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

 



Forgot your password?
typodupeerror
Check out the new SourceForge HTML5 internet speed test! No Flash necessary and runs on all devices. ×
Intel

Intel Unveils New StrongARMs 95

mirko writes "Supported by the Epoc, Windows CE, RiscOS and VxWorks, the StrongARM RISC processor, which features power, low-consumption and high-frequency, could bring lots to the wireless market. This article and this other article describe Intel's new XScale micro-architecture that will be used in the forthcoming 1GHz StrongARMs."
This discussion has been archived. No new comments can be posted.

Intel Unveils New StrongARMs

Comments Filter:

  • .. you could get some rest!

    Somebody port NetBSD to these babies! Quick! =)
  • They can barely get there 1 Ghz out the door, there 1.13 Ghz seems to have lots of stability problems, and there going to try and market this? Come on, get the stuff you are already selling to work correctly and produce it in suffient volume for demand; then start annoncing other stuff. Q. Who in there right mind anounces new stuff when they can't handle their current orders. A. Marketing people for starters.
  • sounds nice, but will it be another intel flop? -TubaMan
  • by mirko ( 198274 ) on Friday August 25, 2000 @02:08AM (#828662) Journal
    Errrmmm...
    Done. [netbsd.org].
    BTW it was damn fast with a 202MHz SA on a RiscPC, even despite its lack of FPU.

    --
  • ...PalmStation [palmstation.com] posted this article about Palm's future with the XScale technology [cnet.com]... According to the article, "The XScale architecture offers performance roughly 20 times the Dragonball and uses less power..."

    Maybe this will be foundation for PalmOS 4...
    -J
  • Here [cnet.com] is another article talking about Palm's interests in these new chips. I must say that I, a PalmOS PDA owner, am very interested in the possibility of jumping from a 16MHz dragonball to a 1GHz StrongARM!
  • Sure it sounds nice... Doens't all new tech ?
    But seriously, have anyone considered that these are RISC processors ? Do they (Intel) plan to abandon their CISC processors for the private user ? Or is this simply Intel's way of saying "we want a bigger piece of the Business pie"
    I certainly think the latter is true. I seriously doubt that we could get along without the CISC, it would just cause to much incompatability, or the translation matrix would make the apparent speed increase gained from the CISC->RISC insignificant. This has no bearing on "us" the private users as I see it.

  • Nope, all you need is EPOC.
    It's _rock_ solid, runs on the Psion. I've had my Psion for 2 years, and it has _never_ crashed. Nope, that's _never_.
    Why is it that everyone is trying to push this wireless crap at us all the time? Look at the amount of cash invested into WAP over here in the UK; and how many people are using it?
    Until we get _fast_ wireless protocols rolled out live, these toys will remain underused.

    Strong data typing is for those with weak minds.

  • Also covered in/on:

    More detail on the StrongARM range can be found on ARM's [arm.com] website.

    Richy C. [beebware.com]
    --
  • Heheheh just wait until the first consumer devices roll out with BOPS DSP Core [bops.com] in an ARM processor. That will truely be /. worthy. Amazing the popular tech press hasn't been all over this story considering these are leaps and bounds ahead of current DSP technology, but it is not vaporware as there is working silicon!
  • Despite the feeling of euphoria that accompanies a first post (I have felt it many times myself), remember the groundwork laid by the trolls who came before you. If you get the chance, pour out a little malt liquor to pay tribute to the fallen comrades among us.

    ..................................
  • More detail on the StrongARM range can be found on ARM's website.
    *Now* I'm sure what the chips are used for - I thought they were just in the RiscPC computers. Cheers for the information - I've now just got to find out how to buy a NetWinder...
  • by kyz ( 225372 ) on Friday August 25, 2000 @02:14AM (#828671) Homepage
    The second article says "built using Intel's StrongARM technology". Surely they mean Advanced RISC Machines Ltd [arm.com]'s StrongARM technology [arm.com], which Intel did nothing but pay some money for.
  • Palm users must think alike; I posted the same thing at probably the exact same time! ;)
    I have to agree with you. Not so much for the hopes of things like video (if I want that, I'll watch TV!), but for the hopes of better battery resilience. I am constantly annoyed at how five or ten minute sessions of a game like Reptoids drains by batteries by about 10%. I don't want be able to do anything significantly more complex on my palm. I want to do what I do now, but for longer.
    -J
  • by core ( 3330 ) on Friday August 25, 2000 @02:22AM (#828673) Homepage
    I guess the editor is probably not aware that arm processors already run a lot of deeply embedded applications. For instance, the soundchip of the dreamcast, or most cellphones. They have a 60% market share for the comms market I think. I am currently working with such a platform (lowlevel system work, and trying to fix issues in gcc as well when I can), and I must say it makes a lot of sense from a design point of view. Highest code density (especially in Thumb mode) of all 32-bit CPUs, quite efficient, and very low power consumption. No wonder it's used all over the place.
  • Actually the StrongARM was designed by Digital, independently of the main ARM processors line.
  • IIRC Digital (who originally made the StrongARM with ARM) contributed a very very significant part of its design. It's based on the main ARM design core, but with Digital's 'optimization' to increase its speed with the use of it's two caches and various other enhancements.
    Intel brought the Digital Semiconductor section and have been enhancing the SA ever since.
    I'm still happy with my 5yr old 202Mhz RISC PC though - it still goes faster than this 1mnth old 400Mhz Compaq Deskpro...
    Richy C. [beebware.com]
    --
  • by gmm ( 218993 )

    Never mind the $3 crack. This moderator has to be totally off his face on acid!

    Knees (Score:1, Insightful)

    sorry (Score:1, Informative)
  • Ah, I remember the ARM Assembler. That was real work of art! Then I got exposed to x86 assembler. The horrors! If you want to learn assembler, to it the right way, and get an ARM.
  • The only reason they keep their main line CISC is because the demands placed on them by Microsoft for backward compatability.

    In fact, if you look at one of Ars Technicas rather good articles, you'll notice that from the Pentium 2 onward, they've gutted the core of the Processor, and the core is RISC. All the CISC functions are broken down in microcode.

    Thus, a RISC processor, the ARM series, which has been used for a while ( this is just Intel's ARM processor...) isn't too odd.

    With the G4 being similar to the P2+ in architecture, ( eg not RISC vs CISC .. its more like hybrid vs hybrid ) chances are the ARM is ment as nothing but a powerful, but low power mobile chip.

    --DanteAliegri

  • by Anonymous Coward
    I'm not sure who told you that RiscOS would support it immediately, but I don't think that is the case at all. The problem is that RiscOS still runs in the 24 bit mode of the very early ARM processors, while the next generation of ARM will no longer support 24 bit emulation. RiscOS Ltd have been talking about supporting 32 bit for a year or two, but as far as I know nobody is actually working on it as they don't have the resources. Perhaps if they Open Sourced their OS they would have more than a couple of developers, but that doesn't seem too likely as the RiscOS world is very deeply entrenched in the world of closed source.
  • what does this mean for the much-hyped Transmeta chips?

    undoubtably, these StrongARM chips are Transmeta's biggest competition. Why would serious competitors in the info appliance market choose Transmeta's unproven chips instead of the market leader Intel's fast and proven chips?
  • You can't compare the Pentium to the new SA - the die is many, many times smaller on the SA which means the yields will be much better.

    It should also be a lot cheaper, but it won't be as fast as a PIII at 1Ghz.

    Still, it *will* give the Transmeta stuff a run for its money - 1GHz at 1.5W is pretty good, and SA's run linux very nicely (as empeg owners, netwinder owners, and iPaq owners know)

    Hugo
  • by tjwhaynes ( 114792 ) on Friday August 25, 2000 @03:06AM (#828682)

    Sure it sounds nice... Doens't all new tech ?

    It definitely sounds nice ... I can already see the river of drool coming from people who own Risc PCs (I almost refuse to call them Acorns since Acorn sold out their workstation division but I digress).

    But seriously, have anyone considered that these are RISC processors ? Do they (Intel) plan to abandon their CISC processors for the private user ? Or is this simply Intel's way of saying "we want a bigger piece of the Business pie". I certainly think the latter is true. I seriously doubt that we could get along without the CISC, it would just cause to much incompatability, or the translation matrix would make the apparent speed increase gained from the CISC->RISC insignificant. This has no bearing on "us" the private users as I see it.

    I think a small history lesson is in order. The ARM architecture is not a 'new' architecture - it dates back to the mid-eighties when Acorn, having decided to skip the 16bit generation, started working on a RISC 32bit processor. In 1987, the first Acorn Archimedes was born, running Arthur OS - a fairly primitive but useable GUI and OS. This was running an ARM 2 processor at 8MHz.

    Later revisions took the processor design to ARM3 with improve level 1 cache. Note these machines had no level 2 cache - as clock speed increased, this would have throttled a x86 style processor, but the ARM has fairly light memory usage as it has 13 general purpose registers, a fairly orthogonal (and small) instruction set and a load/store architecture minimising the need to go to memory for information.

    Then came the ARM6 and 7 cores which took speeds up to 40MHz. At this point the ARM chips were running market leading MIPS/watt ratings - no ARM machine I have ever had has needed a heat sink - but the clock speed was starting to lag the x86 line badly. After a joint project with Digital, the StrongARM was born, screaming along at 200MHz way before the Pentiums got there, and running at less than 1W. By this time ARM Ltd had been born out of Acorn to pursue its chip dreams - but not fabrication of chips. ARM Ltd is a purely design-orientated chip creator - other partners actually build these processors. A quick trip to the ARM website will quickly show you just how widespread the ARM processor line has become - ubiquity is an almost acheived goal :-)

    But just as the ARM 7's had topped out around 40MHz for a while, the 200 MHz (sometimes oc'd to 287MHz) StrongARM has remained the fastest ARM chip for a good while. During this time, DIgital got into a patent/IP dispute with Intel and ended up having to sell the StrongARM team to Intel as part of the settlement. So this is the first news of a faster ARM processor for several years - I got my 200MHz RiscPC workstation a few years ago and it blew my socks off with it's slick performance. RiscOS which is the oft preferred OS for this processor when it is used in a workstation (rather than a PDA, router, or other electronic utility) is pretty quick, and a 5x boost will be fairly insane :-) And naturally there is a port of Linux for the ARM processor (but here on Slashdot we expect nothing less).

    I just regret that my RiscPC is back in the UK and I'm here in Canada with an x86. :-( Still it would almost certainly require a motherboard upgrade ...

    Cheers,

    Toby Haynes

  • The wizzy feature that this "new microarchitecture" has seems to be no cleverer than the power/performance management which AMD already have in their chips.
    It seems as if the processor (rather than PM) architecture is unchanged from the ARM core, yet they've puffed themselves up in their press release to make it sound as if the whole thing is new and improved.

    Oooh, look at the price of Durons, must buy one some time...

    FatPhil
  • Actually 26 bits (not 24), with the remaining bits of PC used as processor status flags (that allowed for saving them as the same time as going into subroutines.. quite smart). But indeed, this is gone from ARM6 and above.
  • Indeed, just something like (in thumb) :

    push {r4,r5,lr}
    ...
    blah
    ...
    pop {r4,r5,pc}

    is more elegant than:

    push ebx
    push esi
    ...
    pop esi
    pop ebx
    ret

    :)
  • No need to port Linux, the article says:

    The Intel XScale microarchitecture will be supported by various operating systems, including Microsoft Windows CE*, VXWorks* and IxWorks* from WindRiver, EPOC* from Symbian and Embedded Linux* from multiple vendors.
  • by morgus morphus ( 175508 ) on Friday August 25, 2000 @03:14AM (#828687)
    There is quite a lot of information on Intels website [intel.com].
    But first I should mention that there is a port of Linux: ArmLinux [linux.org]
    The BSD one seems to be delayed [freebsd.org].
    Now, to the technical stuff.
    According to Intels site, they have added power management features to the chip that allow the clock speed to be adjusted from software. Yes, this is similar to Cruesoe, but it seems like they have taken the concept even further, allowing one to go from 0 (standby) to 1000MHz. Not bad.
    They have also added a few DSP functions for multimedia applications. Further details:
    • 7/8 stage superpiplined core
    • 32KB Instruction, 32KB Data Caches.
    • 2KB Mini-Data Cache to avoid data cache thrashing
    • Performance Monitoring Unit (Like on PII and up)
  • by Anonymous Coward
    I dunno what all the hubub is about. These days, the strongarm is mostly used in embedded apps. For example, the Mylex ExtremeRAID cards use them and they apparently do the RAID 5 parity calculations quite quickly. If one were to quadruple the performance of the chip doing those calculations, we could end up with (finally) RAID 5 arrays that are fast enough to do meaningful work on AV projects. Cheers,
  • There's no point in using the transmeta chips, unless you want to run plain desktop Windows. The crusoe is quite an interesting piece of technology per se, but it's really designed for Windows. If your mobile system is ran by a portable OS (Linux, VxWorks, now QNX RTP..) you just recompile/adapt the code for the CPU most adapted to your goals, like the ARM. No need for expensive emulations layers there.
  • Great summary.
    Whilst device penetration is huge, and ARM-powered machines from thousands of vendors, the other impressive thing is the range of licencing partners ARM have had. It's not just Digital (thence Intel), they've been in bed with other huge uP and DSP companies. For instance they had a cut-down ARM called Thumb, which was used as the master processor on things such as the Texas Instruments 7000/AV processor family - a tru multimedia chip which included several DSPs on one slab of silicon. TI could do _anything_ they want in-house - but no, they knew they'd not be able to improve on the off-the-shelf ARM core. Impressive.

    FatPhil
  • Don't worry. x86 assembler is just a cruel practical joke.

    It might have been pretty standard in the early 1980s, but it beggars belief that it still persists in a largely unchanged form.

    And all those instructions that only work with a particular register - that's not a primitive design which no one bothered to extend, that's just to encourage ingenious register swapping techniques to make your programming more fun.

    Plus, 90% of the instructions are completely useless, so ignore them, and you got a reduced instruction set computer right away.

  • Intel has always made a wide variety of microprocessors, not all of them being x86 compatible. They have the MCS-51 series 8-bit microcontrollers. They have the i860 RISC line.

    They have a large R&D budget for x86 compatible development, since that is a large part of their revenue, but that doesn't mean that is all they know how to do. Neither does it mean that they won't spend money developing an incompatible product line if there is money to be made from it.

    As others have written, this new product is the latest development in a product line that Intel bought a few years ago from Advanced RISC Microdevices, (with some fabrication plants they bought from Digital.) These products are geared towards a high MIPS/milliwatt ratio, so they have often been used in portable devices (ie PDAs like the Psion, the Apple Newton Messagepad, etc.)

    So no, Intel doesn't expect you to throw away your x86 based desktop for a ARM RISC box. It would be a poor use for the technology. (For a desktop, you have plenty of power, and you can disipate a lot of heat. The perfect environment for a Pentium based CPU because it needs a lot of power and generate lots of heat.) But on the other hand, imagine how smart of a smart phone someone could make with a chip like the strongarm.
  • Have you looked into FullCharge [extendcomputer.com]? It's a rechargable battery pack witha modified battery door that lets you recharge the batteries in the device. The charging connector is such that you can even sit it in your cradle while its charging. They also have a car adapter available.

    As a Visor owner, I must wait for them to release it for my PDA, but Palm PDAs can use it now!

  • Euh, it's already ported, and i run it. It runs on Acorn RiscPC's really well.
  • Although the vast majority of RISC OS is 26 bit, parts are in 32-bit already, such as the floating point emulator.

    There was talk of a open sourcing RISC OS when Acorn stopped the desktop machine business, but, of course, Pace picked up the pieces. You aren't going to get RISC OS Ltd to release it as open source, because quite a bit of it is owned by Pace.

    The ARM10 (v5) datasheet mentions that it is backwardly compatible with ARM7, ARM9 and StrongARM processors, but there is no mention of 26-bit mode even in the ARM7 datasheet (I'm guessing that ARM didn't want people to develop any more 26-bit code, and by not mentioning it, they effectively stopped this). However, if it is to be truly ARM7 compatible, then the 26-bit mode should be present (as it is in ARM7, and StrongARM).

    In theory, though, if 26-bit mode isn't present, then with an 800MHz (1000MIPS) processor, and if you could write an emulator that was 20% of the speed, then you'd reach the same kind of level as the current StrongARM processor. I came up with a scheme that I put at about 6% of the speed, and another independant person thought would be 60% of the speed, but it hasn't been proven yet.

    Of course, you could have a dual processor machine - one processor would have 26-bit support, and run all the old applications (and some of the kernel), while the new processor would run new applications at significantly faster speeds. This can be emulated now by switching between 26 and 32 bit modes on the fly.

  • RiscOS Ltd have been talking about supporting 32 bit for a year or two, but as far as I know nobody is actually working on it as they don't have the resources. Perhaps if they Open Sourced their OS they would have more than a couple of developers, but that doesn't seem too likely as the RiscOS world is very deeply entrenched in the world of closed source.

    Isn't the RiscOS 4 release 32 bit? It doesn't run on anything prior to ARM 6 so it as removed the processors that were 26bit reliant. As you pointed out, full 32bit access of memory has been on the drawing board for a while but its status is unclear.

    As for releasing the source to RiscOS, Risc OS Ltd can't open the souce because they only own the license not the product. Element 14 (formerly Acorn) own the rights necessary to make that move. That said, since much of the OS is in ARM assembler, it would make cross-platform moves extremely fiddly. RiscOS is fast because a lot of it is hand-optimized.

    Cheers,

    Toby Haynes

  • by mr.ska ( 208224 ) on Friday August 25, 2000 @03:47AM (#828697) Homepage Journal
    Hey CmdrTaco, there's a bug in the Slashcode.

    It seems that every few days or so yet another Intel story will crop up, but instead of being a real story about chips shipping or computers being made with them or actual R&D they're doing, it'll be an Announcement or Press Release about Something Really Cool (TM) that Intel will be making, shipping, and selling Real Soon Now (TM).

    Please have a look and see if you can fix this. Thanks.

  • it beggars belief that [x86] still persists in a largely unchanged form.

    It certainly does - especially as the x86 is just a few steps up from the Z80 architecture. It does explain why Spectrum emulators are so fast :).

    But, seriously, the yoke of backwards compatibility is a what will destroy the PC in the long run. PCs can't get anything like 1GHz performance out of 1GHz CPUs, because they're actually hardware emulators of the pathetic 1970's 80x86 instruction set, which is still here today because few people wanted to pay for their apps to be ported every time a faster CPU came out. PCs are also cripple by having to use a single-tasking 16 bit BIOS at heart, but can you imagine what it would cost to update this on the millions of PCs out there? Unless Billy G decrees it, then it's not going to happen.

    I hope that one day we will _have_ to give up the entire PC software architecture and only access it through emulation. Then people might see the real fruit of these hardware innovations.

    Plus, 90% of the instructions are completely useless, so ignore them, and you got a reduced instruction set computer right away.

    That's how Motorola's last-ditch 68060 works. Some normal instructions cause an unimplemented instruction exception, and have to be emulated purely in software. This makes them something like 400 cycle instructions, so 'optimised for 68060' simply means all the emulated instructions are avoided.
  • yeah i really feel that the thing that let Acorn down was RiscOS. Their architecture was pretty good, but they insisted on keeping the OS in ROM, which i felt was not good for the developer.

    Although, they only ever officially pushed the StrongARM to 233MHz, and seemed to stop there for some reason.

    I reckon the way Acorn could have saved themselves was by

    1.Rewrite RiscOS for multiple processors (use RiscOS for home users and plums only)

    2.Update their architecture to support PCI and Multiprocessors (PCI was supported in the Pheobe, but Acorn died before the Pheobe was released)

    3.Make their own flavour of UNIX just for these machines (a la IRIX), and target these machines towards the SGI users. (oh, and they would have to put on decent graphics cards for this too.)

  • I found this odd... Saw this fragment [thinkgeek.com] over at ThinkGeek (they've been advertising it like hell, how could I resist?):

    And what's more perfect than hyper-caffeinated iced tea? Well, a 1 gigahertz PDA maybe, but that's it...

    --

  • Their architecture was pretty good, but they insisted on keeping the OS in ROM, which i felt was not good for the developer
    Er, not sure why it's not good for developers (reasons anyone?), but it's VERY good for otehr reasons - more virus and accident proof, plus it boots faster - RISCOS 4 is up and running b4 most x86 boxes are past their BIOS...

    Rewrite RiscOS for multiple processors
    Doubt this would have made much difference - would have just been more of a nicety I'd have thought.

    Update their architecture to support PCI and Multiprocessors
    Acorn were working on the first, and other people are now; multiprocessors would have been nice, but I don't think they would have made much difference.

    Make their own flavour of UNIX just for these machines
    Again, wouldn't have helped - linux and bsd have been ported for a while, and acorn were too small to write something like IRIX anyway. Plus, RISCOS had/has lots going for it nothing else has beaten yet.

    oh, and they would have to put on decent graphics cards for this too
    I'll buy this one - that would have helped!
  • I like how /. posters think they see through corporate media, then post press releases as "articles."
  • I agree than x86 assembler is a joke, I've learn many RISC assembly language and some CISC (6809, 68000, VAX), they were all easy to learn but I've never managed to surpass my disgust of the 80x86 assembly language, barf.

    > Plus, 90% of the instructions are completely
    > useless, so ignore them, and you got
    > a reduced instruction set computer right away.

    Not really, a RISC has usually lots of register, an orthogonal instruction set, a load/store architecture..
    The 80x86 ISA is quite far from these kind of ISA as evidenced by its shitty FP performances due in part to its braindamaged stack-like model for FP operations.

    Still there is so much competition between x86 makers that its price/performance (in the high performance area) is quite impressive (especially for integer ops).
    I'm wondering: if one day Intel managed to sell only EPIC processors, it will become an Intel-only game, not more competition from AMD and the like..
  • push {r4,r5,lr} ... blah ... pop {r4,r5,pc}

    Push and pop? *shudder* No thanks! I'll stick to

    STMFD r13!,{r4,r5,r14}
    ...blah...
    LDMFD r13!,{r4,r5,pc}

    Ta very much!

  • Make their own flavour of UNIX just for these machines (a la IRIX), and target these machines towards the SGI users.

    They had something like this around 1990. It was called RISCiX.

  • Note these machines had no level 2 cache - as clock speed increased, this would have throttled a x86 style processor, but the ARM has fairly light memory usage as it has 13 general purpose registers, a fairly orthogonal (and small) instruction set and a load/store architecture minimising the need to go to memory for information.

    The ARM instruction set is great. It is a joy to program in ARM assembler. I especially like the possibility to add conditions to every instruction.

    Nitpick: it has 16 basic registers, all of which are interchangeable. Only R15 has specific semantics (program counter).

    BTW, the lack of L2 cache was (is) not a good thing. It was just never developed because at the time they couldn't get a foothold in the desktop market with the Wintel monopoly.

    That's why development towards more speed was stopped in favour of extending its already amazing MIPS/Watt. They went the low-power way because the desktops weren't going anywhere -- an ARM doesn't run Windoze, after all.

  • by Anonymous Coward on Friday August 25, 2000 @04:50AM (#828707)
    You're mostly correct Toby, except for:
    >During this time, DIgital got into a patent/IP
    >dispute with Intel and ended up having to sell
    >the StrongARM team to Intel as part of the
    >settlement.

    DEC did not HAVE to sell the fab that made Alpha's, StrongARM's, and PCI bridges. Although we may never know the details, the agreement between DEC and Intel was that in exchange for DEC not sueing the pants off Intel for patent infringment, Intel had to take the fab off of DEC's hands. Intel got the deal of the century. They got a first class fab, the PCI bridge chip business, AND StrongARM. Too bad for them tho that the original StrongARM team up and quit enmass.

    Many within DEC thought that the CEO at the time was just prepping DEC for sale to Compaq. The rumours were that DEC had both Intel AND Microsoft dead to rights on technology that DEC developed (Alpha and VMS) and that Intel and Microsoft aquired without license.

    As I said, we'll probably never know the details. And that's a shame.
  • the magic thing about paying money for somthing, is that you usally own it at the end

    /*
    *Not a Sermon, Just a Thought
    */
  • So Palm is going to pull an Apple and make the rest of the "legacy" application space play the emulation game? Of course, emulating a 16MHz 68000ish processor with a 200MHz StrongARM is going to probably increase performance, whereas emulating a 40MHz 68040 with a 60MHz PPC would've decreased performance, but still :-)

    In all seriousness, though I would like to see a faster palm, I don't want to watch the prices of these buggers go up. Then again, as they supposedly use less power, it would actually mean more usable battery life, and so on.... I guess it's a toss-up.


    --
  • Hmmm, the market for XScale processors will be bigger than the market for Intel x86 processors within 3 years apparently. Intel can fit >20 XScale processors into the same die space as a Pentium III. They can sell XScale processors en-mass for $20 each (i.e., $400 - $600 dollars revenue for the same die space as a $200 PIII).

    Makes plenty of sense to me.

  • Er, not sure why it's not good for developers (reasons anyone?), but it's VERY good for otehr reasons - more virus and accident proof, plus it boots faster - RISCOS 4 is up and running b4 most x86 boxes are past their BIOS...

    ok i must admit there are several times i've completely fucked a riscpc, the been able to just do a ctrl-x-break-del and have it all fine again

  • The ARM instruction set is great. It is a joy to program in ARM assembler. I especially like the possibility to add conditions to every instruction.

    Yes - conditional execution is a major plus and probably helps the ARM assembler get such good code density.

    Nitpick: it has 16 basic registers, all of which are interchangeable. Only R15 has specific semantics (program counter).

    Major Nitpick: Two other registers are vulnerable - R14 is used as a link register for branches and I counted it out. It's also dangerous to fiddle with this when switching IRQ, FIQ or SVC modes as it changes - the same is true for R13. That is why I gave the 13 general purpose registers r0-r12 - I never used r13-r15 except in special cases :-) Really the ARM has more general purpose registers than 16 - there are 27 (ARM 2 and 3) or 31 (ARM6+) registers but you only see 16 at any one time - changes in processor mode can swap registers over.

    Cheers,

    Toby Haynes

  • by victim ( 30647 ) on Friday August 25, 2000 @05:17AM (#828713)
    I've done quite a bit of development on StrongARMs. I find that for typical workstation work I would multiply the StrongARM clock speed by 0.60 or so to get PentiumIII equivalents. That is, a 200MHz StrongARM performs about like a mythical 120MHz PentiumIII.

    That 0.60 is variable by task. Some tasks its closer to 1.0, some its closer to 0.10 (we just don't do those :-)

    So, lets look at the Intel XScale Benchmarks [intel.com] or rather hallucinatory benchmarks since they don't have the silicon yet...

    It looks like a 1GHz Xscale is about three times as fast as a 233MHz StrongARM. Thats three times as fast as a Pentium III 130MHz, or perhaps in the ballpark of a PentiumIII 400MHz.

    So stop having GHz envy and instead marvel at the really neat parts of the architecture.
    • Its a PIII-400 eqivalent at 1.6Watts. Heck, the fan only on your PIII-400 is probably 1.6Watts. Even a Beowulf cluster of these won't make enough heat to keep Natalie Portman's grits hot.
    • It probably costs 10-20% what a PIII costs. There will come a time (has come?) when you just don't need the fastest CPU to run office productivity applications or surf the web.


    (Incidentally, don't b*tch at me about my 0.60 estimate. email me and I'll give you an account on a benchmark machine and you can't run your own. If you can figure out how to email me then you aren't worthy.)
  • Not quite as well as Debian :-P

    NetBSD/arm32 needs a huge abount of work done on it. It lasted about 2 months on my RiscPC. Debian has been on there for about 8 months.

  • One point is that the Dragonball in the Palm has got the built-in display components (can drive a colour LCD screen at up to 640x512 I think), although PalmOS and the hardware only use a 160x160 screen.

    Palm know that their tech is behind the times. This is their answer. Of course we might see iPaqs that win at 400MHz in mobile mode, and 1GHz in external power supply mode, and the processor will cost about $20 in bulk, even at 1GHz (the die is really small, you can fit 40 into the space of a single PIII).

    The XScale does not have a built-in LCD display driver. This would mean a separate chip would be required to drive the display, or added onto the XScale core, which is an option. This would take time.

    Palm are going to use a standard ARM or StrongARM processor for now. Palms are not about speed, but usability. A cheap (

  • RISC OS 4 is still 26 bit. However, Pace are now developing RISC OS and appear to be working on 32 bit mode. The big question is whether they will produce a version which will work on desktop machines such as the RiscPC and its upcoming replacement, Imago. As you can probably imagine, this is a growing concern for the RISC OS community...

    P.S. It's RISC OS. There is another OS called RiscOS which has nothing to do with Acorn/Pace/whatever

  • Reposted: Slashdot cannot handle ...<$... in a posting apparently...

    One point is that the Dragonball in the Palm has got the built-in display components (can drive a colour LCD screen at up to 640x512 I think), although PalmOS and the hardware only use a 160x160 screen.

    Palm know that their tech is behind the times. This is their answer. Of course we might see iPaqs that win at 400MHz in mobile mode, and 1GHz in external power supply mode, and the processor will cost about $20 in bulk, even at 1GHz (the die is really small, you can fit 40 into the space of a single PIII).

    The XScale does not have a built-in LCD display driver. This would mean a separate chip would be required to drive the display, or added onto the XScale core, which is an option. This would take time.

    Palm are going to use a standard ARM or StrongARM processor for now. Palms are not about speed, but usability. A cheap (less than $5) 72MHz ARM would be 20x faster than the current chip, and you can buy them with embedded display components. This sounds the most likely option for Palm to take (at the low-end). At the high-end you might get 110MHz StrongARMs, or even 233MHz StrongARMs.

  • Does anyone have a pointer to the new ISA ?

    All the articles linked until now are quite vague and non-technical.. :-(

    Will they be as elegant as the Altivec ISA ?

    Yes, I do think that some ISA are more elegant than others ARM ISA is quite nice and I like conditional operations :-)

  • Actually the StrongARM was designed by Digital, independently of the main ARM processors line.

    so is intel a licensee of arm or not?

    --
    And Justice for None [geocities.com]

  • How do you go from 0 to 1000MHz in software? I don't think software can do much at all when the clock speed is at zero.
  • This page [dnaco.net] seems a little on the dead side, but yes, I can imagine a Beowulf cluster of these.

    Bill - aka taniwha
    --

  • they have all already been ported, they run on an Acorn RISC PC or a NetWinder (AFAIK), both StrongARM powered
  • You can't, unless it's really, 0.xMHz. However, if it really is 0, then it probably jumps to something more workable in response to IRQ activity. Perferct for the embeded world.

    Bill - aka taniwha
    --

  • They got a first class fab, the PCI bridge chip business, AND StrongARM. Too bad for them tho that the original StrongARM team up and quit enmass.

    Intel got a .35 micron fab when the industry standard was .25, and Intel was moving to .22. That's not what I call first class. Intel had already made PCI chipsets for a while; acquiring DEC didn't vastly change that. And of course the StrongARM team quit enmass -- Intel is a 'hire-em-young-&-screw-em-while-theyre-naive' company, just lke microsoft (and you wonder why both companies have poor quality control). Last I heard a big chunk of the StrongARM guys went to Candence, or some other tools company. Bummer.

  • at less than 1.5W? What heat? :)

    Bill - aka taniwha
    --

  • Where the f***k all my previous posts went? It seems that moderator/cencor/whoeveryouare do not like my comments and wants to keep his job badly, especially after the doodoo with the Kerberos protocol. Heh, screw you.
  • I'd really like to buy a StongARM system if only I could buy the CPU/MOBO in a standard AT/ATX form factor. Anyone know of a modern ARM based system (short of the now dead Netwinder) which can be had on the cheap and uses commodity parts?
  • morgus morphus [slashdot.org] opined:

    The BSD one seems to be delayed.

    I don't know about FreeBSD (that page was last updated in 1995!). However, there is a NetBSD ARM page here [netbsd.org].

    According to that page:

    NetBSD/arm32 is a port of the OS to a variety of ARM- and StrongARM-powered computing platforms. The port has been a work in progress for the past four years, and is maintained by
    Mark Brinicombe [mailto].

    They have a short history of the NetBSD/arm32 project [netbsd.org].

    ---
    In a hundred-mile march,

  • Forget ATX, are StrongARM boards available for the PC/104 formfactor? The fastest pentium series cpu I've seen for PC/104 has been around 233 -- maybe a tad faster, but not much. If I could build a PC/104 based mobile linux box off of a fast StrongARM, my dreams would come true.
    ------
    WWhhaatt ddooeess dduupplleexx mmeeaann??
  • the magic thing about paying money for somthing, is that you usally own it at the end

    Unless the SPA, MPAA, or RIAA is involved, anyway.

  • Well, it isn't backward compatible with an 8086, (unlike all IA32s and even the IA64 Itanium), so I'm hopeful :)
    #define X(x,y) x##y
  • I seriously doubt that we could get along without the CISC, it would just cause to much incompatability, or the translation matrix would make the apparent speed increase gained from the CISC->RISC insignificant. This has no bearing on "us" the private users as I see it.

    Obviously you must be defining private users as users of proprietary software. Private users of Free or Open source software have none of these worries. If StrongARM tech provides what we want, it's just a port away. BSD and Linux both run great on ARM processors, and have for quite awhile.

    Ever seen a NetWinder?

  • Oh no! Thats costing you two precious bytes! But sure, you're saving yourself some stackspace :)
  • The DSP unit is basically a 2 way SIMD integer MAC unit. Nothing as sofisticated (some might say bloated...) as Altivec.
  • undoubtably, these StrongARM chips are Transmeta's biggest competition.

    Umm... no. They aren't competition to the Crusoe 5000 series at all. They aren't x86 compatible, remember. The 5000 chips are, with not only 386+ compatibility, but also 16 bit compatibility, that's the whole point - they are trying to bring the qualities of the StrongARM to market in a form that will run a certain proprietary binary only OS and all of it's applications.

    What would be interesting from my point of view would be a price/performance comparison between the Crusoe 3000 series and the StrongARMS, since the 3000 series runs Linux just as well as the 5000 series, at lower cost (no hardware to support the 16 bit legacy code windows still relies on.) Those could be considered competitors.

  • by Shotgun ( 30919 ) on Friday August 25, 2000 @10:13AM (#828736)
    One poster wrote that the StrongARM is only about .60 the speed of a PentiumIII at the same clock. That number varied and would even go down to .10.

    But at 1.6W and only costing around $20, how many of these could you put together to summarily spank the Pentium performance-wise and still run cooler and leave more in my pocket? Are there any workstations that already have multiple StrongARMs?

  • If you want to learn assembler, to it the right way, and get an ARM.

    Right, or check out the armulator in GDB [redhat.com] and apply this [staticip.cx] patch to get a cute emulated LCD screen(just a linear frame-buffer) as a window in X to dump your debug messages on.
  • by Arker ( 91948 )

    P.S.

    Netwinder [rebel.com] is FAR from dead.

  • If you go to www.jimmy.com the guy there is talking about overclocking IPaq's on the fly.. is this what he's talking about? (he didn't give any details). Accoding to him he can have his games run at around 236mhz (instead of the usual 206), and have it switch back to 206 when it's done (since it screws up active-sync or something). He said there's about 8% more power drain though, but that doesn't sound liek a lot, and doesn't matter at all if your running it AC.

    Pretty Cool :)

    - Ryan

  • With all of this interesting talk of ARM performace, I am curious to know if this ARM architecture is capable of being used for the purpose of Symmetric Multiprocessing . Is there anybody that can offer insight to this question? It is neat to think that you could have an 8-processor system, that performs nicely, and gives off virtually no heat.
  • As mentioned in a previous Slashdot article [slashdot.org] the Compaq iPaq uses a StrongARM processor and runs Linux. I wonder if we can build a small daughter card that drops the Xscale (tiny, BGA package) into the space from a desoldered SA110 (inch square, PQFP package) with the necessary bus conversion so we don't have to wait for Compaq to give us a 1BIPS Linux palm-top with 36 hours battery life... I better go out and buy a really small tip for my soldering iron :-)
  • "Of course, you could have a dual processor machine - one processor would have 26-bit support, and run all the old applications (and some of the kernel), while the new processor would run new applications at significantly faster speeds. This can be emulated now by switching between 26 and 32 bit modes on the fly."

    -now *that's* a cool idea...
    on a similar note, how about a split-architecture, athlon/alpha, with a custom kernel that routes tasks to whichever chip handles it best... the beginnings are there, they're both already seriously smp-able cpus, the amd 750 is based off the alpha ev6 bus (i believe i've seen newer alpha ev-6 boards using amd-750 chipsets), and later alphas were very similar to x86-architecture.


    Walter H. Trent "Muad'Dib"
    Padishah Emperor of the Known Universe, IMHO
  • The Interl site doesn't mention anything about a cache-coherent bus protocol, so I assume that these new CPUs don't support SMP.
  • Many within DEC thought that the CEO at the time was just prepping DEC for sale to Compaq. The rumours were that DEC had both Intel AND Microsoft dead to rights on technology that DEC developed (Alpha and VMS) and that Intel and Microsoft aquired without license.

    Supposedly the Intel Pentium was using branch predict algorithms that were in the Alpha when DEC was trying to see who they can get to support this technology, and apparently Intel stole some details that they disclosed.

    For the Microsoft case, I think the lead designer for VMS went to Microsoft and made a very VMS-like OS there, then called Windows NT. At the surface, the similarities were few (some apps were named the same and performed the same function), but the underlying architecture was said to be very similar. There was talk that that lead designer took a lot of trade secrets and other intellectual property with him and put it in NT.

    Since then, Dec / Compaq has licenced out the technologies with in VMS to Microsoft to integrate into what was then slated to be called NT 6. At this rate, that product will probably Windows 2010.
  • The only reason they keep their main line CISC is because the demands placed on them by Microsoft for backward compatability.

    Would not the fact that WindowsCE runs on it enable a shift so to speak in the processors? I know that Itanium is a Very Long Something Or-other. And that RISC is away from this, but could not something like this enable the desktop to start moving avay from IA32?


    .sig = .plan = NULL;
  • I don't have any applications that require my PC to look like a 8086.
    Fucking Microsoft shit.
  • It was easy to find out how to email you.

    Google.

    Your name seems reasonably unique, and therefore I can say with confidence that the address is

    jim

    at

    federated

    dot

    com

    Google is the answer.

  • Most of the StrongARM processors used in portable devices rarely exceed 200MHz. And now talk of a 1 GHz StrongARM? BRING IT ON!
  • One small correction to the timeline: Apple Computer [apple.com] used the ARM CPUs in the Newton PDA (which Steve Jobs killed off [apple.com] after he took over again - not one of his better decisions).

    It was Apple that insisted that Acorn Computer [acorn.co.uk] divest itself of the ARM development team, so that they could be buying from a supplier that wasn't directly competing with them in the computer systems market. Thus was Acorn RISC Machines (ARM), Ltd. [armltd.co.uk] born.

    The collaboration with DEC [digital.com] came later, and that produced the StrongARM.

  • However, the moron who gave me the URL has already exhausted his usefulness.

    By the way, my Win2k machine is still up and running at full capacity. How's your computer, still breathing the bilgewater of the internet?

  • 0 MHz basically means sleep mode, that is the CPU can be woken up with an interrupt (key press, network data, that kind of thing).
    That's my understanding from the details they provided anyway.
  • IIRC, Digital licensed an ARM core, deverloped it into StrongARM, had an argument with Intel, throwing a few lawyers around in the process, and ended up with Intel buying Digital's chip fabs, the StrongARM products, and a few other things besides.

    I may be wrong though.
    John

What this country needs is a good five dollar plasma weapon.

Working...