Engineering Investigations
Comment
bruzzer2
Solely considering Intel Xeon production, the total Sandy Bridge E Series market ...
bruzzer2
ARM Ltd. has apparently been under financial pressure lately. And got caught ...
Dis-ARMing the data center – Separating myth from reality
Sylvie Barak
12/11/2012 10:05 PM EST
Deliver 64-bit first, talk after
Firstly, ARM has to deliver its new architecture on time with its first ARM V8 implementations with Cortex A53 and A57. 64-bit computing is a baseline requirement to enter the space and today it is, unfortunately, MIA in ARM world.
If AR’sr products don’t have 64-bit, they can be considered dead on arrival in the data center, and the reality is that it will be at least two years before we see any ARM products that have this capability. Fact.
Two years is a long time in product cycles, which means that as this new category of microservers grows, customers will only have one company they can buy product from for the foreseeable future, Intel.
ARM also has to deliver on time and with scale. While Cortex A15 is a tremendous new architecture it has largely limped out of the gate in 2012 and we won’t see the majority of designs until next year. Hopefully, for ARM’s sake V8 will have a smoother birth in 2014.
Secondly, ARM will need to build an eco-system in record time. The server world is a complex one, driven by a broad eco-system of applications and workloads that have been optimized over many years to run exceptionally well on X86 processors. Moving these workloads over to a competing architecture is not a trivial matter, just look at the launch of Windows RT on the consumer side to see the pitfalls of lack of application compatibility and low performance.
Nobody can argue that low power in the data center isn’t a tremendous driver today, but applications compatibility remains essential. In this area ARM will need to step up and create an eco-system that minimizes the deficit of compatible applications and workloads for its architecture rather than simply leaving this to customers.
Management will also be a huge issue that needs to be addressed. A rather large number of companies have aspirations to participate in the ARM server market. Calxeda, Applied Micro, Samsung and AMD are all committed to bringing products to market in the coming years and more will follow.
With the exception of AMD, very few of these companies have any real expertise in data center management which could be problematic as they try and convince enterprise IT executives to deploy a mixed environment of X86 and ARM.
Click for next page >>>
Firstly, ARM has to deliver its new architecture on time with its first ARM V8 implementations with Cortex A53 and A57. 64-bit computing is a baseline requirement to enter the space and today it is, unfortunately, MIA in ARM world.
If AR’sr products don’t have 64-bit, they can be considered dead on arrival in the data center, and the reality is that it will be at least two years before we see any ARM products that have this capability. Fact.
Two years is a long time in product cycles, which means that as this new category of microservers grows, customers will only have one company they can buy product from for the foreseeable future, Intel.
ARM also has to deliver on time and with scale. While Cortex A15 is a tremendous new architecture it has largely limped out of the gate in 2012 and we won’t see the majority of designs until next year. Hopefully, for ARM’s sake V8 will have a smoother birth in 2014.
Secondly, ARM will need to build an eco-system in record time. The server world is a complex one, driven by a broad eco-system of applications and workloads that have been optimized over many years to run exceptionally well on X86 processors. Moving these workloads over to a competing architecture is not a trivial matter, just look at the launch of Windows RT on the consumer side to see the pitfalls of lack of application compatibility and low performance.
Nobody can argue that low power in the data center isn’t a tremendous driver today, but applications compatibility remains essential. In this area ARM will need to step up and create an eco-system that minimizes the deficit of compatible applications and workloads for its architecture rather than simply leaving this to customers.
Management will also be a huge issue that needs to be addressed. A rather large number of companies have aspirations to participate in the ARM server market. Calxeda, Applied Micro, Samsung and AMD are all committed to bringing products to market in the coming years and more will follow.
With the exception of AMD, very few of these companies have any real expertise in data center management which could be problematic as they try and convince enterprise IT executives to deploy a mixed environment of X86 and ARM.
Click for next page >>>
|
|
|
|
|
Navigate to related information
ChipConnoisseur
12/12/2012 7:55 AM EST
How can there be a "proper microserver market" when there aren't even proper micro-server chips for it? This is like saying "there isn't a proper laptop market" 15 years ago before laptop chips even existed.
Intel's recently announced micro-server chip is not even a good one. Avaton will be their first micro-server chip. And ARM has to wait until Cortex A57 for their first proper micro-server chip. So it looks like we don't even have proper chips yet, so of course there isn't a market for this. The market will only begin to shape-up in 2014 and beyond.
And of course ARM is "hyping up" their ARM chips. Why wouldn't they? They will be more scalable and have better energy efficiency and performance/watt than Intel's chips. And Nvidia is set to make a big entrance in 2014, too, with its Project Boulder.
And first you go on and accuse ARM of "hyping it up" and then criticize them for having to build an ecosystem in record time. Well that's exactly why they are talking about it - to get momentum and to build that ecosystem.
Sign in to Reply
help.fulguy
12/13/2012 12:10 PM EST
Hey ChipC, i dont know what you are smoking. Ask ARM Guys, they will tell you that Cortex-A15 at 1.8GHz consumes 6W. Its a Fact. When Intel has a SoC for 6W, tell ARM to jump off the cliff.
Sign in to Reply
iniewski
12/12/2012 10:43 AM EST
Can someone explain to me what is a microserver? To me this sounds like a microtruck, a minature version of something big...dare I say a normal car?
Sign in to Reply
horta1212
12/12/2012 8:52 PM EST
It's pretty simple really. It's collection of chips that have many cores that run very efficiently. It would be like taking today's (or yesterday's) laptop chips, stripping down many peripherals, creating an interconnect and sticking it within a single chip. The major advantage of it should be much better performance/watt than current server chips, which have been designed for years to be speedy, power-hungry beasts. What allows ARM microservers to achieve these goals should be better process technology and the ability to sidestep x86's power hungry ways (by not being x86).
Sign in to Reply
help.fulguy
12/13/2012 12:14 PM EST
Hey Whorton's Horta1212, Check my comment above. Cortex-A15 at 1.8GHz consumes 6W. Its a Fact. When Intel has a SoC for 6W, tell ARM to jump off the cliff. What are you smoking with your x86 power hungriness. Everyone knows ARM can not design a performance efficient design. You are duped by the ARM smoke screen
Sign in to Reply
iniewski
12/13/2012 10:58 AM EST
thank you horta1212 for the explanation...so what is a difference between microserver and server? (beyond one being larger)
Sign in to Reply
help.fulguy
12/13/2012 12:12 PM EST
Amen Sista. Rick Merritt will hate you for this article. You may want to lend him your "Reality Glasses". He has the "Rosy ARM Glasses" on all the time.
Sign in to Reply
przemek
12/13/2012 4:20 PM EST
Of course it remains to be seen whether ARM will deliver on promises, but they did well so far. ARM claims pretty good performance for their 'microserver' chips: 1250 SpecInt2000 for 1.7GHz chip. It is weird that they would quote SpecInt2000 because it's been superseeded by SI2006 six years ago, so maybe those numbers should be taken with some caution, but if you take them on face value, they are pretty good: Intel 1.7GHz chips of that era (e.g. P4) tend to present at about half the performance.
Even after allowing some 'benchmark shrinkage' and improvements in Intel architecture since that time, ARM should be competitive with Intel on performance. Based on their track record, they should do fine on power. As for the price, Intel quoted unit price for their new SoC announcements was above $50---again, ARM should be quite competitive, especially considering that ARM chips are traditionally pretty integrated, with the equivalent of North/South bridge on chip, whereas Intel usually requires separate motherboard/system chipsets.
Having said that, I am reminded of the story I heard from one of the RISC pioneers. He showed up at a Vax shop and demonstrated his machine. Afterwards, the customer said to him: 'So, your machine is twice the speed at half the price of what I have now. Give me one good reason why I should buy it".
Sign in to Reply
MClayton
12/14/2012 4:24 PM EST
AUTHOR:" But let’s face it, Microservers is not even that big of a market anyway, with only a handful of important customers like Facebook, Google and Amazon. " Doesn't Google have the worlds largest data center already? Or close to it. Microservers WILL BE the only market next decade that has any growth in "server" segment in my opinion. And the sky is the limit for clouds (pun intended).
Sign in to Reply
bruzzer2
12/17/2012 2:04 AM EST
ARM Ltd. has apparently been under financial pressure lately. And got caught drinking its own Koll aid in two of four attempts to hit high volume royalty home runs out of the ball park.
Of these only one brought in base holders, one struck out on projections, one made first base, and for the final batter up . . .
Noteworthy while ARM Ltd. was out aggrandizing that market communications could resolve what only world class platform development can secure, beyond smart phone & tablet, neglected its entire business foundation as Intel stormed every industrial beach head which were left not only unguarded by ARM executive management; but unattended.
In setting commercial market expectations so high ARM Ltd. forced a financial cost onto some of its customers seeing their passing. And for reasons that solely have to do ARM Ltd. believing they could talk the market into accelerated Intel victories lacking any market foundation what so ever.
Press relations cannot make a product, or a successful product market. Innovations take time, nurturing the market potentials and not waking up Goliath so early.
ARM Ltd. has been caught in the trap of its own public relations puffery with nothing to show for it.
This is surely an embarrassment for an enterprise capable of world class management with oversight supporting compliment development while guarding against the competitive financial risks.
The executive management of ARM Ltd. will never make this mistake ever again.
Mike Bruzzone
Camp Marketing
Sign in to Reply
bruzzer2
12/17/2012 2:36 AM EST
Solely considering Intel Xeon production, the total Sandy Bridge E Series market for dense ARMs on Blade is 113,594,361 units valued at $72,395,536,747 revenue potential.
Xeon 12xx/24xx/26xx production volume priced less than $250 = 7,466,263 units.
Xeon 12xx/24xx/26xx/46xx production volume priced less than $625 = 24,451,308 units.
Mike Bruzzone
Camp Marketing
Sign in to Reply