Slashdot Mirror
Transmeta Astro Processor
simpl3x writes "Apparently, Transmeta's next generation processor was demonstrated to some folks the other day at Comdex. Tom's Hardware was at the demo and they had this to say: "The new Transmeta Astro was faster in every demo that we saw than the Pentium 4m 1.8GHz chip that was in the Sony GRX." Cnet had some information on the processor also . I just ordered a tablet to play with, though I ordered the Fujitsu which has a P3m (the Compaq has a bad screen according to the reviews). I certainly wish that something like this were available, and i do hope that the manufacturing goes smoothly. Mo options, mo better."
And by god. I was actually impressed with this processor and the Transmeta booth in general.
Though it was small it was:
1) Manned by a really hot and nice chick! (always important).
2) Showed off what has been unanimously voted "My next laptop" by half of my company.
3) Actually contained a chip they let you hold. 1 word: SMALL
"It's not stealing if you don't get caught!"
Does this processor still have low power consumption or is transmeta moving away from the small embeded market, maybe into laptops or other more sophisticated type applications?
I do security
The new Transmeta Astro was faster in every demo that we saw than the Pentium 4m 1.8GHz chip that was in the Sony GRX.
Faster in what type of demo? Dropping a Pentium 4M and an Astro from shoulder height? Being hurled from a clay-pigeon launcher? Downing pints of Guiness at the pub? Blah. Tom's Hardware is so bigoted against Intel after the famous Rambus stoush that anything they have to say on an Intel vs. Competitor story is essentially unreadable.
I was fortunate enough to see this cpu in action at a press demo and I must say I was sadly dissapointed...
The lack of sse2 support greatly hindered this chip in any fps demo, where it was brutalized by the p4 (I'm sure even an amd athlon could beat it under those conditions!).
The 'code morphing' technology also uses an astonishing amount of ram, up to 64mb in some cases, so linux users who need all that ram for gnome should steer clear of this chip. I also noticed that compared to a p4 based system, it was quite unstable, requiring a reboot in windows98se after just 2 hours of demonstrations. I have also heard, from reliable sources, that boards using this chip can only run at agp 2x, which again can hinder game performance.
For power desktop use forget about using this chip, although I'm sure for student or 'dumb terminal' use this chip is suitable.
Stanley Feinbaum, professional journalist and master debater! God bless the USA!
From the CNET article "It will consume less power than the company's first Crusoe chips, the TM 5000 series, but offer substantially more performance, said Chief Technical Officer David Ditzel."
Wow... and according to tramsmetazone the thing was running at 500 mhz for the demo (against a speedstepped pentium) WOW.
Wow, frightening! You NEVER need to reboot Win98 with any other chips! I declare shenanigans! AAH!
The Cnet article said the chip would be lower than Intel's offering. The big thing was that they doubled the intructions per clock cycle, while keeping the lower power consumption that makes it desirable for portables (Tablet & Notebooks).
"Give a woman two glasses of wine and some pad thai, and they'll agree to just about anything." the Sports Guy
Again, as mentioned in the CNet article, "Transmeta executives, though, indicated that the company would beat Banias in price." The Banias is Intel's soon-to-be-released next mobile chip. It should be at least fifty dollars less than Banias, but twenty dollars more than Celeron.
I can already see that this new chip is going to work great in notebooks...but why not push it toward the desktop market too? The noise created and the amount of electricity used by some of today's desktops is horrible. This chip would allow a fast, ultra-quiet desktop (or tiny footprint computer) and won't ratchet up your electric bill by turning the computer on. Back to 200 watt power supplies anyone???
The interesting thing about the transmeta procs is that they make heavy use of caching to speed up instruction translation. Once the cache 'warms up' around a given application, performance is generally much better.
I for one would like to know what they meant by 'better performance' than the intel. Did they compare application startup speeds? Had the machine been running the apps previously? Granted I don't know any of the details, but from personal experience (I'm typing this on a transmeta-based fujitsu lifebook, at 866mhz) the current transmeta chips start applications extremely slowly and then progressively get more reponsive.
I like my laptop and am rooting for the astro! I'm very interested in how they improved the efficiency of their approach.
- - - - - - - -
Don't worry, being eaten by a crocodile is just like going to sleep in a giant blender.
Do you have any references on the large amount of system RAM you mentioned is needed for code morphing ? I find it hard to believe that 1) you need that amount of memory for instruction translation and 2) that a hardware device using that much memory to emulate a CPU (at CPU clock speeds) can be too efficient both in terms of performance and heat dissipation.
There's a computer chip made by Transmeta
Compared to Intel it's really just betta.
But how long can it last
When Intel's big-asst
Let's hope Intel declares no vendetta.
Don't give me none of this "nature theme" business.
No real facts. Even when you read Toms.
So they optimized a few apps on the Transmeta, and pit it against a machine that has some unoptimized apps. To quote toms "DVD playback, Office Applications".
Ok were the even the same office and dvd playing apps? I can show you two different aps that do the same thing. One dog slow, one lightning quick. Put them each on machines with the same specs, and one will open faster than the other.
So give us name of the apps used. Start up times, were they optimized especially for the meta?
I would like to see this succeed, but I hate to see the hype.
Puto
The Revolution Will Not Be Televised
but maybe there is a market for people who would like to have silent, smaller computers. And i'm not talking about laptop.
People who are disappointed by the arm race to the Hrz in cpus, ram, and video, which result in overpriced noisy pcs, just to do the same stuff than with the previous pc.
Just a look around me and I see many persons interrested in the eden and likes motherboards.(When I asked at the motherboard desk of a big pcshop if they had them, the lady looked so pissed off to say no that I understood that I must have been the 60th that day to ask)
Small, silent, unexpensive. With a transmeta, there would even be some horsepower in it. Enough at least.
Of course, I realise this is due to market pressures and that Transmeta just like AMD and Intel has to keep pushing their chips faster and faster to keep up with Moore's law, but nonetheless I lament that Code Morphing's full potential was never realised. Performance considerations aside, a processor that performed instruction decoding in software would have many more benefits. Support for new instruction set extensions like SSE or MMX could be added with a simple firmware upgrade. A new code-morphing frontend could turn the Crusoe from an x86-compatible chip to a PowerPC, MIPS, or SPARC-compatible chip in seconds (which would be a huge boon to embedded developers). A Code-Morphing core could be used as a testbed for new ideas in CPU and instruction set designs. The populations could have been endless. But alas, with Transmeta abandoning the technology, it's doomed to become "just another neat idea", like LISP machines and the Amiga before it.
I remember that the old Cyrix 6x86 chips didn't emulate the complete x86 instruction set, so many common programs would crash or just plain not run. It seems like transmeta is trying to go the same route, by reverse-engineering Intel's instruction set. The results of this kind of thing aren't always pretty, as you can see with such projects as WINE.
I know that Intel chips are the baseline platform for most business software written today, because of their market leadership position, and they seem to have the performance edge also. And the power-consumption issue is really a red herring, since on most portable systems the CPU is only a minor consumer of power (heat is another problem, but that is something that proper internal design can usually cure) compared with the display and hard disk. So is there really any reason to switch?
Benchmarks aside, I'm really pleased to see what appears to be a serious alternative to Intel and AMD. Just as AMD's success has been good for the CPU market in general a third competitor will almost certainly lead to improvements across the board.
The Crusoe is cool, but since it is sorta a "niche" product, it never really got the penetration I had hoped to see. Hopefully Astro will be viable as an option for main-line PC makers. (IBM, Dell, etc...)
the astro does have an integrated chipset. Transmeta is not a big enough company to have many different chipset models developed so they ussually go with the cheapest chipset model with the lowest power consumption.
agp 2x was chosen for power reasons, as 4x would have pushed the (relatively underpowered) chipset and cpu too far.
Stanley Feinbaum, professional journalist and master debater! God bless the USA!
Yes, but Tom fails the mention the two 200W peltiers and liquid helium bath...
I don't know about you, but liquid helium spilling on my pants doesn't really brighten up my day.
-Chris
--an unbreakable toy is useful for breaking other toys--
Although chips are getting faster and faster people seem to forget that most people dont use a laptop as a portable supercomputer. The average user is gonna write papers and browse the web or soem kind of business application ... not that they wont do other things, but the fact is a laptop was never meant to replace the desktop market. Transmeta not only gives intel competetion, but they assure the consumer that intel will have to do at least a little innovation to make their product worthy. A chip that is fast enough for non video games and has an extended battery life compared to ther brands is a good thing. It is what the goal of laptop makers should be. gaming on a laptop is teh niche market, and thats what alienware computers are for.
Choosing the lesser of two evils is a choice for evil.
Are you a troll? ...lack of sse2... ...uses an astonishing amount of ram...64mb... ...unstable... ...only run at agp 2x...
It doesn't even run X86 natively!
64mb or ram costs 15$ The price difference between the P4 and the transmeta will easily be more than that. Buy more ram!
It hasn't even been released. Kernel 2.5 isn't all that stable, but no one complains because it is a testing/prototype.
The speed of the agp bus has been shown to be inconsequential to the performance.
The rumor is that the demo chip is running at 500Mhz at the moment. Comparing that to the 1.8ghz P4 suddenly doesn't seem so out of proportion does it? I gaurantee you it will be running at at least 1ghz when it's finally released. The final board for it (not the notoriously shoddy reference boards) will perform better as the memory bandwidth will probably be improved.
What if I had done the same review of the Itanium 6 mo. before it was released? It was running at 400Mhz, couldn't run X86 software as fast as a 266, and was practically an unstable toaster oven.
Karma Clown
If you can shoehorn a whole PC into a palm-sized device, who needs PalmOS? I think that's what Transmeta would like to do eventually. In the meantime, their chips run cooler so they can build laptops that won't burn your penis
To be fair, I should disclose that I own stock in Transmeta.
For all intensive purposes, "whom" is no longer a word. That begs the question, "who cares"?
SSE2 is used by so few apps that its not very useful for 99% of the stuff people are doing. As far as agp support only being 2x, thats the motherboard's (well northbridge's) responsilibility, not cpu. And besides, agp is a joke, anything more then 2x gives you ZERO performance increase.
Lawyers, MBA's, RIAA? A jedi fears not these things!
Support for new instruction set extensions like SSE or MMX could be added with a simple firmware upgrade. A new code-morphing frontend could turn the Crusoe from an x86-compatible chip to a PowerPC, MIPS, or SPARC-compatible chip in seconds
This turs out to be much more difficult than it first appears. There are a number of low-level architectural features - especially in the memory interface, but elsewhere too - that are very difficult to emulate if you've built a processor using different assumptions. This means that while you might be able to emulate a PPC/MIPS/SPARC on a Crusoe - or even on a PC - by dynamically recompiling code, the only architecture that would perform well would be one with a good match to your actual hardware. The original Crusoe chips were designed from the start to emulate Intel processors, and this new chip is presumably in the same boat.
For one, there simply wasn't much of a market in emulating non-x86 architectures. The available software and knowledge base, particularly for embedded design, is much higher in x86. For the systems that must have non-x86 architecture, generally they'd just get the real system rather than an emulation "hack", as often these other architectures are chosen to get the maximum reliability or performance characteristics that those markets require.
Also, because CISC breaks down to multiple smaller operations easier than RISC, CISC is much easier to get performance advantages with code morphing.
Not that I really doubt Transmeta, but a closed system running benchmarks? Who is to say that they weren't running a P4 and not an Astro? And what do they mean by faster than a 1.8 GHZ mobile Intel chip? Faster than what? Some weird benchmark devised by some marketing department that no one has access to? Whithout specs, this whole thing is a wash.
It may very well be that Java applications run as fast as "native" x86 code on TM chips. I wish they'd show JVM and CLR benchmarks on different CPUs. If I were a betting man, I'd bet that TM chips have an extra edge in less optimized code, such as that produced by JITs. HP did some research on code morphing from PA-RISC to PA-RISC (yes, that makes it much easier to do comaprisons, find bugs, figure out optimizations, etc.) that ran some code faster than running the binary natively. It performaed much better compared to native execution when the native binary was compiled with fewer optimizations.
Thier technology certainly is an elegant solution to deaing with ISAs, particlarly ones that have such high decoding overhead. I wish they also exposed an instruction set that was lower overhead for thier code morphing engine. Maybe something like RTL (HP calculator libraries are compiled to a RTL for portability) or a memory machine ("infinate" registers) like the DIS virtual machine from Bell Labs.
Copyright Violation:"theft, piracy"::Anti-Trust Violation:"thermonuclear price terrorism"<-Overly dramatic language.
Consequently, it multi-processor transmeta systems will outperform single processor Intels dissipating the same amount of heat. This also translates to higher reliability. If the memory busses are done correctly, having inexpensive multi-processors may alos provide significant performance enhancements over a single CPU. (for example, if memory bottlenecks dominate then multiple simple processors that are stalled witing on memory will ustilize every memeory fetch perfectly, whereas a pipelined single processor will waste a large fraction of the memory fetches making it slower).
A schematic of the current trends look something like this.
.......ioo......
|...........i.t..
|..........i.t..
|..........it...
H.........it....
E........it.....
A........i......
T.......i......
|.....io..o.....
|....io.........
|___i____________
Speed--->
o = Transmeta
i = pentium
t = former trendline
Some drink at the fountain of knowledge. Others just gargle.
Watch for Transmeta to go through the roof in sales! They will be one of the few chipmakers who will be able to run open source operating systems and MS is gonna make them all rich if Palladium is really implemented.
And from what it looks like with these chips, moving to TM chips won't be any hardship at all.
No one ever had to evacuate a city because the solar panels broke!
Lack of SSE2 is a bummer but unless you're doing content creation or playing new games it won't matter.
Lack of SSE2 will not matter for any games, new or otherwise, because none of them use double-precision floats in any speed critical code paths. It'll hurt you if you want to render with Lightwave on your laptop, or run fluid dynamics simulations, or whatever. Not games.
Will this new processor let me have my laptop on my lap without burning my penis like this guy did
09 F9 11 02 9D 74 E3 5B D8 41 56 C5 63 56 88 C0
some more [in german] links for the lazy ones.
Either expect to see Palladium and non Palladium versions for years, and the non-Palladium beign more expensive and unable to run certain "media" features or expect it to be mandated by law.
Companies are no stupid, especially the ones that are in a fast moving industry and have proved to survive for at least 20 years.
unfinished: (adj.)
... often do replace their desktop with a laptop.
We have limited desk space for big monitors. And lots of us like to take a computer to class with us to take notes on, etc. Many people plug their laptop into the wall and use it as their primary computer as well. And do [try to] play games on them, etc.
So even if "most people" don't use them as portable supercomputers... plenty do.
I worked for a company that evaluated the crusoe for use in their servers and had to take a pass. The reason it was so interesting is that to build very dense (i.e. small footprint, lots of power) servers, heat becomes the single largest issue. We were building servers that would service telephone company needs around speech recognition, so that you could pick up a phone and say what you wanted instead of dialing. Alas, we couldn't pick the crusoe because it didn't support SSE2, which is not required for speech recognition, but increases the speed of it soo much that you dont need nearly as much CPU horsepower. In the end we went with Intel PIII's because the CPU Mips to heat/power was the right balance.
The people of slash dot need to think beyond their desktop's sometimes and think about how a system will be used by users of servers, and not desktop's. I was really looking forward to the release of this chip, until they decided not to support the SSE2.
Oh well...
It is not enough to not know what I don't, but better to always to know what I do.