The ARM v.s. Intel Thing - Let's Discuss It

[Cerb]

I think this is the main problem the management of Intel have. Should they worry the sale of Atom will cut into the i-cores sales too much. But I don't think they have too many choices now.

I am wonder if the old Wintel thing will come back and create another Anti-trust issue if Microsoft and Intel team up again use the Atom for the Surface RT and the i-cores for the Surface Pro. Is Surface really work as Microsoft claim? without any problem?

That wouldn't be an anti-trust issue at all. They are quite free to create products that aren't well-designed for their customers. It can be frustrating, because we may want a different set of features, but they are quite free to cede more sales to devices coming out of the factory running non-Windows platforms. Trust issues only come in if they are deliberately using their power to unfairly compete with other companies, or treat their customers unfairly, due to their privileged market status (usually difficult, without government-granted monopoly--IE, see the old AT&T).

Once the strengths of MS' vertical integration cease to matter, because users and developers had been forced to learn to horizontally integrate over several years, and are used to some of the minor hurdles of doing so, MS will have no one to blame but whomever they decide to fire at the timethemselves. Now, knowingly creating products that aren't well-suited to their target markets might rile up shareholders...

 

[Ferzerp]

Typing is a chore on an ipad it has the worlds worst keyboard. infact doing anything on it is a PITA.

There are a large number of things that people do with a computing device that don't involve typing. All touch screen keyboards are equally crap. However, I can't agree that doing anything on it is a PITA. It's fine for watching netflix movies, etc.

 

[Idontcare]

Sheltered?

I have worked for some of the worlds biggest companies. Most of which still use Lotus Notes and windows XP. Let alone iPads.

Yes, sheltered. There is a reason the list of the "world's biggest companies" is continually changing, because dinosaurs who work at them can't see the value in change, be it to change their XP desktops to Win7 laptops or Win7 laptops to whatever is next.

The dinosaurs get outmaneuvered in innovation because they are the slow dinosaurs that they are, head buried in the sand yelling at the new kids to get of their lawn.

Let me get something straight here. Content consumption by kids is not "work" nor is what a teacher does on it. Its basically a modern day text book.

You haven't stepped foot inside a modernized classroom in years, have you? I'm willing to bet you haven't seen a "modern day text book" in years either.

Most kids who learn on ipads will have the written skills of an idiot by the time they are 18 and be unemployable. You only have to look on facebook today and see the damage already done to 'da idyots hu spk lyk dis' and think this is written communication. Most cant even use a pen now.

Look, grandpa, that thing you are railing against here is called the next generation and they WILL take over your world whether you like it or not.

Very few elderly generations were happy to see the social changes brought on by their successors, your parents and grandparents no doubt thought your digital calculators were unnecessary distractions in comparison to their tried-and-true sliderule.

Did you heed their wisdom? Despite the fact they too worked at the "world's biggest companies" of the time?

It is the prerogative of the established to pine for the status quo. For today's aging established demographic that is going to be your XP desktops and kids who "learn real good from modern text books, 'see spot run' and all that".

Tomorrow belongs to the kids who write as they choose to write, and you can choose to blame technology for that just as your parents chose to blame TV and Rock'n'Roll for rotting the minds of the youth in your day.

Typing is a chore on an ipad it has the worlds worst keyboard. infact doing anything on it is a PITA. i have owned 2 of them now and sold both because they are just terrible.

If you are trying to use a tablet as a replacement laptop or desktop then you are doing it wrong. That doesn't make the tablet a useless tool, it makes you look your age. 20yrs ago the joke would have been "I can't set the clock on my VCR, but my kids can"...for this generation of kids it will be "I can't figure out how to use my ipad, but my 4yr old grand-daughter just learned her multiplication tables on one!"

No one expects you to embrace technology which you are decidedly against, just don't be surprised, don't act like you were blindsided without any fair-warning, when some tablet-packing "kid" takes your job because they have figured out how to leverage the latest technology tools to out-do you at your own job, twittering on the side all the while

I'm personally not worried about the tablet-generation of the work force, I see them now and they are pretty bright. I am still young enough to adapt and be taught a few new tricks. Companies that don't prioritize the investment of new technology for increasing the productivity and efficiency of their workforces, those "world's biggest companies running XP desktops", they are the next DEC's and Compaq's of the world.

You can't turn around a corporate culture like that, and by the time it becomes painfully obvious that it needs to be done it will be far too late. Eastman Kodak anyone?

 

[atomheart]

I work in a hospital. None of the physicians, nursing staff or techs here are allowed to use their private tablets/laptops (the hospital does not purchase any sort of tablets for use) to access the internal network, only for internet access using wi-fi.

I've seen them used in private offices where GP's work, but I am not aware of any of them being implemented in hospitals in the city I live in.

In a smaller scale facility such as a private clinic where the decisions on to use or not use tablets are going to be guided more by the preference of one or two people, it would make sense. I think this would be true of any smaller scale business though, health care oriented or not. There are situations where a small scale and portable device could bring some utility. If you were speaking to an inpatient, who is more than likely going to be in a bed, then a tablet can bring something to the table for consulting their charts by their bedside. Currently we have computers throughout every area of the hospital and you often use them before speaking to a patient, so I can see some benefit from a tablet allowing you to access records in the midst of being with a patient.

At our hospital it would require a complete rewrite of our software though. The software is custom, search functions and drilling down through records would be a real PITA via a tablet interface.

I see, in my Father's situation the clinic where he works is a government backed non-profit place. The iPads were also provided to the doctors so they are "company property", though I realize now they likely have them because apple advertises on their building and they presumably get a good deal.

It was easier for their doctors to just input it all into the database from the tablet than to write it down and input it on a PC. I used to work for the IT manager at the clinic as a scape-goat err I mean assistant and while they had enough computers they weren't in abundance like at some larger hospitals. But hey the clinic is doing well given the resources available, my Father just recently won them a 5 million dollar grant for updating the facility, it will be interesting to see what they choose as compute devices to carry them into the coming years.

 

[Homeles]

Dang IDC, you are unusually snarky in that post.

 

[Arachnotronic]

"I think this is the main problem the management of Intel have. Should they worry the sale of Atom will cut into the i-cores sales too much. But I don't think they have too many choices now."

It's better to sell an Atom than to let someone else sell a chip in the Core's place.

 

[pablo87]

Intel market cap tell it all. There is a reason for such a low market cap despite the absolutely huge competences inside.

If i was a huge player in the mobile space, why should i chose Intel?

I can get an open ARM standard, where i can change supliers as i like, it gives me plenty of the performance i need. I need to manage my suppliers, not be dictated the other way round. No way. Ask Apple if they need more than A7V? Man even a beefed up little in little-big A7-A15 is enough. All for 10usd for the performance variants.

What do i give a s..t if Intel offered me an Atom that does it at twice the speed for only 15 usd?

There is only strategic disadvantages to chose Intel. The hkmg in TSMC 28nm is effective going to shut the door for the new Atom, no mather how good they are. Excactly as cheap 40nm it is now for the technically superior 32hkmg Atom variants.

While I generally agree with you, there are 3 factors to consider:

#1 - cross subsidy - intel will leverage their latest process and take a "loss" on SOC to gain share, all subsidized by traditional biz.

#2 - innovator's dilemma problem - Haswell is like 3.5" HDD - doesn't quite meet the TDP requirements vector right now but they're getting there.

#3 - ARM - once upon a time, it was beneficial for Apple, now I'm not so sure. Seems to benefit factories (Samsung, TSMC) most. So If Intel is competitive, Apple might be tempted, would you bet against them? I would not.

Anecdotes -even back in 1997, intel had good things to say about Apple. They never burned that bridge. This info straight from the horse.

 

[Homeles]

Apple has spent how much R&D on Swift, now? The iPhone boat set sail years ago, for Intel.

 

[pablo87]

Things change - fast. There's the quick....and the dead.

 

[Homeles]

Apple has already fulfilled "quick" by becoming an ARM architecture licensee.

 

[sontin]

There are atleast 7.

And how many are smartphones? One? Two?

The current Atom is an even older design. Getting a complete uarch refresh next year.

A9 is more than three years old. So with A15 there is a new architecture on the way, too.

BTW: I find only end of 2013 or early 2014 for the next gen Atom SoC:

http://mobilegeeks.com/leaked-intel-atom-tablet-roadmap-bay-trail-t-valley-view-t-detailed/

Like i said: Intel is still one year to late.

 

[IntelUser2000]

And how many are smartphones? One? Two?

-Lava Xolo X900
-Lenovo K800
-Motorola RAZR i(also has a Chinese version called the MT788)
-Megafon Mint(Russia)
-ZTE Grand X IN
-Orange San Diego

Yes, they are all Smartphones. There are also few Android Tablets, not yet here though.

 

[ShintaiDK]

And how many are smartphones? One? Two? .

Atleast 7

I assume you dont want to continue a serious discussion.

Happy new year.

 

[IntelUser2000]

Atleast 7

I assume you dont want to continue a serious discussion.

Happy new year.

Actually, its 6 exactly, unless you want to count the re-named RAZR i for the Chinese market. There are no other officially announced models(hell, there isn't even a rumor outside of the launched ones either!).

 

[Khato]

BTW: I find only end of 2013 or early 2014 for the next gen Atom SoC:

http://mobilegeeks.com/leaked-intel-atom-tablet-roadmap-bay-trail-t-valley-view-t-detailed/

Like i said: Intel is still one year to late.

That's the tablet processor roadmap. The Silvermont core and 22nm is coming to the phone space with Merrifield, though as of yet I haven't seen any dates on a roadmap for it.

More interesting is that apparently the Intel reference design for Merrifield may already be complete, working... and fast as promised - http://www.guru3d.com/news_story/intel_merrifield_soc_benchmark_scores_online.html The Nenamark2 scores are likely not too far off if it is indeed just a frequency-bumped SGX 544 without an MP configuration - aka it may not be a graphics monster. But a score of over 31612 on the current AnTuTu is still pretty close to twice the performance of current competition - haven't been able to find a score for A15 after the most recent update that changed scoring.

 

[Exophase]

Merrifield is probably Z2580 (revealed here: http://www.anandtech.com/show/5592/intel-atom-z2580-z2000) rather than Silvermont-based.

 

[ShintaiDK]

Merrifield is probably Z2580 (revealed here: http://www.anandtech.com/show/5592/intel-atom-z2580-z2000) rather than Silvermont-based.

Its not. Merrifield is 22nm and new uarch.

 

[Khato]

Merrifield is probably Z2580 (revealed here: http://www.anandtech.com/show/5592/intel-atom-z2580-z2000) rather than Silvermont-based.

While there's no question that Merrifield is Silvermont based, it could be the case that the redhookbay platform is using a Z2580 and not Merrifield. After all, we do know that the Z2580 is going to be using a SGX 544MP variant which does match up with these results. And it is quite possible that the AnTuTu scores would go up that much with the combination of doubling CPU cores and a far more potent GPU.

 

[IntelUser2000]

Khato:

I'm in agreement with you there. It's probably Z2580 based.

We can't derive much from the Nenamark 2 scores, because it seems its refresh rate capped at 60Hz. It may well be the SGX544MP2, because that's what the Z2580 is.

 

[Exophase]

While there's no question that Merrifield is Silvermont based, it could be the case that the redhookbay platform is using a Z2580 and not Merrifield. After all, we do know that the Z2580 is going to be using a SGX 544MP variant which does match up with these results. And it is quite possible that the AnTuTu scores would go up that much with the combination of doubling CPU cores and a far more potent GPU.

Yes, my mistake, I didn't actually look into what Merrifield was on the roadmaps and simply assumed that the rumors that it'd be released soon were correct in naming it. So yeah, I guess I really meant that the rumors probably refer to Z2580 and not Merrifield.

In order for this upcoming release to not be Z2580 that'd had to mean it was scrapped entirely, otherwise why bother later?

Also, is there any good evidence that it'll really be 22nm?

 

[Arachnotronic]

Yes, my mistake, I didn't actually look into what Merrifield was on the roadmaps and simply assumed that the rumors that it'd be released soon were correct in naming it. So yeah, I guess I really meant that the rumors probably refer to Z2580 and not Merrifield.

In order for this upcoming release to not be Z2580 that'd had to mean it was scrapped entirely, otherwise why bother later?

Also, is there any good evidence that it'll really be 22nm?

Z2580 is 32nm. 22nm comes with Merrifield. We won't be seeing "Silvermont" in a phone/tablet until Q1 2014.

"Avoton" SoC for micro-servers, however, is a 2013 part. That's where we first see that new core debut.

 

[Fjodor2001]

I noticed that Tom's Hardware just had an article on the very subject in the original post:

"ARM Vs. x86: The Secret Behind Intel Atom's Efficiency"

http://www.tomshardware.com/reviews/atom-z2760-power-consumption-arm,3387.html

I'm surprised that nobody has mentioned it.

My take on the story is that when the CPU is doing actual work, the Intel Atom CPU does quite well with regards to power efficiency.

But when completely idle the ARM is more efficient. 0.0038 W (ARM CPU) vs 0.02 W (Atom CPU). That's a 526% difference! Since that is a very important use case for mobile phones (if you can call not using the CPU a use case :hmm: ), I guess ARM has an edge over Atom here.

 

[Homeles]

I posted the AT version of the article a few pages back.

How does ARM manage such a low idle power?

 

[Tuna-Fish]

How does ARM manage such a low idle power?

There's no silver bullet to it. It's just that for a few decades, ARM has cared a lot more about idle power than Intel. It's a million small design decisions in the cores that accumulate.

It's not about the arm isa either -- I'd bet that if the present ARM were to build a x86 core, and the Intel engineers were to build an ARM core, the Intel ARM core would be faster and more powerhungry than the ARM x86 core.

It's a very common engineer pasttime to disparage the x86 isa. It's true that it's not a very good isa. It's also true that the isa quality doesn't really matter *that* much. Other things, like the quality of the uarch that implements the isa, are much more important.

 

[blackened23]

There's no silver bullet to it. It's just that for a few decades, ARM has cared a lot more about idle power than Intel. It's a million small design decisions in the cores that accumulate.

It's not about the arm isa either -- I'd bet that if the present ARM were to build a x86 core, and the Intel engineers were to build an ARM core, the Intel ARM core would be faster and more powerhungry than the ARM x86 core.

It's a very common engineer pasttime to disparage the x86 isa. It's true that it's not a very good isa. It's also true that the isa quality doesn't really matter *that* much. Other things, like the quality of the uarch that implements the isa, are much more important.

I'd love to see you substantiate that claim with real evidence and information.

ARM is great for battery life, but in terms of performance ARM chips will never compare to intel offerings. Maybe i'm overstating things here, but that's the way I see it - Intel has a huge performance lead, and is catching up rapidly on the battery life front. Once that happens, it isn't far fetched to believe that intel will dominate the mobile space in a few years time.