ARM, Intel Battle Heats Up 260
An anonymous reader writes "Low-power processor maker ARM Holdings is stepping up rhetoric against chip rival Intel, saying it expects to take more of Intel's market share than Intel can take from them. With Intel being the No. 1 supplier of notebook PC processors, and ARM technology almost ubiquitously powering smartphones, the two companies are facing off as they both push into the other's market space. 'It's going to be quite hard for Intel to be much more than just one of several players,' ARMs CEO said of Intel."
Where are the products ARM? (Score:5, Insightful)
I've been hearing about how ARM is going to destroy Intel for the last 5 years at least and I haven't seen the products yet despite the promises thrown about with the Cortex A9. It looks like the cortex A15 willl be able to beat Medfield... but you aren't getting those A15s in large quantities until next year when Intel will have the next iteration of Atom ready anyway. Oh and 64 bit? That's gone from an insanely important feature when Intel didn't have it to being useless bloat when Intel does have it and ARM doesn't, but it's OK because in 2015 you might be able to get an ARM chip with 64 bit support....
Since 2008 when the much derided Atom debuted, Intel has gone from not having anything that could remotely run a smartphone or tablet to having Medfield, which is competitive although not industry leading in the smartphone and table space. I have yet to see ARM come out with anything that even threatens a run of the mill Core 2 yet... so why is ARM talking so much trash?
It might be that ARM is a little more nervous that there is finally some real competition in the mobile space, which is a boon to consumers. I'd like to see AMD get an x86 solution down into this power envelope too so that there would be multiple competitors on the x86 side as well.
Re:Where are the products ARM? (Score:4, Insightful)
My Fusion-based netbook idles at 9 or 10 watts.
AMD still needs to shave the idle power by a factor of 5 to get into tablets and 10 to get into smartphones. I think they can do it, but Bobcat is not the chip for that market.
Re:Where are the products ARM? (Score:5, Insightful)
The only Intel consumer product ARM licensees are currently able to threaten is the Atom product line. Apart from that, both kinds of CPUs are simply serving two completely different purposes.
Re:Simple math, silly! (Score:3, Insightful)
TFA is really dumb. It combines two very separate markets - notebooks and smartphones.
It makes the assumption - always wrong - that people don't want more cpu. People ALWAYS want more cpu. I remember back when pundits were writing "there will never be a consumer market for dual-core processors." Now a dual-core notebook is "bottom of the line".
So ARM will take some of the bottom of that market @$20 per cpu. Intel will take the $80 - $200 per cpu market.
Plus, people want software compatibility. Windows on ARM is all well and good, but nobody's going to re-buy a thousand bucks worth of software to save $50 on a laptop.
Re:Where are the products ARM? (Score:4, Insightful)
No, a tablet needs a chip with a 2W TDP, not a 2W idle; similarly, a phone needs one with a 1W TDP, not 1W idle.
Re:Where are the products ARM? (Score:3, Insightful)
ARM *did* bloody well destroy Intel in the smartphone and tablet spaces. This is not some old ancient niche that ARM has wrapped up -- these products and markets only appeared within the past 5 years or so.
So yes, if you heard people saying that ARM would destroy Intel 5 years ago, they would be right, because Intel has tried and failed to field parts in these markets.
ARM, on the other hand, has not yet tried to compete in PC or server markets. If anybody tried to tell you that ARM was going to destroy Intel in those markets, they obviously were pulling shit out their arses. ARM simply did not have (public) plans to compete here like they do now, although now and again some random company or another tries to put ARMs in low power servers or laptops. Now you see when they do announce plans, they are hoping to take 10-20% of notebook PC market -- that's hardly "destroying" Intel, is it? So what you have been hearing is baloney from idiots, the remedy for that is to stop listening to idiots.
Medfield doesn't change much. Like everything else, it's been a day late and a dollar short. It showed that Intel is actually capable of producing something with a sane idle power draw, but really, we knew that couldn't be black magic anyway. That's not to say that Intel can't take the lead in future, but for now nothing has changed. ARM has some fundamental advantage with instruction set architecture in low power space, but Intel has advantages with manufacturing and process technology, and probably could devote more resources into low power CPU design than ARM too.
Also, it's not the A15 that really changes things a great deal, in my opinion. It looks like a great design, and it's probably a little higher, relatively, than A9 was. But what has really enabled them to compete in this market space is Android and Windows/ARM (and maybe small chance of Apple doing ARMs in some notebooks too), not some sudden big improvement in the hardware.
Their first 64-bit design may be significantly different. It may be a real intention to get into server and/or higher end personal markets.
And Intel has a trick up their sleeve (Score:5, Insightful)
22nm lithography. Intel is, as usual, a node ahead of basically everyone else. Other fabs just got their 28nm half node online not long ago, late last year. So we are seeing products based on that start appearing on the market. The current nVidia and AMD GPUs would be some notable ones, but there are (or at least will be) ARM chips too.
Intel though, they didn't do the 28nm half node (they haven't done half nodes so far), they went straight to the 22nm node and it is online and running full swing. Ivy Bridge chips using it have shipped in large quantities.
What that means is Intel can pack more transistors in to a given die size, and have them use less power per transistor. For mobile, that is a big advantage. That means even in the event their shit does less per transistor, they can make it up with more transistors. Also means things like 64-bit are less problematic to implement (64-bit requires more transistors).
Now I've no idea if Intel what arenas Intel will choose to compete in, but if I were ARM I wouldn't be looking forward to direct competition. I'd hope it remains largely how it is: Intel focusing on the high end (from netbooks all the way up) ARM focusing on the low end (from tablets all the way down). No competition, no problem. I wouldn't be enthused about the prospect of having to compete with someone in the low power market who has a better process.
Intel is likely to keep the advantage too. Everyone else is hard at work setting up their 22nm fabs, but they are probably at least a year away, maybe more. Intel? They've been hard at work building Fab 42 inc Chandler which is to be their first 14nm facility. They say they'll have it online in 2013 (it'll be some time after it goes online until chips are shipping to consumers though), and they are pretty good about hitting their marks on that.
It is one of the things that has given them an edge is their massive R&D in to fabs that keeps them a node ahead of everyone. ARM can't do that, they are just a design company, not a fab, and none of the other companies that do fab work seem to be willing to plow in the R&D money that Intel is.
Re:Random idea (Score:4, Insightful)
Intel is not threatened by technical advantages of ARM per se, it is more about the business logistics inherent in the ARM ecosystem. If x86 is a requirement, your choices are Intel, AMD, and a distant third VIA. If ARM is acceptable, suddenly Qualcomm, Samsung, Broadcom, TI, nVidia, Freescale, and literally dozens more become options, mixing and matching with a few fabrication companies. By and large, business concerns over not being held over a barrel by your supplier has made the concept of avoiding the x86 space very appealing.
Intel should probably consider a smartphone-targeted ARM processor, to break into that specific market that now has gobs of pre-compiled applications for ARM. However, I think the strategy for tablets and larger would be more aggressive licensing of x86 to more providers. x86 still carries a lot of weight in backward compatibility, and the non-iPad tablet market isn't exactly particularly cemented quite yet.
Re:Simple math, silly! (Score:2, Insightful)
The article misses an obvious fact - the small market that arm will take is all on the no-profit, low-end, first-time notebook buyer.
Anyone who already has an x86 laptop is going to stick with x86, just to maintain software compatibility. Ditto for anyone with a legacy application. Ditto for anyone who wants to run games (and everyone wants to run the odd game here and there).
So, who's going to buy this? People who used to be called the "netbook" market.
In other words, cheap, bottom-of-the-barrel, almost-no-profit and few needs.
In other words, they'll take sales away from an already dying market, leaving Intel the higher-margin / higher-priced market.
That's the same strategy Apple has used for years.
It really is about the ability to run existing programs, otherwise we'd already have the Year of the Linux Desktop.
Re:Where are the products ARM? (Score:5, Insightful)
Re:Simple math, silly! (Score:5, Insightful)
Your assertion is dissociated from reality. It completely ignores the netbook phenomenon, not to mention the inception of smartphones and tablet computers.
People don't buy these devices because they "want more CPU". After a certain level, the "CPU" amount is irrelevant and its practical effects are completely unnoticeable. There is a good reason why hardware companies rely on artificial benchmarks designed to push the hardware in completely unrealistic, useless and impractical scenarios to be able to compare their hardware against the competitor's offering, and therefore justify a higher asking price.
To drive the point home, I can tell you my personal case. My last two hardware purchases were a netbook and a smartphone, which, by today's standards, are considerably lacking o the "CPU" department. Yet, they are by far the two pieces of hardware which I use the most. I also have a desktop and a laptop which I've purchased a few years ago, and I actually use them for serious stuff which actually require real CPUs to crunch real numbers. I'm talking about structural analysis and CAD work. In spite of actually having to use a computer to actually do some serious number crunching to actually get a meaningful result, unlike calculating pi to the nth digit after the decimal point, the fact is that both my archaic desktop and laptop are more than capable of handling heavy workloads required for practical engineering work.
And this without even relying on OpenCL to take advantage of the hardware which is already present in the system and basically never leaves the idle state.
So, in short, contraty to what you said, people actually "don't want more cpu". People actaully know that they can't notice it after a certain point, which was actually passed about half a dozen years ago, and people are also aware that the inflated price tag associated with having "more cpu" actually doesn't justify the diminishing returns they get with that purchase. What they want is cheaper stuff that is actually good enough to get the job done, and if the job in mind is checking email, facebook and any other mundane tasks then people do know that the price tag of a supercomputer is completely unjustified, when they can easily get away with it by purchasing a glorified cellphone, with or without an embedded keyboard.
Re:And Intel has a trick up their sleeve (Score:4, Insightful)
The proof is in the pudding: despite their process advantage, Intel hasn't made any inroad in phones/tablets yet.
Also, people don't routinely solve linear equations. FP math is not really used by the vast majority of users, as are many of the more advanced things Atom can do, so the Atom's more advanced capabilities re probably rather irrelevant. On the other hand, ARM does the things people actually use more efficiently: from http://www.androidauthority.com/why-intel-atom-medfield-is-still-far-from-being-competitive-with-arm-chips-59065/ [androidauthority.com]: "A dual core 1.5 Ghz Krait chip has a 0.75W TDP under maximum load, while Atom has 2.6w TDP in “idle mode” alone (when your phone does nothing), and 3.6W when playing a 720p video. So that’s around 4, maybe 5 times less efficient than the best ARM chip right now."
Re:Where are the products ARM? (Score:2, Insightful)
These are full fledged radeon stream processors. They kick the ever loving crap out of anything and everything else in integrated market.
Re:Where are the products ARM? (Score:3, Insightful)
No one can stop the x86 train, not even Intel. Medfield is only the start and while it might slaughter ARM it will make life very difficult for ARM SoC designers, let's just remind ourselves how many architectures by many vendors that were supposed to kill x86 just couldn't, not even Intel's. Not with iAPX480, i860 or i960 or Itanium.