Transmeta Astro -- More Details 142
chill writes "We've recently seen announcements, product launches and reviews from AMD and Intel on their new low power chipsets. Not to be left out, Transmeta has more details on their forthcoming Astro processor. Slashdot covered the Astro back at Comdex in November."
One of these days... (Score:5, Interesting)
Re:One of these days... (Score:1)
Re:One of these days... (Score:2, Interesting)
VIA chips are also a viable solution for these systems, and my next desktop system, literally, I'm going to be building it directly into the desktop itself, will probably rely on one of these low heat, low power consumption, chips.
First figure out how much "power" you need, then get the chip that requires the least power fo
Re:One of these days... (Score:2)
Re:One of these days... (Score:3, Informative)
It sounds to me much more like an 'anything but intel' approach - fine, but at least admit it.
If you want a low power consumption (and quiet) desktop solution now, look into the VIA C3 series, not fast but very low power.
If you want a high power but fast solution, look at Intel or AMD, they rule the desktop one way or another.
I personally would like to se
Re:One of these days... (Score:2)
Performance boost (Score:2, Insightful)
Works for me.
Re:Performance boost (Score:2)
Re:Performance boost (Score:2)
pipe (was Re:Performance boost) (Score:2)
Doesn't the -pipe option of gcc eliminate its use of /tmp? I've started using it, and compiling seems faster...
Re:One of these days... (Score:2)
Re:One of these days... (Score:2)
Re:One of these days... (Score:2)
My present desktop is a dual Athlon, and it is most pleasingly quick. My work is largely building big server-side stuff in Java, and this machine just zips through big Java compiles. I like it very much. But it is noisy. When I was building it I did think about a quad proc
Re:One of these days... (Score:1)
Re:One of these days... (Score:5, Funny)
My next car will either be an RX8 or a Prius.
Re:One of these days... (Score:3, Interesting)
Most of the time I just use a browser, email client and xmms. I also ssh into school to run Mathematica. I don't need a CPU capable of frying eggs thank you very much. An Astro desktop system would be perfect for me.
2) Refuse to sell to someone wanting to build their own desktop system based on your CPU.
I just wan't a CPU and mobo damn it. Why is this so hard to understand. I already have all the other components. I'd be willing to pay $400 for the privilege of having no fa
Re:One of these days... (Score:2)
Re:One of these days... (Score:1)
I wwant just a mobo for a desktop TRANSMETA.
Just for fun.
Cheers,
Re:One of these days... (Score:1)
How much would you pay to get rid of the noise your computer makes?
Not much, fortunately. VIA's C3 processors consume roughly the same amount of power that the Transmeta chips consume, they sell for a fraction of the price, they are reasonably easy to find, they work on TONS of motherboards (most modern P3 boards), and to top it off, they beat the pants off anything Transmeta's put out when it comes to performance (which isn't saying much).
Re:One of these days... (Score:2)
Here's a link:
http://www.mini-itx.com/store/ [mini-itx.com]
Re:One of these days... (Score:1, Flamebait)
Re:One of these days... (Score:1)
I bought a regular mid tower case (that takes the Mini-ATX form factor) two 120GB drives, and with Redhat Linux, I setup a software RAID mirror!
Looking inside this big case is laughable, there's nothing but a teensy little board in th
Not to be a naysayer.. (Score:1, Troll)
Remember Cyrix? (shudder)
Re:Not to be a naysayer.. (Score:5, Informative)
Seems to me the Transmeta chips work fine.
For reference, I'm using a Toshiba Libretto L1, purchased from Dynamism.com.
Re:Not to be a naysayer.. (Score:1)
Re:Not to be a naysayer.. (Score:1)
Re:Not to be a naysayer.. (Score:1)
Re:Not to be a naysayer.. (Score:1)
Re:Not to be a naysayer.. (Score:2, Informative)
Re:Not to be a naysayer.. (Score:1)
Re:Not to be a naysayer.. (Score:2, Informative)
Re:Not to be a naysayer.. (Score:2)
Were I Matrox, I'd be scared. The 'everyday' cards are now getting good enough that the monitor is the limit on the image quality. I use an el-cheapo $249 19" special.
I had a G400. I had a Radeon 7000. I had a Voodoo III. I couldn't tell the difference. Why would I pay more than the $40 the Radeon cost?
But returning to topic, what Tran
Re:Not to be a naysayer.. (Score:5, Interesting)
(That's insightful? C'mon now.)
Transmeta is going off in a different direction. Intel and AMD have gotten to be about trading massive power consumption for incremental performance increases. Now Intel is backpedalling because you just can't stick a high end P4 in a laptop (hence the Centrino). Transmeta is putting power consumption first, which is a different angle.
Re:Not to be a naysayer.. (Score:5, Interesting)
Transmeta is putting power consumption first, which is a different angle.
People often speak of CPU power consumption in the same breath as laptops and it's certainly important.
Despite the troubles of RLX and related companies (probably due to the general market downturn more than their specific product), the server market for low power chips will come back.
At some point we'll probably see benchmarks on TPC/kW or Webstones/rack where Transmeta could make a dent.
Re:Not to be a naysayer.. (Score:2)
An intriguing question. What I wonder is, if server power becomes such a significant aspect of design due to the price of electricity, what does that mean for the clients of these systems? I wonder if it implies tha
Re:Not to be a naysayer.. (Score:1)
At some point we'll probably see benchmarks on TPC/kW or Webstones/rack where Transmeta could make a dent.
The only place Transmeta's going to make a dent is in its investors' portfolios. I expect your TPC/kW prediction to come to pass within 5-10 years, but the only thing left of Transmeta by then will be an entry in fuckedcompany.com's archives.
Transmeta's processors are technologically fascinating and far ahead of their time. However, the company overhyped itself with all that Skunk Works shit (*c
Re:Not to be a naysayer.. (Score:1)
However, the Pentium-M looks like a KICK-ASS blade server processor to me! Beyond the low power consumption, it has 1MB of L2 cache! What's more, it's got a 400MHz bus, which should help for some decent I/O performance.
Re:Not to be a naysayer.. (Score:3, Interesting)
Where does Transmeta fit in? That tiny demographic that's willing to pay the extra cash for lower voltage and longer battery life? How long do you think they'll honestly survive serving a nich market..? Unless they
Re:Not to be a naysayer.. (Score:2, Insightful)
My Compaq Presario 12XL423 is a piece of garbage. Not a day goes by that I don't kick myself for not spending a few hundred more on a better laptop.
Remember Cyrix? (Score:1)
VIA bought Cyrix a while ago; though maybe there's not *that* much difference between getting bought and going out of business (from the point of view of the company that got bought, outside of the folks who ended up getting bonuses because of it;)), and though this article (http://accelenation.com/?ac.id.141.1) says that VIA pretty much put the Cyrix part "to sleep," the market niche that Cyrix had with the Medi
Re:Remember Cyrix? (Score:1)
As for VIA, they
Re:Not to be a naysayer.. (Score:1)
Remember Cyrix?
Remember 3dfx?
More competition for processor production (Score:3, Insightful)
Re:More competition for processor production (Score:5, Insightful)
Decide. You can only have one at a time.
They either give you faster CPUs or cooler CPUs.
First, they go for faster for the price of creating way more heat. Those were the last few years.
Right now, the market has decided that it doesn't need any more speed and that it is more concerned about heat and energy consumption. Alas, not for enviromental reasons, since then we'd see low voltage CPUs and chipsets in desktops, but because it affects laptop battery life and it's potentially unpleasant [wired.com].
I hope that low voltage CPUs will be seen more often in desktops. I hate my computer's cooling fans.
Re:More competition for processor production (Score:1)
They are not necessarily mutually exclusive. Look at the chart here: Heat Down! Intel, AMD And VIA In Detail [tomshardware.com]
A P4-2.53GHz generates less heat than a 1.7GHz Celeron.
Re:More competition for processor production (Score:2)
go faster is because as feature size shrinks, the
leakage currents go up. However there is a lot of
research on controlling leakage. It's just that
up to a point so long as people don't complain
too much CPU makers can ignore leakage and require
ever bigger heatsinks. But now at around 90 nm,
leakage is becoming the bottleneck not only for
heat production but even for signal propagation,
so I expect to see tons of research turn into
tons of practical solutions, like d
It slices it dices (Score:3, Interesting)
Compiler enhancements? (Score:2, Informative)
My question is, will compilers be able to bypass the code morphing software, and directly work with the Transmeta's underlying instruction set?
Re:Compiler enhancements? (Score:2)
Re:Compiler enhancements? (Score:1)
This is how I understand it as well. I posted a question about just this sometime ago somewhere, and I was told that it was stupid/impossible to run "native" Crusoe code because there really is no such thing.
There was a lot of conjecture goi
Re:Compiler enhancements? (Score:1)
On another note, it should be possible for them to implement hyperthreading in their code morphing engine. That'd be interesting. I wonder if Intel has a patent on it.
Re:Silent is good (Score:2, Interesting)
I believe everything compiles as regular ole x86 and the code-morphing is done at a very low software layer. If you'll read more about the Transmeta chips you'll see that several megabytes of memory are con
Originally... (Score:2, Funny)
Re:Originally... (Score:1)
=)
Re:Originally... (Score:1)
What ever happened the to the code morphing? (Score:5, Interesting)
So where's my triple boot OSX/XP/Linux box running on a transmeta chip?
Re:What ever happened the to the code morphing? (Score:3, Interesting)
Re:What ever happened the to the code morphing? (Score:5, Interesting)
The idea of the code morphing is that any ISA could emulated. x86 is the only emulation that they focus on, but it should be able to emulate PPC, Alpha, MIPS, Z-80, you name it.
Re:What ever happened the to the code morphing? (Score:1)
Certainly the code morphing technology should theoretically allow them to execute an arbitrary binary instruction set, but in reality they targetted this system at x86. The goal of the project was to build a more efficient processor. All the tomfoolery about alternate instruction sets was so much speculation on the part of slashdot editors, others.
Re:What ever happened the to the code morphing? (Score:1)
Transmeta probably already has the PPC emulation down pat...It's just that it would be unwise to release it if OSX (Its most prominent potential use) won't run on it. Bad publicity.
Re:What ever happened the to the code morphing? (Score:2)
Keep in mind that Linus works for Transmeta, and OS X is BSD. I mean seriously, who would have the most experience in the entire world at doing this?
Transmeta probably already has the PPC emulation down pat...It's just that it would be unwise to release it if OSX (Its most prominent potential use) won't run on it. Bad publicity.
I am not convinced that t
Re:What ever happened the to the code morphing? (Score:5, Informative)
No, their claim to fame was that their code morphing allowed them to run x86 instructions on a VLIW chip, which may turn out to be more scalable/efficient than either RISC or CISC architectures. The R&D on the code morphing was just as expensive as the R&D for the rest of the chip, so I can't imagine they'd go repeating that for some less popular architecture.
They never said they were about to release code morphing packages for other platforms. Idiotic journalists (and slashdot readers) were the ones that pointed out that the code morphing could work for other platforms.
Re:What ever happened the to the code morphing? (Score:2)
No, the whole point is that code morphing does exactly what they hoped it would do. The only people that said any different were idiots (and were not employed by Transmeta).
Of course, their chips aren't as fast as they might have liked, but that may improve.
Re:What ever happened the to the code morphing? (Score:2, Informative)
Re:What ever happened the to the code morphing? (Score:3, Insightful)
Re:What ever happened the to the code morphing? (Score:5, Informative)
The processor is not RISC, it's VLIW. A meta-instruction is made of 8 smaller, 32-bit ones. The key characteristic of VLIW is that these 8 instructions are explicitly parallel; the processor knows, when processing this instruction, that it can execute all these 8 subinstructions in parallel (now a sub-instruction is RISC-like, I grant you that). The difficulty is finding this level of parallelism in existing x86 programs (this is the job of the software code morpher)
Furthermore, only the meta-instruction is 256 bits, not the registers, etc (which are only 32 bits). That'd be way too wasteful. Most apps don't need more than 32 bits, anyway. Only big servers need more than 4 Gigs; this processor is targeted to mobile applications, therefore I'm pretty sure it can only address 4 G of RAM.
Re:What ever happened the to the code morphing? (Score:1)
It seems too good to be true, so I'm probably wrong.
Re:What ever happened the to the code morphing? (Score:1, Informative)
The point of code morphing was to reduce the extra hardware and make a more efficent chip. Intel did that with IA-64, reducing much of the logic by putting it into the sof
Re:What ever happened the to the code morphing? (Score:2)
Bit of a disaster really.
Why not emulate PPC? Well, for one there's less wrong with PPC than with x86 in the
Re:What ever happened the to the code morphing? (Score:2, Informative)
VLIW improves performance when the instruction stream can be split up over multiple processing units.
Exhibit A:
LOAD A
LOAD B
LOAD C
LOAD D
ADD A, B
MOD A, C
ADD A, D
STORE A
LOAD E
LOAD F
LOAD G
LOAD H
ADD E, F
MOD E, G
ADD E, H
STORE E
Exhibit B:
LOAD A
LOAD B
LOAD C
LOAD D
LOAD E
LOAD F
LOAD G
LOAD H
ADD A, B
ADD E, F
MOD A, C
MOD E, G
ADD A, D
ADD E, H
STORE A
STORE E
Exhibit A is more difficult to make parallel than exhibit B, since the potentially parallelable code is separated, and, fr
no, really, i need one (Score:2)
Separately, Sharp is announcing it will use the exisiting TM5800 in one of the thinnest notebooks on the market.
hmmm, i wonder if i could get the boss to srping for one of these just so i could test it. [yup, after two month's intense scrutiny, i can tell you it runs games very well.]Re:no, really, i need one (Score:3, Interesting)
It is so thin and light because it doesn't have any drives -- no CD/DVD and no floppy. Fine, but if I want to do that, I'll get that Lindows laptop that has about the same specs (Via C3 processor @ 933 MHz) for 1/2 the price ($799 vs $1,499)
Transmeta vs. ARM (Score:3, Informative)
http://www.duke.edu/~kaf3/lowpower/slide28.html
Transmeta 5400! (Score:2)
sort of (Score:1, Informative)
Why aren't these more popular? (Score:1)
Re:Why aren't these more popular? (Score:3, Funny)
Re:Why aren't these more popular? (Score:2)
Try to find a board, that supports AMD Mobile Athlon. This is much easier for the board manufacturer, it has the same socket and it only has to set core voltage, multiplier and FSB correctly.
You can see the results of my experiments in the forums on www.silentpcreview.com [silentpcreview.com]. Search for Mobile Athlon.
Bye egghat.
Re:Why aren't these more popular? (Score:2)
Because most geeks still want Ultimate Performance At Any Cost. The standard pattern is that you can pay a $1000 premium for a new Intel chip that gives you a 9% clock speed boost in exchange for a 15% increase in power consumption. But people are tiring of this.
Where's a feature comparison? (Score:4, Informative)
- Transmeta Crusoe
- Via C3
- Intel ULV (old, now outdated by the new Centrino)
- Intel Pentium-M (aka Centrino, which appears to be a chipset strategy as well)
- AMD XP-M (aka Low Voltage Thoroughbred)
So, please tell me, why should I choose over the other? Where are the conceptual differences?
Order by price/power/performance (Score:5, Informative)
AMD XP-M
Intel Pentium-M
Intel ULV Pentium III
Via C3
Transmeta Crusoe
Least power to most power:
Transmeta Crusoe
Intel Pentium-M
Via C3
Intel ULV Pentium III
AMD XP-M
Cheapest to most expensive:
Via C3
Transmeta Crusoe
Intel ULV Pentium III
AMD XP-M
Pentium-M
It depends on your need; if you are going for embedded systems try a non-x86 processor, which is better in all two categories and in the middle in performance. For a laptop, the XP-M or Pentium-M offers desktop replacement performance; if battery life is your thing, the Pentium-M, Via C3 or Transmeta processors ought to do ok. If cheap is the most important thing then go Via.
Scale needed to make this fully sensible (Score:1)
Anyone seen such figures compiled?
Who'd be a fish
This just in... (Score:1)
Re:This just in... (Score:2)
R'im rorry Rinus....
-- Rastro...
reviews? (Score:1, Flamebait)
Underclocking (Score:1)
Go google for more info. Sounds like a good idea tho. Personally this P4 with a 80mm fan is plenty quiet, not silet, but quiet.
Re:Underclocking (Score:2)
Bye egghat.
Only X86? Why not X86-64? (Score:2)
Re:Only X86? Why not X86-64? (Score:2)
X86-64 brings to the table other things besides 4+GB of RAM. Namely, the extra registers.
I do think that the extra registers would be handy, code-morhing or not.
I want a low power, high performance CPU ... (Score:2)
Transmeta is impossible, cause there are no boards available. VIA is too slow.
One way ist too underclock und undervolt your CPU. Some guys at www.silentpcreview.com [silentpcreview.com] have their Athlons running fanless(!) at 850 MHz and 1,1 Volt core voltage. The CPU doesn't consume more than 15 watts then.
I've done some experiments with Mobile Athlon in normal desktop boards. But not with that great results. Check out the forums of silentpcreview [silentpcreview.com].
Bye egghat.
motherboard? (Score:1)
Re:Important News! (Score:1)
Re:Where can I buy a NEW low-spec notebook? (Score:1)
http://listings.ebay.com/pool2/plistings/list/all