby 3G, Audio Playback, Video Playback all easily off loaded. Fire up that ATOM cpu to run a web browser and bam suck down half your battery in 5 mins or did Intel make a giant leap in power consumption?
Not all CPU manufacturing processes are requivalent. Netbook/Nettop atoms are made on the same high power optimized process as normal laptop and desktop chips. The phone atom is built on a low power process (like existing arm CPUs). The Intel version is reported ~10% slower; but has 10-100x lower idle power consumption than its desktop version. This is enough to get Intel into the same ballpark as ARM SoCs; until Intel gets working hardware into the hands of independent hardware sites we can't know precisely how competitive their hardware is but on the face of it these slides look about right.
Ya that is the question. Another problem is the last time I think intel tried to show similar graphs the problem was SHIPPING smartphones by the time anyone takes their product and turns it into a phone ARM will be forward another generation. At that point you will have a low end SOC that probably draws too much power and no one will buy it.
Intel is a mixed bag with success so we will see. SSDs they got in the game. Graphics at anything other than bottom end they are still a joke despite all the hype about larrabe.
One big thing I notice is that Intel's power consumption numbers only reflect idle and near-idle workloads. I worry that this means it has the potential for performance, but comparatively high power draw if you actually load the CPU.
Yeah, I want to see some real world tests already. Its possible that even with a higher load power draw they get to idle faster and so save power on the whole while doing something like web browsing, and we know this will offload video to dedicated hardware. Its all just talk until we have someone actually test it though. It would be quite exciting if they had higher performance at the same battery use as ARM chips.
Another thing I wonder about is how it would compare to the quad core Tegra 3, being a single core chip itself, and also future A15 designs.
I want a phone that could be used on a phone, but docked to a screen and wireless keyboard/mouse and used as a full Windows PC. Since Windows 8 won't provide a full Windows experience on ARM, Intel will be the only choice to realise that dream.
We don't know yet whether or not the full windows experience is going to be supported or not. There are for too many rumors going either direction to make a legitimate prediction.
Well, we do know a lit. The only thing up in the air is if the desktop is even going to be available on ARM or not.
ARM is not going to run x86 apps without a recompile, so instantly you don't have the full windows experience.
I think by the time Windows 8 comes out, the ARM vs x86 debate will pretty much be over. Intel will likely be the dominant platform for Windows 8 tablets.
As for phones, that may take a bit longer but Intel will get there. They have the best engineers, and the best chip fabs in the world. It would be pretty hard to believe that they won't overtake ARM based chips.
If Medfield were fatally flawed in its power requirements, Intel's in house council would block presentation of the misleading slide (copy above) from the investor's conference even if each data-point was factually correct. The concern is misled shareholder lawsuits and people getting fired. If you seek some fatal flaw to confirm that it is impossible that Intel could compete successfully with ARM, look elsewhere.
As far as good words for posts, "ecosystem" sounds great, once had a scientific meaning, and should sound credible until Intel's mobile market share exceeds 50%. "Baggage" does not work because Intel already has that and the article reveals that from a performance and power efficiency perspective Intel already has "baggage" more than covered at 32 nm. Remember, Intel is still trying to show it understands the rules of the mobile game and Medfield may do that. Show time starts at 22nm which is when Intel reveals it's tick tock A-Team.
I don't care for a x86 android phone. Not unless Wine runs on it anyway. I am however curious about a x86 Windows device in a similar form factor. Maybe it is time for the UMPC comeback.
But aren't we forgetting something before we can even talk phone-sized form factor? I am still waiting to have a decent variant in the comparatively much larger (and so supposedly easier to get) form factor of 9-12 inch tablets. We do have a few options, but they fail in comparison to AMD Bobcat alternatives, and even those aren't too great.
And last, it's not just the CPU that needs focus for a "design win". When will some manufacturer finally comprehend that they can not cut corners with crappy TN panels with resolution worse than my wrist watch, passive touchscreens with no stylus, or only the minimum integrated GPU even for when their device is plugged in or docked, etc?
Regarding the comment about how Moorestown was dismissed for being too power hungry w/o evidence, there is at least one data point: Fujitsu LOOX F-07C. This phone combined both a Z600 processor at 1.2GHz meant for running Windows 7 and an unknown ARM SoC meant for running Symbian.
The phone is equipped with a 1400mAh battery, which is pretty standard for smartphones today. Windows 7 mode runs for only about 1-2 hours. This was despite the Z600 being clocked at a meager 600MHz, which would put its typical performance far below what a 1+GHz Cortex-A9 would give you. And the unit got hot just by downloading things. Part of this is Windows' fault, but that only extends so far.
VR-Zone posted some Medfield benchmarks and it looks pretty damning, only a 40% performance increase over a Tegra 2 in CaffeieneMark 3 with a 1.6Ghz Medfield. I don't see how it has any chance of standing up against Tegra 3, much less anything based on Cortex A15 or Qualcomm Krait processors.
If I remember correctly x86 (Intel) was able to beat the pure RISC chips through being ahead on the process curve. This allowed them to offset the disadvantage of CISC instruction set decoding with more transistors for better RISC cores, faster switching ie higher frequencies and cheaper chips.
I am suspicious that Intel may not have the head room to be far enough in front to offset x86's problems. I remember reading somewhere that there are only 2-3 further design rule shrinks (16 nm, 10/12nm and may be 8 nm) before chip makers have to look else where for performance improvements. This doesn't give Intel much time to get in front particularly with ARM manufactures already jumping to 28 nm which will put them ahead of Medfield on 22nm both in power and performance.
ARM is cheap, doesn't have to worry about x86 overhead and the software is legacy ARM in the mobile space so x86 loses unless it is much better. It will be interesting to see what Intel can do.
I really think that they have an uphill challenge. Tegra 2 isn't Medfield's competition. Tegra 3 is. Qualcomm's Krait is.
I can only hope that Intel manages to push Silvermont to Q4 2012, or it might be quite problematic for them. After all, by then, A15s will be in the market too.
Since Silvermont is speculated to be OoO and have a new architecture, it has hope of really beating (or perhaps tying with) ARM.
Another thing that concerns me is the GPU. What GPU is Intel running? I heard that previous Atoms use the SGX535. Is that right? Hopefully Medfield has an SGX 544MP2 (not 543, Intel would need DX support).
I don't think SGX544 (or at least the dual-core configurations) will be out until NEXT year. And most likely the more valuable choice would be to cut off and use a SGX543MP4 instead (delivers better performance overall than the 543MP2 - if I'm not wrong)
This battle seems to be more interesting to me than the desktop x86 battle. Again we see Intel coming from behind but with a TON of money and world class fab capability. 2012 and 2013 will be fun to watch, for sure.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
39 Comments
Back to Article
dagamer34 - Wednesday, December 21, 2011 - link
An Intel-powered Android phone is quickly becoming the next Duke Nukem Forever.retrospooty - Wednesday, December 21, 2011 - link
Except that Atom has room for growth. This is just now on 32nm, but 22nm is online and shipping in a month or 2 with Ivy bridge... They can stay one process ahead of the rest and compete.Dont forget, the last time Intel had any real pressure they answered with the Core2 Duo/Quad. If Intel puts their focus behind this, they will get it.
dagamer34 - Wednesday, December 21, 2011 - link
Except Intel isn't one process ahead. TSMC is already producing 28nm chips for Q1 2012, where as Intel is talking about 32nm chips. And last I checked, I don't ever remember the Atom line ever getting first dibs on Intel's latest fab process. That always goes to their desktop and laptop designs.Besides, Intel still needs to deal with the biggest problem for switching: in order to beat the competition, you can't just be a little bit better, you have to be an order of magnitude better to get people to switch.
retrospooty - Wednesday, December 21, 2011 - link
"Except Intel isn't one process ahead. TSMC is already producing 28nm chips for Q1"Intel is just starting 22nm while TSMC and others are starting 28nm.
" I don't ever remember the Atom line ever getting first dibs on Intel's latest fab process"
They have already announced that that will change in 2012. Atom will be right in front.
"in order to beat the competition, you can't just be a little bit better, you have to be an order of magnitude better to get people to switch"
And that is exactly what I am saying not to count Intel out of. If they put their efforts into a platform, they will get it. They have some of the best chip engineers on earth, and plenty of them. They have unlimited cash reserves, talent, manufacturing experience and industry clout.
As far as switching, they also have the ability to Run Win8 and x86 apps, so that gives more flexibility and opens up the enterprise market to tablets in a way that ARM never will. I am not saying everything will work out perfect for them and go 100% as planned, but If I were to bet on it, my $ is behind Intel getting it done.
web2dot0 - Wednesday, December 21, 2011 - link
Not so fast Sherlock.Intel is WAAAY behind in the mobile space. It's not that easy to compete with the x86 baggage. There is a limit to what you can do. Throwing more people to a problem doesn't solve the problem faster. Some things just takes time.
Besides, with Apple having their own chip, it's only a matter of time before they create a fully integrated Siri / Gaming solution with their A6-7 chips. With their S/W and H/W all lined up, no amount of Intel intervention can save them.
The problem is not as simple as you make it out to be.
SlyNine - Wednesday, December 21, 2011 - link
Forget the X86 baggage, If you think thats a problem then you don't understand how X86 is done today and how little it effects anything.Intel will compete in the mobile market. Like it or not.
retrospooty - Wednesday, December 21, 2011 - link
That and x86 isnt "baggage" in the enterprise sector. With Win8 and using x86 apps, companies can actually do real business on tablets instead of these "silly" little apps that are written for ARM tablets. X86 will make tablets a useable work computer.JoeTF - Friday, December 23, 2011 - link
No, it won't.You're conveniently forgetting that all those 'awesome' legacy x86 are written for mouse and keyboard interaction and are all but useless in touchscreen based tablet.
At best, trying to use them will be horrible, at worst, it'll be outright impossible.
x86 alone will NOT make smartphones and tablets into useable work computer. Writing new applications that fully utilize touchscreen useage model will.
web2dot0 - Saturday, December 24, 2011 - link
x86 is overkill is obsolete in the mobile sector. There is no dependancies of x86 in mobile. You're no going to run a desktop app on a mobile phone.You'll need to rewrite a mobile app which exploits the mobile phone's capabilities. That is why ARM is such a beast.
Do you really think Intel can compete with RIM in the enterprise sector or Apple in the consumer sector that easily?
Intel's got a LOOONG way to go before I declare them a legitimate challenge. It'll make multiple execution mistakes from either of the companies before Intel has a shot. This is not out of the realm of possibilities, but Intel by itself cannot determine its own destiny in this sector.
fteoath64 - Sunday, January 1, 2012 - link
"Intel will compete in the mobile market. Like it or not. "But with WHAT ?. This junk?!. It loses out in the power consumption department like 2W vs 500mw. Its performance is not outstanding. Have you seen the ARM A15 dual core performance ?. Intel will say WTF!.
So this chip is almost the same as the netbook chip and hardly usable in tablet form. In phone formfactor, its battery life is going to be short. Who wants it when you have great choices way better elsewhere.
retrospooty - Wednesday, December 21, 2011 - link
OKeedokkee... Wait and see then.xytc - Wednesday, December 21, 2011 - link
Wait till Apple sue them like they sue everyone else, then will be game over for Intel Medfield x86 Andoird Phones. Or even worse maybe till Intel manages to release the Medfield in 2012, Apple will already succeeded to ban all Android OS&phones then Intel will have the CPU but no OS to support it or no mobile phone that can integrate it since they will be all banned by Apple. After all that was the dream of Steve Jobs to destroy all Android eco-system phones+OS+processors that means destroying all other mobile phone makers besides Apple, destroying all other mobile OS'es besides iOS and destroying all other processor developers besides Apple, what a wonderful dream of a dead man this was. ROTFLretrospooty - Thursday, December 22, 2011 - link
"Apple will already succeeded to ban all Android OS&phones"What are you smoking that makes you think Apple will win? They have already lost most of their cases that have come to court becasue they have no merit.
Apple is suing for very vague concepts. If you want to say "Apple is being copied", then take it back to the root. Apple "copied" the whole mobile phone idea, as well as putting and OS and apps on a phone from Palm/Handspring. All companies do this. The entire industry builds off ideas of others. It always has, as all industries always have. Its as if to say, Toyota, GM, BMW and Honda shouldnt be allowed to make cars because they all copy Ford. Specifically Appl's suits are as if Ford sued GM because they have cupholders and mudflaps on their pick up trucks. Petty and irrelevant.
Tchamber - Tuesday, December 27, 2011 - link
I agree, let's wait and see...Remember when we all first saw a netbook? It was kinda cool, but it turned out to be a failure...and that was a major initiative of Intel's. Dell just stopped making all their minis. But make it or not, another player is going to be good for us consumers. Let's wait and see what happens, worst case is they fail. Best case, we see Intel chipped tablets and phones. And like it or not, the Intel brand sells. Heck, they'll even try to buy their way into products, and it will probably work. It would be nice to see an Android tablet beat the featureless iPad2 in EVERY benchmark. That's my 2 cents.tipoo - Wednesday, December 21, 2011 - link
Intel is still being annoyingly vague with this, current Atom cores draw magnitudes more power (watts vs hundreds of milliwats) than ARM cores, I'd be surprised if it actually drew less power than ARM cores like they are saying here. And graphics performance is as compared to what? A measly 535, a Mali 400, or a SGX543MP2? Or what is performance in general compared to, a single core Cortex A9 or dual core A9 or quad core Tegra 3, etc etc. I'm excited to see some new blood in the SoC market but this tells us almost nothing.MonkeyPaw - Wednesday, December 21, 2011 - link
Its nice of them to compare to "shipping smartphones," as vague as that is. What range does that include, the 3GS all the way up to Droid Bionic?Hector2 - Wednesday, December 21, 2011 - link
Quite awhile ago, IDF I think, Intel announced that the new 22nm process with the new FinFET 3D transistors has still lower active power and a 20X reduction in standby leakage power over even 32nm products -- that means much improved battery life over Medfield's 32nm. Medfield 32nm gets Intel in the door and in the race. 22nm is the real winner over ARM. While 22nm is indeed a generation ahead of ARM, the 22nm FinFET puts them out even further. No one but Intel has that until at least the 16nm node.Einy0 - Wednesday, December 21, 2011 - link
Agreed... Notice no comparable apps power usage. Everything they show for battery life could be done with a idle or near idle core using on-chip task specific dsps etc... Standby 3G, Audio Playback, Video Playback all easily off loaded. Fire up that ATOM cpu to run a web browser and bam suck down half your battery in 5 mins or did Intel make a giant leap in power consumption?Anand Lal Shimpi - Wednesday, December 21, 2011 - link
Is there any public data showing that a 32nm LP, highly integrated Atom based SoC isn't power competitive under load with ARM Cortex A9 based SoCs?I'm not saying this is or isn't the case, but what if Intel were competitive on that front as well? I suspect we'll find out soon enough :)
Take care,
Anand
DanNeely - Wednesday, December 21, 2011 - link
Not all CPU manufacturing processes are requivalent. Netbook/Nettop atoms are made on the same high power optimized process as normal laptop and desktop chips. The phone atom is built on a low power process (like existing arm CPUs). The Intel version is reported ~10% slower; but has 10-100x lower idle power consumption than its desktop version. This is enough to get Intel into the same ballpark as ARM SoCs; until Intel gets working hardware into the hands of independent hardware sites we can't know precisely how competitive their hardware is but on the face of it these slides look about right.PubFiction - Sunday, January 1, 2012 - link
Ya that is the question. Another problem is the last time I think intel tried to show similar graphs the problem was SHIPPING smartphones by the time anyone takes their product and turns it into a phone ARM will be forward another generation. At that point you will have a low end SOC that probably draws too much power and no one will buy it.Intel is a mixed bag with success so we will see. SSDs they got in the game. Graphics at anything other than bottom end they are still a joke despite all the hype about larrabe.
Matias - Wednesday, December 21, 2011 - link
Let's not forget this a future chip compared to current chips. Let's see how the competition changes until it launches!LtGoonRush - Wednesday, December 21, 2011 - link
One big thing I notice is that Intel's power consumption numbers only reflect idle and near-idle workloads. I worry that this means it has the potential for performance, but comparatively high power draw if you actually load the CPU.SlyNine - Wednesday, December 21, 2011 - link
Not surprising, Intel has always been about hurry up and idle.tipoo - Thursday, December 22, 2011 - link
Yeah, I want to see some real world tests already. Its possible that even with a higher load power draw they get to idle faster and so save power on the whole while doing something like web browsing, and we know this will offload video to dedicated hardware. Its all just talk until we have someone actually test it though. It would be quite exciting if they had higher performance at the same battery use as ARM chips.Another thing I wonder about is how it would compare to the quad core Tegra 3, being a single core chip itself, and also future A15 designs.
iwod - Wednesday, December 21, 2011 - link
Again, without knowing what shipping smartphones is these figure are completely pointless.Graphics better 50% better? I wouldn't believe that is comparing to Apple's A5.
Much Faster? Properly so, but compare to a Shipping Cortex A8 800Mhz?
Third in Power Usage? Those in the charts much be the most power hungry ARM chips ever.
I still believe Intel wont be competitive until 22nm.
ET - Thursday, December 22, 2011 - link
I want a phone that could be used on a phone, but docked to a screen and wireless keyboard/mouse and used as a full Windows PC. Since Windows 8 won't provide a full Windows experience on ARM, Intel will be the only choice to realise that dream.N4g4rok - Thursday, December 22, 2011 - link
We don't know yet whether or not the full windows experience is going to be supported or not. There are for too many rumors going either direction to make a legitimate prediction.Braumin - Thursday, December 22, 2011 - link
Well, we do know a lit. The only thing up in the air is if the desktop is even going to be available on ARM or not.ARM is not going to run x86 apps without a recompile, so instantly you don't have the full windows experience.
I think by the time Windows 8 comes out, the ARM vs x86 debate will pretty much be over. Intel will likely be the dominant platform for Windows 8 tablets.
As for phones, that may take a bit longer but Intel will get there. They have the best engineers, and the best chip fabs in the world. It would be pretty hard to believe that they won't overtake ARM based chips.
dealcorn - Thursday, December 22, 2011 - link
If Medfield were fatally flawed in its power requirements, Intel's in house council would block presentation of the misleading slide (copy above) from the investor's conference even if each data-point was factually correct. The concern is misled shareholder lawsuits and people getting fired. If you seek some fatal flaw to confirm that it is impossible that Intel could compete successfully with ARM, look elsewhere.As far as good words for posts, "ecosystem" sounds great, once had a scientific meaning, and should sound credible until Intel's mobile market share exceeds 50%. "Baggage" does not work because Intel already has that and the article reveals that from a performance and power efficiency perspective Intel already has "baggage" more than covered at 32 nm. Remember, Intel is still trying to show it understands the rules of the mobile game and Medfield may do that. Show time starts at 22nm which is when Intel reveals it's tick tock A-Team.
Visual - Friday, December 23, 2011 - link
I don't care for a x86 android phone. Not unless Wine runs on it anyway.I am however curious about a x86 Windows device in a similar form factor. Maybe it is time for the UMPC comeback.
But aren't we forgetting something before we can even talk phone-sized form factor?
I am still waiting to have a decent variant in the comparatively much larger (and so supposedly easier to get) form factor of 9-12 inch tablets. We do have a few options, but they fail in comparison to AMD Bobcat alternatives, and even those aren't too great.
And last, it's not just the CPU that needs focus for a "design win". When will some manufacturer finally comprehend that they can not cut corners with crappy TN panels with resolution worse than my wrist watch, passive touchscreens with no stylus, or only the minimum integrated GPU even for when their device is plugged in or docked, etc?
Exophase - Friday, December 23, 2011 - link
Regarding the comment about how Moorestown was dismissed for being too power hungry w/o evidence, there is at least one data point: Fujitsu LOOX F-07C. This phone combined both a Z600 processor at 1.2GHz meant for running Windows 7 and an unknown ARM SoC meant for running Symbian.Here are some reviews:
http://www.engadget.com/2011/08/26/fujitsu-loox-f-...
http://www.pocketables.net/2011/10/fujitsu-loox-f-...
The phone is equipped with a 1400mAh battery, which is pretty standard for smartphones today. Windows 7 mode runs for only about 1-2 hours. This was despite the Z600 being clocked at a meager 600MHz, which would put its typical performance far below what a 1+GHz Cortex-A9 would give you. And the unit got hot just by downloading things. Part of this is Windows' fault, but that only extends so far.
ssj4Gogeta - Monday, December 26, 2011 - link
Was the Z600 made on an LP process?Exophase - Tuesday, December 27, 2011 - link
Allegedly, but bear in mind that this has more to do with idle power consumption than active.LtGoonRush - Tuesday, December 27, 2011 - link
VR-Zone posted some Medfield benchmarks and it looks pretty damning, only a 40% performance increase over a Tegra 2 in CaffeieneMark 3 with a 1.6Ghz Medfield. I don't see how it has any chance of standing up against Tegra 3, much less anything based on Cortex A15 or Qualcomm Krait processors.Link: http://vr-zone.com/articles/intel-s-32nm-medfield-...
ChrisOz - Wednesday, December 28, 2011 - link
If I remember correctly x86 (Intel) was able to beat the pure RISC chips through being ahead on the process curve. This allowed them to offset the disadvantage of CISC instruction set decoding with more transistors for better RISC cores, faster switching ie higher frequencies and cheaper chips.I am suspicious that Intel may not have the head room to be far enough in front to offset x86's problems. I remember reading somewhere that there are only 2-3 further design rule shrinks (16 nm, 10/12nm and may be 8 nm) before chip makers have to look else where for performance improvements. This doesn't give Intel much time to get in front particularly with ARM manufactures already jumping to 28 nm which will put them ahead of Medfield on 22nm both in power and performance.
ARM is cheap, doesn't have to worry about x86 overhead and the software is legacy ARM in the mobile space so x86 loses unless it is much better. It will be interesting to see what Intel can do.
skydrome1 - Wednesday, December 28, 2011 - link
I really think that they have an uphill challenge. Tegra 2 isn't Medfield's competition. Tegra 3 is. Qualcomm's Krait is.I can only hope that Intel manages to push Silvermont to Q4 2012, or it might be quite problematic for them. After all, by then, A15s will be in the market too.
Since Silvermont is speculated to be OoO and have a new architecture, it has hope of really beating (or perhaps tying with) ARM.
Another thing that concerns me is the GPU. What GPU is Intel running? I heard that previous Atoms use the SGX535. Is that right? Hopefully Medfield has an SGX 544MP2 (not 543, Intel would need DX support).
Last chance, Intel. Let's see how you dance.
slugrail - Monday, January 2, 2012 - link
I don't think SGX544 (or at least the dual-core configurations) will be out until NEXT year. And most likely the more valuable choice would be to cut off and use a SGX543MP4 instead (delivers better performance overall than the 543MP2 - if I'm not wrong)extide - Friday, December 30, 2011 - link
This battle seems to be more interesting to me than the desktop x86 battle. Again we see Intel coming from behind but with a TON of money and world class fab capability. 2012 and 2013 will be fun to watch, for sure.