OEMs Jump Onto Transmeta Bandwagon

Scooter writes "News.com is reporting that Diamond Multimedia has announced a Web-Pad product based on Transmeta's 3120 processor. The report also mentions that NEC, and possibly a dozen other companies are investigating similar possibilities. It's nice to see things taking shape for Crusoe so quickly. " For more details on the chip itself, check out our recent story.S3 has also announced development work that will be done with Transmeta. They are working on a "Linux-based Internet appliance".

Comments

They all will.

[Yaruar]

This is going to be a great stock lifter for all these companies in this market. It is a great product, but even more so, to the big technologists it will be another bandwagon. + They'll be able to get Linux into their marketing more easily which again will lift their stock. There are myriad companies out there trying to work linux into their advertising and this will go the same way. Talking of which it appears we have just sold our coporate soul (what we had left anyway) to Freeserve...

Crusoe Palm

[Max von H.]

Now, let's just hope the Palm OS will run on one of these... Unless something like LinCE picks the thing up. PalmOS now supports colour, and has a huge software library.

Now that there's a low-power CPU available, I'd love to see a Palm or Visor with a Crusoe CPU, a colour screen, MP3 playback and recording, WAP, etc... The beast still running on 2 AAA batteries that I'd change once a month.

I think it'd be quite cool. What d'ya all think?

Max

Re:Crusoe Palm

[Frodo]

Not on batteries, on those power cells you read about five articles below. Then you need no computer at all, except for data storage :) Add BlueTooth radio-link technology, and you have a real full-strength computer in your pocket.

Re:Crusoe Palm

[Kaa]

Now, let's just hope the Palm OS will run on one of these...

Palm OS is a bit too simple-minded for me. Something like EPOC32 would be much better.

Now that there's a low-power CPU available,

Sorry to burst your bubble, but low-power CPUs have been available for a long time. StrongARM, for example, draws *less* power than Crusoe. The Crusoe's claim to fame is that it is both low-powered and x86 compatible.

I'd love to see a Palm or Visor with a Crusoe CPU, a colour screen, MP3 playback and recording, WAP,

Take a look at Casio E-105. If there were a way to purge WinCE from it and load a decent OS, it would be a great piece of hardware (and yes, you can plug hard drives and digital cameras into it).

The beast still running on 2 AAA batteries that I'd change once a month.

Not going to happen in the near future. The CPU is *not* the main power drain in a hand-held. The color screen is.

Kaa

Re:Crusoe Palm

[jilles]

These things are fats enough to run something larger. Why not run lux with KDE or windows 2000. All you need is some additional applications to provide alternative means for input.

The output is a normal VGA screen so there's no point in running stuff that's written for small, colorless palmtops.

PalmOS is like the DOS of the palmtops. It's hugely popular (mainly because it was the first palmcomputer OS with good developer support) and technologically imperfect. If we're not careful enough it's going to stick around too long like DOS did. In my eyes the PalmOS already is obsolete, crusoe just raised the performance you can expect from such machines by 200-300%. You don't want to run the same crappy software on such a processor.

Developing crusoe was innovative. It's up to the software community to do something useful with it.

Re:Crusoe Palm

[Kaa]

These things are fats enough to run something larger. Why not run lux with KDE or windows 2000. All you need is some additional applications to provide alternative means for input.

That's what Microsoft thought, and look where it got it (WinCE).

Unfortunately, the user interface on a palmtop with a small screen necessarily has to be very different form the user interface for a desktop. It is fairly obvious, but people for some reason have a hard time realizing this. Putting, say, Gnome on a palmtop is NOT going to work.

Kaa

Re:Crusoe Palm

[MindStalker]

A color screen, even one the size of the palm, can easily run 15 watts. So the wattage of the processor doesn't play as heavily in this ballpark. I doupt the old palm processor ran much more than 5 watts, as it already ran at a low temperature. So the tradeoff wouldn't work all that well, but the increase in processor power definatly would be nice.

Re:Crusoe Palm

[jilles]

PalmOSwas developed in a time where you had to work with 16 MHz processors, and tiny black and white screens. That's nice for a calculator.

WinCE machines showed that color screens were feasible but also that the processor power needed to run useful apps on those screens was not present (due to power requirements).

Crusoe changed that. The slowest one runs at 400 Mhz. That's faster than my current desktop PC. That's fast enough to run the PalmOS emulator (if you have to). Screens have gotten a lot better and more energy efficient. Memory sizes have also increased.

PalmOS still makes sense for mobile phones. But anything bigger than that needs a better OS. I wouldn't dream of porting PalmOS to a platform powerfull enough to run DVD's and quake.

Re:Crusoe Palm

[F452]

The output is a normal VGA screen so there's no point in running stuff that's written for small, colorless palmtops.

I think one thing that is missed by this and earlier posts in this thread is that the Palm already supports low power consumption. Just pausing for a couple of seconds causes the processor to go to sleep. So yes, there really isn't much point in using Crusoe technology for the Palm. Maybe for the color Palms, but will Crusoe be making a Dragonball compatible chip?

PalmOS is like the DOS of the palmtops. It's hugely popular (mainly because it was the first palmcomputer OS with good developer support) and technologically imperfect.

Developer support is an important part of Palm's popularity, but how have they earned this support? Palm is hugely popular because they realized what people need in a handheld. They really don't need to play mp3s and watch movies. They want an easy way to manage their calendar and contacts. They want to scribble down a memo. They want effortless synching with the desktop. By enabling all these things and making a product that people want to buy, they gained developer support. Most people want to write programs for a platform that is used by the most people, which Palm has become because they did the job right. Imperfect? Absolutely. What is perfect?

If we're not careful enough it's going to stick around too long like DOS did. In my eyes the PalmOS already is obsolete, crusoe just raised the performance you can expect from such machines by 200-300%.

I still maintain that people can already do most of what they want to on the Palm. Is the Crusoe suddenly going to enable people to do large spreadsheets on their Palm? That would be like looking through a keyhole. There just aren't that many power apps that the majority of people are going to want to run on their Palm. They still want to manage their calendar and contacts, and maybe read a few emails. Something the Palm still supports very well.

Don't get me wrong. I think the Crusoe looks like great new technology. I just don't think it is that relevant to PalmPilots specifically.

Re:Crusoe Palm

[jilles]

Except that the PalmOS was designed for machines operating at about 20 Mhz. 400 Mhz allows you to do all sorts of stuff that the PalmOS never was designed for. In an earlier post I gave the example of running a PalmOS emulator but frankly I think there are much cooler applications you can run.
The only real advantage the PalmOS has is that it has built in support for small screens. You can support small screens on other Operating Systems as well so it's not an essential feature.

Essentially the PalmOS operates well under limited circumstances. Crusoe took those away.

Re:Crusoe Palm

[scottwinsiewski]

It is within the capabilities of the chip, for it t o do this. A code morphing module for the chips PalmOS runs on is really all that's necessary. Based on the presentation yesterday, I don't think development of codemorphing software for non x86 architectures is in the companies immediate future (mainly because they said it wasn't), but it would be nice. What I would like to see is the ability to choose a code morphing module on bootup (something like crilo boot: x86 ), but again I doubt that the company would support this in the near future (again because they said they won't, mainly because it opens the machine up to all kinds of nasty viruses). Two three years down the road, who knows. One may be able to go to the store and buy a computer that you can turn into a Merced, a G9, or an Alpha , and have the ability to wear it on your head (like the Russian guy in the e-trade ( or whatever) commercial). -Scott Wisniewski

Re:Crusoe Palm

[Kaa]

[people] They really don't need to play mp3s and watch movies. They want an easy way to manage their calendar and contacts.

Speak for yourself. I, for example, don't need to manage my calendar and all the phone numbers I need fit in my watch. I *do* want to play MP3s and watch movies. If only there was a decent OS for hardware like Casio's...

Kaa

Re:Crusoe Palm

[Datafage]

Actually, if you look at their website, the slowest one runs at 333MHz. 400 is the TOP speed for their slower processor.

-----------------------

Re:Crusoe Palm

[Nerds]

It doesn't really matter, the Cassiopeia is one of the best WinCE devices out there and it only runs at 133MHz.

Re:Crusoe Palm

[mohaine]

As much as I love my palm, the palmOS is WAY to limited. First off, it is only 16 bit, which just sucks. Second, you have a hard time making a App larger then 32K (Just the app, not counting other dbs the app uses). I think you can make 64K apps but it isn't easly.

Programming on the palm can be a pain in the ass. i.e. Must use StrStr instead of strstr. strstr will compile, but it will bitch about missing libs (and force a reset) if you run the progam. Maybe its just been to long since I've used c.

Re:Crusoe Palm

[j_d]

speak for yourself. I, for example, don't need to manage my calendar and all the phone numbers I need fit in my watch. I *do* want to play MP3s and watch movies. If only there was a decent OS for hardware like Casio's...

Well, since the crusoe's x86 compatable, why not wangle BeOS onto the thing? Since it is the "multimedia OS" and all.
hm. cross this with the recent press release from Be : Conspiracy or Good Timing?

Re:Crusoe Palm

[Bad-Tech]

Tranmeta has made something like LinCE it's called 'Mobile Linux'. That's one of the things Linus was making for them. Check out the FAQ on Transmeta's page.

Re:Crusoe Palm

[TummyX]

Mobile Linux is hardly LinCE, it's 64MB.

Re:Irst Oast?

[Anonymous Coward]

wow, the first two posts were within a few minutes of each other, but now 10 minutes have gone by and still no more. hmmm.

Mobile Linux?

[Anonymous Coward]

Do we know if Diamond will be using Mobile Linux on their web pad? I can't wait to get one of these things!

Looks like a dud to me

[Kaa]

A Web pad -- an appliance for browsing the web... Okay, I can see the market for those. But then: price from $500 to $1000??? Battery life of 4-5 hours only???

Sorry guys, you have to do better than that. A
web pad should cost below $200 and run for the whole day (~12 hours) to be viable (IMHO and YMMV of course).

Kaa

Re:Looks like a dud to me

[Smack]

Well, I'm sure they're quoting list price. So the cost to you will surely be less. But I agree it's a little steep. And the article also says that when it's idle, it uses much less power. So unless you're planning on giving it constant use for 4-5 hours, that should be plenty. It'll probably be like those Win CE devices, where you plug it in every night to recharge, and it's ready the next morning.

Re:Looks like a dud to me

[Anonymous Coward]

Yeah, 500-1000 is a rip off, in my opinion. You'd have to be either making some serious cash to just go out and spend that much money on something like this, or be a complete tech addict.

"Run a piece of Linus in your PC!"

[Duxup]

I'm sure this is not the first of such moves we will see. However I would also think that such moves are not just driven by the quality of the hardware. I think many companies may be aware of the attention the Transmeta's 3120 processor got from the involvement of Linus (I tend to refer to him as Mr. T since I can't spell). If the loyalty shown to Linux can be carried over to processor sales, or hardware that is using those processors, that's big bucks. A fact that was not lost on Transmeta I'm sure (not to say he didn't deserve the job). No doubt we'll see more such announcements.

"Run a piece of Linus in your PC!"

Transmeta's tough ride

[drnomad]

Some sceptisism exists on the new Crusoe chip. And although Transmeta has to fight all sorts of enemies, I still do wish them the best luck with their chip.

IBM surely is going to manufacture the thing, so they have one of the big guys on their side, let the ball roll!

Re:Transmeta's tough ride

[Zoltar]

Arrrrrhhhhhhggggg....

I can't disagree that there will be many detractors to Transmeta, and it will be a bumpy, uphill ride. But I wouldn't really take any opinion of Jessie Berst as an indicator of what these problems might be. Heck... I wouldn't take anything that blowhard says seriously. Jessie Berst is nothing but a load of sensationalistic crap.

Not vaperware

[Shadow-Wing]

OEM's are reluctant to invest Money in a product which will rely on another vaporware products. Transmeta's chip is already in production, as I understand?

from the but-can-it-play-quake dept.

[LocalYokel]

If Transmeta CPU's are parallel in speed to perhaps a K6-2, a 400MHz palmtop should be able to play Quake, but I imagine Diamond is going to set its sights a little lower, and the most interesting thing it will do is play MP3's...

--

Re:from the but-can-it-play-quake dept.

[technos]

It will run Quake, regardless of Diamond's intentions. Does it crunch the kind of numbers Quake requires? Yes. Does it have a display? Yes. Does it have sound? Yes. Does it have a network connection? Probably.

And who is the target audience for the ney Transmeta Toy(tm)? Us! And what do we like to do to our toys? Hack em'.

Wait three weeks after release. I bet we'll see some stripped version of Quake appear for it.

Re:from the but-can-it-play-quake dept.

[Anonymous Coward]

Quake I, yes, but probably not Quake III (depending on if a 3D accelerator is included or not).

Float or Sink?

[mikelu]

It's interesting to contemplate whether or not the Crusoe will actually be able to compete against Intel in anything but the mobile market. Sure, saving power is on everyone's minds, but the majority of people are willing to sacrifice a few watts of power for another 150mhz in clockspeed. I am intrigued by the idea of a chip that is "upgradable" through software, but this brings up even more security issues. Security through obscurity may be the only option here, or risk massive disruption. From what I've heard so far, the potential for damage is almost limitless. A chip whose routines can be modified by software to perform multiple and varied functions raises all my hackles.

Re:Float or Sink?

[Anonymous Coward]

> Sure, saving power is on everyone's minds, but the majority of people are willing to sacrifice a few watts of power for another 150mhz in clockspeed.

I don't beleive so. Heating is a major problem with standard processor too. Having a colder processor enable you to go higher in speed. Imagine what could be an overclocked transmeta processor :-)

Btw, I wonder if there is provision for SMP. *This* is what I am waiting for (ie: the ability to have a few low cost, low power consumption processor coupled together). In such case, throwing twice the money to the processors would give you back about twice the perfs, instead of the 25% you can have with intel chips.

Anyway, the fact that the transmeta processor:

1 - Is heavily optimised to run x86 code (ie: its underlying instruction set is biased toward x86)

2 - Don't publish the real microcode(*)

let me think that it may not be so great for us geeks when the dust settle down.

--fred

(*) Transmeta use a double-edged sword for its marketing. They say that traditional hardware have to decode each instruction each time it sees them, and that their processor will do this less often and cache the result. Furthermore, pretends transmeta, it enable them to optimise instructions on the fly.

But, by definition, gcc -mtransmeta could easily do the same, as it could directly generate what the transmeta code-morpher would produce. (And sure, it could do much better) So for handheld devices it make much more sense, at least for the portion of the code that is in ROM. Beeing able to run x86 code is a plus, but not beeing able to get to the raw processor is dumb...

Re:Float or Sink?

[Anonymous Coward]

"compete against Intel in anything but the mobile market?"

Well, Linux boxes currently succeed as Web servers, right? And if you're stacking up a whole bunch of Web servers in your farm, that wattage adds up to real bottom-line money. And you don't need that extra clockspeed on a server - better to put that money into RAM and disk.

Or, you've got your cable or DSL connection, and you hang a server on it. In NYC, leaving that machine on 24x7 adds maybe $10 a month to your electric bill. Not much money, but then again if it's cheaper, smaller, greener, cuter and still runs Apache, sendmail, ipchains ... well, that's a nice appliance.

Re:Float or Sink?

[rkent]

From what I've heard so far, the potential for damage is almost limitless.

Maybe I'm being thick headed here, but why is the Crusoe more of a security problem then, say, any RISC processor? It basically just takes the RISC philosophy (move complexity off the chip, into software) to the next level: move the task of converting complex instructions out of the hardware, too.

Also, the part that does the conversion (the "Morphing" unit) is in a ROM chip that can only be updated by flashing. It's not like you'd overwrite it on a buffer overrun ;)

Or, again, is there something I'm missing? I've read the Transmeta "technology behind the Crusoe" document, but that's obviously pretty biased towards the positive aspects :)

but the majority of people are willing to sacrifice a few watts of power for another 150mhz in clockspeed

Yes, but at $89, you might as well just buy 2 or 3 crusoes and go SMP at the same wattage :)

When is the IPO?

[Anonymous Bastard]

Here's another company with a potentialy hot stock. With all these established companies supporting Crusoe, the stock has no where to go but up.

BTW, who are the major investors in Transmeta?

This looks good!

[jd]

Crusoe is -hot- technology. (Ooops - cold! I just checked the thermal image pics on their website again. :)

I wouldn't be surprised to hear a lot more companies start offering Crusoe-based systems over the next few days or weeks. I also expect to start seeing major chip manufacturers slash prices, to avoid having their markets vanish.

(What's the point in maintaining multiple product lines, with different processors, if the Crusoe will do the job of all of them? It's much cheaper to use a standard one-size-fits-all package, and tailor it with software patches.)

Depending on the performance of the Crusoe in the field, expect the Itanium (whenever it actually gets released) to sell for only a fraction of what Intel usually try to fleece off it's customers for new releases. If they don't, it's dead. It's going to be slower than a P3, anyway, and companies are going to start asking if it's not better to just upgrade to the Crusoe instead.

I imagine the Alpha (horribly overpriced as it is) to take a knock from this, too. The ARM and the Sparc should be OK, as they're both RISC (so will be faster) and they're not -too- outrageously priced.

Re:This looks good!

[BeBoxer]

It's interesting to speculate on how the Crusoe will affect the Itanium, since in many ways they are very similar products. My understanding of Itanium is that it's a 64-bit VLIW processor that will have some capability for emulating x86 instructions. Sounds a lot like Crusoe. Sure, one is 64-bit and the other is 32-bit, but that could change. Transmeta could easily replace Crusoe's functional units with 64-bit versions and the users would never even know.

More interesting is going to be watching what happens with the patents that Transmeta has on low-level emulation. Is Intel going to be able to keep Itanium from sucking on x86 code without getting a license from Transmeta?

Re:This looks good!

[Dr. Sp0ng]

Sure, one is 64-bit and the other is 32-bit, but that could change. Transmeta could easily replace Crusoe's functional units with 64-bit versions and the users would never even know.

Nope... the Crusoe is a 128-bit VLIW processor, not 32-bit.

"Software is like sex- the best is for free"
-Linus Torvalds

Re:This looks good!

[aeonek]

Depending on the performance of the Crusoe in the field, expect the Itanium (whenever it actually gets released) to sell for only a fraction of what Intel usually try to fleece off it's customers for new releases. If they don't, it's dead.

No. Itanium is initially targeted for real-high-end servers, and will NOT be cheap. It will be fast and power-hungry though. Crusoe is a COMPLETELY different market. You can't compare the two.

It's going to be slower than a P3, anyway, and companies are going to start asking if it's not better to just upgrade to the Crusoe instead.

Expect the itanium to be about twice as fast as a P3, and a lot more expensive. You don't upgrade to the Crusoe. Remember, both the P3 and the K7 will kick Crusoes ass, real hard, when it comes to performance.

I imagine the Alpha (horribly overpriced as it is) to take a knock from this, too.

Err...no. The alpha consumes about 60W IIRC. It's 60 times more than the Crusoe. And it's WAY faster. Again, completely different markets. You're saying that the fastest chip in the world will take a knock from a low-end chip from a start-up? I don't think so.

Re:This looks good!

[aeonek]

It's interesting to speculate on how the Crusoe will affect the Itanium, since in many ways they are very similar products.

They're both VLIW, but apart from that they're not very similar. Crusoe's performance is probably not very impressive, but it's har to know, since they haven't released ANY information whatsoever, other than "it will play DVD and MP3".

My understanding of Itanium is that it's a 64-bit VLIW processor that will have some capability for emulating x86 instructions. Sounds a lot like Crusoe.

Itanium's x86 emulation is hardware-based. Itanium does have software-based emulation, a remotely similar to Transmeta's, for running PA-RISC binaries.

More interesting is going to be watching what happens with the patents that Transmeta has on low-level emulation. Is Intel going to be able to keep Itanium from sucking on x86 code without getting a license from Transmeta?

As i understand the patents, they don't have any patents on the emulation, just the special hardware that supports it. The itanium does suck on x86, and it seems intel can't do much about it. They're of course hoping on good native support.

Re:This looks good!

[Salant]

I'm kinda un-informed in this field, but how can
you say one will beat another, even marginally
when there are no benchmarks, or anything really
out about the new chip.

Re:This looks good!

[Bakerman]

To clarify, the Crusoe is a 128-bit VLIW processor that can run 32-bit x86 code. It cannot at the moment run IA64-code but that should be easy to add support for given the software-based design of the Crusoe.

/Erik

Re:This looks good!

[tzanger]

Remember, both the P3 and the K7 will kick Crusoes ass, real hard, when it comes to performance.

... howso? Mind you I did not see any fp benchmarks on the Crusoe, so you may very well be correct in that aspect of benchmarking. From what I can gather, however, the Crusoe optimizers actually improve performance as they run code. Add on the battery life (not much of a factor in desktops/servers*) and support circuitry**, however, and Crusoe still comes out ahead.

*power consumption *is* a factor in desktop/server markets because it affects the cost of equipment needed to power / cool these devices/rooms. Hotter components also burn out faster.

**If I am reading this correctly, Crusoe includes North and Southbridges on-chip. This would make the motherboards for these devices cheaper and smaller as well, the former variable making desktops/servers cheaper.

Re:This looks good!

[jd]

Transmeta have extensive benchmarks on their website. Check them out. The processor runs Windows 98 SE and Office 2000 faster than a Mobile Pentium III (500 MHz)

Re:This looks good!

[BeBoxer]

The size of the VLIW words (molecules in Transmeta speak) is not the issue. It's the word size that operations are performed on. When a processor is described as being 16, 32, or 64 bit, this generally referrs to the size of the integer/arithmetic units and registers. The fact that the Crusoe can issue four 32-bit commands in a single instruction does not make it a 128-bit processor.

To be honest, I can't find an exact reference to the size of the functional units, but given that they are designed to be x86 compatable, it's a good guess that they are 32-bit units. On the other hand, Itanium will certainly have 64-bit functional units, and being VLIW (EPIC in Intel-speak) will probably issue 2 or 4 instructions at a time. That will not make it a 128 or 256 bit processor, however.

Re:This looks good!

[for(;;);]

If the assembly language is interpreted, can't it
(slowly) appear to be a true 128-bit processor?
Indeed, 128-bits is the processor's I/O size; in theory the
processor width can be anything. (Although
this doesn't take into account the associated
speed hit of emulating a width higher than the
one used by the native language. Of course, none
of that emulation-speed-hit stuff has been discussed
in sufficient detail by Transmeta, nor probably will
be until the real assembly language is reverse engineered.)

Re:This looks good!

[jd]

*cough* I downloaded and printed the Crusoe benchmarks, last night. Uninformed is fine, but why not look at the website before deciding what's been published?

Re:This looks good!

[BluBrick]

*power consumption *is* a factor in desktop/server markets because it affects the cost of equipment needed to power / cool these devices/rooms. Hotter components also burn out faster.

Absolutely. The crusoe makes perfect sense for a low-end to mid-range server-class machine. The very low heat output means that means that the server can be built in a closed case with no fan, thus there is no dust being drawn into the guts of the box. This neatly does away with the requirement to run it in an environment controlled computer room. The low power requirements mean that power supplies for these servers can be a lot smaller than the current crop of standard AC driven ones. It would then be more feasible to include dual hot swappable power supplies in a small form factor. Now rack mount these puppies (they'd only be about 1 rack unit high, after all) and that could open up a whole new world in high-density clustering.

Looks like Transmeta were right....

[media_mogul]

... when they said they said that they weren't announcing OEM deals to focus attention onto the chip itself. Its going to take more than Diamond to make Crusoe work but its a good start. And its good to see Diamond innovating again after the disaster that is RioPMP500.

Interesting article talking about the impact on other chip/OS companies.

http://www.uk-invest.com/homepage/breakingnews.h tml

OT: Incorrect Logo

[Cy Guy]

Please stop using the Crusoe logo to represent Transmeta. The Transmeta logo is a downward pointing blue triangle with a wavy line crossing it.

While I have to admit that Transmeta does use the Crusoe logo on every page of its website, and only rarely uses the Transmeta logo, they only use the Crusoe logo with the Crusoe name.

Re:OT: Incorrect Logo

[orcrist]

Hey! He's right.

Chris

Re:OT: Incorrect Logo

[Smack]

Are you serious? This story is about Crusoe! So why exactly is the crusoe logo the wrong one?

Re:OT: Incorrect Logo

[asystole]

Are you serious? This story is about Crusoe! So why exactly is the crusoe logo the wrong one?

Because the topic is Transmeta perhaps? If all they ever do is Crusoe then okay, but that ain't necessarily so.

Re:OT: Incorrect Logo

[Cy Guy]

This story is about Crusoe, but if you read the ALT text tag for the logo /. uses, it says 'Transmeta', and if you click it, it takes you to their Transmeta story archive.

Since /. doesn't have seperate logos for for the K-6, K-6-2, K-6-3, and Athlon; or for the Pentium, PII, and PIII; they should be consistant and track processor stories by the manufacturer, which in this case is Transmeta.

Transmeta has at least one other product besides Crusoe that /. readers are intered in - Mobile Linux. One can assume that within a short period of time there will be a Mobile Linux story posted. Though this OS runs on Crusoe, it doesn't really make sense to use the Crusoe logo for the story, it would be a Transmeta story, and so, they should use the Transmeta logo.

No no no, this is all wrong

[FascDot Killed My Pr]

I don't want a "webpad" with a pen interface. I want a wireless, diskless laptop running as an X terminal to my PC. Think about it:

-Runs on Crusoe so it is quiet, cool, light

-no disk so it is even quiter, cooler and lighter AND there's no need to sync with the mothership AND it is more robust (HD's are delicate and often fail)

Obviously this is fairly useless once I leave the house (until wireless Internet gets popular), but so what? I'm sick of being stuck in one location while I'm browsing/programming/reading-docs/looking-at-porn

Furthermore, with some intelligent design you could even get rid of the keyboard. Put 8 buttons on the back of an LCD screen (4 on left and 4 on right). Your fingers would rest on these keys as you hold the pad. Pressing them in "chords" causes characters to appear on the screen--just like typing only using more than one finger at a time. Even using only 2 fingers at a time you get 256 different characters.

BTW, if this device is ever patented, the above is "prior art"....
---
This comment powered by Mozilla!

Re:No no no, this is all wrong

[Smack]

Of course, the fact that you have to stretch to chorded keyboards shows what's wrong with this idea. An x-term is still rather keyboard centric. Any device that doesn't have a keyboard just isn't going to be a good replacement for a desktop.

Just because X is a viable solution in many situations doesn't mean it's the best one. I personally don't want the complexity of the desktop in a portable. Isn't that the major gripe with the Windows CE machines?

Re:No no no, this is all wrong

[psin psycle]

Wow. I love this design. I could finally surf while soaking in the tub :) It should cut down on paper use also, because there would be no reason to print off everything everytime I want to get away from he computer.

Add the following things:

• Put some sort of pointer control under the thumbs. Something like the Nintendo controler has. This will allow you to quickly move the pointer around while typing. Don't take away the touch screen though, as this will be usefull while surfing or drawing.
• Give it lots of memory so you can store often used documents and reference websites.
• Have it automatically sync whenever you are in the transmision area. This should be as large as possible. Maybe have different models - 900Mhz (house hold range), FM broadcast (enterprise range, upto 11mi)

Re:No no no, this is all wrong

[horza]

I like this idea a lot, and in fact is what I've been thinking about for a while. Stick a server in the airing cupboard, and then scatter a number of these thin clients around the house.

Have user 'kitchen' boot up with a browser full-screen and homepage set to simplyfood.co.uk. User 'study' can boot up a more traditional X terms type desktop. I'll let your imaginations do the rest.

Forget trying to ditch the keyboard though. Nobody is going to learn those 'chords' (look what happened to the Quinkey and similar). Just give the pad an IR port and drivers for all those IR keyboards you can buy ($30-$40 over here).

Phillip.

Re:No no no, this is all wrong

[Cycon]

I don't want a "webpad" with a pen interface. I want a wireless, diskless laptop running as an X terminal to my PC. Think about it

Actually, there's not reason that you can't have it both ways. As I recall, Any VNC Server is accessable through any java-enable browser. It's not quite as fast as a straight client, but then again, who says that won't be available, esp if the OS underneath it all is running Linux?

Re:No no no, this is all wrong

[Anonymous Coward]

Actually the web pad has no hard drive and is running an X server from flash rom. You could easily use it as a remote X display, and the thing made no noise at all. There was no cpu fan.

On the corded keyboard, you must rule out character 0 as a no-key or key-up, and that aside, I don't think grandma could ever learn to type in binary.

Even so, since this thing will be running linux, you'd probably have the source code to make it act however you want.

The datasheets are useless for design

[geirt]

I have read the data sheets at

http://www2adm.transmeta.com/crusoe/download/pdf/T M3120_DataSheet_1-18-00.pdf

and

http://www2adm.transmeta.com/crusoe/download/pdf/T M5400_DataSheet_1-18-00.pdf

and the chips are impressive. But the data sheets are very incomplete (the TM3120 data sheet is only 6 pages !!). No pinout, no electrical specifications, no programming info, no absolute maximum ratings, etc. They need an additional 1000 pages of documentation before you actually can design anything with it.

What IPO?

[Christopher B. Brown]

I've gotten unsolicited email asking what exchange Transmeta is trading on; apparently some people have no clue.

Transmeta is not a publicly traded company, and so is not required to disclose ownership information to the public. It is known that Paul Allen's Vulcan Group has money in it; other venture capital groups were mentioned in the presentation yesterday; presumably the employees have gotten offered some equity whether as stock or as options on stock.

The stock could certainly head up from zero, but presumably the venture capital folk would want to have some return on their investment, and so it would take a fairly high valuation for selling out to prove worthwhile.

Re:What IPO?

[Anonymous Coward]

If you watched the meeting you would have seen this question, someone asked if Transmeta was filing IPO anytime soon, and one of the rep.'s responded "We have more than enough funding from IBM and many other intrested investors, so we are in no current need for filing IPO, although it may happen eventually." kyle@dontspam.lives.in.theasylum.net

But why use a Crusoe?

[luckykaa]

I thought the main benefit of the Crusoe was that it could emulate all other processors.

The power consumption is good, but so is the power consumption of a StrongArm. What benefits does the Crusoe have? Its not like we need to run Excel on a WebPad.

Re:But why use a Crusoe?

[Anonymous Coward]

> I thought the main benefit of the Crusoe was that it could emulate all other processors.

Not the main benefit, no.

Crusoe does appear to isolate the virtual machine platform (currently an X86 emulation) from the hardware platform. This has a couple of interesting benefits. The first is that your underlying hardware can change at any time without breaking your software (this includes the OS and all applications.)

So while it is theoretically possible to emulate many chipsets, in most cases there's probably very little reason for Transmeta to expend the development effort required to do so. A possible exception is Java. Crusoe is imho exceptionally well suited to inline Java emulation (probably using the X86 memory management hardware to mark specific pages as Java bytecode). Interestingly enough, Transmeta acknowledged that Sun's work on dynamic compilation for Java parallelled a lot of their own development of the code morphing software.

So you won't see Transmeta's marketing strategy promote the Crusoe as a general purpose cpu emulator. They're very specific. They want a slice of the X86 market.

To me, Crusoe's main benefit is the ability to break away from the X86 architecture while maintaining compatibility with existing operating systems and applications.

Consequently, Transmeta can implement the actual computing engine using any architecture they wish. They do take a performance hit but it appears acceptable and performance seems likely to improve as development continues on their code morphing software.

Assuming performance is acceptable to the majority of OEM's, a couple of interesting possibilities suggest themselves.

One (raised by Transmeta at the briefing) is that bugs in their X86 implementation can be corrected by updating the code morphing software. This allows correction of (for example) floating point division flaws by downloading a cpu patch over the Net. Such updates can be generated by Transmeta extremely quickly.

(Of course, bugs in their underlying VLIW hardware will of course require a new silicon pass to fix properly, but there is the interesting possibility that they could release code updates to work around such flaws anyway.)

The second, is the potential for OEM's or other interested groups to lobby Transmeta for the creation of custom opcode extensions to the X86 chipset. Such extensions could then be distributed directly with the software that required them.

(I can see it now: Requirements - Pentium II 500 or Crusoe version 2.62 or higher)

> The power consumption is good, but so is the power consumption of a StrongArm.

Well the StrongArm has a somewhat lower software base than the current Intel dominated market. Much as I like the StrongArm, I think Crusoe will annihilate it.


> What benefits does the Crusoe have? Its not like we need to run Excel on a WebPad.

No, the WebPad runs mobile Linux. The idea is to have a web enabled device that is low power but can also leverage the Open Source behemoth that is Linux. Once the WebPad hits critical mass (or possbily even before), I can see the number of WebPad compatible applications exceeding the number of Windows CE compatible apps by several orders of magnitude.

The 5400 is designed as a replacement for Intel's notebook cpus. In addition to the base flexibility of the Crusoe processor, the dynamic power management allows the chip to run cool, saves battery life and eliminates the need for a fan in your notebook (which further extends the battery life).

Transmeta's marketing people estimate battery life of about 200% over a standard notebook pc. This is probably just wild speculation on their part, but it sounds like a fair estimation to me.

Re:But why use a Crusoe?

[altman]

StrongARM is *already* much lower power consumption than the Crusoe 3120: some of the Crusoe figures are quite funny. Looking at the 3120 datasheet, it takes a mere (!) 1.4W whilst playing mp3's.

Compare this to around 0.075W (30% usage, CPU static when not doing decode) for a StrongARM doing MP3 decode. Hey, even *flat out* a 200Mhz, 1.5v core StrongARM on a 3-year old 0.25 micro process takes less than 0.25W. Just wait for the SA-2 stuff coming out this year - they're claiming more than 2x the performance whilst using less power.

Transmeta pushing mobile linux (and OEMs making 1st-gen designs around it, application support, etc) will probably ultimately benefit *real* low-power chips like the ARM, as linux applications (to a large extent) are pretty architecture-agnostic.

Looking at embedded machines, the Crusoe CPU also needs a lot of support circuitry. As an example, the SA1100 includes (on chip) a PCMCIA interface, real time clock, TFT/passive LCD drive, sound codec port, MMU, DRAM controller, USB slave, IrDA (SIR/FIR), sync serial port, a couple of async serials, and plenty of GPIO pins. Heck, it's almost a webpad on its own - which is why the Itsy can be so small, so cute, and still run off a couple of AA cells while playing .mov's. Add the 1101 companion and you get VGA, PS/2 mouse/kb, USB host and more besides.

The crusoe is impressive as an x86 chip. Once you leave that narrow (in embedded terms) slot, the performance doesn't really measure up to offerings from ARM, MIPS, etc.

Hugo

Re:But why use a Crusoe?

[Anonymous Coward]

I came to the same conclusion in a different thread. The SA-1100 can already do crunchy stuff (mpeg video decode), run linux (ARMLinux), etc.

And with all the support gear the SA-1100 includes (audio, video, serial, etc, etc) it still draws far less power using an older fab process!

--Pat / zippy@cs.brandeis.edu

Sorry typo!

[drnomad]

I meant enemies

Quickly?

[jbrw]

"It's nice to see things taking shape for Crusoe so quickly"...

It's been five or more years, hasn't it?

...j

Re:Quickly?

[Anonymous Coward]

You're just being bitchy. "Quickly" in respect to the first public announcement.

Re:Quickly?

[SEWilco]

"It takes twenty years to become an overnight success"

Something important seems to be missing

[Anonymous Coward]

... a decent web browser.

Re:Something important seems to be missing

[fr0g]

Umm didnt they show one of the hand held web devices running Netscape?


or is that not a decent web browser?

Re:Something important seems to be missing

[gargle]

You guess :)

I wonder what Dell will do?

[vanguard]

I wonder if Dell will using the Transmeta chip? While I don't pretend to understand the details of chip design, it seems like OEMs would be missing out on a speedy, cheap, low wattage chip if they ignored Crusoe. Also, we know Dell has been chomping at the bit to find other products to help them maintain their growth and profit margins.

On the other hand, Dell has always enjoyed "Best Customer" status from Intel when their supplies are running low while disloyal companies like Gateway get the shaft.

If you were Michael Dell what would you do? Would you enter a high growth area and risk your PC business or stay with Intel all the way?

Re:I wonder what Dell will do?

[Larry_Z]

But haven't Dell and IBM announced a very tight partnership, especially in the notebook division. While we know Transmeta didn't say much about OEMs IBM's name came up more than once. It would seem that Dell would sell the Crusoe processor almost defacto, through their cobranded IBM products.

Re:I wonder what Dell will do?

[Anonymous Coward]

Well if Dell really do want to find other products why are they so reluctant to deal with AMD? Playing both Intel and AMD off against each other, especially now that AMD is as fast as Intel means you can't lose, should get lower prices. So if you do that, you may as well include Transmeta in your plans. A/C due to not having an account. Snail.

Re:I wonder what Dell will do?

[belgin]

But haven't Dell and IBM announced a very tight partnership, especially in the notebook division. While we know Transmeta didn't say much about OEMs IBM's name came up more than once. It would seem that Dell would sell the Crusoe processor almost defacto, through their cobranded IBM products.

This partnership has not really included processors, thus far. Dell uses IBM hard drives, pretty much the best in the quality department. Dell uses IBM Global Services to do all of their support stuff, and shares technology, etc. Processors isn't part of the deal yet, as far as I know. However, the vast majority of IBM employees didn't know we were involved in Transmeta to any great degree before yesterday. (Yes, I work for IBM.)

B. Elgin

Re:I wonder what Dell will do?

[Anonymous Coward]

Dell's deal is with the IBM components division, not the PC company.

Actually, this would be lovely

[aheitner]

At CMU we now have wireless ethernet everywhere on campus. It's not all that fast, just 1-2 mbit, but it's enough. You can very reasonably run your laptop with X -query yourhomemachine.res.cmu.edu and have everything everywhere.

Till your battery runs out after an hour and a half.

But give me 6 (better, 12) hours of batter life and things begin to look very reasonable. With X style connectivity in a campus environment, you could have all the power of your desktop with you everywhere. Granted, it may be some time before areas larger than a college campus can be wired like this, but it is reasonable for businesses. So if you're willing to do most of your computing in a limited area (i.e. you do spend 40+ hours a week at work or at school, right?), you can have excellent connectivity today. How fast is PalmVII's "everywhere" connectivity? I imagine it'll be some time before that goes broadband...

sigh. I think my SPARC laptop is what Ditzel was talking about when he said people weren't willing to deal with 10 pound laptops that run 90 minutes :)

Re:Actually, this would be lovely

[psin psycle]

So if you're willing to do most of your computing in a limited area

I usually do most of my computing within a few feet of my very difficult to move 17" monitor :)

Re:Actually, this would be lovely

[disappear]

I get six hours of battery life. Sony Vaio Z505S with the "3-hour" extended battery. I don't get six if I'm building kernels all the time, but if I'm in vi and playing nethack, I get six easily.

OTOH, with Crusoe, double the battery life and shave another pound off of it and I'll buy it all over again.

Aarrggh!

[icing]

Someone announces a chip and the someone else announces a computer using that chip and now we have comments on /. like "wow, cool, this is a nice product!"

Give me a break.

three transmeta stories at once?!

[Anonymous Coward]

Come on people. 3 Transmeta stories at once on the front page?! Doesn't anyone think this is a bit much. Someone must be so excited over Transmeta that their going to tinkle in their shorts if they're not careful.

How about all the companies that have actual products, performance, documentation, etc.?

Re:three transmeta stories at once?!

[springpin]

No kidding. After all this suspense, I was hoping for something more along the lines of a Warp Drive or something.

Shame on Diamond

[Anonymous Coward]

TSK TSK Diamond!!! I have lost all respect for your institution. In Iran we have a saying "You use crap parts, your institution is crap."

You are crap. All you Americans are crap and I hope a camel fornicates with you and Allah punishes you for beastiality.

But the question is this? What does this all have to do with LIIIINNNNUUUXXXXXX!!!!!!!!!!

Im not sure! Let me poll the audience.
OK

A) nothing - 12%
B) linus is my false god - 66%
C) MEEPT! - 1%
D) /. sucks, rob sucks, hemos is a woman, first post baybee - 21%

hmmmm......well Mr. Moderator, I'm going to go 50-50!
OK

B) linus is my false god
C) MEEPT! - 1%


hmmm......well Linus is not my God, only Allah! Praise be Allah! and MEEPT cannot be worried over matters such as this....so I shall call a friend Mr. Moderator.
OK. The fascist corporation of AT&T is now calling Bill Gates.
Bill: Hello?
AC: Hi Billy Boy! I just called to tell you I am going to be a billionare!!!!!
Bill: .....I could buy you and your family. Leave me alone peasant!
CLICK

So Mr. Moderator, my final repsonse is...........

E) YOU HAVE BEEN TROLLED!

PDA Purchase Delayed

[dkh2]

I had plans to buy one of those PalmPilot thingies later this spring. I was also looking at the TRGpro as another option. After seeing the Transmeta presentation yesterday I'm starting to think seriously about postponing that purchase to see what happens with Crusoe.
"For every complex problem, there is a solution that is simple, neat, and wrong."

Time for an annual hypocracy award?

[MassacrE]

If Diamond indeed ships out a Webpad running Mobile Linux (their page lacks any press releases at this point), I think they surely deserve some sort of Hypocracy Award, if not an annual award than a 'Lifetime Acceivement' award. It would be truely ironic for a company to ship a webpad that only runs linux, after years and years of outright denying specs for things as trivial as the Rio uploading code (claiming it was "valuable intellectual property") to things like specs/help on video card drivers (based on S3 chips, the big help was needed because Diamond deviated in such fscked-up ways from the reference design).

Yes, Diamond deserves a nice trophy anyways, but if they really plan to ship an entire computer now (mobile or not) running the linux operating sytem when they have yet to support a single project under linux.. well, let me just say it is too early in the morning for me to fully imagine what the figurine at the top of the trophy should look like, and what it will be doing ;-)

Re:Time for an annual hypocracy award?

[orcrist]

well, let me just say it is too early in the morning for me to fully imagine what the figurine at the top of the trophy should look like, and what it will be doing ;-)

A two-faced figure bending over backward to kiss Tux's ass?

Chris

Re:Time for an annual hypocracy award?

[Paul Komarek]

Diamonds support of non-MS operating systems for its video cards is much better now than it used to be. They even get special mention on the XFree86 lists.

-Paul Komarek

Nice how attention has been diverted...

[TREMOR]

I was REALLY excited about the Crusoe chip when speculation first arose that it would be able to run executables from multiple hardware platforms. Then came the speculation that Crusoe would be aimed at the mobile market (I lose 50% interest right here).

Now that Transmeta has made their announcement, I have no real interest left in it. They've done a nice job of diverting attention to it's power consumption, and that's about it. It's x86 compatible...so what? It's theoretically compatible with lot's of stuff, so pony up. I wouldn't buy one of these JUST because it's not Intel (I don't use PDA stuff, so that's not a big drawing point for me). My MAIN interest was in being able to run applications written for Apple computers, or Sun workstations. And then you have the benchmarks...nice fluff work there. Combining their low power consumption (see, here it is again) with performance doesn't even come CLOSE to giving a fair representation of how it stacks up against a comparably clocked Intel or AMD chip.

And of course, the price on those web "appliances" (aren't you sick of that term?) is still too high for what amounts to a big kids toy. You're not going to get any real work done without a keyboard (in most cases) so basically what you are paying for is a $500 - $1000 Rolodex with some added functionality. (And yes, I know, virtual keyboard or whatever they called it. Did you ever try to do any touch typing on the old Atari 400 membrane keyboard? If so, you know my objection here)

I really think notebooks are going to be where Crusoe blooms, if for no other reason than to not melt your lap while your working with it. But is $329 for the 700MHz really any kind of a bargain?

Re:Nice how attention has been diverted...

[technos]

Yes, yes I did. It only took me two months of trying before I went out and bought the Atari 800, with a 'full' keyboard. Granted, it was better than the chicklet keyboard on the TI or the sloppy strokes of a PET, but it just didn't measure up to the Ann Arbor terminal I had back in those days..

Re:Nice how attention has been diverted...

[tzanger]

And of course, the price on those web "appliances" (aren't you sick of that term?) is still too high for what amounts to a big kids toy. You're not going to get any real work done without a keyboard (in most cases) so basically what you are paying for is a $500 - $1000 Rolodex with some added functionality.

Think broader. A net-accessible device that runs for weeks. It's not just a rolodex. It's an extension of the 'net that you have anywhere you go. That opens up tons of opportunites in all manner of fields: instrumentation, administration, gaming, medical, scientific... And that's not even going into the geek sector. Sit on the can and web-browse. Read in bed. Code in your lazy-boy. Browse/code anywhere in the transit system.

(And yes, I know, virtual keyboard or whatever they called it. Did you ever try to do any touch typing on the old Atari 400 membrane keyboard? If so, you know my objection here)

I too saw little use there. Similar to the Palm pop-up keyboard. Blah. I'll carry along a fold-up USB keyboard (there is a serial one for palm in the making).

Remember that this device is targetted for mobile and low power apps. You don't need to learn new APIs or chips. Use what you know; the chip will emulate it. I didn't see anywhere the option to code it in its native language but then again you would lose the self-optimization that it is capable of doing. This is a good and bad thing.

Transmeta didn't just show off the power consumption, although that is a MAJOR big thing. They also showed off its "code morphing", dynamic optimization and emulation features. Don't write this off; this is a major hit.

Re:Nice how attention has been diverted...

[tzanger]

Sorry about that, I didn't grab the last part I wanted to comment on.

I really think notebooks are going to be where Crusoe blooms, if for no other reason than to not melt your lap while your working with it. But is $329 for the 700MHz really any kind of a bargain?

At 1/60 the power consumption it'll do more than not melt in your lap. Your batteries will last longer. It'll run quieter. Replace the HDD with a lower-power device and it'll run longer and quieter yet. The laptop can be physically smaller (no heat pipe/fans and at least 1/2 the chipset is gone). Those are some major savings. How much does a mobile P3-700 cost? I betcha it's more than $329 and you need to add on those items I mentioned above.

Re:Nice how attention has been diverted...

[David Greene]

Some of us were thinking about the x86 issue today. Obviously, Transmeta chose the x86 because of its market share.

Then it hit us. Crusoe can do well at x86 translation because of the utter lack of registers on the x86. If Crusoe even does just an average job of mapping of memory operations to registers (stack locations come to mind), that in itself could cover a lot of the translation overhead. Especially if the code cache is working well.

PowerPC, Sparc, etc. may not translate as well because their ISA's have more registers. There is not a lot of spill code in those object files. One win that could be had here is getting rid of some of the function call overhead. Saving and restoring registers is nasty stuff.

--

The interesting thing about Crusoe is

[Kaa]

...not that is it reasonably low-powered. The interesting thing is that Transmeta is actively trying to prevent people from writing in its native instruction set, thus creating historic compatibility problems. If successful, Transmeta will be able to change chip architecture, instruction set, etc. etc. without breaking any existing applications.

This is a big thing -- consider that PIIIs and Athlons still have to be able to pretend they are 8088 processors. If you believes that does not put a huge cramp in their style, think again. If Crusoe manages to be free from this limitation, it could evolve much faster than the usual CPUs. That could be a decisive advantage several years down the road.

Kaa

Re:The interesting thing about Crusoe is

[PhilipKDick]

I don't get your point really. How can you say that they will end the legacy support hell if their primary target with Crusoe is x86?

They are promoting Crusoe as a x86 emulator for a reason. They claim that it's only because of the advantage of large software base but I find it quite hard to believe. Why? Because if Crusoe really is that flexible they should have released code morphing code for at least a few of the major chips out there: PowerPC, Mips, Sparc. why not have a competitive advantage? Why not grab the whole market with one big sweep?

Instead they decided to release x86 instructions. Duh! How is that freeing us from the legacy loophole? software that can run on Crusoe must be written as if it's an Intel chip because they won't publish the internal opcodes. If they really wanted to be innovative then at least they could have come up with some nice modern instruction set that would not be a pain to code with. In other words create a "native" Crusoe platform. I suspect that this whole code morphing business is just blowing hot air! If it's so flexible show me some alternative emulations. Yes, I know it handles Java bytecodes but they were designed by Sun so they are very straightforward to implement in hardware (think Sun's Java chips).

So I think the concept behind the Crusoe is an extremely powerful idea, much more powerful than the whole Java business or the mobile fad that's going on. I feel that Transmeta either bastardized their own market by not supplying additional code morphing software or they simply can't techincally do it because their focus on x86 compromised the flexibilty of Crusoe's design.

Re:The interesting thing about Crusoe is

[Anonymous Coward]

I don't get your point really. How can you say that they will end the legacy support hell if their primary target with Crusoe is x86?

I'm not the original poster, but I'd like to try and answer this.

The primary target is X86 because that's how they'll make money. The emulation allows them to break with the X86 *hardware* architecture. This allows them to employ techniques which would otherwise be impractical or restricted on an X86 legacy hardware platform.

They are promoting Crusoe as a x86 emulator for a reason. They claim that it's only because of the advantage of large software base but I find it quite hard to believe. Why? Because if Crusoe really is that flexible they should have released code morphing code for at least a few of the major chips out there: PowerPC, Mips, Sparc. why not have a competitive advantage? Why not grab the whole market with one big sweep?

Mips, Sparc, PowerPC. The return for emulating these three would simply not justify the development effort required. The X86 market is the largest market on the planet. Choosing what cpu to emulate really is a no-brainer.

Instead they decided to release x86 instructions. Duh! How is that freeing us from the legacy loophole? software that can run on Crusoe must be written as if it's an Intel chip because they won't publish the internal opcodes. If they really wanted to be innovative then at least they could have come up with some nice modern instruction set that would not be a pain to code with. In other words create a "native" Crusoe platform.

Yeah. And they'll ship around 100 units. You can't compete with the Intel juggernaut, it's too late. A new CPU has zero chance of competing as an alternative to the Intel CPU's *unless* it's backward compatible with them. Again, this is painfully obvious.

And publishing the opcodes really would defeat the purpose of the exercise. It'd immediately tie them down to maintaining legacy hardware compatibility with previous Crusoe hardware implementations. This is exactly what they don't want. They want the ability to totally transform the hardware without impacting upon legacy applications at all.

I suspect that this whole code morphing business is just blowing hot air! If it's so flexible show me some alternative emulations. Yes, I know it handles Java bytecodes but they were designed by Sun so they are very straightforward to implement in hardware (think Sun's Java chips).

The current VLIW hardware platforms are designed so that Intel instructions map well onto the VLIW instruction set. Other CPU's may not map so well but the difference would be reflected in performance and frankly... who cares.

The PowerPC probably represents the largest alternative consumer target market and it's dwarfed by the X86 market. There may be some opportunity for a PowerPC emulation at a later stage but the return (which would consist of selling Crusoe chips to Apple for their portable Imac's) would have to justify it.

So I think the concept behind the Crusoe is an extremely powerful idea, much more powerful than the whole Java business or the mobile fad that's going on. I feel that Transmeta either bastardized their own market by not supplying additional code morphing software or they simply can't techincally do it because their focus on x86 compromised the flexibilty of Crusoe's design.

Rubbish. Their focus on X86 is based on their desire to make a buck. Additional code morphing software is simply not required because the market isn't there to justify it. You could only justify the PowerPC emulation if you were extremely generous. You also have a slight problem in that Apple is your only OEM. Apple won't commit until you can demonstrate tangible benefits, but who wants to spend goodness knows how much time and money developing the code morphing software for a single vendor that may not even pick up your product.

Re:The interesting thing about Crusoe is

[aok]

Actually I tend to agree with the original poster.

It doesn't free _us_ from the legacy x86 "loophole". Instead, it frees Transmeta of this legacy loophole.

By maintaining compatibility with the x86 instruction set via software translation, they should be able to change the hardware design a lot more freely. The legacy x86 support then does not become a crutch to them as it is with other cpu makers so they can completely change from VLIW or whatever if something better comes along. I think having the legacy x86 support is more important than you believe. Why has Intel stayed with that for so long? Their OEM customers want to be able to run all those Windows-based software. I don't think the OEM's would be interested in other architectures.

During the Q&A, they had said that they had to reverse engineer the x86 and MMX from scratch. I would assume that this takes a lot of time (and money) and they'd probably don't want to delay their products by reverse engineering all the other chips you've mentioned and writing code-morphing for all of them (for the time being). It might be simple to do, but it sure takes a lot of time.

Re:The interesting thing about Crusoe is

[springpin]

You have a point. But remember that intel is stuck with an almost 20 year old instruction set because they want to maintain backwards compatability. Transmeta can make any change to their processor that they want and just write new CMS to utilize those changes. So I don't think a fuocus on x86 will hurt them too bad since they can optimize for something else later and have some new CMS to make it compatible with whatever they want.

You're right that x86 is still a relatively old and backwards instruction set, and it still sucks that Transmeta still forces you to code for it. But the difference is, they can make a switch to a new instruction set whenever they want and still support older software.....as long as no one writes any native code that isn't CMS.

There may not be any CMS that isn't x86 yet, but it's only a matter of time. We can't use x86 forever.

And plus, it's my understanding that this whole VLIW thing is in its infancy; 1st gen RISC chips weren't that great either, so I'm betting that by the time we get to 4th and 5th generation Crusoe chips, they'll be pretty hot.

Re:The interesting thing about Crusoe is

[Anonymous Coward]

>If successful, Transmeta will be able to change chip architecture, instruction set, etc. etc. without breaking any existing applications.

Ooh, that's impressive!

IBM have been doing this for about a squillion years on their as/400 boxes.

Re:The interesting thing about Crusoe is

[BinxBolling]

Rubbish. Their focus on X86 is based on their desire to make a buck. Additional code morphing software is simply not required because the market isn't there to justify it.

It's quite possible that they're releasing the current Crusoe and hyping the low power requirements because it's a way for them to go ahead and start making some revenue to fund future development. There's no reason to assume that Crusoe is the ultimate application they've visualized for the technology.

You could only justify the PowerPC emulation if you were extremely generous.

One of the beauties of the software-based approach is that Transmeta need not develop emulation themselves for every IS that gets supported. They could license the required technical info (VLIW layer, etc.) to Apple under NDA, and let Apple develop the PPC morphing layer. So this way they both make money from the licensing, and from selling chips to Apple. Generosity need not enter into it.

Re:The interesting thing about Crusoe is

[sammy baby]

Except that IBM has total control over the architecture, and uses what they call the TIMI (Technology Independent Machine Interface) to translate between applications and various versions of the AS400 hardware.

Whereas Crusoe can translate between... well, theoretically, any instruction set, and its native enviornment.

Which means they're not the same at all.

Re:The interesting thing about Crusoe is

[Anonymous Coward]

So is it interpreting each instruction set?

Surely they can't build in support for every known opcode/addressing mode/status registers/bug-in-intel etc?

Re:The interesting thing about Crusoe is

[sammy baby]

Actually, I believe they can. From the Transmeta web pages:

Transmeta's Code Morphing technology is obviously not limited to x86 implementations.

That's not to say that they actually will - getting every last instruction set in there probably would be more work than it's worth. (Of course, I can make this bold statement because I have precisely no idea how much work it is.) But if it can perfectly emulate (and optimize!) the x86 set, I don't see why they couldn't build the code morphing layer around whatever set they feel like.

Beware of New Diamond Products

[winterstorm]

I absolutely love the idea of Webpads. In fact I'm posting this from my Sharp Triapd connected via wireless ethernet. I would never buy a new device from Diamond though. Since the technology is new there is a greater than average chance that you'll have to send your device in for RMA work. As anyone who has dealt with Diamond's RMA department can tell you... there is a good chance you'll never see your device again after you send it in for warranty work. You'll be out-of-pocket for the cost of the device and have nothing to show for it.

Yep, that's what I want too

[delevant]

. . . although I'd disagree about the key-chording, but that's probably just because I'm a keyboard bigot . . .

But seriously, what about the Clio form-factor? Clio sucks because it uses WinCE (I own a CE device, and CE still sucks). From a design perspective, Clio rocks the house! I *love* that reversable laptop-now-it's-a-slate concept.

If someone could make a Clio-shaped device with a bigger screen and an easily-accessible CompactFlash slot (IBM Microdrive!) -- I'd buy one in an instant.

Also, you can get around the problems of wireless range depending on what tech you use. A powerful, but battery-destroying, option would be to include a cellmodem that automatically switched into action when you moved outside of regular wireless range.

Lastly, let's not forget about durability. With the Clio form-factor, I'd say use crazy alloys or carbon-fiber. Of course, that would cost a fortune, but *man* it might be worth it.

No CrusoePalm

[dmorin]

PDABuzz is reporting that Transmeta doesn't plan to get into the PDA market with their chip, instead choosing to go after the "sub 4lb notebook" category. Makes sense -- as people have pointed out, there are already processors out there like the StrongARM that make Crusoe look like not such a big accomplishement. PDA's don't necessarily need x86 compatibility, as we've seen. (Unless you're one of those evil Wince people :)).

d

Re:No CrusoePalm

[samael]

>PDA's don't necessarily need x86 compatibility, as we've seen. (Unless you're one of those evil Wince people :)).


Win CE doesn't require x86 compatibility either. It's designed to compile on all sorts of chips.

Re:No CrusoePalm

[Anonymous Coward]

There is no WinCE.

Jumping on? So quickly?

[dmorin]

Ummm...sorry, but just because Transmeta finally decided to share their toy with us publicly doesn't mean that it's the first time any of these companies is glimpsing it. I would suspect that those deals have been ready to go for a long time, and companies like Diamond have merely been sitting under NDA waiting until the Big Day. On the subject of quickly, how long has Transmeta been around? In theory, the marketroids could have cut the deals before work on the chip even began.

Beware, that links to a Jesse Berst article!!

[Smack]

How dare you... linking w/o attribution. I've sworn his articles off. Now I feel dirty.

A Question:

[Rabbins]

I just had a friend write to me and ask about a company called Seligman Communications & Information. The reason he asked was because he thought this company owned Transmeta??????

Well that is not a company, it is a mutual fund. How on Earth did he hear this, especially considering he works for IBM?

Re:A Question:

[cantrade]

The reference to Seligman came from the Wall Street Journal article about Transmeta. That may be a valid way to sidestream an investment with the co. since it's not public yet. But it's not profitible yet either. Lots of interest may spur an IPO to get some more cash into the company.

THEY ARE A BUSINESS - hypocrisy is normal

[Smack]

Excuse me, but why were they supposed to spend time and money developing drivers for Linux? To support the small market that would develop them themselves anyway, at no cost to Diamond? I don't think so. Not a smart business decision.

Now using Linux on a webpad... Well, it's free. Much cheaper than Win98. That's a smart business decision. Maybe they are hypocritical from your viewpoint. But from the viewpoint of their investors, they're quite consistent. They always act in the way that will gain them the most money. That's how public businesses are REQUIRED to operated.

Re:THEY ARE A BUSINESS - hypocrisy is normal

[Ralph Wiggam]

Hey, that's about enough common sense capitalism out of you. Here on Slashdot, any company that doesn't spend millions of dollars on Linux development with remote prospects of return is evil and should be burned to the ground.

On a less sarcastic note: When a company like Diamond is making its money off of hardware, there's something to be said about customer support. It's not like they need a 100 person staff working around the clock. If they would just cooperate more, people wouldn't hate them.

-B

Re:THEY ARE A BUSINESS - hypocrisy is normal

[gfxguy]

To support the small market that would develop them themselves anyway, at no cost to Diamond?

But they would never even release the specs to the community to allow this free development... In other words, it wasn't about spending money on development, it was about helping MS alienate a particular group in the hopes that they'd eventually "just go away." Why? Make it easier on themselves, I suppose. As far as I can tell, the NEVER released specifications openly, and never officially supported anything but MS operating systems (not OS/2, not Be, not anything but MS).

So the hypocritical part is that now, not only are they finally recognizing there is a world outside of MS, they are releasing a product based on that fact.

----------

Re:THEY ARE A BUSINESS - hypocrisy is normal

[Mawbid]

(The following is tangential to your main point, with which I agree)

I don't imagine the poster you're responding to has any interest in seeing Diamond develop and release Linux drivers and support programs. He specifically mentioned specs. It's better for the open source community (including not only the Linux community) to receive the specs and write its own drivers and utilities than to have some binaries handed to it.

Now, I'm not familiar with the Rio uploading issue, but if MassacrE's description is correct, Diamond denied requests for specs from people who were willing to write and release, at no cost to Diamond, tools that would make the Rio usable for more people. Is that a smart business decision?

Often it seems like we free software commies and linux zealots want companies to give us their goods for free. We want something for nothing and when we get it, we thoroughly inspect the gift horse's mouth. What a bunch of ungrateful, demanding losers!

I can only speak for myself, but when I complain about companies not releasing information, it's not because I think I have a right to get it or that they don't have the right to control it or that "information wants to be free". It's because I feel it would be in everybody's best interest if the information were free. "Everbody" includes the company. By stubbornly guarding register specs etc., I feel a hardware maker is shooting himself in the foot, locking out potential buyers and inadequately supporting their current customers. If I'm not a current customer, that's fine. I just spend my money elsewhere. But if I am, then I have a problem that exists solely for illogical reasons of corporate paranoia and that is what bugs me so much.
--

Re:THEY ARE A BUSINESS - hypocrisy is normal

[sjames]

Excuse me, but why were they supposed to spend time and money developing drivers for Linux?

Why did they steadfastly REFUSE to release any documentation on how to communicate with the Rio (which they should have known would be figured out anyway) so that Linux developers could create the tools for them gratis? Now that's a REALLY dumb business decision. Gain the appreciation of a small but vocal and growing market for FREE or be the bad guy (also FREE) in order to gain a brief delay before everyone knows how to interface with your device anyway (I think they 'gained' a whole 4-6 months). I thought free positive PR was a good thing!

Let's have some real innovation

[Steeltoe]

Such chords are slow, error-prone, non-intuitive and cumbersome. It is suitable only for people familiar with playing piano or similar instruments. While a keyboard is big and clunky, or else difficuly to use. I would recommend a "webpad" device to be modular, so that you can connect a small keyboard or mouse to it if you want to. Or any USB- and network device you like for that matter.

I fully agree these "webpads" should have the same capabilities that laptops have today. Just strip them of CD-ROM, harddrive, cooling-fan and much of the other baggage. They might serve as mobile display-panels which you may connect to your laptop, TV-outlet, VCR or whatever. It should be possible to fasten them physically to a display-less laptop machine of the future. In fact, all these devices (e.g. keyboard, trackball) should be possible to fasten physically to each other by using a holder between them or something.

Btw, with 8 buttons and 2 fingers you have a total of 7+6+5+4+3+2+1=28 unique combinations. Personally I like to have choices on the same device, and I prefer Palm-like pen interface for such small devices. But anyone who wants to
connect to it a mouse, trackball or touchpad instead I fully support.

These ideas cannot be patented as this is "prior art" too. ;-)

- Steeltoe

Re:Let's have some real innovation

[Anonymous Coward]

On the subject of keyboards - the best keyboard on any small-enough-to-be-useful PDA I've seen is the psion 5mx keyboard. I use mine a lot for telnetting into my PC. It's quite pleasant to touch type on, and at my normal usage levels, the psion (36MHz ARM 710 CPU) batteries last for ages.

Star Trek[tm] PADD's - Couldn't help but notice...

[NeoTron]

...the similarity of the look between the WebPad and the PADD's from the sci-fi series...

"Captain's Log, Star........"

(A ramble, I know, but I'm on early shift, and it's only 20 mins to go home )...

but we do need to run Netscape...

[Smack]

...and all the related plug-ins. Every time a story is posted on Slashdot that link to a .mov file or a RealAudio file, people bitch because the appropriate software isn't available on Linux. It's surely not available on StrongArm! But it is availabe on Windows. So to really get a quality web browsing portable at this time, it has to be X86 compatible. Which leaves StrongArm in the cold.

Re:but we do need to run Netscape...

[luckykaa]

This suggests that despite all the impressive morphing technology, most companies only want a low power x86.

I'm sure Transmeta don't really care as long as a sale's a sale, but it just seems a bit of a waste.

Re:but we do need to run Netscape...

[orcrist]

This suggests that despite all the impressive morphing technology, most companies only want a low power x86.

Most hardware companies want to sell their products. Starting with compatibility to such a widespread architecture means a solid base of code for several operating systems which will run out of the box with devices running Crusoe.

I'm sure Transmeta don't really care as long as a sale's a sale, but it just seems a bit of a waste.

They mentioned specifically that this is only the tip of the iceburg. It sounds like a solid strategy: build up some trust and reputation in the industry as well as get some return on their investments (a couple hundred million IIRC); meanwhile they can refine more innovative things to do with the chip. It sounds like they've left a lot of room to improve.

Chris

Re:Silence from the Open Source Movement?

[Anonymous Coward]

Are you a bot? or is there a real person powering that broken record?

Re:big flipping whoopie

[auntfloyd]

Don't you understand? LINUS TORVALDS, creator of Linux, works there! Therefore, we are all compelled to PURCHASE TRANSMETA PRODUCTS in the hopes that we may somehow be buying a piece of the man we so dearly love and admire.

CONSUME! CONSUME! CONSUME! CONSUME! CONSUME! CONSUME! BUY! BUY! BUY! BUY! BUY!

~~~~~~~~~
auntfloyd

Clio is close...

[PhineasFrog]

There's a project going on now to port Linux to the MIPS processor, with complete emphasis on the mini, till now CE type devices. The Clio is the big one, in fact. The folks on the project actually have a Linux Kernel running in ROM on a Clio, I believe!

(Cooler people than me have the details here)

The depressing hang-ups at this point are really:

• Power sucks- the Clio isn't exactly long life (look ma, I'm on topic :)
• The fact that Linux isn't really built for living in in such cramped quarters (except maybe now it is- any word on Mobile Linux from our fearless leader?)
• The lack of little, artsy apps in a light framework to run on the thing (except I hear Squeak is going well for you Dynabooky types, and then there's always the Gimp, if it could be pared down... And its only a matter of time till somebody smart builds a Flash editor, now that the format is open...And some professional music sequencing software is coming out here, too, some of it has to be smallish...And then there's film editing stuff..never mind)
• umm.. did I mention power?

The Clio's design may be copyrighted (You'll have to ask Vadem about that...)

You didn't need to imagine this

[tilly]

You were thinking of the, "Head up ass" reward?

:-P

Cheers,
Ben

This isn't "quick"

[barzok]

In the press conference yesterday TransMeta said they have had customers lined up and ready to introduce products for quite some time. My guess is, they've been working with them for at least a year, under a VERY tight NDA, so that TransMeta could pop up at the conference with plenty of goodies to show off - and in the afterglow, those partners could say "here we are! we're on the trolley!"

Yeah right

[Anonymous Coward]

Yeah, usually when a company puts out a press release for a new product they understate the capabilities and overstate the price. That way it's a nice suprise for people when they find that product exceeds the manufacturer's claims.

Um, ya.

The Best Way to sell Transmeta products:

[auntfloyd]

Subliminal ads in the Linux kernel. If "Buy Transmeta(tm)" showed up for a few microsecs every now and then, don't you think their sales would increase?

They should force Torvalds to do it.

[joke -^ ]
~~~~~~~~~
auntfloyd

Future of high end PDA / low end laptop

[jeffcuscutis]

If the price point for these webpads drops to the $300-$400 range, does this mean the end of the PalmOS and WinCE?

Palm covers a nice niche (I know, I have one), but if I could get a webpad that is smaller than a laptop but larger than a palm and runs my software, Windows or Linux, why would I need a PDA? Now, I think Palm will continue on in lower cost PDAs but I think this is the death knell for WinCE. WinCE is the OS in search of a niche.

I think the biggest thing is the ability to use the same software as my desktop. In fact, you could use this as an entry level desktop that can go with you.

Imagine a ruggedized version with a solar recharger and wireless communications given to villages in third world countries. It could be used to teach children and keep the villages in contact.

Cool.

--jeff

Re:Future of high end PDA / low end laptop

[Anonymous Coward]

I think my village would rather have basic necessities met first, such as food,shelter,medicine,etc.

Its amazing how people will find problems to apply technology to, when in fact, they should be trying to find technology to solve problems.

-chairman.mao@unixville.com

Re:Future of high end PDA / low end laptop

[orcrist]

I think my village would rather have basic necessities met first, such as food, shelter, medicine, etc.

Give a man a fish, you feed him for a day. Teach him to fish...

Why do think such things are lacking? Knowledge is the key to fixing these things, and as long as the finite number of agricultural experts, civil engineers, doctors, etc have to travel to each location to help the people, they are limited severely. But transporting such devices to the villages in question so that villagers from several villages can consult with the appropriate expert all at the same time, or look up references to such information when an expert is not available...

Its amazing how people will find problems to apply technology to, when in fact, they should be trying to find technology to solve problems.

I realize that information is not the same as knowledge, but knowledge can be transmitted through information, and any technology which lowers the barriers to doing this is a very significant part of the solution to such problems.

It's amazing how people who want to help other people are so often not capable of seeing the forest for the trees...

Chris

I want one

[Dr. Sp0ng]

I don't know about you people, but I'd love to have one of these bitches... something about the combination between a wireless network connection and streaming porn just makes me want to spend $1000.

:-)

"Software is like sex- the best is for free"
-Linus Torvalds

What I think we were all really hoping for...

[PsychoSpunk]

Honestly, I thought Transmeta was going to announce their intentions to destroy the world by rereleasing "New Coke" in the form of a giant stream from outer space unless the monopoly known as Microsoft was brought to their knees and humbled. Thoroughly.

But I guess a webpad is cool too.

Dissemination of Misinformation

[Postmaster General]

From the original post:

"The report also mentions that NEC, and possibly a dozen other companies are investigating similar possibilities."

From the actual article:

"About a dozen companies plan to use Transmeta chips, Ditzel said. NEC, a manufacturer of notebook computers, is evaluating the chip, said Leonard Tsai, chief technologist at NEC's PC Silicon Valley Center."

Nowhere does it say anything about a dozen companies "investigating." It does say that about a dozen companies are planning to use the chip. Investigating the chip, and actually planning to use the chip, are two entirely different things.

According to this article, NEC is the only company mentioned as currently evaluating/investigating the chip.

Yeah, this may seem like nitpicking, but I find it a bit frustrating. I sometimes do not have the time to read through the referred articles, and instead just quickly scan the Slashdot headlines (and no, I do not post a reply about stories if I have not read the referred article.) If I had done that with this story, I would have been misinformed.

No keyboard?

[FascDot Killed My Pr]

I see a lot of responses that say "chords are no good, keep the keyboard"

But it's so big and clunky! Look at the Palm. With no keyboard it fits in your shirt pocket. With a keyboard it has to go in your backpack/briefcase/etc. But put 8 keys on the back (which would fit, at least on my Pilot 5000) and you have the power and speed of keying, but the size is constant. The retraining to use chords would probably be similar to Graffiti.

Example: Let's say you put the remote client in the kitchen like you mentioned. Where's the most natural place? On the fridge. But if it has a keyboard that won't work. Either the keys are vertical (making it impossible to type) or it sticks out (making it hazardous and ugly). So now you've got to put it on the counter along with the toaster, food processor, blender, drying rack, etc, etc, etc. No damn good.

With my specs, you put the unit on the fridge. Then you can either interface via touch screen (for quick browsing) or pluck it off the surface and key it in (for more detailed work).


---
This comment powered by Mozilla!

Acorn Webpad?

[horza]

My RiscOS machine runs on StrongARM and handles .mov files fine. The browser is faster and more reliable than IE too. Come to think of it, Acorn demonstrated a Web pad along similar lines a couple of years ago (way too long ago to remember any details). Vaugely remember something along the lines of the ARM 7500 at 30mW? It had a bit of a heavy battery I think. Can anyone fill in the tech specs?

Phillip.

Re:Silence from the Open Source Movement?

[yellena]

Other than some cool reading material, it wouldn't be of any use. The only people that would benefit from Transmeta completely opening their hardware design would be Intel, AMD, IBM, Mot., etc. They have the ability make changes to the design and then actually manufacture the chips. I know I don't have a fab in my garage, I wish I did.

But.. 75% of this technology is in software and Transmeta does seem willing to open up some of that. So I'm not outraged, I'm anxiously awaiting.

The Obvious question

[NullGrey]

Does it run Linux?

Oh, I guess it does.

Okay, the next-to-obvious question:
What's for lunch? I'm starving.

Imagine emulation on this

[586]

What would be really be nice would be to run stuff like gbc and snes emulators on your webpad!

Batteries!?

[Anonymous Coward]

The Palm V runs very nice on its rechargeable Lithium Ion battery built into it. :-) Drop it into the cradle when I'm around it.. never a problem with dead batteries again for me. ;-)

Palm and Crusoe do not go together.

[edremy]

Everyone here seems to think 1 watt is great. Guess what- it's great by desktop standards, but certainly not by Palm standards. A Pilot, running flat out (Screen, backlight, serial port, CPU and all the trimmings) draws something like 0.25 watts (assuming I did my math right- 0.085 A at 3V.), the vast majority of that drawn by the screen, serial port and backlight.

Stick a Crusoe in there and your battery life will be a fifth of what it is now- you'd be changing cells every 2 hours.

This is why Transmeta isn't interested in palmtops- Crusoe + a color screen just won't fit energy wise. Something more like a Newton is a better fit, although StrongARM does better on power.

Finally, for everyone complaining about the PalmOS, it's not supposed to be a real OS. It does what it does very well, and fills a nitche. Sure, it would be nice if it could play MP3s, but not at the cost of losing the wonderful, simple functionality and very long battery life. (You'd think folks would realize this after the WinCE debacle.)

Eric

Adding a real keyboard

[AJWM]

At the press conference somebody mentioned in passing that the web pad had a USB port that you could use to add (among, presumably, other things) a keyboard.

The pop-up virtual keyboard on the touch screen is probably sufficient for truly mobile use -- e.g. when you're holding the pad in one hand (kinda like a clipboard) and just want to one-finger type in a URL or a few simple commands. For serious typing I'd rather have a real keyboard and something to rest my hands/arms on anyway, which means putting the thing down on a table, etc anyway.

(These things are almost at the tech level of the pads in "2001: A Space Odyssey" -- recall the scene where Bowman and Poole are eating while watching the TV (?) broadcast about their mission, each watching on his own web-pad-like device. At least something from that movie came about in the right timeframe. Too bad it wasn't the orbiting hotel and the bases on the Moon.)

Um, so?

[Anonymous Coward]

"The only people that would benefit from Transmeta completely opening their hardware design would be Intel, AMD, IBM, Mot., etc"

So? Where does the OSS religion say WHICH people should "benefit" from OS?

Uh...

[Anonymous Coward]

Uh, why don't you get it now with the Sony VAIO? Sub-laptop, runs Windows and Linux. I think you are missing the point of PalmOS AND Windows CE. We dont WANT desktop OSes for those kinds of devices.

Really, the stupidity on slashdot is amazing.

Re:Uh...

[jeffcuscutis]

Well, actually we do want desktop OSes for devices larger than a Palm or WinCE product.

This can actually reduce software costs. If I want a program to run on Palm or WinCE that already runs on Windows or whatever, I have to either recompile or rewrite if I even have the code. If I can have a machine that is portable, long running and nearly as fast as my desktop and can run my existing software, this covers my needs better than a Palm does. (I have a Palm and like it, but I'd rather have a device midway between that and my desktop or laptop)

--jeff

Re:mp3's

[altman]

Errr, the Cirrus 7209 (ARM7T core) CPU uses only 0.087W when *playing* mp3's, and *less than* 0.001W when in standby.

The Transmeta chips are low power compared to other x86's, but not low power when compared to the best of other architectures in terms of mips/w (eg, StrongARM, ARM10, etc).

Hugo

There's more to Crusoe!

[Uksi]

The most exciting feature, for me, of Crusoe is code morphing. Reading the white paper on technology behind the chip (something that *a lot* of posters here should do before posting) got me excited even more.

Basically, after a piece of code is translated to native code and optimized, it is cached. Next time it is executed, if it's still cached, the already translated and optimized verison executes.

The benefit of this is speed. A lot of people doubt this speed, saying things like "an emulator can't possibly run at 75% speed of the native system", etc. There are two reasons why Crusoe can outperform the native system, one of which is really not apparent and ignored by almost every person that criticizes Crusoe.

The main thing to remember here is that Crusoe has some radical, very different technology decisions.

First, as any experienced software engineer would point out (backed by experimental data), 90% of a program's execution time is spent in 10%(!) percent of its code. What this means is that if ONLY that 10% of the code is optimized, it will speed up 90% of program's execution time. Crusoe's code caching mechanism helps this immensely because as a program runs, these 10% become cached in native code and translation from non-native machine code is done only ONCE.

You may be saying, "So what, in the best case, the program will run almost as fast as the native system, but it simply can't beat the native system." That's where you're wrong.

The second reason is that the software layer not only performs translation, but optimization as well. You may now object that if the original program is optimized by the best optimizers, Crusoe's optimizer can't do better. Well, it can because of Crusoe's architecture. Note that, for example, x86 processors have a small number of registers (which are areas for data stored internally *in* the processor; such data is accessed the *fastest*). Crusoe's VLIW architecture, however, has a lot more registers and its out-of-order pipelining, branch prediction. Also being a very-long-instruction word processor, it executes a lot of small instructions (atoms) in one big full instruction (molecule). Molecules can be executed in parallel (pipelining). Crusoe's optimizer takes advantage of these features, making the translated code use more native registers, instead of accessing normal memory or L1/L2 cache (which are slower) and groups code to be processed in parallel.

Crusoe's optimizer performs really aggressive optmiziation. Perhaps the neatest feature is how Crusoe handles aliasing. Here's some pseudo-assembler code that loads from the same memory location twice:

load from %X to %register
...(do some stuff with %register)...
store %anotherregister to %Y
load from %X to %register
add %register and something else
etc.

This is the tightest optmiziation a compiler can perform. The compiler can't eliminate the second load operation to the register because %Y may be an alias for %X (that is, %Y may point to the same memory location as %X). Such aliases come up rarely, but they can come up, and so the compiler can't risk eliminating the second load instruction because it can't predict whether %X is an alias for the %Y. Nobody can, not even the processor.

Crusoe takes a radically different approach in this situation. Its optimizer ELIMINATES the second load operation, assuming that %Y is not an alias for %X. However, in case it is, it marks an internal bit that protects %X from being overwritten by the store instruction. So the code that one ends up with doesn't have that load instruction and when the case of %Y being an alias for %X does happen, it simply generates the extra load instruction on the fly.

This may seem like an insignificant optimization, but in reality, it can be quite significant since things such as these happen in programs very often (and often %Y ends up being not an alias for %X). Elimination of extra loads permits better pipelining (more code executed in parallel), and an extra load may take quite a bit of time if the load has to be done from the memory.

There are a whole bunch of cool other things about Crusoe's technology which makes it a great all-around processor.

So, what this means is that thanks to the revolutionary architecture, Crusoe's optimizer can optimize that 10% BEYOND the original and actually run faster.

Users of computationally-intensive programs will especially benefit from this. For example, a 3d ray tracing program spends a lot of time in the small, tight rendering code. Having that optimized so well by the processor can have a significant effect.

Crusoe also uses filtering techniques to avoid caching code that is executed once-an-hour (thereby preserving translated native often-executed code in the cache as long as possible).

As the website mentions, most benchmarks only measure a bunch of tasks done in 10 or 20 minutes. The website asks: do you really repetitively do 10 different tasks on your word processor for half-hour or do you actually sit in front of a processor and type most of the time? This is indeed a valid rhetorical question.

Most benchmarks are too short to let Crusoe speed things up as much as possible.

Although I don't like the "mobility features" that Transmeta keeps pushing every other sentence (damn marketing) and I don't like the fact that their benchmarks mix performance with "mobility features" (even though there is some validity in doing tat), I think that Crusoe is a very exciting technology and wish I had one.

Stop thinking in terms of megahertz. As processor technology gets more advanced, all these things stop mattering. In one app, your 700Mhz AMD may perform much slower, in another it can perform much faster. It's never same speed all the time.

Re:There's more to Crusoe!

[Anonymous Coward]

blah blah blah. and this is why java is so darn fast, right?

Re:There's more to Crusoe!

[David Greene]

Hey, thanks for the information about the aliasing situation. I didn't realize Crusoe did this.

This is really, really great! Insanely great! Is the code optimizer smart enough to do cross-call optimization? That is, can it get rid of the call overhead?

Obviously I need to go read some documents, but how much code scheduling does it do? What does it do about control and/or data speculation, if anything? With the optimizer, you have the tradeoff between optimizing really aggressively and being able to cache as much generated code as possible. How is this tradeoff made?

--

Re:There's more to Crusoe!

[FJ!!]

First, as any experienced software engineer would point out (backed by experimental data), 90% of a program's execution time is spent in 10%(!) percent of its code. What this means is that if ONLY that 10% of the code is optimized, it will speed up 90% of program's execution time. Crusoe's code caching mechanism helps this immensely because as a program runs, these 10% become cached in native code and translation from non-native machine code is done only ONCE.

Well, let's hope then that there's plenty o' room in that code-cache for optimized code that is not the system idle process, because that's the first process that's going to get optimized and it will never be kicked out.

Re:There's more to Crusoe!

[patrikr]

The code cache will be in the RAM area reserved for the code morphing software, so there *will* be "plenty o' room"... :)

--

3120 is a bit expensive for its market

[xener]

The 3120 chip is a bit large at 77mmsq for its target market. This
makes it significantly more expensive than the competition. Competing
chips in this market are more on the order of $20 and 20-30mmsq.
Transmeta has compared the 3120 to PII and PIII in their release, but
it is important to note that PII and PIII are not important players in
the much more cost sensitive embedded market which the 3120 is
intended to address.

BTW, S3 recently acquired Diamond, so I don't think S3 has a separate
project going with Transmeta.

Slashdot product placement (OT)

[jabber]

Did you see the slashdot plug on the Transmeta 'going mobile' page. It just gives ya the warm and fuzzies... Ahh.... Now where'd I leave that The Who album with "Going Mobile" on it??

In production

[Anonymous Coward]

Yes, its being fabbed by IBM's Burlington Vermont fab. According to my yankee cousin up there, we're churning them out like flapjacks on a gridle.

Re: x86 compatible

[jabber]

We need to consider just one thing. If we were releasing a new chip, capable of running any other (theoretically) architecture's instructions, and thie feature being in upgradable software, with the intention of putting something on the market in reasonable time.... Which ONE architecture would we choose to support?

I'm not at all devastated by the fact that 86k, PPC, Z80 or whatever else isn't supported. In time, the smaller segments of the market will either be supported, or will convert.

What I would really like to see now is direct Java bytecode support. :) That is, no VM layer.

As for the power consumption aspect taking center stage, it's right to do so. The general public and casual user of portable devices isn't hampered by poor performance, they're hamstrung by battery life. This is HUGE.

Mobile users have never, EVER considered running multi-platform apps on the same machine. Code morphing is wizz-bang, but not much else to them.

Hey, will this thing multitask platform specific apps? Or is there a reboot needed for platform switches?? Anyone figure that one out yet?

I think what you (and I) want will be done!

[Anonymous Coward]

Check out http://www.transmeta.com/press/download/pdf/chapma n.pdf.

It appears to be a presentation (probably powerpoint) on products with their chip. On page 5 is a reference to "Mobile Internet Devices" running Mobile Linux. One of the devices pictured next to the "2lb Web Pad" is a "2lb Handheld" (looks like a mini-laptop), with such highlights as "No spindles (drives)" and "Flash Card Storage".

If done right (maybe a big if!) it may just be what we want!!!!!! Woo hoo!!! The ability to check email and stuff, using a device like that, plugged into my home network, from my TV room, or any other room with a RJ-45 would be neat-o! Wireless would be cool, but I'd rather have that be an add-on, because I really don't want to pay for it at this point...

Crusoe Seen Running BeOS

[dhuff]

A story today on BeNews had the following, interesting rumor:

BeNews has receive reports from trusted sources who claim to have seen a CNBC report demonstrating BeOS running on TransMeta's new Crusoe chip.

BeNews editor Scot Hacker states that they are "hot on the trail for more information on this development."

Re:Crusoe Seen Running BeOS

[Guy Harris]

BeNews has receive reports from trusted sources who claim to have seen a CNBC report demonstrating BeOS running on TransMeta's new Crusoe chip.

Umm, I'm not sure why it's an "interesting rumor" that BeOS is running on systems built with a chip that, as Transmeta says, is "Fully x86 compatible" and "is compatible with the complete range of x86-based operating systems", given that BeOS comes in a version that's "x86-based".

Transmeta doesn't have a chance!

[Anonymous Coward]

Ok this market is already served by Intel (StrongARM) and Motorola(PPC). Performance must be a real dud otherwise they would have published some benchmarks using industry metrics. Looks hoakey to me.

Games: Transmetta Inside (Gameboy/Advance & more)

[Cebert]

You know, it's a shame Nintendo's Gameboy/Advance won't be using the TM3120. Can you imagine a 400Mhz Z80-compatable processor? :}

Anyways...I'm eagerly awaiting to find out what lucky company will be the first out of the gate with a handheld gaming device based on a Crusoe processor once prices on the devices come down.

But really, all I want is a portable MAME-playing handheld. :)

S3 IS Diamond

[winterstorm]

The blurb implies that S3 is a different company than Diamond Multimedia and that there are at least two vendors announcing Crusoe based devices. This is not so. S3 owns Diamond Multimedia. If fact the article about S3 explicitly states the fact: "S3's recent acquisition of Diamond Multimedia(TM)..."

Don't count your chickens before they hatch... and don't count them twice before they hatch... :-)

ha

[Phil-14]

"Give a man a fish, and you feed him for a day.
Teach him to fish, and you can sell him tackle."
(origin unknown).

Past: Wintel Future: Linmeta!

[Anonymous Coward]

Actually I don't expect Wintel to disappear any time soon, but if these Internet Gizmos begin to fly, I predict the new buzzword will be Linmeta. Or should that be Transux??? umm, no Linmeta sounds about right.

Crusoe useless for non x86

[Anonymous Coward]

From the transmeta web site:
"To ease the translation process from x86 to the core VLIW instruction set, the hardware generates the same condition codes as conventional x86 processors and operates on the same 80-bit floating point numbers. Also, the Translation Look-aside Buffer (TLB) has the same protection bits and address mapping as x86 processors."

In short, internally it is completely optimised to hell for x86 and would be shit for any other instruction set. PPC, Sparc, Alpha, no way.

Low power consumption? Who cares?

Tons of prior art

[XNormal]

This idea has been discussed to death over the last years. There are a few devices like this already shipping but they are very expensive. They used for special application like the healthcare industry (yes, they replace the doctor's clipboard).

The problem is not coming up with ideas, any slashdotter can do that. The problem is implementing them in a way that works and at the right price.


----

C'mon

[auntfloyd]

A troll?

You should know that it's a 'This Modern World' parody (though I am a fan of the strip).

http://www.well.com/~tomorrow/


~~~~~~~~~
auntfloyd

Re:$329 Bargain

[Anonymous Coward]

Yes of course it is. Have you seen prices on Intel? Duh.

the personal, home server...

[Anonymous Coward]

WebPad? killer application? no, try a personal,
low-power, home server with linux. doesn't inflate your power bill. doesn't crash every two seconds. with a reliable access line (dsl and some dynamic dns trickery), you can easily have all sorts of personal information available from anywhere, but also under your control. when all of asktog.com is back up, look at the castle keep article on security and privacy, then think what a couple of low-priced, low-power, fast-enough servers can do...

crusoe + nv memory = killer combo?

[Anonymous Coward]

It would be interesting to see if the Crusoe processor could be coupled with low-power-consumption memory from NV Memory. NV was bought by Hortitech recently. Can't find much more info about them other than the stock press release under HTIC though...

Go S3

[dr_labrat]

Buzzword frenzy:

Linux Transmeta internet wap synergy pda wireless

Shame the Amiga stuff was vapourware..

[Stormie]

OK, I know the only thing I've said about the Amiga in recent years has been the "it's dead, dead, DEAD!" of an ex-loyalist. But reading about these Transmeta chips, it occurred to me that it really is a damn shame that nobody's trying to make an Amiga with them.

I mean, think about it. What really ruined the Amiga was development of the 680x0 line ceasing. It hit the point where a whole new CPU family was needed, PowerPC was chosen, but it all fell apart because there was no C= anymore, and all the peripheral companies like Phase5 were competing to see who could produce the most vapourware. Rewriting the OS was a job that nobody was really up for, nor even writing an emulator. So all we got were hugely expensive PPC addon cards with libraries for running routines on them while the 680x0 ran the main system.

Imagine, though. If a Transmeta chip can code-morph x86 code and perform like a 500MHz P3, surely with a rewrite of the software layer, it could code-morph 680x0 code and perform like a (some hundreds of MHz) 68060? Just because the physical 680x0 architecture petered out at 50MHz doesn't mean the logical architecture has to die there!

You could make a new Amiga without even having to rewrite any software. ;-) Retargetable graphics was a mostly solved problem towards the end of the Amiga's life (I had a CyberVision3D and it worked fine), so all you need is a modern-specced box with a Transmeta CPU and.. well, there you go.

'Course it'll never happen.

Comfirmation: Crusoe Seen Running BeOS

[Jeff_Uphoff]

I can confirm this: in order to demonstrate x86 compatibility, we demonstrated several operating systems at the launch. BeOS was indeed one of them. Others were various flavors of Linux, Win98, Win2k, and Solaris x86.

Where do you think we got some of our ideas?

[Jeff_Uphoff]

Making sci-fi a reality is about as enjoyable a job as can be found.

Wearables!!!

[chinakow]

I was thinking last night that this would be awsome for wearable computer , think about it, the proccessor only runs about 11 degrees farenheit warmer than my hot tub so that means that the case that you put the computer in would be enough to dissipate the heat and now I cold finnaly find a setup that would be much faster than a 486.

just a thought :-)

Ok, who's going to buy a webpad

[TummyX]

That runs Netscape.

Total mistake IMHO. Mobile Linux isn't that _mobile_ at 64MB (32MB compressed), and Netscape isn't 'mobile' either. Under X, it has really crappy fonts, with no anti aliasing etc.
It's also slow, and has problems rendering.
It certainly isn't the best choice for a webpad. This may sounds like flamebait, but wouldn't Windows CE + IE make a better choice? Certainly much leaner, can be loaded into ROM, and uh, it works :P.
IE for CE supports Flash and all that stuff too.
Transmeta doesn't seem to have an 'anti-microsoft' attitude (well except for Linus).

Just a small point, Diamond == S3

[throx]

Thought I should point this out as the initial post makes it seem like 2 OEMs are considering using the CPU. Remember Diamond bought S3?

John Wiltshire

Hardware Hysteria

[radsoft]

The 70's were a period of intense UNIX hysteria in Northern Europe. Suits who had practiced saying "IBM" so well finally went for broke and learned the unprecedented four letter mystery "UNIX" by heart and every office had to have a UNIX box. Hardware OEMs were not slow to discover what was going on, and in no time flat the market was flooded with UNIX solutions. Unfortunately, few of these "solutions" were ever tested. Several did not work satisfactorily at all. And UNIX gurus were often heard to mutter "I don't know what the f+++ it is, but it's not UNIX!" The Crusoe is a great omen. But let's watch out for the OEMs. Greed can still spoil the day.

The main problem I see is...

[java.bean]

Apologies if this has been discussed in any of the recent Transmeta articles.

They are proud the chip can be updated over the net. Is this leading chips down the same path we are already going with software, namely release now and patch later? Will there be a case where it's "don't buy a Transmeta chip until it's on Service Pack 2"? As development cycles get shorter and net access gets more available, the quality of software appears to be going down because of easy patchability. Is hardware next?

--jb

Re:The main problem I see is...

[Potatoswatter]

Bloat causes unnoticed bugs. I'll bet the few (kilo)bytes of machine language in a Crusoe are probably pretty easy to debug, and any problems would show up. I think the processor engineers at TM will be a little more careful than the average MS programmer, too.

And don't forget the original Pentium division error - not having a net to fall back on doesn't make engineers behave better, either.

hmm ?

[serialk]

when will they actually be available and

standard ?

Re:But why use a Crusoe? (ISA extensions)

[Anonymous Coward]

The second, is the potential for OEM's or other interested groups to lobby Transmeta for the creation of custom opcode extensions to the X86 chipset. Such extensions could then be distributed directly with the software that required them.

Hmm. The OEMs would provide software that uses the new opcodes, but you'd also be able to run all your old x86 code. It wouldn't work the other way around, though: Intel's (or AMD's, or anyone else's) x86 CPUs wouldn't recognize the new opcodes. But that's nothing new, really: we already have x86 dialects with extensions that are incompatible with each other: MMX, 3DNow, etc. The same disadvantages apply here.

As for which ISA extensions to add: that's a tricky issue. Some extensions are only useful with proper support in hardware. Some extensions could have been 'found' by the code morpher anyway, without explicitly having to put them in the x86 code. An example: consider the multiply-add operation (MAD: x=a*b+c), well-known in the DSP world.

1. Suppose you added the MAD operation to your OEM's version of the x86 ISA. Two scenarioes unfold:

• a. The Transmeta VLIW has hardware support for the MAD operation. The code morpher would translate the x86-MAD directly to a native MAD. All the benefits of the MAD are yours! (faster execution, fewer operations, no intermediate register needed, etc). However, you did have to use a strange x86 dialect.
• b. The Transmeta VLIW does not support MADs. The code morpher splits the MAD into a separate multiply, followed by an addition and schedules these two operations for its internal VLIW. It's as if you never specified the MAD in the x86 code in the first place, lot of good that did! And your code does not run on Intel platforms anymore...

2. Suppose you did not add the MAD to the OEM's version of the x86 ISA. Again, two scenarioes:

• a. There is hardware support for the MAD operation in the Transmeta VLIW. The code morpher could combine subsequent multiplies and adds and map them to its native MAD operation. The advantages listed under 1a apply in exactly the same way, and your x86 code would not have to be changed (== would still run on other x86 platforms).
• b. No hardware support for the MAD, nothing changes (duh).

Conclusion: you'd much rather let the code morpher optimize the execution of your x86 code than modify the code itself, because then the x86 compatibility of your code goes out the window. And if you're generating code in a Transmeta-specific x86 dialect, why not compile to the VLIW directly? (possible answer: to maintain binary compatibility between members of the Crusoe family, which happen to speak the same Transmeta x86 dialect but have a different VLIW core. But we have to provide different binaries for other x86 platforms anyway, so why make an exception here?)

Of course, there is only so much the code morpher can do, dynamically. I can name several ISA extensions (can you say MMX?) that it will not be able to exploit unless you specify them explicitly (in the x86 code). It will never be as powerful as an off-line compiler (it doesn't intend to be). In the old superscalar-vs-VLIW debate, it's somewhere in the middle, which has its advantages, but also its disadvantages.

Marnix.

mebbe the technology, but not from this co.

[Potatoswatter]

Somehow I don't see this building Transmeta into an instant giant. They will need time to grow, and in the meantime Motorola (for example) can implement at least some of these ideas into the 683xx/Coldfire series (the processor used in PalmPilots). Staying with a dedicated ISA (68K) that's easy to do in a small number of transistors (say 68,000) in the 1st place could probably reduce the wattage/transistor count while keeping another variable - manufacturing process cost - down.
Or mebbe the ARM or PPC embedded lines would be better for high-power/low power (gag) apps.
In this way, Transmeta, being independent, is the worst company to come out with a Crusoe - they have to keep their processors needlessly flexible.
Not all of their tech is patentable - VLIW has been floating around for a while. Do we really want to depend on a company that depends on patent enforcement?

Cool that this comes from the same people who brought us RISC, tho. They said thatwasn't practical...

Amiga and Transmeta

[alynna]

Does anyone know if Amiga Technologies is still planning on being "in bed" with Transmeta after the turnover? I could certainly see (and drool over) a computer running AmigaOS (68K and PPC), Linux, and Wintel binaries on one screen... and for that matter, Mac... I personally like a computer that will run any code I give it...