Slashdot Mirror
Alpha 21264 And Athlon 850 Review
Arg! writes: "Hi. There's a comparison review of an Alpha DS10 with a 466 MHz chip running AlphaLinux up at this link on Ace's Hardware. The system is compared against an 850 MHz Athlon box (also running Linux) and there are a lot of different benchmarks also showing some memory comparisons with some other PC chips, like the Celerons, as well as some Sun Ultra benchmarks. The config tested was $5500, but a base DS10 is supposed to be around $3500 ... maybe not too bad for a nice 64-bit box. ;)"
An excellent point. Sort of like 286/386 days with Harris & AMD outdoing Intel on their own masks.
ds-10l
40 of those boxes in a single 19" rack makes for a pretty nice cluster.
The article states that gcc was designed with the x86 architecture in mind, and no optimizations are available for RISC chips. This is exactly the opposite to the way the compiler has evolved - gcc was designed with RISC optimizations in mind, and not too many x86-specific features. That is why egcc and pgcc came into being - to add pentium-specific optimizations (egcc and gcc merged, and IIRC include some of the stuff from pgcc).
I wonder if the reason the benchmarks did not compile right was that the compiler itself was not built for the Alpha, or if the Alpha optimizations are different from the other RISC chips because of the 64-bitness of the architecture. Anyone with gcc on Tru64 tried a comparison between the compilers? It is hard to believe that gcc cannot take advantage of the FP registers...
The 21264 won't ever see 1.6GHz, or even 1GHz. The now shipping 21264A (EV6.7) and upcoming 21264B (EV6.8) will see those numbers, though. The EV6.8 will be 0.18u with copper interconnects, and should arrive before the end of the year. Of couse, the EV6 was supposed to have scaled to 1GHz by last year, and we're just now at 733MHz. Now that Compaq has finally settled most of the confusion caused by the DEC buyout, things should get back on track very quickly.
And to those who think the Alpha is a dead architecture, you've got another thing coming. Sure, its more expensive than an Athlon system, but it's not meant to compete in that market. Plus, no PC can offer the sheer memory throughput or clustering capabilities that are offered by VMS and Tru64 Unix on Alpha (and no, beowulf doesn't even come close).
--
http://gammatron.weblogger.com
If I remember properly, Compaq was giving out free
copies of the DEC C Compiler for Linux a while back,
I don't know if they still are. I have the set and
they scream on my 533 21164a.
For most of the pci-based alphas, most of the
major manufacturers are supported in XFree86 4.0,
though there are a few buggy drivers, (*cough* mga
*cough*) this has nothing to do with whether the
machine will accept it or not. the boards run
whatever 'vga bios' and then run their own firmware
underneath it. (and for the guy three posts down,
alphas do NOT run OpenFirmware, they run SRM, ARC,
or AlphaBios)
-c
besides competition is good - since when have you, as a /. reader, been against competition ?
i'm not against competition, but in a competition, there has to be winners and losers. sad fact is, MIPS, Alpha, SPARC etc etc are losing, or have already lost, to the x86 juggernaut. i don't care if an Athlon is a series of ugly x86 kludges piled upon a RISC core...the Athlon system cost $2,000, and Alpha system cost $3,500, and there wasn't $1500 worth of extra performance between the two systems.
As sad as it is, the Alpha loses.
I recall from many years ago that the byte benchmark sucked when you failed to compile the benchmark using proper byte alignment. This was exposed when gcc suffered compared to ms compiler on windows I believe. The deal is, the cache works twice as hard to feed the cpu if words are not aligned on cache line boundaries, wich might be 64 or 128 bytes or something. The gcc compiler did much better when alignment was fixed. This may be more of a problem since the floating point numbers may actually be double precision by default (?) I wonder if this benchmark aligned properly for gcc (or for the compaq compiler for that matter).
The problem is that artifical benchmarks are dumb. The only thing that really matters is application performance. If the applications you use run faster on one CPU than another, voila, there you have your benchmark. Of course, good artifical benchmarks are possible if they emulate application code (like the 3D 2000 max or whatever benchmark that uses actual game engine pieces to test performance.) Cross platform testing is a bit hard. You'd have to test app that were equally optimized for both platforms. It shouldn't be too hard, however, with good optimizing compiles. Take GIMP and compile it using the Intel x86 compiler (even more optimizing than the Microsoft compiler) and test GIMP compiled with the Compaq Alpha compiler.
A deep unwavering belief is a sure sign you're missing something...
Alphas are far from dead. Use the right compiler (Compaq - and it is Free) and a 21264/750/8MB and the Athlon gets pasted to the road under the performance of the Alpha. (can you say 'Score of 74 in SpecFP95'?)
Oh and by the way, you can buy a dual Alpha. You can NOT buy a dual Athlon.
Not enough for you? Wait a few months and the .18 micron chips Alpha chips will be out running @ 1.2, 1.6 GHZ - umm thats GIGAHERTZ.
If you are serious about your need for fast float you will pay for it. And it is paying me back in spades.
Ever have a buggy AMD chip? They are not fun. I am in the process of replacing dozens of 166s and 200s which all have the paged memory bug above 32MB. (Replacing with Intel Pentium MMX 233s and clocking them where I can - MB dependant.)
Need to move some data around? The alpha 21264 will do it heaps faster than the Athlon. 64bit vs 32 bit. Need a SuperComputer? #5 on the orb is an Alpha/Linux Cluster and it fuckin rocks. Cya, Dan
Adults are obsolete children. - Dr. Seuss
Use the right compiler (Compaq - and it is Free) and a 21264/750/8MB and the Athlon gets pasted to the road under the performance of the Alpha.
Well its not that surprising...8MB of L2 cache?!?! how much is that going to cost?
Oh and by the way, you can buy a dual Alpha. You can NOT buy a dual Athlon.
maybe not this month...the Athlon itself is SMP capable, and the next generation AMD chipset will support SMP.
there's no doubt that a 21264/750/8MB will be faster than an Athlon. It just gonna cost a shitload more, and i don't believe that it offers a shitload worth of extra performance. the intense competition in the x86 market is driving along the kludgy x86 architecture to higher levels of performance at an ever increasing rate, and at cheaper and cheaper prices. The Alpha (and other traditional RISC chips) are going to have an even harder time than they are now trying to compete, simply because of their high cost. MIPS is pretty much out of the game already.
Trying to categorize RNA or DNA or protein sequences using suffix arrays with dynamic programming, including sometimes large datasets.
A substantial portion of the gene sequencing being done now is on the Alpha. This is the sort of thing that the Alpha really excels at.
--GnrcMan--
There's a post at Kyles HardOCP regarding the 'demise' of the Athlon, due to the fact that they're coming out with the socket A processor. What's the general consensus?
I'm sorry. What I meant to say was 'please excuse me.'
what came out of my mouth was 'Move or I'll kill you!'
I disagree with some people when they say that Alpha is a dying platform. In reality, it is far from dead. Aside from the hideously expensive POWER3 CPU, the Alpha is the fastest CPU out there. With the release of the EV6.7 and EV6.8, they may again capture the fastest proc known to man crown again. A 1 GHz Alpha is not that far off, Compaq demoed air cooled 1GHz Alphas a few months ago. In fact, Alpha may be the only competition left for Merced (I refuse to use that Power Ranger-esque name Itanium!) in the mid to upper range market. There was an article a while ago (on Tom's Hardware I think) cogigating on whether or not Alpha would still be faster than Merced. They cited various points about how plain RISC may beat out VLIW if implemented properly (like in the Alpha) and how the DEC guys have quite a leg up in clock speed (at least at that time.) Judging by when Merced will be out the 1GHz + Alphas should be out, and should provide quite a strong competition since
A)Alphas could just be faster, and
B) Alphas have much more market penetration and a larger support network built up. With Intel's power, that will change, but Alpha will have quite a head start on Intel.
Then there is the fact that Alpha is aimed at a much broader spectrum, and Intel might just not be able to take the market with Itanium.
A deep unwavering belief is a sure sign you're missing something...
The compiler situation presented by the article hilights a key advantage that Compaq has over Itanium. The compiler needed to take advantage of Alpha is already freely available, while (if intel keeps with it's current practice of charging for it's compiler) one would have to pony up quite a bit for Intel's compiler. The compiler is critical because Itanium (based on VLIW, which places all code ordering work on the compiler) is heavily dependant on a good compiler for any semblance of performance. Sure GCC compiles Itanium code, but if it can barely optimize x86, do you really think it has any hope of producing good Itanium code? This might not be important on Windows, but as OSs like Linux and BeOS, which depend on the freely available gcc to compile many of the applications, the availibilty of a good free compiler is very important.
A deep unwavering belief is a sure sign you're missing something...
the right compiler is sold by compaq(/digital)
Don't be mean or my friend Oog will smash your head
You can get a $2999 Alpha by visiting http://www.alpha-processor.com and signing up for the development platform.
This is a 600MHz/2MB cache Alpha with AGP. We've been running banner ads on Slashdot and Freshmeat for a few weeks now.
disclosure: I work for API
What's my Karma Mr. Burns? "Excellent"
Almost any card that is supported in XFree will work. The major exception is the Nvidia cards. They make BIOS calls that are not supported by the x86 BIOS emulator.
The API UP1000 is the only Alpha currently availabe with AGP.
I work for API
What's my Karma Mr. Burns? "Excellent"
Just one thing to consider, though, is the incremental cost of increasing processor speed. Much of that price is in the cost of the MB, RAM, and other peripherals. I'd wager the 21264 MB they used can support much higher clock-speed processors. So, to increase that baby from 466 to 733 or so may only be a price difference of a few hundred dollars. Now the alpha will really outperform the Athlon. Too bad you can't get the Athlon in higher speeds (yet...)
make world, not war
I'm pretty psyched. I just picked up an Alpha 21164LX Motherboard + 533MHz 21164 CPU for $200 2 weeks ago. It's a really cool system. I just got MILO up this morning, and I hope to have linux (Either RedHat or Debian) on it soon. My first foray with the Alpha!!!
make world, not war
The config tested was $5500, but a base DS10 is supposed to be around $3500 ... maybe not too bad for a nice 64-bit box. ;)"
Uh, $3500 is too much for a basic box
For about $2500 you can have SUN Ultra5/366Mhz UltrasparcIIi/128MB ram/8GB ide-7200rpm disk with a 17 inch monitor.
The same combo will cost you only $1300 if you are a student.
The advantage of SUN's is that you can have Solaris on it (which I really like) and it has better application support than Linux on non-intel platforms (Linux on non-x86 platforms lacks most of the commercial/binary-only software you can have on intel)
The only thing that I see as a big disadvantage about SUN workstations is that the SUN compiler still has to be purchased (for like $3000), otherwise you are stuck with gcc again which just like in Alphas' case does not optimize very well.
They should have used pgcc, egcc with better flags, or VC++. What flags did they use?
. html
:-)
/usr/lib/gcc-lib/i586-mandrake-linux/2.95.2/specs gcc version 2.95.2 19991024 (release)
- -----:------------
The comparison is totally bogus. I like Alphas, but price/performance is not there.
bytemark for unix:
http://www.math.vanderbilt.edu/~mayer/linux/bmark
Test system
Athlon 700, Asus K7M, 384 MB PC133,
Cheetah ST318203LW
Not overclocked
flags:
-s -static -O3 -fomit-frame-pointer -Wall -mpentiumpro -march=pentiu mpro -malign-functions=4 -funroll-loops -fexpensive-optimizations -malign-double -fschedule-insns2 -mwide-multiply
Reading specs from
(cut and paste this table to a fixed font editor/term program, sorry but pre doesn't seem to work)
You can see that these scores are better. Dunno about the neural net weirdness - NN blows up and makes the FP index way off. I would expect a KX133 Athlon 850 to outperform my 700. And I'm not using any of the high speed math libraries which would help.
BYTEmark* Native Mode Benchmark ver. 2 (10/95)
Index-split by Andrew D. Balsa (11/97)
Linux/Unix* port by Uwe F. Mayer (12/96,11/97)
TEST : Iterations/sec. : Old Index : New Index
: : Pentium 90* : AMD K6/233*
--------------------:------------------:-------
NUMERIC SORT : 528.24 : 13.55 : 4.45
STRING SORT : 51.58 : 23.05 : 3.57
BITFIELD : 1.3486e+08 : 23.13 : 4.83
FP EMULATION : 50.599 : 24.28 : 5.60
FOURIER : 8949.6 : 10.18 : 5.72
ASSIGNMENT : 5.0644 : 19.27 : 5.00
IDEA : 1059.3 : 16.20 : 4.81
HUFFMAN : 410.32 : 11.38 : 3.63
NEURAL NET : 15241 : 24483.02 : 10298.45
LU DECOMPOSITION : 354.4 : 18.36 : 13.26
==========================ORIGINAL BYTEMARK RESULTS==========================
INTEGER INDEX : 18.045
FLOATING-POINT INDEX: 166.002
Baseline (MSDOS*) : Pentium* 90, 256 KB L2-cache, Watcom* compiler 10.0
==============================LINUX DATA BELOW===============================
C compiler : gcc version 2.95.2 19991024 (release)
libc : unknown version
MEMORY INDEX : 4.417
INTEGER INDEX : 4.569
FLOATING-POINT INDEX: 92.072
Baseline (LINUX) : AMD K6/233*, 512 KB L2-cache, gcc 2.7.2.3, libc-5.4.38
* Trademarks are property of their respective holder.
Anyone have a KX133 Athlon 850? Please post your scores.
-pitmaster
Can you name an editor like emacs which was there before emacs? Stefan
The DS10 is not the smallest Alpha you can get. There is also a DS10L which is a 1U machine. You can also get this preloaded with Linux.
The Alpha is not limited to 2-way SMP. The Alpha can also be put into much larger SMP configurations. The AlphaServer ES40 is 4-way, the GS60 is 8-way, and the GS140 can have up to 14 Alpha processors in it. There is even a new SC that can have 64-512 processors! These are SMP machines, not Beowulf clusters. The Athlon is not even 2-way capable yet.
There are numerous supercomputer Beowulf clusters running Alphas. There are many graphics rendering companies running clusters of Alphas to render the graphics for movies.
The Alpha is far from dead. The comparison was a past-generation 21264 EV6 466MHz vs a new Athlon. The newest Alphas are the 21264 EV67 which perform about 50% better than the EV6. They also have higher speeds up to 733MHz. The Alpha is also slated to replace the old MIPS processors in the Tandem systems. Tandem systems run about 90%+ of the world's financial systems.
BTW, the Athlon has features that were licensed from the Alpha, such as the 200MHz frontside bus.
The Alpha is expensive, but it is worth it on the high end. It is not designed to be a home system, although I would like to have one!
Interesting... They compare the lowest end 21264 to the highest end K7. Looks real fair to me! NOT! ;-)
It seems to me that a multi-processor athalon would be the way to go.
:)
...and where were you planning to buy that?
<i>The reality of precompiled binaries means that there is a real benefit in sticking with a x86 compatible architecture.</i>
Not everyone runs debian/redhat/others with precompiles.
Furthermore, some apps really benefit from being compiled at the user's preferences, so that one can optimize for that specific machine and to specific preferences.
<i>I guess for more specialized applications where either only a small set of programs need be run or custom programs need be run (i.e. scientific applications) the alpha would be ideal. </i>
Could you imagine a beowulf cluster of these?
(sorry... couldn't help myself
Many cheap Multias come with a soldered 166 MHz CPU, no floppy drive, and no hard drive. The more expensive ones (~$25 extra) have a socketed 166 or 233 MHz CPU, a floppy drive, and sometimes even a small hard drive (400 or 500MB).
These Multias run Alpha Linux just fine. They're around the speed of a Pentium 100 at integer computations, and a Pentium 200 at floating point.
You also might want to look at the 21164A, which is quite cheap these days. You can get a 533 MHz CPU, motherboard, and perhaps even a DIMM for around $500. This will be about the same speed (or a little faster) than a 450 MHz Pentium III at integer ops.
I have a 21164 500Mhz box with 256MB of memory, total cost was around $1k. This was when memory was expensive, too...
Not a bad system at all. Nowhere near as fast as the 21264's, but much, much, cheaper. It would have been pretty usable with less memory, too...
My blog: http://www.seebs.net/log/ --- My iPhone/iPad app: http://www.seebs.net/seebsfrac/
As far as I know, there is still no motherboard to fully support AMD's 200 MHz bus...if I am correct, I think its going to be amazing how fast the athlon will fly when it does have the full motherboard support...
"spare the lachrymosity when the fulminations have inveighed"
"spare the lachrymosity when the fulminations have inveighed"
-madd
The MHz's must be smaller on an Athlon than on an Alpha. This is similar to the US gallon vs the UK gallon problem. It's time we switch to metric units when reporting computer speeds.
That the DEC compilers for AlphaLinux were that good. Wow. If only they would merge their optimizations into GCC... Incidentally, I just noticed that DEC has available a new version of em86 that should work on the 2.2 kernels, and that they also have been kind enough to make a nice RPM of netscape for DUNIX with the needed DUNIX libraries that Linux needs to run it.
For every problem, there is at least one solution that is simple, neat, and wrong.
The article said that you need a special graphics card for an alpha. Can you use all your other pci cards on an alpha?
I know very little about gcc, but I do know that the PPC also has a large number of registers compared to x86 chips. Does anyone know if ppclinux is at a similar disadvantage?
(I hope this isn't too off topic...)
I would like to see a Alpha put up against intel processors, like the p3 1 ghz. It would be an interesting battle, especially because in my opinon, Alpha's are a whole ton better than p3's. As someone above commented, the Alpha is doing to be *direct* competition against the intel merced, especially seeing as how as far as i know, the merced is going to need completely new software/operating systems to run, because of its being native 64 bit. The alpha already has software, operating systems, and had already demoed at 1 ghz, which intel does nto believe to reach until 3rd or 4th quarter 2001. Could it be that intel will at last loose it's foothold in the processor market, with AMD taking away market share in the main consumer market, and compaq/dec working on the workstation market......
Don't get me wrong, I very much like Alpha's. I have three Multias, one each running Linux RH5.2, OpenBSD and Compaq Tru64 (hobbyist).
But take a look at the 21264 datasheet: 107W [sic] maximum power/heat at 633 MHz (2.35V & 46Amps). This is HOT, but it's also 0.35 um process. If they shrink it to the current 0.18 um, DEC could bring it down to ~20W @ 1.4V. Very competitive.
But will Compaq make this investment?
I'd like to see a DS10 versus an Athlon system measured performing tasks that I actually need to do quickly. These include:
There might be some things that I've missed. Why don't you folks chime in with what kind of tasks really matter to you. Basically any time you end up _waiting_ on the computer, or anything that would be of higher value to you if it could use more CPU cycles.
If I did scientific computing and simulation then of course I would have included that here. Hm -- in fact, I might be doing something like that on my next computer, so include something like:
If some of the people who have access to both Alphas and AMDs could do some benchmarks which helped me predict the performance of these kinds of tasks I would much appreciate it. (Hint: hard disk latency might be a big issue.)
Zooko
1. It keeps you honest. Alpha Linux by default core-dumps on divide-by-zero error, where Intel Linux and SGI Irix silently return infinity. Also, Alpha seems much more likely to dump core on memory access error. Running the heterogenous environment that we do helps us find those errors more quickly. All of you that write perfect code the first time need not consider this reason.
2. Alpha is the first of the 64 bit systems. When trying out new ideas for animation tools (which is what we build at my company) it is useful to try them on the 64-bit machine, to see what performance gains there are due to the 64 bit-ness. All of our workstations will be 64-bit machines someday; it's useful to have a prototype today.
One interesting note is that (at least with gcc) a 'long' on an Alpha is 64 bits; while an 'int' is still 32 bits. This revealed not a few bugs (or, perhaps, future anachronisms) in our code.
So, long live heterogenaity!
thad
I love Mondays. On a Monday, anything is possible.
Cool! Where do I find the -$3500 deal? ;-)
;-)
If you go here and do a search in the bottom frame, for "alpha", you'll see some of the $3000 models listed as being available!
I still want to actually build my own Alpha... as the Penguin-Ferrari article points out, we need diversity, and anyway I like messing with different stuff. Anybody know of more recent articles, or have personal experiences to offer?
I bought a refurbished Alpha Digital Alpha Workstation 433au (21164 version, either EV5 or EV56) from egghead.com for US$1,199 a couple of weeks ago.   It just came in last week and it's up and running Red Hat 6.2 for alpha, kernel 2.2.14-6.0.   The box (without monitor and keyboard) came with a 433Mhz alpha CPU, 128MB RAM, 2MB cache, an Adaptec 2940 SCSI controller, 2.1GB Seagate SCSI drive, 12X CDROM, Intergraph video card (and something with Cirrus Logic video too), built-in EtherWorks ethernet, and built-in SB-compatible sound.   It also has 2 64-bit slots and 2, shared ISA/PCI slots.   It's one of the older boxes (circa '96-'97), but it's processing seti@home work units (non-optimized) at around the same speed as a PIII 450.   One of the main reasons why I bought it was because it is upgradeable to a 600Mhz 21164 processor (although I am finding that the CPU alone is exorbitant and I would do better buying a mobo w/CPU and memory!).
During my difficult search for any alpha info, including parts (I am realizing how little is written about alphas as compared to x86s), I stumbled upon this site that sells DEC Alpha hardware (and others like Sun), and they have a link here called "Build Your Own Alpha System", where they list the various parts you can purchase separately to put a system together.   There are a few other places out there too, but I don't have the links handy.
I would say go for it - I've seen prices for 500-600MHz alpha mobos, w/64MB RAM for like $1500.
All in all, this is my first non-intel (or non-intel compatible) machine and it's been a really decent learning experience dealing with the Penguin on the 'ole Ferrari!
-- Win2k: "It's not so much that it's only 65,000 bugs, it's just that they stopped at 65,535 to prevent an overflow."
A recent camparison of many platforms (including various Alpha and two K7's) with benchmarks related to computational chemistry is here. http://www.dl.ac.uk/CFS/benchmarks /compchem.html The K7's hold up well in a broader range of benchmarks.
your gravity fails and negativity don't pull you through
I recently bought a 600MHz 21164 Alpha and am running it with RedHat 6.1... The machine runs VERY good usually, but I have LOGS of "unaligned traps" (mostly from Postgres and Emacs) showing up in my /var/log/messages. X also freezes at least once a day, and I think it could be a related problem. How can I recompile those apps with the proper bit alignment?
Thanks!
Cool! Where do I find the -$3500 deal? ;-)
Let me point out an article I liked from Linux Gazette on how to build your own inexpensive Alpha. It's almost 2 years old, so some of the details aren't as relevant, but I think some of the stuff explaining the gotchas of the Alpha platform for someone used to x86 (like me) are still informative.
I still want to actually build my own Alpha... as the Penguin-Ferrari article points out, we need diversity, and anyway I like messing with different stuff. Anybody know of more recent articles, or have personal experiences to offer?
"The best we can hope for concerning the people at large is that they be properly armed." - Alexander Hamilton
Did you buy the cpu/mobo from ebay or was this a complete system?
Only the State obtains its revenue by coercion. - Murray Rothbard
... in the comment that HP is betting solely on EPIC and MIPS has stopped processor development altogether. Given the slippage in Intel's original roadmap for Merced, HP were smart to keep a hand in the PA-RISC and while MIPS may not be revving their processors like the others, they earn a very tidy income from licensing their IP and creating variants of their processors for the embedded market while continuing to source high-end designs from SGI (who still have a 5 year roadmap for their R14K, R16K).
... more like unpaid advertising sometimes. I suspect that past 1 GHz, the CPU performance is of only marginal benefit (outside niche areas) as the speed limit is the bandwidth limitations anyway.
From a personal perspective, it is rather disturbing from an architecture point of view that so much attention is focused on the branding and MHz rating. If we use the analogy of cars, the peak revolutions per minute has got nothing to do with the actual real-world engine performance. A lot of factors depend on the I/O subsystem (gas tank + injection system), cache design (suspension), and more recently stlying (bodywork). Just because it runs hot, doesn't mean that it runs well, in fact from a thermodynamic perspective excess heat is an indication of inefficiency. Just as in real-life, there is a distinction between buses (good ol' shared memory Suns), industrial trucks (IBM workhorses), SUVs (SGI drool-designs) or motorcycle packs (Beowulfs). Pretending a souped up scooter with over-granished rusty frame can do the job of everything is a serious indication of cluelessness or delusion.
Just as in real life, the limitation is the overall transport system (network) which is still an information back-lane despite the heavy hype. Sure a speed-demon Porsche (Alpha) can outrun anything in a speed race but most people settle for a Ford (Intel) or Chevvy (AMD) to commute to work. Some may prefer a flashier Saab (Apple) or stick with the boring but solid Volvo (IBM) or even go upmarket with a BMW (SGI) but they all serve a basic purpose (mobility) and dominate specific niches. You get paid for maintaining a professional non-bias and correctly matching your company's needs to the available choices.
The quasi-technical mainstream press really has to
get their act together if reading the IT section in any general newspaper is any indication
LL
IMHO the current drive towards having one power-hungry-but-fast CPU in most commercial systems is not the best approach for delivering high-power and low-cost systems. A large gain in computing power could be made by changing the machine design to one based around several low power CPUs. A CPU design such as the ARM architecture, if modified to support multi-processing (the StrongARM does not support it as-is, I do not know how the situation is with other ARM chips) would be good for this as ARM CPUs are sufficiently fast and are power-friendly. (see http://www.arm.com for more details).
It would then be possible, once the chipset and motherboard have been designed and manufactured (not a small task by any means) to have a system with a lot of processing power but not costing a great deal more than a typical high-end system today. Also the power requirements for such a system would be on a par with a current system as well, if not less (depending on the number of CPUs employed and the system with which it is being compared).
Call Compaq about some of the discounts they have available. Through a reseller and with software developer discounts you can get the price REAL close to $2500.
Why did they blur out the Compaq logo on the photograph of their test system?
If tits were wings it'd be flying around.