Slashdot Mirror

I have been using RiscOS computers for 6 years (and I am not a veteran) and I currently feel quite happy to see that other people tend to agree on its qualities in terms of power consumption, but also modularity, ergonomy...
>A HREF="http://www.riscos.org">RiscOS is IMHO one of the most optimized operating systems ever. It usually comes in 4-8MB ROM from which he boots in a few seconds.
It includes an excellent GUI and whatever you need to start work (TCPIP stack, Draw, Paint, Editor, tools, etc.).
It is the only 100% Plug'n Play Platform I have ever used and, most of all, as it is fully modular, whatever you dislike in this system can have its original ROM module be replaced with one of your RAM modules.
Now, if you consider that RiscOS has only been ported to specific architectures such as Acorn Computers' which implement the excellent ARM processor then it is obvious why this product is so power-efficient.
Now, an even more interesting case would be to implement a RiscOS platform around a forthcoming Amulet asynchronous processor which hardly consummes a single milliwatt when on idle.
--

During the last few years, a group has been working upon an asynchronous processor : AMULET.
This CPU uses the ARM core.
It is so power-efficient that it could only rely on the induction power resulting from its pins transmitting information.
Current status specify delivery of the AMULET3i.
--

ISTR that OpenCores were warned not to do an open source ARM compatible processor by ARM. This was probably because ARM is really an IP only company, and if someone comes along and builds their own which is free, then their entire market could collapse.

Then again, the ARM7 processor isn't ARM's latest offering, so they may be lenient.

If you want to know more about the ARM 7 processor, then here is the place to go.

ISTR that OpenCores were warned not to do an open source ARM compatible processor by ARM. This was probably because ARM is really an IP only company, and if someone comes along and builds their own which is free, then their entire market could collapse.

Then again, the ARM7 processor isn't ARM's latest offering, so they may be lenient.

If you want to know more about the ARM 7 processor, then here is the place to go.

Contrast this with Sun Microsystems who use the SPARC processor under license. As far as I'm aware, they don't even manufacture SPARCs themselves, but rely on a third party foundry. Why is this relevant? Because SPARCs are also used by many vendors and you can even get the chip architectures if you wanted to implement it yourself, then have your design properly verified.

Of course, your comment is slightly invalid because StrongARMs are made by Intel!

You're right though - why anyone would use an x86 in one of these devices is beyond me. Surely ARM has that market sown up by now?

A lot of people seem to be concerned about the problems with 'open hardware' development - fab. costs, logistics, and so on. These certainly are major stumbling blocks.

However, how about a more modern business model? Here in the UK, ARM have been designing first-class processors for years, and yet they don't make any chips themselves. They *licence* their designs to other manufacturers (eg. VLSI, Intel, etc.).

So - all we need is an OpenHardware licence, some outstanding technology, and some effective advocacy. Think about it - the openh team could design an absolute corker of a processor, then some manufacturer could manufacture it, and would be obliged to put their 'real-world' improvements/refinements/fixes back into the open. After a few iterations of this, momentum would gather, and we'd have a well-tested, well-designed, real-world piece of hardware.

Wishful thinking perhaps, but if you'd have told me twelve years ago that some companies would be making money from selling products based on an entirely freely available, hobbyist-designed OS, I might not have believed you. Things change, sometimes for the better.

The only trouble is, all those chip manufacturers would get rich quick off the labours of the open hardware designers. But that's a philosophical argument for another day... :-)

So, um, what's the timestamp on your last check, then? Because last time I checked (i.e., thirty seconds ago), the milestone page over at ARM's pages stated pretty clearly that the ARM architecture was developed by Acorn Computer Group. Way back in 1987. It goes on to say that Digital licensed the tech in 1995, and also produced the StrongARM version that same year. So, there.

So, um, what's the timestamp on your last check, then? Because last time I checked (i.e., thirty seconds ago), the milestone page over at ARM's pages stated pretty clearly that the ARM architecture was developed by Acorn Computer Group. Way back in 1987. It goes on to say that Digital licensed the tech in 1995, and also produced the StrongARM version that same year. So, there.

>...the embedded market at some stage over the next few years. I fear for Intels future, in this regard.

Clearly you've forgotten about Intel's XScale architecture (the successor to the StrongARM). The ARM processor currently holds a HUGE segement of the embedded market, and Intel is promising the same low-power high functionality technology at speeds up to 1GHz in the near future. If anything, their presence in the embedded market is growing.

>...the embedded market at some stage over the next few years. I fear for Intels future, in this regard.

Clearly you've forgotten about Intel's XScale architecture (the successor to the StrongARM). The ARM processor currently holds a HUGE segement of the embedded market, and Intel is promising the same low-power high functionality technology at speeds up to 1GHz in the near future. If anything, their presence in the embedded market is growing.

Don't be too quick. There is an ARM chip out there that can run Java bytecode (native). If it can run it native, why bother with runtime?

However, I'd still say C. Judging by the tone of the question, it seems the person already has decided on C, so adding a few yeahs is superfluous. Besides, C is has a lot less overhead. If you're running an ARM, you probably don't have much memory to bask in, and you'll need a fair deal of it for voice processing. A final comment is that C also gives you more control, but at the cost of more complexity. If you don't have much time, Java probably is the way to go. If you just like control (don't we all? ;-) go with C. Besides, which language are you more familiar with? You make your move.

We just discussed about power shortages and you keep your hungry hardware ?
Come on !
i just think we should take a deeper look to the low-consumption alternatives around, like this, or this.
What ? Vapourware. Nope. I own many machines running these processors and my brother just bought a transmeta laptop which he's in love with.
Don't believe the hype and aim your purchases towards a brighter future.
Intel's selling radiators, so is Nvidia.
--

right then

you have a problem with mobile phones they cant store info so you must provide it to them over the ether so to speak

so here's WML + iMode

they get the text and convert that into apps

you need to do something select on the relevent *link/button* and the server then servers up another stream for you (and only you)

but wait you are just getting a serialized verion of the app and only parts of it great for text mode stuff where latancy is not a problem but whta about a game ?

you move to the left to dodge the fireball and wait and wait... while the next part is sent Not Good

so we find that you have to serialize the most important parts of the logic or all of it. Now what can be "sent over the wire" yep thats java you just download to your phone the app and frag those bad men in their flying machines ahahah

colour as well and ajustable to screen relitively easy ! security for online buying built in, manages fonts and such well and vectors for victor are now in (after a deal with shockwave)

yeah JAVA's cool yeah it rocks BUT

its slow has garbage colection problems and needs quite alot of room (try telling the folks @ windriver about how little the KVM takes up and they can have a list of application an arms length that will ALL at once fit in the space )

most mobile phones infact I am at a loss to say which ones dont use the ARM arch CPU at their core

now the ARM Instruction Set maps apprently quite well to the java bytecodes so they can do that

but what are they doing about libs will be intresting I would have said that this would be fairly easy but SUN have done some strange licanceing

but it has good things for linux if they chose to implent the Frame buffer and use the pocketlinux distro and libs

http://www.transvirtual.com/pocketlinux.htm


well I hope it all turns out intresting

more info on ARM java

have fun

regards

john jones

check out arm's jazelle technology. it does just about what you're talking about!

--
And Justice for None

Transmeta now appears to have a similar business model to ARM. They both design processors for the low-power, portable markets, but there are differences: Transmeta's processors are larger and faster, but use more power. ARM's processors are used in devices like mobile phones and organisers where low power consumption is vital, and pure speed is not important.

ARM have been doing extremely well so far with this business model...

Most Nokia and Ericson phones have their OS stored in flashable memory. It is possible to fetch the version and revision number by entering a code. I guess it would be possible to do some reverse engineering and write your own OS.
Linux for Phone ?
I like this idea :-)
I was actually thinking of FPCGAs in order to update the processors themselves.
For example, most phones contain an ARM processor.
Their is a patented technology which allow the use of an ARM as a soft modem's platform.
I was then thinking of the ability of rewriting the CPU's internal logics in real time in order to embed such features without the user even notices it.
We would then have an enormous potential here.
Imagine: an evolutive BeoWulf cluster of apparently-looking phones that would in fact allow any of the permanently connected users to share his unused bandwith with the other people whose phone would have the same technology. BTW, the processing (unlike bandwidth) power coul also be shared in order to help each other in case he has a tremendous amount of data to (un)encrypt, hence the BC
I know, it is not a good idea to mention a BeoWulf cluster in a Slashdot comment as it usually gets moderated down but I think this is not off-topic here.

Concerning the hefty discount you mention, I still think it is viable to just give the phone away (along with its communication) and actually gain some money this way.
--

The second article says "built using Intel's StrongARM technology". Surely they mean Advanced RISC Machines Ltd's StrongARM technology, which Intel did nothing but pay some money for.

The second article says "built using Intel's StrongARM technology". Surely they mean Advanced RISC Machines Ltd's StrongARM technology, which Intel did nothing but pay some money for.

• The Register
• C|Net (twice)

ARM processors use around the tenth of the power that a PPC require.
If a PPC burns less than a Pentium, it still burns a lot compared to these.
Please check on the ARM website for the actual specs of these processors, maybe it'll look like science-fiction to you.
--

Last I checked, the StrongARM didn't even come close to approaching the kind of clock speeds that PPC has hit. Although I suppose you could just use like 16 StrongARMs :)

Eval kits and other cheap devices have always been my savior. Not the $3K ones that some companies dish out (ick), but in the $100-300 vein.

The uCsimm has already been mentioned, and that is based on the Dragonball (MC68EZ328) just like the Palm. You can get an ARM evaluation board that has a 25MHz ARM implementation from Sharp (LH77790B) for about $150. The URL.

Both of these have all sorts of logic already on board, such as serial ports, LCD controllers, timers, yada yada. The uCsimm runs uClinux (again, as mentioned before), and the ARM eval. board can run eCos, a product of Cygnus^H^H^H^H^H^H Red Hat. Both CPUs are supported by gcc, so no having to deal with weird third-party compilers. eCos is a little rough around the edges, but it might be sufficient for what you need.

Advantech has a fair selection of x86 hardware of all different shapes, sizes, colors, textures, and flavors. Their use in portable applications is questionable at best... (Where did Transmeta go?!?)

There is also the LART, which is a StrongARM-based board, but they aren't sold pre-assembled, so it is a DIY job. And unless you have the facilities to do boards with surface-mount components, it would be rather difficult to accomplish solo. I would have one were it not for that one wrinkle.

You can do web searches on things like "embedded processor", "microcontroller", "digital signal processor" and find other eval kits (maybe even reasonably-priced ones!). There are plenty out there.

Mobile 'phones have already entirely replaced land lines for a few people I know, and have become the primary contact for many others. Around 40% of the UK population own a mobile phone, I believe Finland leads the world with over 70% usage. Extremely competative markets have put pricing within reasonable reach for many unemployed and students, even school kids. Mobile 'phones are sold in pre-packaged boxes in supermarkets.
Part of this is because most European telcos stopped charging the mobile 'phone owners for receiving calls quite some time ago. I understand that this still isn't always the case in the US?
In the UK, the coverage is very good in reasonably densely populated areas, and weak only in the very least densly populated areas of the country.
With upcoming technologies like GPRS and UMTS, mobile data will become a sensible proposition. Given that the mobile phone operators need to make 370UKP (about $590) profit from every man, woman, and child in the UK to just cover the costs of the recent radio-spectrum auction, you can bet that the companies will be heavily pushing products suitable for everyone, from accessing AOL and shopping channels to real-time video conferencing. You can also bet that the 'web pads' and the like, will be using CPUs from Transmeta and ARM, and hopefully those that aren't running EPOC will be running a free O/S.

Its processor core is based on the ARM9 series, but since it is asynchronous (ie it hasn't got 'clock cycles' like normal synchronous processors) it should go very very fast (simple processes will rush through without being delayed by slight harder/longer processes).

While I haven't had a chance to get my hands on one of these yet, the spec's I've seen (I can't remember if they are public or not) look good and the chips should be compatible with current ARM chips - as used in my RISC PC (BTW a RISC PC is used to run the 'Who Wants to Be A Millionare' shows!).

It is difficult to place an exact Mhz rating on these chips due to the way they work, but the current version (AMULET3i) runs at roughly 120Mhz - but they have started from the basics, without using much 'proven technology', so expect development to last a few more years - but the 120Mhz version should be out next month/late this month.

IMHO the current drive towards having one power-hungry-but-fast CPU in most commercial systems is not the best approach for delivering high-power and low-cost systems. A large gain in computing power could be made by changing the machine design to one based around several low power CPUs. A CPU design such as the ARM architecture, if modified to support multi-processing (the StrongARM does not support it as-is, I do not know how the situation is with other ARM chips) would be good for this as ARM CPUs are sufficiently fast and are power-friendly. (see http://www.arm.com for more details).

It would then be possible, once the chipset and motherboard have been designed and manufactured (not a small task by any means) to have a system with a lot of processing power but not costing a great deal more than a typical high-end system today. Also the power requirements for such a system would be on a par with a current system as well, if not less (depending on the number of CPUs employed and the system with which it is being compared).

More info about ARMs.

Current ARM powered products.

More info about ARMs.

Current ARM powered products.

The ARM7TDMI core, on which both the Atmel AT91 series and this new chip are based, does not include an MMU.

This was probably quite difficult to implement, but isn't exactly conceptually brilliant. Modern computers already run at different clock rates internally. Your disk I/O bus runs at one speed, your video processor runs at another speed and the CPU still spends a lot of time waiting for stuff to come down the system bus from memory.

It's even less conceptually brilliant, when you see what people elsewhere have been working on - namely wavepipelined architectures.

Funny... people just keep on reinventing the wheel... fire... and then they patent it to hell.

IIRC, the guys at Manchester University were working on this back in 1989/1990 (or at least they were when I went on a tour of the place...). Back then, it was just called the "wave pipelined RISC chip" - these days, it's the "Amulet". Check it out. It's based on ye olde ARM processor architecture - but the implementation is completely asynchronous -- that is, each individual logic element is clocked separately.

Sure, it's still experimental... sure, it's slower than other chips - but it also predates IBM's announcement by about 11 years. Just goes to show - academia ain't entirely useless ;-)

Links
Architectural Overview at Berkeley

The Amulet Asynchronous Logic Group at Manchester University

Who needs clocks? Bah!

Simon

You say "Intel quite clearly owns the StrongARM processor technology". This isn't true. Intel is a licensor of the StrongARM technology, as are a number of other companies. Check out ARM's website for more details.

Here's the ARM press release from Sept 99:
Nintendo uses ARM® processor in next generation Game Boy

Here's the ARM press release from Sept:
Nintendo uses ARM® processor in next generation Game Boy

What else to do? Diversify is the key. Intel already makes the ARM processor (licensed from the UK's ARM holdings) and Intel will pretty soon have a big share in DSPC. What do these two companies (ARM and DSPC) have in common? Both are targeting the cellular market - and both have a good share in it already.

Instead of having all its eggs in one basket, I see this as a strategic move from Intel to diversify its equity. Getting a foot in the door you may say...

...by the pricking of my thumbs,

It's probably using the ARM 710 CPU Macrocell, which can be embedded in any ASIC... so it'll be on the same cell as the memory it needs... saves chip space (especially as it'll be cartridge based), but possibly will stop people from adding more memory to it.

C'est la guerre.

(Btw: it could also be using the 7TDMI, or the 7100)

Simon

Why not the Apple Newton 2100? That beast has a 162 MHz StrongARM CPU (optimized for "MIPS per milli-ampere" to begin with), 8MB of RAM, and a 4-bit greyscale touch screen, plus optional keyboard, and two PCMCIA slots.

Sure, it's orphaned, but it'd be a kick-ass system...

To me its not the end - its just another bringe on the same road because the athlon is still tied up to the original 80386 design wich was tied up to the 80086 design which was derived from the 4004 (Intels firts production processor).
I think the x86 line will be dead and the wintel marriage too when another architecture like the ARM or the PowerPC will make standard machines bought by normal end users .....

ARM Ltd (the firm who originally thought of the whole ARM idea and co-developed the StrongARM with DEC) are planning to release the ARM10 core sometime this year. Complete with a FPU. Check out


http://www.arm.com/Pro+Peripherals/Cores/ARM10/

for more details. IMHO it looks better than the planned StrongARMs.

Acorn invented the ARM (originally Acorn Risc Machine). Then DEC got it. Then Intel got the ARM from DEC. Intel is now talking about its plans for SA2xx.

See http://www.arm.com/Partners/Intel/. Seems that Intel has StrongARM, but not ARM, as you wrote. That page seems to describe StrongARM as something ARM Ltd licenses to Intel.