ARM targets Intel with 2GHz multicore chips

ARM targets Intel with 2GHz multicore chips

Summary: ARM announced the development of dual-core, quad-core and eight-core Cortex-A9 processor designs explicitly aimed at markets currently served by Intel's x86 chips and IBM's PowerPC.

UK-based chip company ARM has today announced the development of dual-core, quad-core and eight-core Cortex-A9 processor designs, explicitly aimed at markets currently served by Intel's x86 chips and IBM's PowerPC.

"This is a huge departure from what we've done in the past", Eric Schorn, vice president, marketing for ARM's processor division, told ZDNet UK. "We really wanted to take off the handcuffs and see what could be done with performance, performance, performance."

The new designs, available in two variants optimized for low power consumption or high performance, are intended for use by companies building their own chips. ARM claims that the new processors, which can run at up to 2GHz, are up to eight times more efficient than Intel's low-power chips in terms of performance per watt, with the high performance part running at five times the throughput of Intel's Atom chip for similar power levels.

The low-power part delivers twice the performance at a quarter the power, according to the company's published benchmarks.

"The sweet spot for most customers is dual-core," said Schorn, "but the base design can go up to quad-core and some partners are already building those. Eight way is coming. Everyone's high-end roadmap is putting down more cores, and we do that. We're headed in the direction of Intel's mainstream processors. We have other plans that surpass the current performance, and we'll intercept Intel in a high-margin area, not just with Atom."

The dual-core parts, which are designed to be made using fabrication company TSMC's 40nm chip manufacturing process, can be licensed now with delivery of the finished designs to partners in the fourth quarter of 2009. ARM itself will be making evaluation chips available to partners and software designers in the first quarter of 2010.

To date, ARM has mostly partnered with companies making components for wireless, consumer and automotive equipment. However, this new design will see new enterprise partners coming on-board. In particular, Schorn said that the high-performance multi-core ARM approach would open up parts of the market currently dominated by companies with large proprietary design teams — "blowing the doors off that by offering freely available IP", as he put it.

"Enterprise is a key opportunity", continued Schorn. "Our existing partners are executing extremely well in their existing markets. We have a new license signed, with a number in the pipeline, and enterprise is well represented. The design is applicable to all sorts of servers, is cache-coherent so can do SMP, and will be wonderful for Linux, Apache and other parts of the enterprise stack".

ARM announced on September 14 that it had joined the Linux Foundation.

ARM also intends the multicore Cortex-A9 design to be used in consumer equipment. "If you look at the high end of embedded systems, netbooks and the like, there's not much innovation relative to the mobile phone area. We want to take the rate of change of mobile phone design and innovation into other areas. Consumers will see a lot more diversity at a lot faster pace," said Schorn.

The company says it gets its claimed level of performance at low power by having very finely tuned control over the different areas of the chip, with seven power zones able to turn off parts of the cache, maths, media and general processing areas automatically when idle.

Schorn said that he was not concerned by ARM's lack of Windows 7 compatibility. "We don't have a Big Windows announcement to make. We do have staff at Redmond, and we'll see what the future will hold. Talking about Windows is the wrong way of looking at it.

"If you look at what's happening with web-centric, internet-oriented demographics and things like Java virtual machines, just-in-time compilers, widgets and so on, it's not architecturally dependent. Look at Samsung with Yahoo widgets in its televisions. I don't see the need for Big Windows on your television."

This article was originally posted on ZDNet UK.

Topics: CXO, Hardware, Intel, Networking, Processors, IT Employment

Rupert Goodwins

About Rupert Goodwins

Rupert started off as a nerdy lad expecting to be an electronics engineer, but having tried it for a while discovered that journalism was more fun. He ended up on PC Magazine in the early '90s, before that evolved into ZDNet UK - and Rupert evolved with them into an online journalist.

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
  • Great platform for next-gen OS development

    This sounds like it would be a great platform for somebody to develop the next generation OS we so badly need as a replacement for all of the existing 20th century OSes we're currently using.
  • Still primitive - OS has a long way to go

    I use the NT CPU affinity tool to assign programs to cores to boost performance of multimedia processes, but there is a long way to go.

    8 cores is great, but 8 dynamically re-taskable cores would be a real step forward.

    Imagine that the OS needs more GPU capacity to run a game and assigns 3 of the 8 cores to work in parallel to increase graphics capability.

    In another example, you want to burn a DVD. The OS assigns a core to that task to isolate it from other tasks and prevent the burn operation from failing. In conjunction, a HAL gives that core priority access to the required hardware I/O subsystems.

    All automatically. Just point, click, and the OS automatically configures things as needed.

    This light years ahead of any consumer operating system. It seems like we have treads running willy nilly on whatever core, without any overriding strategy.

    And while there is process priority and thread priority, there is not good core management.
    • Definitely - need new OS geared for new age

      Patching up all of our 20th century OSes to take advantage of the future MANY-core CPUs is just a bad idea. We really need a 21st century OS designed from the start to use a massive number of cores. The hardware is so far ahead of the operating systems at this point that they couldn't possibly catch up. I say start over from scratch and design something bullet proof from the ground up. It's long overdue.
      • Oddly enough...

        Google have announced their OS is going to run on ARM. Which is intriguing in that they don't have to worry about years of legacy that much as do Microsoft, Apple, and the *nix's. And they are probably better positioned because of their entry time to do a better job of multi-core and GPU support.

        And as a side note, that could be very cool for Linux if they GPL their work for ARM and multi-core, with it seeming likely that their OS is going to have Linux underpinnings to it.
      • hahahaha need new os

        So funny, ever heard of linux? Safety-wise its
        running in condom of root account. Windoze has
        much to learn from it. Btw do You still need to
        run external software firewall, antimalware,
        antivirus, browser security component, lan securer
        and all other crap which is not required on first
        class oses? And wonder where does Your battery
        capacity go within all that crap crippling Your
    • Definately dont need a new OS at this point

      Today's OS's can use 256 cores very well. We're still a few years out from seeing standard desktop/laptop/netbook/phones with 256 cores (not counting a gpu with say 64 dedicated cores). And in the server space while there's a number of options for 128/256 core machines most datacenter designers have decided that 256 is enough of cores for a single point of failure and it's better to scale out than scale up past that, at least until a 256 core box costs about what a 4 core does now...

      It's the apps that need to be better at spreading their work out in a parallel way. There are all kinds of core affinity and priority and syncronization mechanisms for them to use to do it. Why would a media transcoder app for example be geared to about 8 cores for some inexplicable reason? Not sure where your dvd burning example was going, that's all io bound and takes only a small fraction of a single core...
      Johnny Vegas
      • Example

        The DVD example wasn't good, but where I was going with that is that the OS manages threads, not cores, and sometimes it is useful to purposely corral a parent process and all it's associated threads on a dedicated core until the job is complete (or more exactly, reserve a core for the exclusive use of a process and it's associated threads).

        On my system I frequently run Halflife2 in a window, have a TV tuner window open, MSN messenger, and I might be buring a dvd or something in the background. The system runs poorly with NT's default process management. I get best perfomance by assigning Halflife to one core, and the TV tuner to another. Everything else more or less lands on the two remaining cores.

        Why can't the OS automatically:

        1) Figure out a combination of processes are highly CPU intensive

        2) Each individual process does not exceed the processing capability of a particular core

        3) Segregate the processes and associated treads onto dedicated cores if available


        • No need to segregate processes based on cores. Give them CPU time, which

          could be any fraction of a single core, or more
          than a core.
        • Not a new idea..

          This is not a new idea. I know of at least one (mainframe!) OS from 35 [b]years[/b] ago which accomplishes this feat by measuring the CPU utilisation of a process each time it runs (subject to timeslice/resource requirements etc.). This is used to determine the current (dynamic) 'load' on a CPU. New processes are scheduled to the CPU with the lowest 'load', thus distributing processes 'away' from busy CPUs. All done automatically...!
          • interesting

            this is very interesting. It would be a much more
            efficient way of running computers.
  • From the sounds of the announcment ...

    Arm may be positioning itself for Linux to do the heavy OS lifting.
  • Netbook will be the next killer product after Mobile Phone

    Kindtao announced netbook 100% full size keyboard,
    CPU is intel or ARM or VIA, OS is microsoft or google or linux, they all runs inside, keyboard are people use direct.
    Kindtao keyboard can make netbook sell over 300 million a year.
    please see

    After computer invention, CPU,OS,Hard Disk,Memory, all change and change,up and up, but keyboard never change. It's time to change keyboard!!
    • Non-Standard keyboard?

      Good luck re-training the worlds touch typists! I'm only slightly beyond 2 finger and those would drive me nuts! My sons on the other hand are touch typists and refuse to use the smaller size keyboards since they can not type at normal speed on them, and don't care to take the time to learn!!
      • Standard QWERTY keyboard, and new ABCD keyboard

        It's Standard QWERTY keyboard have 100% full-size, and New ABCD keyboard for new PC user.
        Please see
  • RE: ARM targets Intel with 2GHz multicore chips

    Not being a Linux Guru, just an Ubuntu user! I am pretty sure that Ubuntu is running on ARM processors right now, and the Os is multi-core capable, though a lot of the applications could be written better to take advantage of this feature of the OS!!
  • RE: ARM targets Intel with 2GHz multicore chips

    Shorn said "Look at Samsung with Yahoo widgets in its televisions. I don't see the need for Big Windows on your television."

    He'll be eating those words in a few years!