Slashdot Mirror
HP Terminates Itanium Workstations
vincecate writes "The largest Itanium system maker,
HP, has terminated its Itanium workstations.
It seems their workstation customers have spoken in favor of x64.
In related news, Intel expects to ship
over 100,000 Itaniums in all of 2004
while AMD is estimating
1.5 to 2 million AMD64 chips in Q4."
Let me put it this way. I would not buy a server from HP anyway.
http://ebgp.net/ccc/
I've heard that HP actually sold both of the Itaniums they had in inventory, so there shouldn't be too much to write off.
It's good to use your head, but not as a battering ram.
... HP Terminates Carly Fiorina...
... hi bingo
Isn't x64 the program that runs the VICE C64 emulator? ;-)
Makes me think about their technical vision
I AMD has caught up to intel a couple of times in the desktop market only to fall back again. Could this be the time that they leapfrog over Intel and be far and away leader in a market? One could only hope. In a tech world of dominate players (Intel, MS) its nice to see the underdog win with a superior product.
"All I can tell the "lesser of two evils" folks is that if they keep voting for evil, they'll keep getting evil."-Lp.org
The only reason I'd consider IA64 on my desktop was if it was a VMS Workstation...
Damn... First the Alpha killed then this.
Guess it's up to SimH on Athlon or P4 to emulate one.
I wish the hell HP ported VMS to IA32 instead 8-).
Bill
AMD sold around 100,000 Opterons in Q2 however. This should increase to 200,000 in Q3 given recent products from HP, Sun, IBM etc, especially with the increase in 4P systems.
Of course, the ASP of Itanium is a lot higher, so Intel need to sell a lot fewer Itaniums to get the same money back as AMD. On the other hand, AMD haven't sunk $billions into K8!
Top 10 Itanic jokes:
:-D
10. HP decided that they didn't want to go down with the Itanic
9. Hear that flushing sound? That's billions of dollars being invested into a lemon.
8. HP must of realized it was a 64-bit Pinto.
7. HP's just upset that they didn't get to sit on the bow and yell, "I'm the King of Computers!"
6. HP's Itanic line is sunk.
5. "The Itanic is the most advanced chip of her kind. She's practically unsinkable!"
4. HP didn't want to be compared to Leonardo Di Caprio
3. HP Execs suddenly realized that Di Caprio dies in the end
2. Intel assured HP that the Itanic was not sinking, despite being hit by a AMDBerg
1. "My clock wiiilllll, count on and on!"
Sorry, I just couldn't resist.
Javascript + Nintendo DSi = DSiCade
AMD deserves the win here for pushing 32 bit backwards compatibility, Intel had to and still is playing catch-up with them in this arena.
Good job AMD!
...unfortunately no one can be told what The Mat^H^H^HGoatse is...they must experience it for themselves...
I remember 5 or 6 years ago the new 64-bit chips from Intel were "hot" with everyone talking about them, and also supposedly right around the corner in terms of schedule. AMD surely stole their thunder on this.
O tempora...
I hadn't known there were so many idiots in the world until I started using the Internet -Stanislaw Lem
I guess because (for some moronic reason) AMD are "good guys" and Intel are "bad guys" we just have to get all giggly and rub their noses in it.
BFD. Sometimes you win, sometimes you lose. Some products take off, some don't.
Itanium looks like a good architecture for transaction processing, at least on paper. Turns out the market was more interested in backwards compatibility.
I don't need no instructions to know how to rock!!!!
Why doesn't Intel just get over the NIH syndrome and start fabbing the Alpha (proven design, existing software base, the geeks love it)... Don't they own the rights for it via some legal-fall out with Compaq?
- Friendly A.C.
The article says that they killing the workstation Itanium line. What about the server Itanium line? I find it hard to believe that they would just throw up their hands and calls it quits - especially because they funded a fair portion of the development of the chip.
Gotta get me one of these!
Not much. Apart from the Pentium-M, for which there exists a couple of motherboards outside the laptop market ... Transmeta's new Efficeon should run at 1.5GHz. VIA's C7 might make 1.5GHz when it is released.
AMD sell a 35W Opteron, 1.8GHz I believe, I'm not sure. Maybe it is 55W @ 2GHz.
OTOH AMD's consumer processors include Cool'n'Quiet which downclocks the processor when you don't need lots of processing power, and hence cuts the power consumption a lot. With a decent fan the fan will also slow down.
Or get an iMac G5.
Competition is good for market economies. Monopolies suck.
What the hell were they thinking.
Honestly, Opterons/Athlon64s are fairly low power. If you want passive cooling, go with a C3, but know that your floating point work will suck. If you want the best performance/power ratio, go with an old Mac G4 (I think that's still the best). However, if you just want something that is fairly low power but can really kick ass, go with one of the lower-speed Athlon64 offerings.
If you're willing to settle for 1Ghz, VIA has a line of low power processors.
You might want to look into Pentium M, AMD XP-M, Via's C7, a Transmeta Efficeon or an iMac G5. I am not kidding on the last, it is supposed to be quiet. I don't think any of these are necessarily cheap though, but they are fabbed for low power.
poster = troll
This shows how big a problem proprietary closed lock-in has become. Well, I've got a message for HP: Bring it on! You can pry my workstation from m%#y co%@$(
I was thinking about that the other day too.
I have two boxes at home, and the Linux box I suspect is not exactly a power-saver. The Windows box is better, but one can definitively tell the difference on the electricity bill (between now and before I had these boxen).
When you think of it, everyone hates to wait, but just a little bit of patience and you don't need a killer CPU. Plus you waste less energy.
If I was only sure VIA chipset-based boards were reliable and stable, I'd seriously consider buying one of those little fanless, power-saving things they make.
Looks like all HP's done is trade an old dog for a new dog. Say what you like, but they're both still dogs.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
In "favour of AMD64" is not at all the same as in "favour of x86-64". Considering of course that x64 is something freshly invented here ;)
What was Intel thinking?
An architecture switch breaking x86 ISA compatibility (i.e. emulation is noticeably slower than the original item) would put it on a level playing field with other 64-bit workstation/server-class chips, yet they never seemed to offer either world-beating design improvements or substantial price benefits, or appear as though they would in the future.
This looked like a loser from the first minute I saw it, and I obviously wasn't the only one: I mean, the chip has been "The Itanic" in Register parlance for years now.
Intel, for all their flaws, is a smart company with a lot of smart people working for it. I must just not be seeing the whole picture. They must have had some good reason not to have flushed this project years ago, right?
Want to Know How to Cheat the GPL? Read On!
Get a 1.8-2 gig celeron, they're cheap and fast. With the same video/RAM/mobo config, Doom 3 plays the exact same on the 1.8 Celeron as it does on a 3.06 P4 with HT (at least from what I could tell).
I only say 1.8 because IIRC, that's as slow as you can get on a Socket 478 mobo, and you probably don't want a 423 based board, because it's likely to only support SDRAM or RDRAM.
Get one of those big Zalman passive heatsinks if you don't want a fan. Just be careful moving the machine or find a way to brace it properly. I bolted mine through the mobo and directly to the steel backplate of the case, all stress on the case and not the mobo. I just dont trust a plastic clip to secure a half kilo of copper just inches above my Radeon 9800.
The newer prescott based Celeron D's perform like a champ (as in, really close to their P4 counterparts) from the reviews I've seen. I think they start at 2.4 gigs.
Stay away from bleeding edge stuff. It's just a waste of money, and won't improve your computing "experience", unless you consider bragging about artificial benchmark scores "computing".
I don't need no instructions to know how to rock!!!!
That isn't what I'd call an upgrade from dual-333MHz PII though!
... I'd get the PIII.
The C3 is pretty dire unless you suddenly want to spend all your time doing encryption. The FPU is very weak, the integer is also weak. There's a reason it is low power!
C3 1.2GHz or PIII 800MHz
90nm Athlon64s 939 soon to be available!
:)
90nm A64s seem to draw much less power than 130nm A64s.
There is also Transmeta which produces the Efficeon CPU and VIA which makes EPIA.
You may also get an AMD Geode
The interesting thing is 3 RISC chips were killed because of the threat of Intel - MIPS (well, at least in workstations, embedded lives on), Alpha, and PA-RISC. PA-RISC even had a technology that could be seen as the opposite of EPIC, instead of moving scheduling logic to the compiler, they actually moved some of the optimization the compiler could do to the chip itself, since it knew current state of the machine and the compiler couldn't. Just shows you what a bit of monopoly muscle can do I guess.
Yeah.. I just ordered the IA-64 linux developer's kit CD from HP (for free) last week! Jeez..
parent = offtopic
You know, I was speccing out AMD64s too...and I was planning on running AMD64 Gentoo on it too ! The power util was my main concern...till I found a nice page which showed the power consumption of various processors...an AMD64 3200+ runs at 45W idle, 90W peak. The Pentium-M runs ~ 35W peak power. So, the different is only 55 Watts. That's ~ 1 KWHr/day. 30 KWHrs/month. At 12 cents/KWHr, that's 4$ more a month.
This puts the OpenVMS users into a pickle. HP will stop making Alpha servers. They were planning to migrate the OpenVMS users onto the Itanium servers.8 4
http://www.theinquirer.net/?article=132
Now that HP will stop making Itanium servers, is HP going to have a migration plan for OpenVMS users to go onto Operton?
Hopefully this won't kill off OpenVMS, the Operating System that won't die.
Nope it's not just you.
Maybe the writing-on-the-wall dept needs to be terminated.
Architecturally, IA-64 is a very advanced architecture.
Ok, many people don't like it. And OK, it's complex. And OK, many people are making other quite good 64-bit processors.
If its competition was Power or MIPS, then OK, I'd say that the worse it is, let IA-64 die, but x86 (and x86-64 as well) is UGLY and laden with all kinds of OLD JUNK. Come on, it will be junked sooner or later. Granted, Intel can make high-performance x86s, but that at a price of devoting over 1/3 of the stages for decoding!
Or, let's put it that way. It is a Good Thing (TM) to have several different architectures. If all we'll be stuck with will be x86, it'll be quite sad.
Of course a 1.4GHz Duron will outperform a 2GHz Celeron P4. See the comparisons on numerous websites that have done the comparison.
P4 based Celerons on the 400MHz FSB are crippled sad creatures. The latest revision which ups the bus to 533MHz (and the L2 cache? I forget) improves the situation somewhat, but I think they start at 2.8GHz (and being based on the Prescott core, they eat power like a geek drinks Mt.Dew). Celerons are cheap, and they are also cheap. I don't think they provide good value.
The only thing I agree with is that bleeding edge stuff is a fool's game.
Has AMD finally proven that the x86 "standard" can produce truly 100% compatible CPUs, without Intel IP, after decades of doges and ruses, including MMX?
--
make install -not war
Good luck finding a proc at that speed needing no fans. Most heat sinks rely on some amount of air movement, so if the proc requires a heat sink, it generally requires a fan.
Even laptop processors run too hot.. The centrino uses a smaller amount of power, proportional to the computation being done. It also implements heat throttling, so I wonder how effective it would be if you remove the fan completely (probably not very effective at all) since the geometry is quite small and the heat density is high.
You could even try going with an Xscale, which runs nearly 1 GHz at 1+ watts. At that power dissipation, it doesn't really need a fan, just a heat sink. It also implements the throttling IIRC, so will not fry if you run it too hard. I don't know if you can buy an OEM board for it though.
Then there's your price issue. I don't think you are going to get all that power savings you want and at the same time save money.
It sounds like what you really want is a super-cheap system to get you by until your next super-cheap upgrade. You may want to permanently stay 5 years behind the consumer curve, which is way on-the-cheap. Try looking at pricewatch for a complete system (your choice of OS). They have older models (such as a 2.0GHz P4, etc) for ~$250.
Amazing, isn't it, that a Honda Civic would outsell such a high end car?!?!!! It just boggles the mind.
The Opteron isn't in the same league as the Itanium, no matter how much AMDroids wish it were. AMD needs to be comparing Opteron/AMD64 sales to Xeon/Pentium4 sales. Itanium is a very high end processor and it's one of the best you can buy for certain high-end applications.
Not to say Intel didn't make a mistake in trying to push Itanium too early as a general purpose CPU - it's clearly not.
Actually, the linux box may very well save a lot of power compared to the Windows box because it won't occupy your CPU when it's not doing anything.
...
:)
As written on the CpuIdle site:
"Under normal circumstances the CPU isn't always active but spends much time waiting for the keyboard, harddisk or CD-ROM. What would be more logical than to turn off the CPU for that period? That's exactly what the HLT machine instruction (Opcode F4) does.
Modern operating systems like Linux execute the HLT instruction in an idle priority thread. This thread is always executed when the CPU is otherwise idle. No additional execution time for HLTing is needed, the CPU will not run slower.
While other operating systems like Linux always used this mechanism, Windows only learned it with NT. But even with NT and following versions it is only enabled when the BIOS and ACPI implementation is recognized by the OS."
Basically, not only will Linux keep your CPU cooler this way, it will reduce power consumption since the CPU is literally not doing anything when it's "idle".
I run CpuIdle on my WinXP machine at home and it goes from a normal temp of ~45 degrees Celcius to an average of ~30 degrees, during average desktop usage... Linux will show a similar level of cooling by default.
Doubtful unless Intel is weak on their better chips .. A friend of mine had a 2.0+ Celeron and Doom 3 ran 14 fps with an ati 9600 pro .. my system similar setup AMD 2500+ with 9600 xt ran over double the speed. I beleive it is related to the lower cache size on a Celeron .. i have consistantly ran games better because the AMD doesn't puke during intensive moments.
HP is nice and shiny and make good printers and are fairly Linux-friendly, but they have issues. I think the issue they blamed in my case was something about a shortage of memory chips. =/
The World Wide Web is dying. Soon, we shall have only the Internet.
Check out this article: IBM mocks Itanium server sales - again, make sure you look at their very amusing graph of changing sales forecasts.
P4 based Celerons on the 400MHz FSB are crippled sad creatures
How do you figure? Have you used one? I can't tell the differnce between a 1.8 ghz celeron in one machine, vs a 3.06 ghz P4 in another (identically equipped) machine. They were both 3.06's until one died and I didn't want to spend a lot of bucks "fixing" it, so I chucked in a chip for a meager 40 bucks.
And like I said before, that includes "CPU killing cutting edge games" like Doom 3.
I have to run phony benchmarks like SiSoft Sandra to "see" an imaginary difference.
I run it with one of those flower heatsinks, it's actually not even a Zalman but a knockoff.. It's a completely fanless machine (save the PSU) and never cracks 60C under load.
Methinks you've been brainwashed by corporate fanboyism. Just because arse technica is paid to say "Intel Sux, AMD rox!" doesn't mean it's true.
And, IIRC, going with a Duron 1.4 limits you to older motherboards with SDRAM, and those god-awful buggy VIA chipsets.
I don't need no instructions to know how to rock!!!!
Is it just me, or does the article gloss over the fact that "EM64T" is actual a clone of the AMD64 architecture? Are intel's market-droids trying to brainwash people, or are people really that clueless to the fact that INTEL IS MAKIGN A CLONE OF AN AMD CHIP?
Give credit where credit is due.. EM64T is clone crap, and is signifigantly slower than the AMD chips.
oh no! what a waste of $0! =P
You obviously don't run windows.
Seriously, you are probably right... but then I use my machine principally as a home entertainment centre, and having a nice fast CPU means I can watch nicely compressed DivX movies (95% of which I own, but DVDs are fragile) with full AC3 5.1 sound without skips.
A friend of mine recently bough a philips dvp-642 (I think) with DivX playback. It obvious the difference in processing power. He suffers a lot of pixelation and slowdowns when decoding movies.
Norman Cook's Ode to Sl
[begin:humour] :) :) :)
:)
Weee! Itanic's sinking! Go AMD go go!!!
Or perhaps Intel will bomb AMD Dresden fab with the unsold Itanics... too bad for Intel the Itanics don't have pins!!
[end:humour]
I wonder what Intel was thinking when designing the Itanic. Even if x86 is not suitable for some applications or not perfect, it is cheap and available everywhere. Adopting a different arch means more cost, both for the hardware and the software but also for hiring new engineers who know how to program the new arch. In a business world which increasingly seeks to minimise cost, it is inevitable that expensive and new archs like IA64 cannot succeed. x86-64 is the way to go now!
It doesn't matter who wins, or even if the top player switches a lot. As long as the top dog has to worry about losing it's market share to someone else, we've got healthy competition.
In fact, the 89W TDP measurement for A64 processors is for the entire family, a 3200+ will rarely get above 75W at max load. The 90nm processors will be even better, probably not above 60W (although the power density is a lot higher of course). AMD already has 35W TDP 90nm processors out for mobiles.
I'm a mac guy, and I'm not generally interested in processor politics, on either side of the fence.
So, what I'm wondering here is, what's so bad about the Itanic? I'm always hearing people joke about it and so on...
Is it just that it isn't selling? Or is there really something wrong with it?
lorem ipsum, dolor sit amet
No, AMD has doen no such thing. Years ago they agreed to a cross IP licencing agreement that allows them to use intel ip and intel to use theirs.
Well.. maybe. Or Maybe not. But Definitely not sort of.
The Itanium is a high-end workstation/server chip. ONLY. -- While the AMD64 architecture is AMD's entire product line right now. It's their desktop chip; it's their workstation chip; it's their server chip; hell, it's even their notebook/laptop chip.
Whoever submitted this article seems to think that every AMD64 sold is going to be going into the high-end server market. Either that, or he thinks that home users are buying Itaniums. Funny... I don't seem to recall ever seeing a laptop with an Itanium in it.
A more honest comparison would be the 800 series Opterons vs. Itaniums, the 200 series Opterons vs. Xeons, and Athlon64's vs. Pentium 4's.
/dev/random
The current Durons run fine on any Socket A motherboard including tasty nForce2 ones. Even so, a cheap Athlon XP or Sempron will also suffice, and they are cheaper than corresponding Celerons. I never read Ars Technica either, and your witty "arse" joke is rather puerile ... especially given that AMD don't pay hardware review sites. Now Intel on the other hand ... THG, AT ...
The P4 core loves bandwidth. The low cache on the Celeron kills performance. Getting a slower Celeron is okay I suppose, it won't be affected as much. Faster Celerons showed extremely bad scaling, in lots of REAL WORLD benchmarks, not just the artificial ones.
I suppose that you can't see the difference, you have nothing that needs it. To be fair, doubling the memory in a system is a better investment than another 20% clockspeed though.
I suppose my point was that for $x, you could get okay performance with Celeron, or good performance with a different processor.
I'll bet Intel still makes more profit on those 100,000 Itaniums than AMD makes in it's 2,000,000 Opterons. Of course there's the huge R&D cost that Intel (& HP) will probably never recover from Itanium. Still, Intel probably makes AN ORDER OF MAGNITUDE more profit than AMD on their P4 vs. Athlon lines as well.
I don't know anything about the reliability, but this guy says that VIA chips are outperformed by AMD/Intel CPUs of equivalent power (and somewhat slower clock).
You would be surprised how many others did.
When HP stopped being about engineering and started being about ham-fisted second rate marketing - well, I won't buy any of their products except printers and even there, i'm investigating other solutions.
Carly Fiorina will end up being the person who drove a stake through the heart of that company.
HBI's Law: Frequency of calling others Nazis is directly correlated with the likelihood of the accuser being Communist.
Get a 1.8-2 gig celeron, they're cheap and fast. With the same video/RAM/mobo config, Doom 3 plays the exact same on the 1.8 Celeron as it does on a 3.06 P4 with HT (at least from what I could tell).
Fast? Not for the price they aren't.
We went from a 1.8 Ghz Celeron build machine to a 1.8 Ghz non-Celeron and our build performance TRIPLED.
One thing that all of these posts are losing sight of is that itanium is still doing fine in the server space. The negative comments about Itanium performance are curious in sight of the fact that today, 3 of the top 5 TPC-C benchmark results are on itanium servers:
t s. asp
http://www.tpc.org/tpcc/results/tpcc_perf_resul
Yes, this is a small niche, but it is still a viable niche.
-Jaro
I think they have a massive memory problem with the DL145s, we got one on loan and tried to put extra micron memory in and it would lock up, so we pulled the ram out and tried loading 64bit RHEL, which crashed with known good cds on cd2. HP swears up and down the machine is fine, but it just won't work, where as our sun v20z runs just fine.
Now that HP will stop making Itanium servers...
Re-read the original post, please. HP is discontinuing Itanium workstations, not servers.
For all its flaws, Itanium does have more headroom to grow than the x86-64 architecture. The whole reason HP and Intel got into bed over Itanium and its EPIC architecture was because it's getting harder and harder to wring more performance out of a chip by adding parallel instruction pipelines. In order to crank clockspeeds higher, those pipelines have to get longer and longer (witness Prescott's 31-stage pipeline). The more pipelines you have and the longer they are, the worse is the penalty for branch misprediction.
It's this problem that led HP and Intel to VLIW, where the parallelism is explicitly compiled into the code, reducing or eliminating the need for a lot of transistors that currently break code down into parallel-izable chunks and try to predict branches.
Unless somebody invents a new way of architecting chips that will eliminate or substantially reduce the branch misprediction penalty without substantially breaking x86 compatibility, Itanium (or something like it) will eventually reign supreme.
Hello, off-topic? It relates directly to what the parent poster said...
Goatse troll in sig!
> You obviously don't run windows.
Hehehe.. some truth in this, tho memory is your friend really.. a relatively slow cpu with 512mb+ will work as well with office as it will get.
> Seriously, you are probably right... but then I use my machine principally as a home entertainment centre, and having a nice fast CPU means I can watch nicely compressed DivX movies (95% of which I own, but DVDs are fragile) with full AC3 5.1 sound without skips.
Hmm... a pIII 600 with a nice videocard that has good xvideo support, 128mb ram, a minimal X configuration and mplayer.. or if your card is supported directly, you won't need X either.
Has served me as a media center for quite some time, and didn't have problems with playing anything unless it was badly interleaved avi files (fixable problem)
As soon as your video hardware supports things like yuv colorspace, hardware scaling and motion compensation, you need a lot less power for playing video very well.
Outsource carly!
-- I am. Therefore, I think!
The sad thing is I got stuck with an itanium as my work machine. No we didnt' pay for it, they gave it to us so we can compile our software on their crappy chips. So now I'm stuck with red hat 7.1 for the rest of my days here :(
I am sad to hear this because I was telling folks that for the 1st time in history, an iMac was less money than the = Intel box.
If you got an Itainium workstation with the same vid card, LCD screen, etc , it would be WAY more.
Oh well
* Carthago Delenda Est *
For better or worse Sony will bring out Cell (and lets pray it is more elegant than the patents make it out to be). Which as far as peak performance will be concerned will probably be quite impressive at least.
... Im still waiting for a x86 manufacturer to just put a lot of _small_ x86 cores on a single chip, instead of just taking already huge cores to dual core chips mostly because they have just run out of ways to use the transistors they can use.
Stream processors will come, disguised as GPUs most likely.
Hell maybe Transmeta will realise that simply following the big boys will get them nowhere
Where did you get the 90W peak figures from?
Do you have evidence to show that the current single core AMD64 chips use more than 45W at peak at specifications (not overclocked)?
If it's from the TDP spec, I think those specs just mean you're supposed to design stuff to cope with that amount of heat coming out (whether or not the chips actually do generate that much heat or not). If you check, the TDP is 89W for ALL frequencies, which doesn't make sense if it's for actual ratings.
I think the idea is if the system builders make stuff for 90W, when the dual core AMD64s come out, you can just drop them in and those will run 90W peak (45W x 2 = 90W) without major issues - same heat sink, same case fans, same power supplies (maybe just need to update your BIOS). The evidence seems to be that way based on what AMD has been saying. I think they planned it that way right from the start.
I'm not sure you'd be able to say the same for Intel's dual core offerings if they still keep to the P4/Prescott style CPUs. As far as I know, the evidence is the Prescott CPUs actually do use 100W. If that's true, 2 x 100W is kinda scary for home PCs.
Does TFA say HP is cancelling Itanium servers?
$#!^ happens, but why does it always have to happen to me???
The sad thing is, that at those ratios, Intel probably stands to make about the same amount of revenue as AMD, thanks to the price of the Itanium.
Around here, you used to find all kinds of people complaining about the old kludgy x86 architecture and how the backwards compatibility placed terrible limitations on the CPUs and on software that runs on it.
Now, everyone jumped on the bandwagon spouting "what were they thinking? Trying to define a new architecture.. dumb asses!"
So, which is it?? I learned architecture and assembly on a Motorola 68k processor. So, the x86 stuff has always seemed kludgy to me. Have the problems been overcome, or do people just not care anymore?
Sounds like the cache. If a processor has no cache, then for most of the time, it's going to go about as fast as the memory bus in the vast majority of programs. That's the main reason I wouldn't go with a bargain CPU, no cache. However, to keep things on track, the Itanium does come with up to a 3 MB on chip L3 cache.
"Anyone who attempts to generate random numbers by deterministic means is living in a state of sin." -- John von Neumann
Now I was bidding on a dual itanium on ebay a while back, it seemed like a cool piece of exotic hardware with decent performance (my alpha is nearing EOL..;) 40GB of SCSI drive, 2 800Mhz IA64s, 2GB of RAM. I bailed at $800 and it went for $975; original price of the hardware was $12k to $14k. The alarming thing was when I was searching IBM's site for information, it was practically non-existant. I asked some employees to look around inside, it's a real machine the specs are correct, no info because they literally sold under 500 of them.
There used to be all sorts of Linux on IA64 sites, they've been drying up. People are still doing stuff but it looks like some well backed projects have just dried up. Like the trillian project. Also, it doesn't seem like anybody is making an IA64 linux distribution anymore, there are some projects but all the big boys look like they have one they made back a couple years and never sold it and never updated it, SuSE has an 8. Redhat has a 7 (?!? RH 7? How old is that? Is that even a 21st century release?) and it looks like a RHEL 2.1 which is more reasonable, Mandrake has never been terribly strong off of IA32 but they have an 8.1 which is ancient and, Debian and Gentoo look like that have projects but they are kind of fossilized. I imagine that once the installer is done for most distros, it's mostly just a job of recompiling packages and then some kind of QA effort or a "beta" labeling goes on everything, not to make it sound easy or anything but once it's built it shouldn't require a huge team to maintain. Maybe Intel would kick in a few dollars too, they need Linux for IA64 internally and if they really want to sell the hardware they need some OS for it.
So Intel has pumped a trmendous amount of money in to IA64, a huge amount of time and they have all but decaired it their future architecture so presumably that leaves them at a bit of a disadvantage should they abandon it. SGI has bet on it. HP has bet on it. It's really down to POWER/PowerPC, x86 and x86-64, and then sort of Sparc. Does Intel keep kicking this dead horse? When does it turn the corner? and how? The next gen chips are all supposed to be socket compatible between the EM64 and IA64, if Intel starts shipping $400 Itaniums then maybe it will start to get some traction but why would you buy one when you can buy an em64 that will run Windows and tons of other software? I don't see how they back out, and I don't see how they can make it win, it looks like AMD has forced their hand and what that really does is make IBM the only contender in enterprise 64bit heavy duty computing right now.
Itanium was meant for workstation and servers, don't compare it with the total of all desktop, workstation and server AMD64s. Compare Itanium sales with Opteron sales, which is the sub-variant targeted to servers and workstations. Even though 1.5M to 2M chips sold in a quarter sounds like a lot, I'd be interested to know how it compares with Xeon and Pentium 4 processor shipments for the same quarter.
Being that wrong takes talent. Pulling something out of your ass qualifies as precision work compared to this.
Help fight continental drift.
http://anandtech.com/cpuchipsets/showdoc.aspx?i=21 39&p=7
For the record, I have a 900MHz Celeron. Those were good processors. Nortwood Celerys just plain suck.
how long until
I think this was related to their order processing system. I believe they were switching/merging to one ERP platform and mis-executed. A bunch of executives got whacked.
The smaller party that prevents a monopoly form being established to the detriment of the consumer is always the good guy.
By the way MS was delaying Windows64 probably at the behest of Intel but even MS has now realized this is a loosing strategy as Linux is making inrads fast at the serverspace that MS thinks they have a chance at .
You know their TCO fairytales.
Help fight continental drift.
The main post is horribly misleading - it compares the sales for Intel Itaniums with AMD64 chips which are in a totally different class. The Intel Itanium 2 is in fact overtaking its real competitors - the processors used in Hewlett-Packard PA-RISC servers and IBM Power-series servers, and those used in Sun Microsystems Sparc servers.
.NET on Friday, causing lots of /. readers to gloat about the death of Microsoft.
HP also dropped Intel's Itaniums because customers preferred _Intel_ x64 Xeons, not for any AMD chip, in contrast to what the deliberatly misleading post implies.
In related news, Apple has sold more IPods in the last week than Microsoft sold copies of Visual Studio
The Itanium story proves that software is more important than hardware. People don't care what the underlying hardware is (generally speaking, of course) as long as it runs the software that solves their problem. Software is much more important than hardware.
As Intel moves 64-bit support to the forefront in their x86 chips, the support will get faster. Remember how Pentium Pro made tradeoffs on speed for 16 vs 32 bit? P2 corrected this.
Intel will surely correct as 64-bit stops being a checkoff item and moves to being a measured performance item.
Right now, AMD holds the lead due to their foresight here. But Intel aren't dopes, they won't get frozen out of their own market.
I think the better comparison is a Toyota to Mercedes. While Itanium has some current advantages (primarily its Machine Check Architecture), and has more advantages coming (Pellston cache self healing, Foxton power management, and Silvervale vitualization), all that is irrelevant if there are no apps.
But beware when Toyota comes out with Lexus (a model with the same build quality as Mercedes). It is easier for AMD to add reliability and virtualization features to Opteron than it is for Intel to change the ISA of Itanium to support 32-bit x86 applications at full speed.
Intel forgot that compatability is not only a feature, it is the most important feature.
Itanic was their 'bet the company on Intel 64' strategy. Now they killed PA-RISC, gave away the Aplha, killed VMS, destroyed the enterprise support network they acquired from Compaq, ditched an in-house MP3 play for the IPOD (I smell desperation) and continue to gut the company.
Dell and Linux will kill them at the bottem end while IBM and AMD64(Linux being able to run in 64bits while Windows does not) are dominating the higer end. They may be able to pull it out with the Xeon but we will see. They are becoming nothing more than a WinTel box shifter.
Innovate? I think not. Carly needs to be fired.
putting the 'B' in LGBTQ+
Xscale is not compatible with any normal motherboard afaik. It is also not x86 compatible. Yes, you can run linux on it, but that does not turn it into a desktop machine.
.18 process, not .13 or .9 (which are less expensive in the long run).
Besides that, it seems that 1 GHz is not available, let alone at 1 W. See also: Xscale processor line-up.
These parts are not that expensive probably, they are manufactured with a
Wow. I didn't even know they included self-destruct hardware!
hp withdrew itanium from their workstation offerings. Does anyone still use workstations? Of course they do, but not very many. SGI, Sun, and IBM still make risc workstations, but they are expensive, and not much better than a high-end PC. It's a market that's more-or-less gone already. Failure in that market doesn't really mean very much.
Merced goes on for years, uses lots of Alpha technology
No it doesn't. There isn't a scrap of Alpha technology in Itanium, not yet. It's still in the pipe line !!
Macka
Absolutely nobody wants one or even cares about it either.
The closest analogy would be to consider Itanium to be an Edsel instead.
I'm sad that everybody everywhere dies at the end. :*(
Here's a funny story. I was at a rockin' party the other day, and I overheard this conversation:
I'll never touch a Cyrix after I saw one give a floating point error.
I laughed outloud and leapt to Cyrix's defense. What about the C7?
I have poured hot grits down my pants. Thank you.
I haven't read every post, but most of the modded ones, and did not see even one that pointed out that what they are replacing their workstations with is Intel Xeons with 64 bit extension, and go on to make it sound like intel created this and AMD followed in their footsteps, which is definitely not the case.
Because the latest Linux distros would be up and running in about 2 weeks, while MS would be working 24 x 7 for months to crank out a buggy Alpha version of XP. Intel rarely offends MS, despite the fact that MS needs Intel more than the other way around.
After all its unit markets share is WAY under 0.01% of total processor units shipped!
;)
-Huh. When people stop making apples to oranges comparisons. AMD sells low end market and itanium is for high end, with some hope of moving downwards over time. AMD sells for desktop expect big sales Itanium sells for highend servers expect lower unit sales, with bigger price...
Yes I made the comparison. Average 64bit processor on access under 1MB of system ram
And most processors sold are 8bit ones... AMD sells lower end of market while itanium sells for highend so volumes are different and so are prices...
Emacs is good operating system, but it has one flaw: Its text editor could be better.
C7 appears to be pretty much the same core as the C3 with a new bus unit and some more security features. Not that much has come out about the C7 yet.
ia-64 is the most dissimilar, but only because everyone else is doing exactly the same stuff. Does the really include any design features not present in some form in ?
x = a->b->c also stumps hardware pre-loading.
itanium 2 doesn't do next-line prefetching, but it does read 2 bundles of instructions per cycle. This, depending on the density of those bundles, does everything that a prefetch might do, and more given available execution units.
Your contention is correct that itanium doesn't solve all the problems that face a modern risc architecture. Does that mean that no one should bother trying? Should processor makers churn out the same stuff and wait for moore's law to make things faster? Hope that multi-core cpus will somehow be better utilized than smps?
The simple fact of the matter is that there is a finite speed at which one can execute a serial sequence of instructions. One can try to execute pieces of code in parallel, but there is finite parallelism in most codes. Processors have been fighting for ways to minimize the percent of that parallel code that is mistakenly executed serially, but one is bounded by the actual structure of the code.
Loading data and instructions from memory remains an extremely expensive thing to do, and it's only getting worse. Really solving the problem would require some radical design that completely undermines current methods of programming. I applaud intel for being daring, and the end result is not a disaster, it simply fails to live up to the hype. As a replacement to pa-risc, alpha, and mips, I think itanium is a pretty reasonable choice. As a replacement for x86, not so much.
audio reinforcement marketing...
l s?Sym bol=AMD+
Perhaps a loud QUACK or maybe a good beer belch to follow every audio mention of AMD.
Yes, the belch would be good. Play up the hard working, not too expensive, blue collar image for AMD.
Hyena bark might do the trick as well, followed by a good redneck rendition of 'hey, lookit this'.
The market doesn't seem overly impressed with AMD
http://clearstation.etrade.com/cgi-bin/detai
youre either misinformed or a troll.
most benchmarks for amd are using either gcc or microsoft compilers in 32bit mode.
the amd64 line has on-chip memory controller leading to significantly better memory speeds than intel counterparts.
in fact the amd64 is an all round faster chip than intel 32 bit chips, despite operating at roughly 1/2 the mhz.
whether amd can continue to scale the amd64 design past 3ghz remains to be seen, but amd have a lot of margin left -- while intel is currently near the ceiling for their designs.
I just finished compiling Gentoo on my rx2600 cluster. Now what do I do with 'em, serve pr0n?
I suspect that Carly got the job during the height of the Dot Com boom largely because the HP Board of Directors were jealous of the successes of the Dot Com companies that, at the time, were overvaluated by factors of hundreds to thousands.
Here was HP, a real technology company that had produced real hardware for generations, and these gimmicky newcomer Web sites (essentially just a bunch of pages with hyperlinks), founded by gangly 20 year olds, were worth billions of dollars. HP's board probably thought, "We have to get in on this action, even though it completely defies logic."
Back in the Dot-Con boom, a lot of companies soared in the market place using "romantic" press releases about their companies' histories. Some of these histories were fakes, or overly simplified tall-tales, but who cared about journalistic integrity in the days of Henry Blodgett (a financial "analyst" who rated highly the companies that his employer was taking IPO) and day traders? To get a sense of the era and the attitudes of the day, look at the Real Video segment reported by Paul Solman in February of 1999 on the PBS news program, "The News Hour with Jim Lehrer" at http://www.pbs.org/newshour/bb/cyberspace/jan-june 99/internet_2-4.html. In other words,
1. Create a "cool" story, which...
2. Attracts the press and media (always looking for good stories so that people will buy their rags or watch their financial "news" shows; more eyeballs means more advertising revenue), which...
3. writes exciting stories that capture the imagination of day traders and other amateur investors, causing them to invest (gamble) in the stock, which...
4. Causes the value of the stock to skyrocket, which...
5. Makes people want it more, which...
6. Goto 2. (Repeat infinitely until the world runs out of money. Or people wise up.)
Thus, Cisco Systems fabricated the story about its founders, Len Bosack and Sandra Lerner; according to the company history, Bosack and Lerner, who were married (how romantic!), wanted to find a way to communicate with each other across disparate networks so they could synchronize the feeding of their domestic cats (how cute!), and voila!, invented the routing technology that became Cisco. In fact, the technology had been started years earlier as part of a funded project before Bosack had arrived from the University of Pennsylvania -- but in the Dot Con boom, reality (and mundane histories) didn't mean anything. (See http://www.pbs.org/cringely/pulpit/pulpit19981210. html)
Likewise, EBay's humble beginnings were also faked, as detailed in Adam Cohen's book "The Perfect Store: Inside EBay" . According to EBay's websites, Pierre Omidyar wanted to sell his fiancée's Pez candy-dispensers, and voila! created the auction web site to solve his problem. The geek and the fiancée(how romantic!), the selling of Pez candy-dispensers (how cute!). Cohen reveals that the story was completely phony, concocted by a PR person, but it helped to encourage press editors to run stories and press releases about EBay.
Even billionaire Larry Ellison recognized the value of the press in warping the logic of the financial world. He hired a CNET journalist , Gina Smith, to become CEO of his New Internet Computer Company (NIC) (http://sanfrancisco.bizjournals.com/sanfrancisco/ stories/2003/04/21/story7.html?page=1). Who in their right mind would hire a journalist to become CEO of a technology company. NIC would tank after the Dot Con bubble collapsed. But it seemed logical during the era, didn't it? Who better than a journalist would be the master baite
...in what way, exactly?
you can build a farm of many amd64's for the price of one itanium, get several times better performance, and failover to boot.
of course this only really applies to stuff which can be parallelized, but still.
ia64 has failed to meet nearly every single stated design goal. i wonder how much longer intel will continue to beat this dead horse.
They are single core licences.
Not a problem with most linux distros
HP was making most of their money from Printer Supplies long before Carly showed.
The world should hate Carly, but the reality is that HP had FAILED as an "Engineering Company" maybe a decade ago and was just skidding along. Carly sucks in a lot of ways, but she shouldn't get blamed for the fact that shitwad printers were/are/will be HP's only profitable product.
You're no Yakov. Sorry.
Ah, yes. "HP killed it" revisionist history.
As someone who spent an number of years (1992-2000) working for Digital ("DEC") in the group making binary translators/optimizers/StrongARM tools/... I actually know a bit about the facts.
Don't blame HP for the cancellation of Alpha. It was smashed by Crap-paq via Mr. Capellas' golden parachute (ok, so the parachute part is speculation). But "Mikey" was the one that cancelled it (destroying API Networks, a joint Samsung/Digital venture doing $300M/year in sales as a side effect).
The Itanic was a compiler-writers dream - permanent (life + 99 years) employment because it exposed so much of the machine to the compiler, requiring it to perform heroic (if not impossible) feats in order to get code to perform at full theoretical capability. An interesting RESEARCH architecture.
However, with Intel's marketing muscle, it was exceptionally successful - it killed Alpha and MIPS utterly, in spite of it probably being a multi-thousand dollar loss on a per-itanic-cpu-sold basis (based upon the amount of truly exceptional engineering talent being wasted on the Itanic - a large number of people from DEC's legendary AMT and VSSAD groups)
But in "defense" of the Itanic, it is a wonderful engine for FORTRAN code which has very large and long straight-line code sequences to perform lots of floating point ops, when thermal conditions (and subsequent cooling costs) are irrelevant.
That is, if you can afford to ignore the refrigeration and power consumption costs, and want to model large, memory-predictable, floating point intense systems in FORTRAN, Itanic might have been a good choice. Otherwise, it wasn't, and that fact was blatently obvious to a lot of Alpha developers from day zero.
rcg
Software is much more important than hardware.
So why can't users of other architectures just ./configure && make install on their important software? Is it that the IA64 compilers still cost too much? Or do you claim that proprietary "[s]oftware is much more important than hardware"?
Please, start making nice calculators again. Designed by people who actually USE calculators every day, with nice keys, you know, the HP signature. The standard by which everything is judged. Hell, RPN might have been the original "think different".
Once upon a time they made some of the best test gear in the world.. now they sell rebranded Apple hardware and third-rate PC's.
Way to go. I wonder what Hewlett and Packard would think of this. (Irony being, of course, the HP story, in context of your post).
..don't panic
The fastest Linux cluster and No.2 on the TOP500 list, the LLNL Thunder, uses Itanium 2s.
Itanium is not the only casualty of its own overhyped marketing.
In the late 90's, SGI had 2 processor projects, follow-ons to the R10k. The Beast, and Alien.
They were hellaciously fast, even by todays standards.
Someone (that means you Forest Baskett) made an amazingly bad decision to ditch these two incredible processors in favor of taking the Red pill. This chart (well without all that pesky data that contradicts the predictions) was part of the rationale.
Bad move.
Many of us pointed out that the Itanium was unlikely to ever come close to PIII levels of sales. This was the justification, a secondary generation of demand for high end machines by the proliferation of high powered processors with lower prices due to economies of scale.
We were ignored.
The sad thing is that we were right.
There are lots of corpses in the IT/computer worlds. Good ideas that died for one reason or the other. Products with massive potential, ditched for political or business reasons.
Then there are bad ideas that don't seem to die. I'll leave you, gentle reader, to decide what belongs in that category.
Finally, there are the walking dead. Alpha until recently, and now Itanium. A fair number of computer companies belong in this category as well. Including ones who bet the farm on Itanium.
Yes, I agree it would be nice if we all could have gotten some of those alternative platforms. But I for one never could afford a $3,000 NeXT or BeBox. To be precise, I have only twice ever [in 20 years] spent over $200 on a computer. Of course, I am limited to PC's and older Macs, but that hasn't been a horrible situation to be in.
The fact is, as much as I may believe in NeXT or any other non-fictional innovator [thinking Microsoft here], the fact is nobody has ever paid me enough to support a bleeding-edge-platforms habit. And that is probably true for a lot of us. I am just happy *any* workable platforms have made it down to my income bracket!
The only place some decisions could have been made differently is at the business level. The business community really screwed up choosing MSWord over WordPerfect, and generally looking up to B-b-b-bill as a god. But that is water under the bridge.
Okay, and the judiciary really screwed up too in losing its nerve about antitrust-law abuse. I mean, any idiot can see that no two of [OS, Browser, Office package, Development package] can ever be monopolized by one company without quickly monopolizing the whole industry. But the OSS posse is working on ameliorating that.
Luckily for intel, some companies were run by PHBs that didn't have a clue about processor design. In this way, intel managed to kill off development of Alpha (the fastest 64-bit processor in the world), MIPS and PA-RISC. What a way to nail your competition.
Some people were more forward-thinking and that's why POWER (and PowerPC), UltraSPARC (and SPARC64) and AMD64 survived or came about.
intel managed to completely and utterly fail to produce something that people wanted. It's expensive, hot, difficult to program, doesn't have an established software base (or operating system), and has lackluster performance on everything except the SPEC floating-point benchmarks. Thus it has found a niche amongst scientists and engineers with more money that sense and very good air-conditioning.
Over the years, intel and HP have tried very hard to silence the academic and professional itanic dissenters. Alas the PR and FUD machinery couldn't cope (as with all dictatorships) and the empire has crumbled.
It was really funny (and somewhat sad) when a couple of years back the IT press was talking about "the transition to 64-bit computing" when most people, except intel (actually, including intel, just not with itanic) had done it back in the '90s (DEC, SUN, SGI, Cray (maybe the 80's or 70's), HP).
Rather than being a radical new architecture, itanic was actually based on theoretical supercomputer designs of the 1970s that were overtaken by developments in RISC processors in the 1980s by IBM, Sun, SGI, DEC, Fujitsu and NEC.
However, those with the $$$$$$ get to write history, and as I mentioned above, the FUD machine managed to silence many credible critics. Perhaps this will be forgotten. In this case, the market has spoken.
What really bothers me, is that back in 1988 intel produced an absolutely brilliant processor called the 80860 and it died a death. It was genuinely ahead of its time, Unfortunately, poor marketting and MS-DOS sent it to an early grave.
Stick Men
>AMD is estimating 1.5 to 2 million AMD64 chips in Q4
That estimate of 1.5 to 2 million is for all K8 cores. However, the new Semprons are K8 cores but have 64-bit disabled. So the real number of AMD64 chips is lower.
It is interesting that customers are still buying Alpha workstations even though HP has been trying to kill Alpha by not putting money into Alpha R&D.
p /3 413621
http://www.internetnews.com/ent-news/article.ph