Slashdot Mirror
Microsoft Dropping Itanium Support For Clusters
upsidedown_duck writes "According to an article at TheStreet.com, Microsoft is opting not to support Itanium on its coming release of Windows Server 2003 Compute Cluster Edition. Instead, Microsoft will focus on AMD's offerings and Xeon."
Aww, you know the rest.
SGI and HP are the only ones left on the Itanic. HP looks to be hesitant anymore though, hell it plopped a fuckton of its own money on IA64 dev and just recently killed off its IA64 Workstations. One of the few places that Itanium sold fairly well.
Sun might bring solaris to it, but... why?
IA64 is a really cool chip (no pun intended) and I hate to see it flounder like this, but with PPC, x86, and SPARC all stepping up with new R&D.... Who needs itainium?
(oh and the nasa cluster based on it is neato)
I hope you die painfully and alone.
The only place I see the Itaniums making it anywhere is SGI. They're using them for all their supercomputers running linux. Let's hope they keep the mips line... just in case ;)
||| I still can't believe Parkay's not butter.
I think this is going to sink the itanium project.
Does Microsoft's dropping of the Itanium from it's supported platform list herald the end of Itanium? No. In fact, Microsoft wasn't even the first to drop it, rather HP was the first to go ahead and stop using it in its high end servers. The whole thing boils down to the cost/benefit ratio which is insanely high for Itanium-based machines.
So Intel now gets a boost to its Xeon line of chips which are leading the high-performance server market percentage-wise. With this, Intel can put more effort into ramping Xeon production and subsequently driving the prices down there, and likewise continue producing the superfast Itaniums in servers running Linux or some other proprietary supercomputer operating system.
The demand for supercomputers is low. It will always be low. As technology progresses, the normal users like us get to reap the rewards of this high technology and eventually those supercomputers will be available to us on a single board. The supercomputers of that future will be supersupercomputers and the demand will still be small.
So let the Itanium fit its niche in the super-highend market. Let the Xeons fill in the normal server market. And let Microsoft stay out of the supercomputer market where it simply doesn't fit.
This is a smart move. The Itanium was built for a niche market. Due to it's high price, and low performance to price ratio, the Itanium isn't popular. But Microsoft has so much weight that it could probably stop supporting intel processors and still come out alive, albeit heavily damaged. If I were Microsoft, I'd try to buy (or merge) with AMD or Intel, then stop OS support for my competitor, leaving them helpless. It would be risky, but if I were a selfish, inconsiderate, greedy, power-hungry, monopoly driven CEO, that's what I would do :).
I forgot to add on the end:
</captainobvious>
Itanium is too small a market for Microsoft to devote developer time to. They're better off getting longhorn ready than supporting an already dead platform. Itantium will go the way of the Pentium Pro, another hyped up CPU that never really delivered.
Seems like the Wintel alliance isn't so strong these days. Microsoft opting for IBM's PPC processor for XBox 2 is another example of how they're looking what hardware is best for the job, instead of what their traditional partners can offer.
Does anyone want a Windows Supercomputer anyway? Does Microsoft really think they have a chance in this sector considering how entrenched *nix is?
Dammit, I can't blame MS for this move.
As much as we all like MS-bashing, this action does not seem evil.
Or, is it? (Please?)
Has anybody just bought a big Itanium-cluster to run Windows Server 2003 Compute Cluster Edition on it?
BTW, is the name really "Windows Server 2003 Compute Cluster Edition"? Sounds terrible...
I don't need a signature.
One really has to wonder how long intel is going to stick with the itanium after its dissapointing sales figures and a move like this from the software giant is sure to really hurt. Maybe they will eventually drop their itanium line in favour of a AMD type X86-64 instruction set like they are using in their new P4's and new Xeons.
This is actually an exciting opertunity for AMD since they can increase their margin in the sever and business arena where the big money is. They should seize this opportunity and start pushing their server lines.
The Pentium Pro never really delivered? In it's various incarnations (Pentium Pro, Pentium 2, Pentium 3)have been around for a while...
:)
But anyway, this is news how? I wasn't aware that there were enough Itanics around to MAKE into a cluster
It was an audacious move for Intel to rhyme its architecture with "Titanic" and still not expect its utter perdition.
Given the rhyming, I'm surprised it lasted this long.
Could the unholy alliance be breaking down?
I bought 100 Itanium PCs in order to have lotsa computing power, so I can create realtime virtual porn featuring Princess Fiona, Aki Ross and me. And now those PCs are doomed to stay and collect dust. :( Life just can't get any worse.
Linus was right, then, I guess...
while true;do echo -e -n "\033[s\n\033[u\134_\033[B";done
... :(
.NET
Or did I?
I don't remember. There was too much hype back then and too much cocaine. We bought everything that fell in our hands like madmen.
Now, I've invested in
In a way, this shows us the limits of closed source developpement :
.NET for it's OSes. But until then, they are tied to Intel x86, and can make some exceptions a few times...
Compagnies have to concentrate their (limited) efforts on a few software/platform combinations. They cannot developpe a version for every CPU existing on this planet.
Microsoft has already a lot of work to do (Longhorn, 64bits XP, XP reloader, still supporting deprecated Win98, developing specials like WinCE, WinMedia, etc...) so they just cannot afford supporting more than 2 CPU types.
In open source, it's the opposite. Because the source is Open, even if the main developper can only target 1 CPU type, everyone is free to try to recompile/port the code to another architecture.
Just have a look at the impressive number of architectures supported by Linux (including weird platforms like cellphones, gaming console [DreamCast/XBOX/GameCube] ).
Maybe this trends will change if Microsoft finds a way to use "write once run everywhere" vm like
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
Wonder how this will affect the market. /. land? Does the big M$ gorilla's 'endorsement', Sun's decision to use opteron in their low end servers, AMD technical superiority, Intel's seeming 'mis-steps', the overall market upswing, the fact that A64 is a NICE piece of hardware, that AMD is NOT intel, and make AMD a very attractive investment?
/.'ers who invest are planning to react to this Intel news.
AMD 2 year chart.
I bought a little bit back when the Athlon 64 was announced. Trading volume has been up since. Opteron announcement didn't seem to make much of an impression on the market.
Post election, the markets been up overall.
Do you think we'll see a runup to $30 over the next couple of days?
Now I'm feeling like I should have bought a bit more AMD but historically I've been bitten on almost every investment decision based on the techniclal merits of the product.
WHat's the feeling out there in
Whay about AMD taking on $600,000,000 debt the other day and adding a guy from Radio Shack (see latest SEC filing).
My favorite way of looking at stocks (useless for decisions as I still don't grok it) is the correlation between the analyst recommendations and price/volume.
What sort of analysis do these guys do? Ouija board?
BUT wait. What I really want to know is how you
Now I'm the grandest Tiger in the Jungle!
Obligatory Lord of The Rings quote:
"It began with the forging of the Great Rings. Three were given to the Journalists, immortal, wisest and fairest of all beings. Seven to the Engineers, great designers and craftsmen of the computer chips. And nine, nine rings were gifted to the race of Politicians, who, above all else, desire power. But they were, all of them, deceived, for another Ring was made. In the land of Redmond, in the fires of Mount Doom, the Dark Lord Gates forged in secret a master Ring, to control all others. And into this Ring he poured his cruelty, his malice and his will to dominate all life. One Ring to rule them all."
Oh I bet intel loves this one, but hey if you were microsoft would you really care about intel? I mean lets think here though, who depends on who?
http://www.theinquirer.net/?article=14310
(the link to the video is at the end).
I think we all know EPIC is dead. So is Moore's law.
Get used to learning how to parallelize (??) your
program.
Itanic I knew it not at all. Lot's of 64 bit CPU's out there means we can (finally) write nice emulators for the 36 bit ones (grins)
Siemens and Bull (both major vendors in Europe), Dell, and IBM, and probably a lot more that I'm forgetting support ia64.
Actually pretty much every hardware vendor (that's traditionally worked with Intel CPUs) supports ia64 in one way or another.
But this article isn't a surprise. ia64 is just presently a pretty crappy CPU for clustered computing because it's very hot, sucks a lot of power and very expensive. When building a large cluster you naturally have to balance heat, energy and cost against performance much more than you do with most setups.
http://finance.yahoo.com/q/bc?t=5y&s=AMD&l=on&z=m& q=l&c=INTC
Must of taken a *long* time to get specfp up given the brain damaging "software has to do it" thing on itanic. All I want (personally) is a low watt, high screaming 64 bit version of the 11...Somebody resurrect the Alpha or implement the stanford cpu please? (You are right VLIW was soo 1980's wasn't it..) - oops I wrote 32 bit initially.
The irony is that when we get a mass market 64 bit
processor the first thing some of us will do is
to make a good emulator for the old 36 bit cpu's
(grins)
Does that leave us with ANY next generation chip? Or are we stuck with the x86 architecture until 2020?
Too bad HP killed off the Alpha architecture in favor of Itanium. Maybe they could restart it...
sPh
Now we cannot imagine a bewolf cluster of these...
Pfff!!!
how long until
First Amd beat Intel in 64 bit, then they beat Intel in performance, they they got them with value (performance and price) and now they are making faster chips then Intel. Will that become a trend for the next few years?
One might suspect Intel realized a while ago that Itanic was never going to make it. Now they're generating various scenarios, trying to figure out how to write off the investment at the least painful moment. One good instant might have been when Andy Grove left. Or maybe the next guy is revving up for this. Anyway, the shoe is going to drop sometime in the next 12 months. Don't expect much sudden drop in their stock as the market willprobably anticipate this.
More old Intel , they try and try but they just can't get the albatross of the x86 off from around their necks. They tried years ago with the i860 and they tried recently with the itanium but its just not happening. Personally I wish x86 would die ASAP as its an inefficient , bloated and power hungry architecture but if big corps like MS won't support itanium we can only hope that open source does even if that makes a lesser impact on the market as a whole.
Oh, puke on! I like to see interesting news on Slashdot. Even when they're somewhere else too, because I've got a job and try to limit my waste of time to Slashdot only ;).
... it just smells that way ; but hey, why don't HP take it out of its coffin, Intels starts printing 'Alphanium inside' labels, and here we go again !!!
Change the record.
x86 has come a long way over the years. We now have a multitude of streaming SIMD instructions and the biggest complaint of x86, the lack of GPRs, has been remedied by AMD in x86-64. It's cheap, relatively easy to code for and is not going away any time soon.
And you say x86 is power hungry? What does that make Itanic?
For all intensive porpoises your a bunch of rediculous loosers
Monday Forbes reports Intel told software companies they should license a multi-core chip as one processor. Also on Monday, Intel compared their new Itanium to the "best published RISC" machine. Their graph indicates a 64-processor Itanium is about the same SpecIntRate as a 64-processor RISC machine. Now the funny part is for the RISC result they used the 32 chip Power5 SpecIntRate as 64-processors. So 64 Itanium-2 chips are really about the same as 32 Power-5 chips. So while Intel advocates per-chip licensing, they use per-core benchmarking. It is also interesting to note that this new Itanium-2 SpecIntBase of 1590 is just a bit faster than a 2 Ghz Pentium-M and much slower than a 2.6 Ghz Athlon-64-FX.
I am TheRaven on Soylent News
"x86 has come a long way over the years. We now have a multitude of streaming SIMD instructions and the biggest complaint of x86, the lack of GPRs, has been remedied by AMD in x86-64. "
BFD. A polished turd with a pretty bow is still a turd. The majority of high end non-intel server CPUs manage the equivalent MIPS at less Mhz and producing less heat. x86 is the Model-T of the 32 bit world that if it wasn't for backwards compat would have been put out to grass years ago.
When the Itanium came out and was given that goofy name, I always thought it would be the 'Edsel' of processors... and indeed it sure enough is turning out that way.
http://www.byte.com/art/9608/img/086bita2.htm
As you can see, PPro improved FPU performance quite a bit but integer wasn't improved that much.
2.1 vs 2.8 for integer. Of course the PPro could be used in dual CPU arrangements, but only with NT.
Interesting to see how far ahead and better the PowerPC processor was at that point.
"Itanium" and "Windows Cluster Edition"!
It's like saying "Bum Rashes announce they won't support haemmorhoids"...
Yes the legacy reason is the main reason x86 is around and I won't deny it. As for RISC with a bolted on x86 decoder... why??? WHy not just have a RISC chip and let the compiler do the work? We don't need complex instruction sets in the 21st century! x86 type sets are a hangover from the 70s.
If Intel would come up with a replacemenet architecture for the x86 that was a credible alternative, they could do it.
Here's what they've tried so far:
iAPX432: arguably the CISC of CISCs. Out-VAXED the VAX, the only instruction set more complex was one of the Japanese TRON designs.
i960: this one had a chance, it was a fairly conventional RISC with good performance, but it was too early. Intel was still enamored with the x86 architecture, and it got stripped of its MMU and shunted into embedded systems lest it compete with the x86.
i860: Baroque RISC variant that forced the compiler to do an incredible amount of work to get decent performance. Kind of a trial balloon for the IA64.
IA64: Even more baroque RISC/VLIW blend, instructions are basically RISC-like, but bundled together in wide instructions. Again, the compiler has to be insanely great. There are some insanely great compilers for it now, we'll see...
XScale: take the DEC StrongARM and give it the Intel touch: long pipelines, heavy dependency on the compiler, the 400 MHz XScale was not a lot faster than the 206 MHz StrongARM. It's still got a shot of taking market share away from x86 at the low end, except that other companies like VIA and Transmeta are waiting to take that on if Intel really starts trying to push.
If they really wanted to wean themselves from the x86 they'd have kept the Alpha EV8 team working on the Alpha, release it as the Intel AXP Architecture, and pretty soon people will forget that it's not their design.
I don't think Intel's managers really want to wean the company from the x86. They say they do, and may believe it, but their actions don't show it.
You're telling me MS is just getting to release an OS with the date 2003 in it? Last I checked, it was getting pretty close to 2005!
It's not a good idea to bet all future processors on x86-64.
People who dislike China tend to mention Tiananmen Square a lot, but they always forget the Tank Man is also a Chinese.
"And you say x86 is power hungry? What does that make Itanic? "
Power has very little to do with ISA.
It is the implementation that matters there.
Didn't work. It's different architecture, but it's not better. It's worse.
if intel management had a clue, they'd drop itanic, swallow their pride and bring back dec alpha. a proven archtitechure with an installed base, including compilers and applications. its either that, or drop their pants and adopt amd 64 bit athlon stuff ....
I think the biggest problem with the Intel Itanium CPU was the fact you literally had to code from scratch to fully take advantage of the CPU. Of course, that is extremely costly, to say the least.
Meanwhile, the AMD Opteron and Intel Xeon CPU's can pretty much use the legacy base of x86 program code, updated of course to take full advantage of these server CPU's.
It just doesn't seem like Intel could buy luck at this point...
28:06:42:12 - That is when the world will end...
You mean to tell me that those bastards in Redmond have been enriching Itanium? This clearly makes them a member of the "Axis of Evil". I suggest an escalation of the terror threat level to magenta... or at least a very, very deep reddish tone. I will be FASTING until further notice.
Seriously though, may I have another slice of yellow cake?
We are considering a mixed Linux/Windows design. Some programs we need to run are only hosted on Windows for the forseeable future. This leads to a mixed solution where 90% is highly scalable using Linux and 10% is dedicated Windows boxen with dongles and other license restriction items....
By "Power970" you seem to be referring to the PowerPC family. Don't forget that this chip family is based on the Power architecture from IBM (with some help from Apple and Motorola). The Power architecture contains other chips too, some of which don't have the limitations you cite. Certainly the chip architecture is fully capable of supporting machines with a larger number of CPUs running a single system image.
Although the really big (and custom) Blue Gene systems are apparently clusters, there isn't anything about the IBM Power Architecture itself that would prevent large monolithic systems from being designed and built.
The SPARC architecture can be used for machines like this, too. (Remember the CM-5?).
Building a supercomputer with a large number of CPUs running a single system image is a unique task with a limited client base, and SGI has experience with that. A whole lot more than CPU choice goes into making it work. The way they tell it it was quite a rush. The internal conversation must have gone something like this: "OK, team, we're going to build exactly one of these, and we already decided the price!" NASA doesn't build rockets like that, but SGI can build supercomputers like that. Impressive.
SGI deserves kudos. But if we step back and look at the big picture from the vantage point of SGI, it sure looks like SGI chose the IA-64 CPU for marketing reasons, not technical reasons. I'd have to guess that their engineering tasks would have been made easier by using a CPU that draws less power, for example. They've been on the ropes for years and conventional wisdom says to back Intel if you're in trouble because that's the safe bet for marketing. Why this remains conventional wisdom when the track record clearly shows that UNIX vendors who switch to Intel are cut up and fed to other UNIX vendors, is another topic.
You're right of course, that there are two different classes of super computers on the Top 500 list, with one class based on the cluster concept, and the other based on the concept of a single system image. Clusters are radically less expensive, and monoliths are better at certain computing tasks, and it's hard to compare them.
Monoliths often get custom case mods, though, and thus tend to look cooler. Who would hang a poster of a beowulf cluster of generic beige 1U rackmounts on their office wall? Everybody wants a poster of a Cray or a CM-5 or a Mach 5...
Hey! I just realized monoliths don't seem to look as cool as clusters lately. What's up with that?!
Things should be made as simple as possible, but not any simpler. -- Albert Einstein
The answer to the first question, taken literally, is "yes, obviously". Presuming you really mean "anyone" as a casual way of saying for "a very large portion of the general market" then the answer right now is "no". But...
Does *nix really think it a chance in the desktop sector considering how entrenched Windows is?
This is a different question altogether, and the answer is "yes".
See, most people really DON'T care what OS brand name they use so much as they care about being able to play well with others - whether the "others" are other computer environments that the user is already familiar with, or other people playing the user's favorite game, or websites on the internet and email clients on their friend's computer, or being able to look at the slideshows that someone else produced and uploaded, or whatever...
Most people also don't want to blow wads of money on licensing if they don't have to.
The "typical" computer user these days seems to be interested almost entirely in email, web browsing, and "Mahjong" games. These basic functions are already well supported in *nix environments and ready to be sold as "appliances" running *nix to anyone who is satisfied with those basic requirements. Related to email and web, though, people also want to be able to watch all those little internet videos that their friends email to them, which are often in proprietary formats. Now, MPlayer already supports all of the major formats pretty well, and plugins are available to use it to play internet videos in Microsoft(r)'s formats, Apple(r) Quicktime(tm), and so forth, not to mention the existence of the Helix media player as well. So, that's possible to take care of.
The slideshows (I refuse to call it a "presentation" when there is nobody actually presenting...), word-processor documents, and spreadsheets can all be handled pretty well by OpenOffice. There are still a few formatting differences that come up sometimes when loading a file produced by a Microsoft(r) program, but I'd call it "good enough for typical home use". Plus, the ability to generate .pdf's natively built in means if someone is USING OpenOffice they can generate documents that look correct on everyone's computers. So, for ordinary home users, this is also at a "good enough" stage.
That's not all of the market, or I think even a majority, but it's a pretty big chunk. What's really missing, as the Slashdot discussion boards echo loudly with every time this subject comes up, is video games. Right now, most are written exclusively for the purpose of being installed on a Microsoft(r) Windows(tm) general-purpose operating system, and this does create a genuine speedbump in the path of *nix desktop marketshare.
However, the concept of having a dedicated "boot disk" for running a video game has been around for a very long time. Tech support people tend to love them, because when used, the video game in question ends up running on a known, well-characterized environment without other processes interfering. Because providing tech support costs money, software company tend to love anything that reduces the need for tech support.
Since it seems like most people who are playing anything more intensive than "Mahjong" or "Solitaire" usually play full-screen and dedicating all of their attention to the game (and generally want as little running in the background reducing their framerates as possible), the possibility of distributing videogames on self-contained boot CD's is very real. The boot disk might be a no-license-fee-paid-by-the-software-company Linux disk, as they've talked about doing (have already done?) with America's Army. I think the only technical capability lacking to make this really feasible is full write support for NTFS (since
Hacker Public Radio is our Friend
As God is my witness, I thought turkies could fly!
Things should be made as simple as possible, but not any simpler. -- Albert Einstein
Hooray, yet another hardware platform that Linux will run on but Microsoft(r) Windows won't...
Does Microsoft's refusal to support the Itanium bother Intel at all? If so, will they perhaps "retaliate" by focussing a bit more on Linux support? Maybe even helping GCC develop good Itanium code optimization routines (I know Intel has a proprietary compiler, but the segment of the market that might buy Itanium hardware to run Linux AND be perfectly content only licensing Intel's proprietary compiler rather than being able to use GCC has got to be ridiculously small...)?
After dropping the ball so badly, initially, on the "Centrino" chipset support for Linux, it would be nice to see Intel have more reasons to more openly support Linux development. It sounds like Linux is really the only chance they have of finding future uses for the Itanium (other than perhaps ceasing production and using the existing stock to set up a "museum of market failures"...)
Hacker Public Radio is our Friend
This is a seemingly easy question being that a TON is 2000 pounds. A dollar bill (and all other currency notes in the United States) weighs 1 gram.
... uh ... fucking?
Thus, mathematically:
454 Grams = 454 Notes
454 Notes to a Pound
2000 Pounds is 454 Notes x 2000
That means a FuckTon is equivalent to 908,000 bills.
The question is: how many bills of WHAT TYPE and how many, pray-tell, would be made non-denominational by the act of
That's another calculation for someone else.
...y?
Linux is your daddy!
http://www.cs.wisc.edu/condor/description.html
Are you in fact making that statement in comparison to the x86_64 - aka Athlon64? While it can execute x86 instructions it is definitely a big leap forward.
My year-old 2GHz AMD64 can keep up with even the latest Intel P4s at most applications (there are a few where the raw GHz helps). It certainly puts out FAR less heat than a typical Intel chip. And that isn't counting its capability to throttle down when idle.
Backwards compatiblity is a big deal. Even though the amd64 architechture is nearly identical to the x86 there are still tons of apps that are buggy when compiled 64bit. As a result, I can just run them 32bit. That gives me 64bit performance on most applications without having to make tough decisions over "must-have" apps which refuse to work without significant patching.
Don't get me wrong - even x86_64 has a lot of baggage from its x86 heritage. However, if you do a little reading up on it you'll probably find that it gets around many of the x86 limitations.
There is plenty of room for improvement, but the x86-based architechture has been remarkably long-lasting. I look forward to the day when there is a smooth migration path to something better, but we're not there yet...
'Cause Windows won't run on the RISC ISA, that's why. And people won't buy a new computer if it completely negates all prior software purchases.
If you want to blame someone for this, blame IBM. The System/360 introduced the idea of an ISA being seperate from any single machine, and therefore the idea that programs could be moved from one machine to another without recompiling.
How can you use my intestines as a gift? -Actual Hong Kong subtitle.