Slashdot Mirror
Crusoe As Server CPU
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."
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
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.
If you're not part of the solution, you're part of the precipitate.
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.
-I just work here... how am I supposed to know?
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.
> 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?
My God, it's Full of Source!
OUTSIDE_IP=$(dig +short my.ip @outsideip.net)
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 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--
Program Intellivision!
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--
Program Intellivision!
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.
--- I do not moderate.
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.
--- I do not moderate.
RocketLogix is now RLX Technologies. Don't ask. It's a stupid patent thing.
/. reader.
An RLX Employee, and loyal
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.
.. time to get some RC5 crunching action happening in those spare cycles.
Indeed
--
Delphis
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.
--
Delphis
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.
Baker's Law: Misery no longer loves company. Nowadays it insists on it
http://www.sigsegv.cx/
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.
---
As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
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
Remember Amalek.
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
Remember Amalek.
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.
If it's for-profit but free, you're not the customer -- you're the product (e.g., the Slashdot Beta's "audience").
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:
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.
Slashdot - News for Herds. Stuff that Splatters.
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.
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.
I'm old enough to remember when discussions on Slashdot were well informed.
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.
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.
Trees can't go dancing
So do them a big favor
Pretend dancing stinks!
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.)
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.
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.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Friends don't let friends enable ecmascript.
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
This is SO educational! -- Kintaro Oe
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.
I am !amused.
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.
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.
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.
Only the State obtains its revenue by coercion. - Murray Rothbard
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.
For all intensive purposes, "whom" is no longer a word. That begs the question, "who cares"?
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)
Oh, and by the way, fuck you, too.
Fuck 'im up, Tim! His views are invalid! -Pirate Corp$
Sorry for the rambing....
Fuck 'im up, Tim! His views are invalid! -Pirate Corp$
Of course, this ignores all the supporting hardware around it, but I seem to be ignoring reality left-and-right today, anyway.
Fuck 'im up, Tim! His views are invalid! -Pirate Corp$
NetBSD awaits...
Fuck 'im up, Tim! His views are invalid! -Pirate Corp$
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.
WARNING: there is a trojan on your
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.
;)
__________________
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).
;) But I think I'll believe it when 1) I see it and 2) I see it working.
I mean, hey, if so, more power to them. Not a bad strategy.
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.
'the Internet is right.'
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
I couldn't resist...
Might wanna use the fish unless you know german.
--Dave
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.
-atrowe: Card-carrying Mensa member. I have no toleranse for stupidity.
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
The properties important in mobile environment (low power consumption => low heat) are also important in a server farm where those things are magnified.
regards
A number of reasons come to mind:
/. 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!
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
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!
--- Will in Seattle - What are you doing to fight the War?
Static web content only?
--
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.
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
But at least they never did a country song.
I didn't pay for my operating system either
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.
"On weekends, to let off steam, I participate in full-contact origami."
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