Follow Slashdot blog updates by subscribing to our blog RSS feed

 


Forgot your password?
Close
typodupeerror
×
Transmeta

Crusoe As Server CPU 90

Posted by Hemos from the interesting-approach dept.
rxmd writes "Heise has an article on Transmeta's Crusoe processor being used as a x86-compatible server CPU by companies such as rebel.com and RLX (read their press release on the project), supporting Linux as well as other "established operating systems". Basically, it's about the Crusoe's lower power consumption and temperatures enabling server manufacturers to put more processing power into the same amount of space than with Intel or AMD cpus. Interesting that a CPU designed for mobile applications should find its way into the server market."
This discussion has been archived. No new comments can be posted.

Crusoe As Server CPU More

Crusoe As Server CPU

Comments Filter:

  • Re: sailboats (Score:1)

    by Anonymous Coward
    But then again, I don't really understand how sailboats sail into the wind.

    They can't sail directly into the wind. Roughly 45 degrees on a tack is optimal. So you can break this into two vectors: one parallel to the boat and one perpendicular.

    The wind force along the perpendicular vector causes the sail to fill. The boat isn't pushed laterally very much because of its shape, and the rudder.

    The wind force parallel to the boat is moving from bow to stern. Since the sail is filled (see above), it is shaped like a wing. The air moving across the sail creates lift, which moves the boat forward. Once again, the rudder helps counteract the lateral force.

    That's why you tack back and forth to maintain a course into the wind.

    On a similar note, a sailboat generally can achieve faster speed on a jibe than moving directly with the wind - even with a spinnaker(!) Once again, this is due to airflow over the sail creating lift.

    - some salty dude

  • This would be an option if you could get cheap PPC-based motherboards.

    If there were cheap PPC motherboards, I'm sure a whole lot more people would run Linux on PPC just out of this being an interesting alternative to Intel and AMD.

    But the fact is, there aren't cheap PPC motherboards. You have a choice of buying pretty pricey hardware from Apple, or buying ludicrously pricey hardware from IBM or Motorola.

    Selling cheap motherboards isn't a primary business for any of these companies; what's needed is to attract companies like ASUS, GigaByte, Shuttle, ...

    And they will only seek to sell cheap motherboards if they are quite certain that they can amortize development costs across gazillions of sales.

    That only happens if there are VARs and wholesalers prepared to purchase gazillions of cheap PPC motherboards and sell them pretty cheaply. Which requires having a bunch of system vendors.

    I seem to remember there being some; Apple basically drove them out of business, thus leaving only the high priced vendors of PPC systems to drive the market for PPC-related hardware.

    Note that I never said a word about electricity in any of the above; the only time when vendors start trying to sell people on "power efficient" is when they haven't any more compelling argument to make. I knew Corel Computers was in trouble when they spent much of their marketing material selling the fact that their machines were cheaper to run due to low power consumption.

  • I dissagree.
    I don't think that the 12:1 ratio is correct, but it could be an exageration on your part...
    I can see this as being important where machines are not at 100% useage most of the time and where redundancy is a must. Like the average web farm.
    With this you could afford to put a few more boxes in place and survive abnormaly large traffic just as well with smart web routing packages. A much better performance than what you would get on a single box.
  • Stop right now mister.

    You do not want to write to a native Crusoe!

    Not not not not not.

    If you do that, then you tie yourself to the hardware too closely and when they decide to make a new frobnitz that'll make doing Distributed Net's blah-blah-challenge run 75% faster, you'll be SOL.

    What you want to do is, identify that little bit of core CPU intensive code that is doing the majority of the work and seeing if you can code it in a way that the chip will do it most efficiently.

    I can foresee future Crusoe's with little bits of DSP hardware doing FFT's when it morphs some code that does that kind of or, or something like that. You should be getting the idea...

    Stop it with the native stuff. Save the native stuff for when you're on an island with a hot polynesian babe. Then you can go native.
    _______
    computers://use.urls. People use Networds.

  • Not this again... (Score:5)

    by slothbait ( 2922 ) on Monday January 22, 2001 @03:35PM (#490035)
    > Seems to me that it'd be pretty cool to write to the native Crusoe architecture rather than going through the x86 ``emulation''. Does anyone know if it's even possible to bypass the emulation at all, and write native machine code

    Just about every Crusoe posts comes standard with one or two of these questions. Actually, I don't know the answer, but I expect it is *not* possible to write to the "native" ISA of the Crusoe chips. In so doing, you would be circumventing important architectural features of the chip, which operate in their ultra-low-level ISA emulation software.

    But most importantly, even if you could, they do not *want* you to. Their code-morphing software also performs some optimizations, which would be thrown out the window if you went "native". More importantly, though, native could would be irrevocably tied to *that implementation* of the Crusoe. Transmeta is under no obligation to build the next Crusoe with the same ISA, and probably won't. Since they are emulating another ISA, the physical architecture is only seen by their software, thus they can tweak the architecture as much as they like between revs without having to worry about breaking binary compatibility. As any design engineer knows, this is a Thing of Beauty, and a luxury no other company is allowed. If people started programming native, they would lose that luxury.

    So, while writing straight to the Crusoe silicon (if possible) may be fun as a hack, it would not result in maintainable software. Moreover, it is in Transmeta's best interests to discourage such behavior

    --Lenny
  • Is anybody making SMP machines that take advantage of the crusoe software layer to do intelligent optimizations with SMP?
  • I don't think this is the case. If all you want to do is spew files down a big pipe you don't really need a terribly fast processor. An efficient OS and loads of memory should be enough. ftp.cdrom.com set multiple bandwidth records when it was a dual Pentium Pro 200.

    20 2u machines in a rack generate a large amount of heat, and if all they are doing is acting as web frontends to a backend machine that is doing the heavy database lifting I could see the saving in machine room cooling and UPS power to be significant.

  • In a dense pack server farm, a dense rack or CoLo cage the enemy is heat. The heat pumps grow much faster than server capacity the denser you pack them. So anything you can do to reduce heat is a good thing assuming of course that under typical load a Crusoe is actually cooler. That is, if it's never idle is it cooler than Intel machines?

  • Uhm, whatever. First of all, the numbers I've seen suggest that computers have slowed the growth of electricity use in California, because they increase the efficiency with which everything gets done. This article on Salon [salon.com] goes over the information in pretty good detail.

    Once you accept that computers actually represent a small %age of California's power burden, you also need to realize that the incremental cost of cooling those computers can't be much higher. Even if it took 2Wh of AC for every 1Wh consumed by a computer, the overall impact on the electricity budget would still be small compared to the rest of the stuff sucking up energy. Stuff like TVs that are left on most of the time, microwave ovens (typically 700W or higher when they're on, as compared to the ~200W a typical computer draws when its crunching away), electric stoves, electric heat, and AC for personal dwellings that would be there regardless of computers.

    And don't forget, running computers in the winter cuts your heating costs, to offset the increase in AC costs in the summer...

    --Joe
    --

  • Average US household has the TV on for ~7hrs a day, even though it's only watched for about half that time. Most (near 100%) of households have TVs, and most of those TVs are larger (and draw more power) than typical computer monitors.

    In contrast, fewer people have computers, and fewer still leave them on 24/7. (Just because people here on Slashdot leave their PCs on 24/7 doesn't mean the rest of the world (or even the bulk of California) is.) Most people also use the Windows default settings for APM which do shave a few Watts. (Ever hear of Energy Star?) Same goes for those PCs at work.

    --Joe
    --

  • Re:Not this again... (Score:4)

    by Mr Z ( 6791 ) on Monday January 22, 2001 @04:22PM (#490041) Homepage Journal
    Transmeta is under no obligation to build the next Crusoe with the same ISA, and probably won't.

    ...and already haven't. Their existing two part families (the TM3200 and TM5400/TM5600) have different ISAs under the hood. Apparently, the TM3200 doesn't handle legacy 16-bit code as well, so they went back and improved that with extra functionality found only in the TM5xxx families.

    Now what would be interesting is if Transmeta offered a better "meta-assembly language" that was both easier for them to decode and translate, and simultaneously served as a better compiler target. That's perhaps asking too much. At least the "Transmeta running x86-64/AMD-Hammer" [cnet.com] thing sounds interesting...

    On a different note, another reason they don't want you coding to the native ISA is that not only are the x86 instructions emulated, but also some of the legacy x86 peripherals are emulated as well. It makes perfect sense to at least partially swallow up some things, like timers and interrupt controllers and emulate them in software, avoiding unneeded bus traffic. It speeds up the CPU and reduces power.

    --Joe
    --
  • That's what IBM RS6000 servers are made for; they use multiple PowerPC chips and can run Linux.
  • "Most servers don't need an FPU"?

    ... and just what kinda servers are you building?

    Please don't answer web only and think you are safe. I'll let you figure out on your own why that is wrong.
  • Nope. The simple fact is in today's internet if you are building a large commercial cluster of webservers you are doing two things: CGI and SSL.

    You *need* a FPU. When I see people expounding the merits of non fpu boxes with a minimal amount of ram for a cluster it becomes obvious how many large clusters they have actually built. You want maximum ram on each box just for the disk caching alone... the goal is to make sure the network (& equipment) is your bottleneck.
  • RocketLogix is now RLX Technologies. Don't ask. It's a stupid patent thing.

    An RLX Employee, and loyal /. reader.

    And yes...the boxes are cool. Very cool. 'nough said.

  • a CPU spends most of its time doing strictly nothing but wait for the rest of the world.

    Indeed .. time to get some RC5 crunching [distributed.net] action happening in those spare cycles.

    --
  • Please don't answer web only and think you are safe. I'll let you figure out on your own why that is wrong.

    I'm wondering if you mean Linux servers and the fact that that kernel requires an FPU or FPU emulation coded into it.

    Although an interesting point, MOST of the work of the server will be with non-FP programs, like web servers and the like. If you're doing math, then yes you need an FPU but otherwise the kernel emulation will do fine.

    I think you're trying to be smug but in reality an FPU wouldn't ACTUALLY make that much difference.

    --

  • The ratio for average server performance is more than 1:2 not 1:12. So you logic is flawed. Transmeta is not that slow. Tried it. It is about as fast as PIII at the same frequency on integer math and this is what matters for a server. Also, for real server operations quite often the bottleneck is the IO, not the CPU anyway.

    The reason why people use PIII and not transmeta or AMD (which also has very good power saving under UNIXes) is the fact that there are no server boards available. For example try to find a mainboard for AMD with console redirection and enjoy the nightmare. At the same time all high end Intel and ServerWorks boards support it.

  • This does make sense, but there is no one selling to this market. Apple is still the only company that sells affordable PPC boxes/motherboards. Until this changes, PPC isn't going to live up to its potential, and no one is marketing PPC boxes as servers.

    Apple can't do it, because their OS (up through MacOS 9) pretty much sucks as a server. Sure, you can load Linux or NetBSD on it, but Apple has a lot of ego invested in MacOS, and to them, Mac+MacOS is a single product. Their marketing doesn't include the concept of selling a Mac just to have another OS get installed over MacOS.

    (Aside: maybe that's a good thing. I remember my shock and disappointment when I found out that IBM was selling computers with Win95 instead of OS/2 Warp. Shock and disappointment aren't emotions that you want potential customers to feel.)

    What this means is that it may actually make a lot of sense for a user to buy a Mac for use as a server, and put some Unix on it. But they aren't going to get the idea to do this, from Apple's salesmen.

    MacOS X may change the situation, since it should be good for servers. So Apple probably will start marketing their boxes as servers. But that's in the future; MacOS X isn't at release yet. When MacOS X comes out, I think the personal computer world is going to become more interesting.


    ---
  • Note that I never said a word about electricity in any of the above; the only time when vendors start trying to sell people on "power efficient" is when they haven't any more compelling argument to make. I knew Corel Computers was in trouble when they spent much of their marketing material selling the fact that their machines were cheaper to run due to low power consumption.

    Ah, but power consumption is about to be a serious consideration in California. The cost of electricity has gone up by a factor of TEN. Right now, PG&E et al are not able to pass on this added cost, but sooner or later, it is going to be passed on. When the server farms see their power bills go up by a factor of 5 or 10, spending an extra $100 on a computer to save $1000 on electricity is going to be smart business.

    -jon

  • Re:Why not PowerPC? (Score:3)

    by TWR ( 16835 ) on Monday January 22, 2001 @04:08PM (#490051)
    And this is why I suggest that it would be good for Apple to make a rack-mount G3/G4 system, which could still be fanless. They could design a box which delivers the same performance, runs the same apps, and uses significantly less electricity, making the slight difference in cost go away in a matter of months.

    Mac OS X is going to be the long-term key to this plan, but Linux/PPC isn't a bad place to start from. With Larry Ellison sitting on Apple's board, I would expect Oracle to be running on OS X within a year. That'll give you Oracle, Apache, and JDK 1.3 all on one box, which uses a lot less power.

    This should be a no-brainer, since the power problem in Silicon Valley is going to get worse before it gets better; winter is the OFF season for power, and we're running out (yes, I know there are lots of power plants offline now, but the same principle applies)...

    -jon

  • Why not PowerPC? (Score:4)

    by TWR ( 16835 ) on Monday January 22, 2001 @03:27PM (#490052)
    Using Crusoe strikes me as silly when there's another CPU out there which uses a heck of a lot less juice than x86: the PowerPC. Granted, it won't help the WinNT people, but for those running Linux servers in server farms, it's ideal. Low power, low heat (iMacs, iBooks, and Cubes don't even have fans), and a lot faster than Crusoe.

    I've been waiting for Apple to start running ads in California trumpeting how much less power Macs use, compared to PCs. This might be a good place for Apple to start; G3/G4 rack-mount, anyone?

    -jon

  • Does anyone have any experience with Black Lab Linux? Is it faster than YellowDog Linux or Debian Potato 2.2 PPC?
  • Look at the current situation. We keep making boxes smaller (because the CPUs are getting smaller) but they're getting much hotter. We're already having concerns at work with our newer Intel boxen; We're cramming more and hotter CPUs into the same space, and having to get a lot of cooling fans in there.

    California's power shortages are being partially blamed on Silicon Valley.

    Crusoe would be great in this situation. Low power consumption, low heat output. Reduce your electicity bill twice, and eliminate those rolling blackout.s

  • I've been of the opinion all along that the low-power mobile application of Crusoe is something of a ruse. I'm betting that when Itanium ships that Transmeta will jack up the power and release a like-speed or faster Itanium-compatible chip. You heard it here, first.
  • I don't know about this, I guess it could just be me, but I dont think I could ever see a Crusoe inside a server. Now if they were doing some massively parallel stuff like 8 of them all in one box it might be feasible, but the whole reasoning behind it seems a bit shaky. If you run the article through Babelfish and actually read it, you'll see that that's what they are talking about. In the same space you can fit 42 1U rack-mount dual-Pentium III boards (with requisite cooling) for a total of 84 processors, RLX will fit 750 Crusoe processors. 9X the CPUs with less power consumption and heat. Not bad in my opinion.
  • Seems to me that it'd be pretty cool to write to the native Crusoe architecture

    Yes, it would be cool. It would also be impractical. The native Crusoe ISA is strikingly similar to "horizontal" microcode[1] from a long-ago era. Even I came on the scene too late to hack that kind of microcode, but I was close enough to know that it had a couple of interesting characteristics:

    • It was very unsafe. Horizontal microcode was characterized by a very high level of parallelism even within one instruction ("molecule" for Crusoe), with little interlocking or safety checks. Programmers were expected to know which micro-op was compatible with what. Forget, and you could lock up or permanently damage the processor.
    • Getting anything to work at all was hard. Trying to optimize was mind-bendingly hard.
    • The micro-ISA kept changing every time a new chip implementing the same macro-ISA came out, meaning that you'd have to go through all that incredible pain all over again.

    Having said all that, I still think it would be cool.

    [1] For those unfamiliar with such ancient terminology, there were two trends in microcode. "Horizontal" microcode was characterized by fewer, longer lines on a program listing compared to "vertical" microcode. RISC and VLIW assembler are strongly reminiscent of vertical and horizontal microcode respectively. Of course, microcode didn't quite have the same "view" of things like registers or exceptions, and all of that OOI/OOC/renaming kinda stuff just didn't apply at all, but the similarities are still there.

  • RocketLogix and FiberCycle are looking at Crusoe in the same way

    I'm not posting links... you should be able to figure them out.

  • Actually from things that I can't really disclose... The Crusoe is exceptionally fast in it's native instruction set. If you actually run on native hardware it's FPU is supposed to be extremely fast. The catch....

    Is that Transmeta does not gaarantee that the instruction set will ever be the same between different revisions ot models. They want to support x86 apps and OSes.

    The Crusoe is a strange beast and benchmarks very well against clock equivalent Intel Processors. Actually integer performance is through the roof, sometimes doubled.

    This interger performance is exactly what servers need. You think that Apache is doing some heavy fp math? No.

    Floating point is great for games and scientists. but it's not always the most important thing to look at... the UltraSPARCII is a good example of FPU not being everything.

  • Everyone knows and trusts PCs. The apps are already there. This affects Linux also. If there is a cool commercial linux app that you want to try and you have a Sparc, Alpha, PowerPC, MIPS, m68k, etc... you are pretty much screwed. Commercial support, even for Linux, is pretty much locked into x86.

  • Seems to me that it'd be pretty cool to write to the native Crusoe architecture rather than going through the x86 ``emulation''. Does anyone know if it's even possible to bypass the emulation at all, and write native machine code?

    True stoneage thinking. Me not know how to use computer. Me know how to use hammer. Me use computer as hammer. See! 'pooter is useful!

    Yes, you can write native machine code for one particular Crusoe chip. After all, the code morphing layer is written in native code. The next Crusoe chip that comes along won't be able run your code, because the internals will have changed. Transmeta don't want to be in the position of Intel, having to build backward compatability into their chips. They won't do it. So in six months you'll have to compile your program for the next Crusoe... and the next... and the next... and you'll have to support users using all those versions, so you'll need to keep a machine with each version in house...

    True stone-age thinking.

  • A project. A little sumpin-sumpin.
  • Well, in that case, why not just relocate the farm to somewhere cold and close to a power plant; you get airconditioning for free (open the window, eh?) and electricity is availible. If opening the window isn't an option, land should be cheap enough so that you can afford to space your servers out a bit.

    and you can now stop leasing expensive california real estate.
  • Regardless of how good the ``emulation'' is, it seems like it'd be faster and more efficient to optimize for the real hardware

    Yes, it may seem that way. However the actuality is that compile-time optimization can be inferior to RUN-TIME optimization. [arstechnica.com]

    So never minding forward compatibility, you probably will wind up with faster code compiling for intel. As for hand-written Crusoe Assembly, obviously that's theoretically capable of the maximum performance, however depending on the instruction set, from a practical point of view it may not be possible to surpass translated i86 code.
  • The real problem is with propogation delays between the internal transistors, rather than heat. Now, as you cool the chips, the propogation delays go down, so cooling does allow you to run substantially faster.

    However, on a chip where heat is not the main issue (as the Crusoe easily may be), it is possible to overclock to a point where, heatwise, the chip is fine, but in which it will never boot because signals are simply not moving fast enough for instructions to process. Cooling can help, but overheating is not the problem in such a case.

    (Try this: take a 486DX33 and overclock it to 50. With cooling it will easily run, but it will not heat dangerously with just an ordinary heatsink fan. However, it will not run.)

  • pretty much a first (Score:4)

    by po_boy ( 69692 ) on Monday January 22, 2001 @02:42PM (#490066)
    at least someone is using it.
  • One thing that nobody seems to be mentioning is that this also increases indirect OS competition. One of the biggest perceived problems to going to Mac OS X is the need to get new hardware. With a Transmeta server all you would need to do is change the emulation and voila, same hardware, Unix OS, and you don't have to up your admin costs for a unix admin, just use Aqua as your admin interface.

    DB
  • Performance at doing what though. If the power consumption is very low and you want a farm of web servers, you can embed 8 of them in one 2U rack box, which will have much more performance. The whole point here is that not everything is CPU limited AND you may get better bang per unit volume with lots of small Crusoes. I don't know about better bang for your buck as that depends on what kind of performance you need. If you want a box to run a CPU intensive process that needs scalibility in the CPU realm (i.e. SMP) and isn't inherently distributed, then obviously 5 or 6 or 8 of these Transmeta boxes are clearly at a disadvantage to one powerful SMP PIII box. The right tool for the right task.
  • That is extremely reductionist of you. I think the whole point of this is that for certain applications that are not CPU limited but I/O limited, let's say, you want more machines per unit space at a similar cost rather than more CPU speed. So 8 Crusoe boxes may take the same space and power as one Athlon but can push a lot more bits through their buses combined.

    Also, you are completely ignoring that fact the relationship between power consumption and processing capability is not at all linear. 8 Crusoes may draw the same current as one Athlon or one PIII, but for an inherently parallelizable or distributed application may be able to do 2-3 times as much work (all together) as that one Athlon. For other applications that are less amenable to distribution/parallelization, they may do significantly LESS work than 1 Athlon or 1 PIII. It isn't a one-size-fits-all problem and there is no absolute metric of "Processing Power" for all applications, nor is "Processing Power" the only relevant factor for all applications.

  • Of course the answer is no, and the previous poster already pointed out why. But consider also that if you *could* do this, you would simply be wasting half the processor. The whole point to crusoe is x86 compatibility. If all you want is the low power consumption, that's what the ARM processors are all about, and they're quite available. Check out the NetWinders at rebel.com.

  • We've been waiting for this for some time, since it would at the least make it a lot quieter in here, and give us a lot less trouble with heat dissipation. We do web hosting here, and we've been considering buying one of the many x-by-1U server packages, but 4P3x1U seemed like it would be a lot of heat in a very small area. We were about to order some of them anyway, but if we can get Crusoes to do it, all the better. Our boxes seem to be mostly limited by memory, network and other I/O related issues, as opposed to processor.

    We'll probably still run at least dual P3s on the dedicated database machines, but there are fewer of them. The space they take up is of less concern, especially since they house the database disk arrays, which are large enough to completely eliminate most if not all 1U and 2U size boxes.

    It'll be good to see how they do on benchmarks for serving web pages and the like. I agree with the previous posts that they should be very effective at it, with the code morphing. Maybe it should even be seen if we can take a little cue from khttpd and see if we can get an on-chip web server. :) Not that I really think the bonuses would be a lot better than the kernel web server, but hey, you never know.

    -- Braeus Sabaco
    Member of the Roman Legion
    Customer/worker at Phenomenal Internet Solutions [phenominet.com]

  • If a crusoe can be plugged into a server, what's preventing them from plugging them into a mid tower as well? I'm sure that overclockers would have a field day with low power low temp processors like the crusoe.
  • In the article they talk about replacing 84 pentium III's with 750 crusoe's, approximately nine times the amount of processors for the same rack space.

    I'm not sure how it all factors out cost wise, but on a space/performance base thats got to be a major gain. It also makes you realize why they are so badly after cpus that run cool.
  • Low power, low heat (iMacs, iBooks, and Cubes don't even have fans)

    While it's true that the PowerPC consumes less power than comparable Intel and AMD processors, that's not the only reason the Macs don't use fans.

    First, because Apple has complete control of the design they were able to design the motherboard and cases to maximize airflow driven by heat. Most x86 PCs don't have the same luxury of custom design for heat management, they're constrained by the form factors of earlier systems that produced less heat. There are people who've built cases with chimneys to suck air through without fans, but the internal case layout really isn't very good for this.

    Second, what's the wattage of a Mac power supply? If you have very limited internal expansion, you can budget your power supply pretty tightly and make it weak enough to work fine without a fan. It's possible to get a PC power supply that will work fine with no fan, but standard AT and ATX supplies are generally not vented properly for that, nor are the cases that they're put in. What's the last PC case you saw that had vents in the top?

    -- fencepost

  • IIRC they use more electricity for AC than to run the computers.

    Uhhh... No. It's actually more like an 8:1 ratio in favor of the computers. I must admit though, it is interesting to see the look on an architects face when you tell them you need something like 1-ton of A/C (1 ton = 12,000 Btu) for every 14 square feet of space in a room. They tend to fidget a bit, and say they'll run some calculations for you, since you must be completely out of your mind. It's usually at that point I start talking about how many 225-amp 3-phase distribution panels I'm going to need. The smarter ones start to get it at that point. :-)

    Don't get me wrong, it is an issue, and not just during the summer. I think the thing that bugs me most is that here in the middle of winter, it's like 60 deg./F or less outside, and we have to run A/C in our lab. Seems to me we should design these buildings to vent in cool filtered air from outside.

    Temkin

  • 2. Most servers are redundant ones, hot spares, etc.

    What are you smoking? Can I have some of your server budget?

    Temkin

  • Now if we could just get some of those California web hosting companies to adopt these en-mass.... I could turn on the lights in my office again... :-)

    Temkin

  • Maybe some enterprising PC OEM could make a nifty PC like the Mac Cube with no fan. I'm tired of staying up at night listening to the rush of air coming out the back of my Linux box. I'd spring for a Crusoe workstation that could just convect.
  • I don't think it's intended that way.

    Having this extra layer, allows them to adopt a radically different hardware-architecture for their next-gen product, without having to worry about breaking compatibility, since that layer takes care of that.

    You can try to do that in hardware, but you'd end up with the systems amd and intel are using (breaking x86 ops up in smaller ones), and that costs you a significant amount of die space.

    I suppose it would be possible to make something native for the crusoe. Problem is it would probably be compatible with this version only!

    Don't focus on the situation as it is now. Try to look at it as a "process", an evolution.

    I think with the setup they currently have, they'll be able to design new chips that remain x86 compatible and make improvement, at a faster rate than their competition. The people that design the software can ask the hardware guys for specific features that would make emulation faster, and the software guys can make very specific optimizations to that specific fixed hardware - they don't have to worry about the common-denominator problem (what happens with the speed on amd's if i optimize for intel and vice-versa)

    I think it definately has a future. Some people might think they're off to a slow start (i'm definately not one of these people - having an emulator perform this good is not an easy feat i believe) but i think they will have the possibility to include improvements and innovations faster than the traditional chipmakers. (unlike for instance intel that has to design a core and live with it for over 5 years).

    At least that's what i think...

  • For larger companies, and people that really need a lot of power, I'd put that list as:

    1. Preformance
    2. Expandability
    3. Stability/Quality
    4. Price
    5. Size

    If you need a power house, then performance is very important aspect. Expandability is also important, as if you're investing much you want to make sure it can do what you want it to do over the next few years. Stability is always a toss around, is it the software? Substandard hardware? Prehaps quality would be a good qualifier as well. Price doesn't matter as much, and while physical size is important in certain situations, usually if you need something that important, you'll make room for it. Not to mention, expandability partly reflects size.
  • Does anyone know if it's even possible to bypass the emulation at all, and write native machine code?

    Of course it is. How do you think CMS was written?

  • Have a look at the DEC DNARD cluster at http://www.cs.utah.edu/~danderse/dnard/setup/

    I would love to have one of these boxes but it seems intel killed them pretty quickly.

  • Slashdot's corporate parent--are they going to do this? If there is a Transmeta CPU that will fit in a Pentium socket and work like a Pentium then VA has time, but if this requires a special MoBo it looks like VA is behind. I guess if this requires any real effort they will just partner with one of these companies as a VAR. They are certainly not in a position to acquire anything these days.

  • Re:Just in time for California (Score:3)

    by rgmoore ( 133276 ) <glandauer@charter.net> on Monday January 22, 2001 @03:16PM (#490084) Homepage

    This is actually a pretty serious problem; it turns out that server farms are a major part of the increased power consumption that's driving the electrical crunch. The worst part is that computer power consumption is only the tip of the iceberg. There are so many servers packed into such a small space that their air conditioning costs are actually huge; IIRC they use more electricity for AC than to run the computers. If you can cut the power consumption of the computer it pays back double or more because you can cut your AC costs, too, and probably capital costs for backup power. Back of the envelope calculations suggest that switching to low power consumption chips could wind up saving money overall over a period of a year or two just on decreased electrical usage.

  • I think it was on tramnsmeta's homepage I read that a HP-48 running an emulator program of it's CPU could execute programs faster than if those programs were ran natively, due to run-time optimization ... ie the compiler can only guess how the execution path will be going, while the CPU can know (or at least guess better)
  • Okay, poor choice of words on my part. Obviously, I know that it is not currently possible. However, unless I am mistaken, one of the objectives of the Crusoe is to allow code-morphing firmware patches or upgrades. If that's possible, then it should be possible to roll your own. If that's possible, then it should be possible to write a bridge to their ISA. Unless their ISA just doesn't really map to the ISAs that we're familiar with. Maybe it just doesn't make sense to write natively to it. I don't know, because I don't know what their native ISA looks like. Maybe someone else out there does.

    Oh, and by the way, fuck you, too.

  • Since the response I responded to got moderated down, it looks like I'm bashing myself. Let me assure you that this is not the case. Browse at -1.

    Sorry for the rambing....

  • Oh -- and as a side effect, it might allow us to figure out how to emulate a PowerPC, or an UltraSPARC, or a MIPS, or even a Z80, if you wanted.

    Of course, this ignores all the supporting hardware around it, but I seem to be ignoring reality left-and-right today, anyway.

  • I'm not an expert in convection, but it seems that trying to make a fanless rack-mount server would be difficult. Most rackmount cases vent either from front to back or side to side because there's another big heater right on top, and below. So pumping more heat to the next unit doesn't really help, unless you're only really concerned about the machines on the bottom of your rack. And I don't think it's possible for the convection that they use in the fanless Macs to work in that way. But then again, I don't really understand how sailboats sail into the wind.

    Which is not to say that they shouldn't make rackmount machines. I believe that they should, and maybe if MacOS X takes off in the server arena, as it should, then they will.

  • Seems to me that it'd be pretty cool to write to the native Crusoe architecture rather than going through the x86 ``emulation''. Does anyone know if it's even possible to bypass the emulation at all, and write native machine code? Regardless of how good the ``emulation'' is, it seems like it'd be faster and more efficient to optimize for the real hardware. And it ought to still keep it's low-power, low-heat features.

    NetBSD awaits...

  • Put 16 of those in a rack, and you've got yourself a server farm. Granted, the G3 isn't really designed to be a server chip, but it's a whole lot better for the task than x86. They run nice and cool, too.
  • What's preventing them from plugging them into a mid tower as well? Performance. What's the point of overclocking a CPU that basically underclocks itself so as to draw low power and produce low heat?

    I'm not cutting down the Crusoe here. I think it is quite an impressive chip and would like a laptop with a Crusoe inside. But I wouldn't get it for my desktop and then try and overclock it.

  • Oh yes! I want one of these.... in a black case.
  • Because Red Hat or Turbolinux won't hold your hand while you install PowerPC Linux.

    Because Oracle isn't available for PowerPC Linux. (OK, so I didn't check, but I'm guessing it isn't.)

    etc.

    The big-business world is extremely conservative.
  • One of the most effective ways to move heat in a fanless system is with a chimney. You used to be able to get one for the Mac Plus and SE type cases (or make your own). For the server rack, you could have a MacChimneyConduit (tm) running along the back of the rack stack. Heat would vent up the chimney and cooler air would be drawn through strategicaly placed vents. You'd be amazed how well this works. I had a Mac Plus that would over heat and reset. I made a chimney out of cardboard and put it on top like a hat which solved the heat problem.

    If any one can figure out how to vent a fanless case, it's Apple.

    This would make for an impressive server room, silent!

    Cheers

  • I have a sneaking suspicion that this is what was intended all along. I've been asking myself all along why Mr. Torvolds, who could undoubtedly have begun a career just about anywhere he pleased, would go with Transmeta if all they were going to be was a small-time competition for portable devices.
  • You're saying that native code is not always faster tha compiled? I thought this was a law of nature!!!!!!
    ;)

    __________________

  • Irony [dictionary.com]. Do you know what the word means? Good! Then let's play a game!

    My previous post contains three separate indications that the comment is ironic. A US$5 Paypal payment will go to the first Slashdotter to describe each one. Describe all three before anybody else describes any, and I'll kick in an extra $5, for a total prize of $20. Myself to be sole judge, etc. etc.

    __________________

  • Hrm. Low power consumption is nice, but part of me wonders how much of this is actual concern for such things, and how much of it is trying to cash in on the Open Source community's obsession with Everything Linus (tm).

    I mean, hey, if so, more power to them. Not a bad strategy. ;) But I think I'll believe it when 1) I see it and 2) I see it working.

    On the other hand, being able to emulate would mean you'd never have to buy different hardware for running other chipets...maybe they're on to something.
  • If you read their original filing with the SEC, Transmeta spoke of the idea that their technology would apply the same level of scalabilty of Linux to processor design. There have been several instances in which they referred to Linus' involvement as part of their scalability plans.

  • I've heard rumours that currently Crusoe runs Linux as just another x86 OS - using its hardware translation mechanisms. Now, that's a nifty technique, but wouldn't it be quicker if Linux ran using generic Crusoe instructions? I think that would be a bit (10%) quicker, and also allocate some system resources that were previously occupied with translations. Noone will mind if it won't be x86 anymore

  • Thing is that apple would not want to use Linux on these machines.

    The Mac OS gets egg all over its face.

    Of course Apple might be able to do this with Mac OS X just on the horizon....
  • Actually back in 1997, Microsoft did release version 3.5 of WindowsNT for the PowerPC. Motorola, which at the time was also a MacOS licencee, shiped a PowerPC computer that ran NT. A good article describing the details behind this change is located in Windows2000 magazine [win2000mag.com]. The bigger question, of course, is why anyone would want to run a server operating system other than some variant of Unix?
  • Might wanna use the fish [altavista.com] unless you know german.
  • Look at it this way: Would you rather have a dozen Crusoe boxes humming away in your server closet, or one P3 workstation doing the same amount of work. Their low power/low heat argument is moot because in order to obtain the kinds of processing power you'd need to run a server, you'd need to have several times the number of Crusoe's as you would need Alphas or P3's. Not only would the power consumption/heat generated be similar, but I would imagine a 100 Crusoe machine would take quite a bit more space than an 8 way or 16 way P3 machine.
  • This news is already out of date and I submitted it over a week ago. Slashdot is rapidly descending into the depths of suckagehell.
  • When the server is low power (I mean porcessing, not AC), than you need more servers to handle the load. The problem I see with this is that they will need to run twice as many servers now. That will probably bring it back up to the power (AC) of an Athlon. Nothing is free (not even software when you really look at it). They seem to be just looking around for a market to jam this thing into.

    -Spackler
  • There are some nice G3 and G4 clusters out there, they are just not very cost-effective. Here's a howto [ameslab.gov] on building a G4 cluster from a national lab, and there are some prebuilt systems like those running Black Lab Linux [terrasoftsolutions.com] they were showing at MacWorld New York last summer.
  • The properties important in mobile environment (low power consumption => low heat) are also important in a server farm where those things are magnified.

    regards

  • Why this is a Cool idea ... (Score:3)

    by WillSeattle ( 239206 ) on Monday January 22, 2001 @03:50PM (#490111) Homepage
    A number of reasons come to mind:

    1. California has too few power plants - anything to save energy is good.

    2. Most servers are redundant ones, hot spares, etc. These would be great with the low-power consumption, especially as the disk access is very low on such boxen until there is a demand spike.

    3. Most servers do a lot of the same things over and over and over - this may turn out to be where the highest return on investment (ROI) is for code morphing chips. That plus their ability to ramp up on demand.

    4. Think about the /. effect - if we all hit these servers asking for the same thing, the code morphing chip will get very good on the third, fourth, fifth request. So in actual practice, a Crusoe server would handle /. effect very well, not to mention many brute force attacks, as it optimizes itself for redundancy. Extra added bonus for the superbowl effect, for those remaining .com advertisers!

    5. Especially useful when reading Jon Katz articles. Lots of excess verbiage, repetition, and waste of space - maybe the Crusoe chip could just go to sleep and save power whenever someone made a mistake and tried to read one of those!

  • Most peoples TV's are on a couple of hours a day, and most microwaves are on a few minutes a day.

    Compare this to computers and monitors left on 24 hours at work.

  • Nop, it makes sense (Score:4)

    by The Fanfan ( 264958 ) on Monday January 22, 2001 @03:55PM (#490114)

    It all depends on the application, but most servers "require" :

    1 - small code (always the same app running)
    2 - mucho data, not so mucho processing.
    3 - mucho I/O

    For a good design server, a kick-ass bus and lots of CPUs is way more important than having the latest 5.3 zillion Hz processor. The speed and width of the bus/switch fabric sets the upper limit on how much data you can move around. Having a lot of processors is good so you can max out your bandwidth, some processors using the bus while others stall on I/O or locks. In a data server, a CPU spends most of its time doing strictly nothing but wait for the rest of the world.

    There are some applications that would prove me wrong : web server with very complex / sophisticated / bloated dynamic pages may be, scientific computing definitely. But the above is more or less the rule of thumb when looking at a data server.

    My $0.02
  • When I first read the press release on this chip, I thought, "Mobile, hell -- wait till those guys at Kryotech get thier hands on one." The real barrier to speed is how to keep the IC from turning to slag. If it's cooler to start with, make it run as hot as an Intel, and see how fast it'll go.
  • I have been thinking of using a Crusoe-based server in a specialized application. My list would be: 1. Survives high ionizing radiation 2. Redundancy Multiple CPU boards, with most of them off until the active board fails, next in line automatically turns on to replace the failure. 3. Stability 4. Power 5. Speed 6. Size 7. Cost (actually cost doesn't matter up to $1-2M) Gregory Nemitz Orbital Development gnemitz@orbdev.com http://www.orbdev.com
  • Well it's not surprising in retrospect! Nothing ever is ;)
  • Yeah, tell it brother. Or The Skull Beneath The Skin. Those early albums rocked. The new stuff blows so hard.

    But at least they never did a country song.

  • I don't know about this, I guess it could just be me, but I dont think I could ever see a Crusoe inside a server. Now if they were doing some massively parallel stuff like 8 of them all in one box it might be feasible, but the whole reasoning behind it seems a bit shaky.If you ask me, the whole chain that I run through when buying a server is...

    1. Price
    2. Stability
    3. Power
    4. Expandability
    5. Size

    Of course for a real company, (not a small one like mine) the list may be juggled around a bit with Price landing up closer to the bottom.

    Still this is an interesting proposition, I wonder if Sun or anyone else will catch on and start using it in their value line of servers? All I know is that those 1U boxes they were showing last week were pretty damn sleek, and had quite a lot of power for the under a grand price tag.

  • The Crusoe will mean something to me when I can buy one on pricewatch w/mobo and all and see for myself what all it can do.

    We can read about it and hear about it all we want, but until we can get one in our hands (that isn't in a lapotp) we'll never know :-/

    Those folks in California could probably use a few ;-)

Slashdot Top Deals

It's a naive, domestic operating system without any breeding, but I think you'll be amused by its presumption.

Close