Catch up on stories from the past week (and beyond) at the Slashdot story archive


Forgot your password?
Operating Systems Software Microsoft Hardware

A .Net CPU 341

An anonymous reader writes "Windows for devices has an article about the .Net CPU. The chip is programmed with a subset of the CLR and runs the same software as the SPOT smart watches. Among other things, "[t]he computer module is implemented in the format of a 32-pin "DIP" (dual inline package) chip, allowing the module to conveniently plug into a standard 32-pin DIP socket. In addition, the ".netcpu CPU Module" integrates 4MB of nonvolatile Flash memory (interfaced via an SPI interface on the SoC). It also provides 24 general purpose digital I/O lines, which are multiplexed with other functions including 8 VTU ports, a USB port, two serial ports, and SPI and I2C interfaces." More information about the product can be found at the .netcpu company website."
This discussion has been archived. No new comments can be posted.

A .Net CPU

Comments Filter:
  • .Not a .NET CPU (Score:5, Informative)

    by Gopal.V ( 532678 ) on Tuesday December 14, 2004 @05:56AM (#11079959) Homepage Journal
    It is really just a CPU on which CLR runs , not a real .NET CPU in hardware. (or so the TFA seems to indicate from the diagram). Also of the more convenient peices of the ECMA 335 spec.

    It's an embedded chip which has a CLR on top of it. Nice idea, sorry that Sun thought of it earlier ( The Green Project []) - Sun seems to be consistently missing the BUS here. They came up with "Network is the computer" and now MS is selling ".NET " :)

    I've seen a couple of stack based engines but by its polymorphic nature .NET bytecode is not suitable for a direct CPU (you could do something like dynamic translation [] like the Crusoe chip had). But then it's still a JIT , right ? :)
    • by Gopal.V ( 532678 ) on Tuesday December 14, 2004 @07:09AM (#11080154) Homepage Journal
      Yeah, this is very much like ROM Basic [].

      Looks like this idea's been around for god knows how long ... So much for innovation, we seem to be going backwards here ?.

      This is a plug , but I've been working on a .NET CLR which can be trimmed down to around 400k (for a full opcode set, no less !!) for the last 3 years.
      • by antoy ( 665494 )
        That CLR of yours sounds very interesting. It will surely make packaging .net desktop applications easier and more convenient than including the the gigantic dotnetfx.exe with everything. How's it going? Anything we can see? Will it be a commercial product?
    • Re:.Not a .NET CPU (Score:2, Insightful)

      by Anonymous Coward
      the Jini's fall is solely based on cost. Why spend almost $100.00 for a single jini chipset for your devicewhile a regular embedded CPU costs $7.00 has more speed and can use established programming languages like C.

      the Java on a Chip Jini is a really cool device but it is horribly overpriced for what it is, when the Dev kit costs almost $300.00 and the Jini board it's self is $100.00 in single quantities nobody will touch it, and that is exactly what happened.

      if Microsoft wants this visual Basic chip to
    • Re:.Not a .NET CPU (Score:2, Interesting)

      by winfx ( 798360 )
      Polymorphic translates : easier to write compilers, harder to JIT it.

      Direct CPU mapping has the same difficulty as JVM bytecode, polymorphic instruction set is not a problem compared with the dynamic loading types, inlining, virtual calls, GC etc that the CPU architecture must solve
    • Sun wasn't first either. There's been a number of "LISP Machines", designed to run LISP efficiently, and there's been several microcontrollers designed with some of FORTH:s lower-level words as opcodes.

  • by rleyton ( 14248 ) on Tuesday December 14, 2004 @05:57AM (#11079960) Homepage
    They must be very small, but I think I can see them if I look really closely and squint a bit.
  • Parrot (Score:4, Informative)

    by hey ( 83763 ) on Tuesday December 14, 2004 @06:01AM (#11079972) Journal
    I'm waiting for a Parrot [] chip.
    Now that would be exciting.
  • by ezelkow1 ( 693205 ) on Tuesday December 14, 2004 @06:14AM (#11080020)
    this thing seems like an overpriced piece of junk just trying to hawk its .NET and VS support. Most of the microcontrollers out there i have seen can in some way or another be programmed in C and its various forms. 200 dollars just for the cpu seems to be asking a lot when the only advantage i see is that is 4mb of flash, and other MC's can always be expanded to that anyway. Besides the fact that other MC's out there that are cheaper also contain a whole lot more peripherals and features than this one. But maybe thats just me
    • Don't think of it as a product part, think of it more as a BASIC Stamp for people who want something more than a BASIC Stamp can manage.

      BASIC Stamps are good for when you only want to do one, and don't want to lay out a board with crystal, peripherals, etc. Although I have a tendency to do my own boards, I can see that BASIC Stamps are good for some projects.

    • that is because it's trying to become a "super" basic stamp.

      It's way overpriced and has no advantages over the microchip or Atmel offerings.

      io and ports are multiplexed. what moron engineer though that was a good idea? put it in a 40 pin DIP if you want to follow that legacy form factor or a QFP for regular use (please do NOT use BGA, BGA is from the devil!)

      I see this as a no starter. the .NET chip has a really hard time trying to get into a market that is dominated by HUGE companies with decades of h
  • Security ? (Score:2, Insightful)

    by Anonymous Coward
    What happens if someone discover a flaw in the CLR ?
    Do we have to buy another processor ? or flash another CLR ?

    Placing anything on a processor is a *pretty* stupid idea.
  • Gee I though Gumsticks were already mainstream... oh.. but of course []

    these thingys aren't from Redmond...

    dang it.. too late...

  • by Anonymous Coward
    Clippy turns you off.
    A drm hardware dream.
  • by david.given ( 6740 ) < minus author> on Tuesday December 14, 2004 @06:41AM (#11080091) Homepage Journal
    According to the products page on their website:
    • 384K of SRAM, single cycle access
    • 27 MHz ARM7TDMI
    • FBGA chip form
    • ~450,000 instructions per second
    • 4MB non volatile flash
    • 1.8-volt core, 3.3-volt I/O
    • 32768 Hz real-time clock
    • 32-pin pinout, including 24 GPIO ports multiplexed with other functions (8 VTU ports, dual serial ports, SPI, and USB port)
    • SPI and I2C interfaces

    I assume FBGA is a typo for FPGA. This thing sounds suspiciously similar to one of those standard FPGAs with a built-in ARM7 core.

    It actually sounds like quite a nice little embedded system, a kind of grown-up Basic STAMP []. I expect that the .net VM is in ROM; on start-up the FPGA is probably bootstrapped from it. I wonder if it would be possible to replace it with a real operating system?

    • by Pemdas ( 33265 ) * on Tuesday December 14, 2004 @06:57AM (#11080129) Journal
      I assume FBGA is a typo for FPGA.

      When referring to packaging, FBGA is usually Fine Ball Grid Array. I really doubt it's a typo. From the programmers point of view, the package virtually never significant.

      Overall, this sounds remarkably similar to picoJava [], which, last I checked, was going nowhere, and for good reason.

      Designing bytecode formats for VMs is not really the same as designing opcodes for microprocessors -- shoehorning hardware that way is painful and generally results in less elegant, more expensive designs.

      OTOH, the bytecodes in question aren't really significantly worse than, say, x86, and look where that is today...

    • 27 MHz ARM7TDMI, 450,000 instructions per second

      Wait a minute, does it spend _60_ clocks per instruction on average???

      (Yes, I understand that supposedly they are a bit higher level than even x86, but still....)
      • I expect that is .NET instructions per second, not ARM instructions per second.

        So yes, 60 clocks to perform one .NET instruction.

        Part of me thinks "Sod .NET, write in native ARM assembly and get something that is up to 60 times faster".

        0.45 MIPS is about as fast as a 4MHz 68000, or a 16MHz Z80 variant. And there are a lot more embedded programmers who knows these, and ARM, than .NET. And they are perfectly happy not using Visual Studio. All this hardware will do is bring Visual Studio weenie programming
      • Maybe it's 450,000 .NET opcodes per second. 60 instructions per opcode would be pretty good, actually.
    • 27 MHz ARM7TDMI

      The .NET Compact Framework crawls on a 400MHz ARM9 chip. What sort of applications are they intending this thing to be used for?

  • Where is the hardware-implemented JVM we've been promised for years and years? Not like this gloified BASIC stamp, running an implementation on the .NET runtime in software, but a real hardware implementation that runs bytecode natively.
  • by nathanh ( 1214 ) on Tuesday December 14, 2004 @06:46AM (#11080099) Homepage

    Isn't this exactly like the Java CPU that Sun was selling a few years back? And it was simply a close relative of the Lisp processors from the 80s.

    C#, Java. .Net, J2EE. CLR, JVM. .NET CPU, Java CPU. So should we expect Microsoft to simply repeat everything that Sun did with Java? If so, wake me up when they declare they're going to release CLR under an open source license.

  • by quigonn ( 80360 ) on Tuesday December 14, 2004 @06:48AM (#11080105) Homepage This piece of hardware is tres cool, as it implements the _complete_ set of Brainf*ck instructions as native instruction set.
  • Is it OK for them to use the '.NET' in the CPU name instead of ILCPU or ECMAwhatCPU?

    In addition, their 4-color windows symbol resembles the Windows symbol just too much.
  • Ahnetkpuh? (Score:4, Funny)

    by martin-boundary ( 547041 ) on Tuesday December 14, 2004 @06:59AM (#11080135)
    Ahnetkpu? Is this an Elder God?
  • That's funny (Score:5, Interesting)

    by le_defaut_tragique ( 653169 ) <tragic.flaw@mac.cHORSEom minus herbivore> on Tuesday December 14, 2004 @07:14AM (#11080173)
    Check out the company website, and Google them. I just did and it turns up that this company was founded on Oct10.2k4ce by Mark Phillips. A Google turned up... the company website, the original submission, and a couple other press releases. this is their only product, and they made it in two months.

    Microsoft's only connection with them is that Mark Phillips guy, who, when googled investigatively, appears to have founded A Dot Corporation in Apr.2k3ce and they were involved in... SPOT Watch technology and claim microsoft to be a business partner (

    So is Mark Phillips using his work with microsoft's SPOT developer team to create something to market under a different name? Both companies list only Mark Phillips as founder and, in fact, confirmed employee, although one site listed A Dot as having 24 employees.

    Yeah, so that's funny...
  • by linebackn ( 131821 ) on Tuesday December 14, 2004 @07:20AM (#11080183)
    It boggles my mind, every time someone comes out with a bytecoded language in order to attempt to achieve hardware independence, someone comes along and creates hardware to execute it! Thus defeating the original purpose.

    Of course people see the need for hardware acceleration because interpreted or even JIT compiled bytecode languages are always going to be slower than precompiled native binaries.
    • Running bytecode will always be somewhat slower than native binary, but Sun has done a good job of getting most of the overhead out of the running code and into the VM startup. Most overhead people experience now with Java isn't from the VM at all but from the constraints Sun puts on the Java language specification (exs. ALL arrays must be bounds-checked, dynamically allocated memory must be garbage collected). C,C++,BASIC,etc. do not have these requirements built into their language specification and the
  • Where's my Java chip? They promised us cheap, safe little Java chips, with embedded DSPs and ethernet. I want one in my phone!
  • This would be more accurate then calling it a .Net cpu...

    Dont expect to see these in a general use pc anytime soon ( if at all )..

    There are several 'dedicated language' chips out there, like for java and forth.. but none really catch on outside their little niche markets..

    They may be neat, but not too practical.
  • They weren't single chip (single board), but they did take bytecodes (and sometimes source code) over a bus and execute them. Sometimes it was BASIC, and sometimes it was PICK assembler, etc.

    If this puppy ran bytecodes for a simple BASIC (Which I am sure could be arranged...) then it would be very close to the old MAI Basic-4 minis, which did this on a single(8x12) circuit card.

    Makes me feel sort of, uhm, nostalgic...

Man is an animal that makes bargains: no other animal does this-- no dog exchanges bones with another. -- Adam Smith