Experiment 19: The back story of Microsoft's work to bring NT core to ARM

Experiment 19: The back story of Microsoft's work to bring NT core to ARM

Summary: A new Microsoft Research page acknowledges efforts dating back to 2008 to move the Windows NT core to ARM, which ended up impacting both Windows RT and Windows Phone 8.

SHARE:
TOPICS: ARM, Mobile OS, Windows
13

Back in 2010, I wrote a bit about a Microsoft Research mobile project called Menlo. Part of that project involved a skunkworks team effort known as Experiment 19.

experiment19

At that time, my sources told me that "Menlo" was a hush-hush research project which seems to be focused on replacing Windows CE/Windows Embedded Compact with Windows NT inside of mobile devices. "Experiment 19," my contacts said, was a graphics platform of some kind that researchers were building to complement Menlo.

As "Felix9" noted over in the Microsoft Channel 9 Coffee House forum on July 13, the Experiment 19 team has finally gone public. And members of that team are now admitting to have helped "prove... that Windows NT and the CLR (Common Language Runtime) could deliver better performance than Windows CE and the .NET Compact Framework on identical hardware."

"Within months of the completion of Experiment 19, Microsoft launched efforts to build what would become Windows Phone 8 and Windows RT for ARM tablets," according to the updated Experiment 19 profile on Microsoft Research site.

This was a bigger and more encompassing project than I had heard. More from the team:

"We started from a Windows core (called MinWin) and a port of the Windows NT kernel to the ARM processor. Working closely with MinWin pioneers—Adam Glass, Mark Russinovich, Richard Pletcher, Richard Neves and Bryce Cogswell—and with partners at NVIDIA (My aside: there's the graphics platform piece of the project), we created the device drivers and firmware necessary to boot and run MinWin on our prototype phones. We created an ARM JIT (just-in-time) compiler for the CLR and ported the CLR runtime to ARM (Another aside by me: Redhawk-related?)  To complete the system, we ported the phone implementation of Silverlight to run with our ARM implementation of the CLR."

The Experiment 19 team is echoing the message of the Windows Phone team, which claimed Microsoft decided to replace the Compact Embedded guts of Windows Phone with the NT core because the NT core would work better on the new multicore processors available today and in the future.

I've heard some Windows Embedded backers disagree with this contention, but that's what the official party line is here. And as @DrPizza, a k a Peter Bright with Ars Technica, notes, low-end Windows Phone hardware may not be Windows NT-kernel-compatible. There has been talk that Windows Phone OS 7.8, built on the existing Embedded Compact kernel, will continue to be the only OS available on lower-end Windows Phones. Microsoft officials are not commenting on that rumor. (I've asked.)

If you want to check out the Experiment 19 team's demo of Windows Embedd Compact vs. Windows NT core performance on phone prototypes, there's a video clip (dating back to 2009) that's also available for viewing as of this week. The new Menlo page on the Microsoft Research site also mentions Little Rock, a low-power sensing project inside MSR.  Blogger Manan Kakkar recently unearthed lots of  Little Rock details.

Update: As one of my readers privately reminded me, the timing on this Experiment 19 work also feeds in with reports of Microsoft's work to port Vista to ARM, in a project codenamed LongARM.

Topics: ARM, Mobile OS, Windows

About

Mary Jo has covered the tech industry for 30 years for a variety of publications and Web sites, and is a frequent guest on radio, TV and podcasts, speaking about all things Microsoft-related. She is the author of Microsoft 2.0: How Microsoft plans to stay relevant in the post-Gates era (John Wiley & Sons, 2008).

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

Talkback

13 comments
Log in or register to join the discussion
  • If they could run minwin and clr on a 600Mhz tegra with 256M ram they could

    certainly run it on todays low end phones. They said it ran better than CE/.netCF even on the low end hw. They shouldnt need CE/.net CF for even the low end WP's that came out almost 2 years ago. I hope the new WP8 hw also leverages from little rock
    Johnny Vegas
    • What you're forgetting...

      Is that under a manufacturers warranty, theres no way to remove the firmware and reformat the handset totally on WP7 without returning it to the manufacturer for that to be done.

      Its all well and good to say that they 'could' do it - but realistically once the handset is in the wild with the consumer, theres no way they can effectively recall the handset to supplier for update without doing damage to the brand.
      Master_T[RG]
    • ^_^

      I am a single biker woman. My friend told me about___seekingbikers.com___she told me it is the best place for bikers to find Friendship, Love, and Romance! I have tried, it is fantastic, hundreds of thousands of hot biker men and biker babes are there. Come in and give it a shot, you will find your biker match to share the passion for motorbikes! :)
      ChristinaSpears
    • @johnny

      There is a HUGE difference between proving that a series of benchmarks can run faster on platform X than platform Y and naturally shipping a comprehensive, secure, flexible, serviceable software platform.

      Early ARM devices, for example, didn't provide good support for various kernel level hardware features such as multi level TLB, cache coherency mechanisms and other memory management and processor/thread sync issues.
      bitcrazed
      • @bitcrazed

        multi level TLB, cache coherency prevented Microsoft in porting WP8 to legacy hardware. Gen 1 WP7 phones are not ready for this, IMO. Otherwise MSFT wouldn't have planned for Win7.8 for the WP7 phones. They would have gone for WP8 straight.
        Ram U
  • I don't get it...

    why would anyone invest corporate resources developing for anything but the iPad/iPhone? The vast majority of SALES happens there, so I'd love to see the rationale to split efforts to useless endeavors. It's gonna be a whopper of a tall tale!
    Tony Burzio
    • And Android

      Don't forget Android.

      That said, Windows is a massive sales cow for Microsoft. It makes sense for Microsoft to do this and long term could very well help Windows Phone app support, then therefore user uptake.

      It's gonna be rocky at first. There are very little Windows Metro apps (for Windows RT) and there are zero Windows Phone 8 apps. In the short term, I can see Windows Phone developers still coding for the Windows Phone 7.x (WinCE) code base.
      bradavon
    • One ring to rule them all?

      You could just as easily ask why anyone would bother developing for anything but Windows on the desktop. In which case Apple would have died a long time ago and there would never have been any iOS devices. Likewise for Linux and derivatives like Android.

      Some people are content to go with the 800 pound gorilla and others have a need to stake their own ground. Having everybody go one way or the other would get boring very fast.
      epobirs
  • Wow, Such A Big Deal

    Windows NT originally started out as multi-architecture in the early 1990s, didn't it, with implementations (albeit 32-bit-only) available for Alpha, PowerPC and Itanium. But all of these failed to garner any momentum, leaving it as an x86-only system. Shame to see none of that old multi-architecture support has surived into the modern era, with this epic struggle to get it running on a simple little ARM chip.

    Meanwhile, another OS that is about as old is currently running on about 2 dozen different processor architectures, including not just ARM but also those MIPS chips coming out of China (which will also blindside Microsoft and Intel just when they think they've got a handle on this ARM menace). And it has had full native 64-bit capability since about 1994, and multiprocessor support since not long after that.

    I'm talking, of course, about Linux. Which is the power behind Android. If you look at the current Android SDK, you will it already has support for generating native code for ARM, x86 and MIPS.
    ldo17
    • Commercial vs. Open-Source

      Don't forget that Windows is a commercial OS implementation. Therefore, it's no wonder that x86 had become the only supported architecture over the years, simply because there was no market for other architectures in the areas where Microsoft is big (business, for example). Now that changed for ARM, because of the growing demand for such devices. Itanium? It was dropped because its complexity and lack of native 32-bit backward-compatibility (which x64 delivers). No one's going to miss that, so why support a "dead" platform? Alpha was dropped on Windows 2000 because Compaq canceled support for Windows NT, as far as I remember.

      Linux might be superior in the number of architectures it supports, but the truth is that most of these architectures are very specialized and have a nice existence.
      sevenacids
  • Experiment 19: The back story of Microsoft's work to bring NT core to ARM

    @Tony Burzio
    "why would anyone invest corporate resources developing for anything but the iPad/iPhone? ..."
    the us economy is not as big as it is now had u.s. corporations stop innovating just because of one product that sells well. and whether you believe it or not, it will take just one generation to ditch the us to the dustbin of history if corporations heed your advice to not invest in anything but your beloved iPad/iPhone. nokia went down in less than a year from the number one post, and relegated to a has been because they stop believing in their own capability of innovating their product line and instead embraced someone else's innovation...
    kc63092
  • TRUTH:

    Mary Jo is the best columnist of any of these wannabees!
    Great story!

    ZuneResurection.blogspot.com
    Ballmerfeld
  • That's a statement too far surely???

    Surely even the most devout Apple devotee cannot believe that the igadgets have come so far as you suggest? Great consumer devices but so are many others an I would hate to see one company own a whole market.

    Me on my corporate ipad, pass word protected, needing secure apps once I get in, and more passwords. They dont talk to each other, I cant take notes and email them. Thats no use for the enterprise but hey-ho that's what I've got. Then there's you telling me this is Nirvana... Trust me it aint and I'll gladly try anything without Appple lock in. That's why I use an Asus Transformer myself despite having an ipad. I can plop media in as I want, and I can use my mouse/keyboard to connect to the enterprise via citrix now.

    It's still got a lot of work to do in many areas but this works for me. If only some folk would stop branding the iPad as all embracing... it most certainly is not.
    johnmckay