ARM vs Intel: The fight for the datacentre hots up

ARM vs Intel: The fight for the datacentre hots up

Summary: ARM and Intel go head to head over the processors at the heart the datacentre, but can mobile chips really prevail against their established rivals?


There's little doubt that the nature of servers is undergoing a fundamental change. As Jack Clark points out, big web content providers, such as Google, Facebook and Amazon, may be considering switching processors. Or at least, that's what ARM would like them to do.

ARM — originally the Acorn RISC Machine — is a rare success story in the processor business whose time has arguably arrived, courtesy of the huge and ramping demand for low-powered CPUs to drive battery-hampered mobile devices.

The future of mobile chips is interesting, but it's their role in lowering energy usage that could have the biggest impact on most people

It's hoping its chips, whose design it licenses out, will become the basis of tomorrow's servers, driven by the increasing imperative to cut the costs of powering and cooling the datacentre.

It's not going to be all plain sailing, though. As an article in Wired about Intel and the decline of Dell, HP and IBM in servers points out, Google et al are showing little sign of switching from the x86 architecture. To do so would be tantamount to throwing away millions of years of developer effort to code for a new hardware platform.

Instead, they're taking a new route. Rather than buying servers from Dell, HP and IBM, whose combined market share of the server business has been dropping, they're building their own.

So far so unsurprising. We've known for years that Google takes this approach. What is interesting is that Intel has confirmed that eight server makers now vie for a share of the same pie — 75 percent of the server market in 2008 — that was previously sewn up tight by the big three.

Server builders and customised machines

More interesting still is that Google is not alone. Many server builders are making customised machines for the likes of Facebook, something Intel obviously knows since it's selling CPUs to Google — the only web company to buy direct, according to Wired — and to the smaller server builders.

They are making systems that include such features as a Facebook-designed friction hinge, making server maintenance quicker and easier.

And all include Intel processors, which Intel reckons can get close to the kinds of power usage that ARM offers — just 15W — but without the humongous hassle of changing platforms.

Market share figures in this area are a bit speculative, since Intel doesn't reveal its sales figures, and market research companies such as IDC — the main data source — cannot or find it harder to count private sales to Facebook et al.

The future of mobile processors is interesting, but it's their role in lowering energy usage that could have the biggest impact on most people, whether or not they know it.

For a discussion of how this issue might play out, including a discussion of AMD's potential role, take a look at Jack Clark's piece Intel draws battle lines.

Topics: Processors, Data Centers, Mobility

Manek Dubash

About Manek Dubash

Editor, journalist, analyst, presenter and blogger.

As well as blogging and writing news & features here on ZDNet, I work as a cloud analyst with STL Partners, and write for a number of other news and feature sites.

I also provide research and analysis services, video and audio production, white papers, event photography, voiceovers, event moderation, you name it...

Back story
An IT journalist for 25+ years, I worked for Ziff-Davis UK for almost 10 years on PC Magazine, reaching editor-in-chief. Before that, I worked for a number of other business & technology publications and was published in national and international titles.

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.


Log in or register to join the discussion
  • ARM vs. Intel

    Arm is a threat? Really? I don't think so.
    • Very insightful.

      You give such a good argument, only a fool would refuse to listen to such words of wisdom.

      No doubt you will not be revealing your source any time soon.

      After all, information like that is priceless.
  • Datacente hots up?

    Is that a UKism? Or is there no one to check grammar in the digital age?

    Also, "throwing away millions of years of developer effort to code for a new hardware platform" is just a big, steaming crock of horse dung. Google, Facebook and Amazon run Linux in the DC, so all that's needed is to recompile their code. Any bits of x86 assembly will a tiny fraction of their code base.
    • ".. all that's needed is to recompile their code"; really??

      Things always look simple, until you start doing it.

      The scope of the work to be done is not always as simple as what they appear to be, and, code recompilation is not all there is to a switch to a different architecture. A data center is not defined by just the CPU of preference.
      • Continuous improvement.

        No-one is expecting a complete swap out.

        I am in no doubt that all the big companies, yahoo, google, facebook, twitter, are undergoing trials using ARM chips.

        If the cost savings are relevant and real, then I see no reason why they would not start building ARM data centers.

        I doubt very much these companies are prepared to pay more out of brand loyality.
    • Yes, Junior

      It is a UKism.
  • Really??

    Doesn't anyone proof read any more. 'Hots up'???
    • Yes. People read.

      It wouldn't surprise me if more English-speakers (actual ENGLISH, vs "USAian" speakers) recognise it as equally acceptable, or preferable to, "heats up".
  • Heeter than this

    The spelling police may stand down. I Googled "hots up" and found that it is indeed one of those places where the Americans and the British are separated by a common language.
    Robert Hahn
  • Intel is moving down the power curve a lot faster than arm is moving up

    the perf curve. Any switch to ARM at this point would be senseless. Intel will be at or below ARM power by the time you switch out hw and intel will still have it 20x perf advantage at that same power. I am really looking forward to intel replacing arm in the net wave of smartphone handset and tablet refreshes.
    Johnny Vegas
    • Perhaps.

      But you don't plan a data center on tomorrows chips. It would be very rare if you planned one on todays chips.

      I am in no doubt that trials are underway, a feasibility study, to see what is cost effective.

      You simply can't plan a data center on what chips may be available tomorrow, and especially not on the recommendations of a known Internet troll. No matter how valuable you consider your own opinion.
  • "Throwing Away Millions Of Years"

    Do you know what the "sunk-cost fallacy" is?
    • I wouldn't expect a reply.

      Some of the authors of these blogs tend to confuse consumer markets and business markets.

      They tend to let their own brand loyality cloud their judgement somewhat. As though this is going to have any bearing on the guy who signs the PO at Google/Facebook when it comes to the crunch.

      Can you imagine.

      "So why are we continuing to spend x amount on brand y, when we could have saved
      a amount with brand b and had no resulting loss of performance?"

      "Well, I read on ZDNet, that the author didn't like brand B."

      Just wouldn't wash, would it.

      By the way, you're absolutely right. But please, you're expecting too much from ZDNet and the people who comment here.
    • Sunk cost fallacy

      The point was not just the sunk costs (which I do understand but despite its flaws, it remains a potent force in most decision-making) but more importantly, the coding experience, knowledge and developer ecosystem that now exists around the x86 architecture. That's a lot of inertia...
      Manek Dubash
  • I would just like add.

    That a lot of comments on ZDNet seem to quite ridiculous with regards to specific brands. I have no idea what their intentions are to be quite frank.

    Perhaps in the consumer space, yes, there will be brand loyality.

    But in business, it would be hard pressed to go to the shareholders and explain you paid an additional x amount of millions because you used brand x rather than brand y, because you really really like brand x.