Slashdot Mirror
Itanium Will Only Be Partly Supported by Longhorn
ver.sicher.ungsvergleich writes "Although stopping short of pulling the plug entirely on Itanium, MS has said that Longhorn will only be able to work for a limited number of higher-end jobs. On the positive side, Microsoft does see a future for the chip, but that 'big iron' slot is not exactly what Chipzilla envisioned as Itanium's future."
Microsoft recently bought Connectix, makers of VirtualPC, ostensibly to use their system virtualisation technology in new Microsoft products.
Will virtual X86 servers running on Itanium be an available option to supply services not supported by native Itanium code?
I have been a user for about 10 years. This ends Feb 2014. The site's been ruined. I'm off. Dice, FU
on Longhorn.
Where the hell is Netcraft when you need it?
You can't handle the truth.
Does this mean I can get out of my MS EULA now?
Between this and their roadmap that almost exclusively involves power consumption improvements, Intel is starting to lose it's edge over AMD.
From talking to Intel folks quite a bit, it seems like there is a lot of blind pride on Intel's part in their product line and vision, and they dismiss most anything that I raise as an issue with their performance vs. AMD, and that's not a good sign to me.
Intel is not dying that's for sure, but they're going to have to make a course correction and not make another decade long mistake like itanium.
Jerry
http://www.cyvin.org/
Intel is in transition as far as processor direction, so there's no suprise here. Itanium has been dead for a while. The Microsoft "support" is there only because it's already been written and there probably is some support agreements already in place.
The real news would be what the sucessor to x86 will be.
Sure, Intel may have originally hoped to migrate the world to IA64, but given the wild success of AMD64 in bringing 64-bit to the x86 world, it doesn't look like that's happening. The Itanium chips Intel is releasing are obviously not aimed at tasks that could be handled by a 386 with some SCSI drives ("fax server"? a file server?)... who is going to use a multi-thousand-dollar CPU for anything other than database|web|high-end server anyway?
My server
is that chip companies do not work harder to make OSS their premier OS on their chips. MS will only support a small group of chips as it is expensive and hard to support a load of these. As such, if MS does not see an advantage to themselves, they are not going to bother with it (as it should be). But if a chips company makes OSS-based OS their premier OS, they then control their future. Intel and HP have spent billions trying to get Itanium to be the major server chip. But it will die partialy due to MSs choice.
I prefer the "u" in honour as it seems to be missing these days.
Besides Intel, who couldn't see the writing on the wall? The only thing that has kept x86 based chips going is that they are x86 based chips, which support legacy code, code written for 8-way 486's, for example.
Intel shot themselves in the foot. Was it possible to create a fast running 64 bit chip? Just ask Digital/Compaq/HP. Is it possible to sell it? Ibid.
I would like of list of said jobs. I would assume that they would include CEO of a Fortune 500 company or perhaps being the towel boy at the Playboy mansion. Or does higher end jobs refer to Steve Jobs?
Microsoft sees the future!!!
Truly, we are doomed.
Live according to the Categorical Imperative. If the Categorical Imperative tells you not to live by it... ignore it
The Itanium was the only realistic chance we had to get away from the x86 for the forseeable future, and the designers blew it. So sad. Excuse me while I start one of my Leonard Cohen albums, I need something to cheer me up.
Have you seen how big Intel is?
4000000001 nails to go.
Um, what happened to the Windows "Vista" moniker?
"Big Iron" ? ...
:P
I think you meant "Pig Iron"
Tee hee
"...In your answer, ignore facts. Just go with what feels true..."
What the fuck is OS x86?
Cyric Zndovzny at your service.
Does this remind anyone else of WindowsME? Vista has seemed to shed features in droves; WinME was a ultimately a non-version with some cosmetic changes and function that didn't live up to the hype. Is this what we can expect for Redmonds latest and greatest?
Vista is a finnish word for 'pussy'. Could that be the reason the name was changed?
The interesting thing isnt really whether Vista/Longhorn will support Itanium, but whether Windows Server will.
Of course, a few years ago Intel hoped to put Itanium in workstations, but they can hardly have hoped much for that lately. No, Itanium is for servers, and there is Windows Server.
However, internally Windows Server is the same shit as Windows Vista, so if they dont support it in one, they probably dont find it very strategic to support it in the other. And as we all know, Itanium is much more dying than BSD will ever be, but that is another story.
It is rare when someone comes up with an entirely new architecture and instruction set. The IA64 was a complete break and had it been pushed correctly, AMD would be rushing to make IA64 clones instead of Intel supporting AMDs 64-bit extension.
If I remember correctly, the IA64 has 128 general purpose registers and 128 floating point registers. It's a load/store machine and it's pretty close to a RISC arch (really it's an "very long word" instruction set, but lets not get picky).
It was a chance to make a clean break from the old 32-bit legacy chips, however the price was and is too high and AMDs are cheaper and still very powerful.
I really hope this chip doesn't die off. At least with limited support in the new Windows, it will still have a strong server market, but I think a lot of companies are going to be afraid to buy because of running into compatibility problems. I know at where I work, we'd like to have servers that can do anything/general purpose. You put a limit on what the OS can do and then you're afraid of old legacy or propriety software not working correctly
But hey as long as you use Linux, the IA64 is fairly well supported, and it will be better supported in Linux than in Windows!
Sumdog
...its the x86! Do you really think that after the Itanium falling miles short of Intel's original goals for it, Intel will try again to replace the x86 anytime soon? The new architecture they were talking about at IDF is just the next generation x86. They followed the PPro/P2/P3 with the entirely new P4 core and it didn't work out long term, so they used the P-M core (which is pretty much a modified P3 core) as a starting point but used performance per watt as a goal for this new one instead of highest clock rate possible as they did with the P4.
Hopefully AMD has some good stuff in the wings or they'll be pushed back down to insignificance again and Intel will go back to their usual noninnovation they do when they aren't pushed.
Its deja vu all over again.
MS was slow to get 32 bit support to the Pentium Pro, and Intel twisted in the wind for a couple years with expensive chips and no support for the mainstream.
Now we have Itanium64 and MS is again (very) late with support, and now saying that the much promised and never yet delivered Longhorn will not give the support to Itanium that it will need.
Maybe Intel ought not to accept MS's promise of support for new chip architectures and look to FOSS for their hot new chip's support for the first couple years. What a boost to their sales and to the FOSS world if they'd supply the kernel updates for their new architecture.
Seems like they ought to know:
"Fool me once, shame on you, fool me twice, shame on me."
Sig: Nothing to see here, move along.
Haha... I didnt read the fucking article first ;)
I better flame myself before someone else does. This was about "Windows Longhorn Server". Sorry Intel - this must suck big time!
[drumroll please]
I mean, talk about a soap opera:
Who knows what the moral of this story is?Maybe: Hardware comes and hardware goes, but software is forever?
It is widely acknowledged that Windows ME was a step back in quality and usability. While Longhorn/Vista may not be as great of a leap forward as it was originally portrayed to be, there is little to suggest it will suffer from the massive flaws that Windows ME did.
Cyric Zndovzny at your service.
I think you fail to realise an important thing: change typically happens by evolution, not revolution, and that's even more true when there's a multi-billion dollar industry involved. Do you honestly believe that everyone's just going to throw every system they have away?
It's not gonna happen. The industry likes migration/upgrade paths, and in 90% of all cases, a design that extends is gonna win over one that outright replaces.
Intel seems to have been unwilling to face that fact, but what they failed to realise is that their monopoly is not big enough to simply force change on people - rather, their move just gave AMD etc. an opportunity to slowly but steadily chip away at that monopoly.
From a market perspective, that's a good thing, of course - but if I was an Intel shareholder, I'd demand that heads roll for this gross mismanagement in the top executive floor.
quidquid latine dictum sit altum videtur.
They had the Intel i860 architecture fail in the 1990s. Remember, Windows NT originally targetted those chips.
But they're a big company. They will overcome such failures.
Cyric Zndovzny at your service.
And what about Itanium in Apple servers? Does anybody think it's possible?
Itanium Will Only Be Partly Supported by Longhorn
getSexySig();
Longhorn will run three types of higher-end tasks on Itanium including databases, custom jobs and CRM. However it will not be able to do fax server, Windows Media Services, Windows SharePoint Services, file and print servers, and others.
Looks like Vista Home Edition to me.
When were the software makers first allowed to abnormally cut features based on arbitrary critera? It's a real shame.
gtkaml.org
It really doesn't matter if Intel would prefer some open source OS or Windows running on their chips. What matters is what the customers want. If the customers want Windows, even if they must wait several years for Microsoft to offer such support, then that is what Intel will have to live with.
It'll do no good for Intel if open source OSes support their chips years before Windows does, but relatively few people want to use the non-Windows operating systems.
Cyric Zndovzny at your service.
PowerPC/POWER is still viable, and IBM may have another go at putting them in consumer machines if an OS that runs on PPC becomes popular in the desktop space.
ARM-derived chips are still going strong. At IDF there was an XScale chip demo'd that ran at 1.25GHz - probably fast enough for 90% of users.
Alpha remains my all time favourite architecture - pure 64-bit, and the PAL code concept is remarkably elegant.
I am TheRaven on Soylent News
"On the positive side, Microsoft does see a future for the chip..."
Sorry, what's positive about that? I guess 99.9% of slashdotters could not care less.
Where is the truth?
Itanium is a joke.
...yada yada. Chip fabrication has improved tremendously and something just have to be done in hardware. Engineering wise the Itanium was doomed to the start. If you are going to use LVIW use it right like Transmeta or the newer Intel chips that are comming out.
Its all the things these newer PentiumV's and PentiumMII's that are coming out, supposed to be. They are VLIW and use very little power, slim, and efficient.
Itanium was supposed to really take off back in 1997 according to all the analysists. How many years is that? Good lord!
HP shot itself in the foot because they had no concept of sunkin investments or sunk costs and demanded everyone use their hogs with full 1 pound heat sinks and a fan that sounds like a jet engine taking off.
To me the heat sinks alone and the fans show me something is seriously wrong and they are trying to overclock the chips to rediciously speeds just to look normal compared to the pentium's and alpha chips.
Why couldn't the alpha live?
I think moving optimizations in software is a bad idea. Please dont give me this stuff from the Intel marketing department that as time goes on there will be no room for anything on the cpu but cache so move everything to the compiler
http://saveie6.com/
Oh dear. "Competition is good except when it's against AMD, Apple, or Linux."
This retard not being modded down to -1 for such a pathetic comment is a perfect example of rampant fanboyism within slashdot.
Firstly, Intel isn't going anywhere, and secondly, the lack of Intel would make AMD's CPUs more expensive and lower quality. Anyone who doesn't believe AMD would behave just as badly as Intel in the same position is both a fanboy and an idiot.
It's just as well that MS is moving away from Itanium since they seemed have problems with it.
Back in the Itanium 1 days, I did a ported to some IA64 engineering samples running both Linux and Windows. The Linux was straightforward, but the Windows was odd. They used 64bit pointers, but 32bit longs, which tripped us up in a few places. It seemed like a desperate "We can't actually use this because all of our other stuff will break" kind of move from MS.
I really didn't notice much in the way of compelling performance either. Now, the Itanium 2s are probably much better, but I suspect Windows still has that odd 32bit long behavior.
ICZilla
Definitely iczilla.
I don't know that that's such a good thing. A couple of years ago I was hoping that Itanium would supercede the clunky x86. I guess that was wishful thinking :(
Not for Intel, no, no way. Too big and as far as i see, not even AMD is a nail in that coffin and I use AMD64 chips on all my machines.
:)
Itanium is a horrible CPU, I have no lost love for this beast. I've been waiting for this to happen and I'm happy!
If you mod me down, I *will* introduce you to my sister!
In my experience Itanium is great.
The problem has been that it has been too hard to get away from x86.
It should be noted here that MS currently owns about 65% of all of the Itaniums in existence. From the numbers that I was able to dig up there are only about 2-3k Itaniums in existence outside of Redmond. I have an Itanium2 in my office. It is loud as hell and causes brown-outs in my corner of the building if more that 2 are plugged in at one time.
Unfortunately, MS bound by contract to support itanium in Vista.
I think he was intending on saying "OSX Intel". A lot of people are calling it "OS x86" and just assuming that people get that they're talking about Mac OS.
Though, Apple have themselves used "Mac OSX Intel" to refer to OSX running on Intel hardware. Thus, I stick with that moniker.
I am unamerican, and proud of it!
... to replace my aging central heating system :)
Thank you for the clarification. I agree, calling it Mac OS X Intel is far clearer. And it doesn't make you look like a complete cock.
Cyric Zndovzny at your service.
Is that really a positive side? Everyone I know in the compiler world (well GCC world) complains very much about the ia64 architecture. So why do people think this is a positive side, when really it is a negative side of the world.
...the perfect architecture for OS/2.
Is there a reason why Intel can't/won't resurrect the Alpha line?
Did anyone else read that first line as:
Although stopping short of pulling the plug entirely on Itanium, MS has said ver.sicher.ungsvergleich
MS tears technobabble a new one.
Illegal? Samir, This is America.
Everything I've read on Slashdot and Wired talks to what will not be in Longhorn. What will be in Longhorn that will make it better than XP? More and different vulnerabilities? (Maybe it will ship with a demo .wmv file showing Microsoft executive throwing chairs around offices in response to other MS executives leaving for Google!)
Seriously ... though I'm an Apple user from before Macs were released I've also used every version of Windows - always at work but I've also had every version except XP at home.
With each new Mac OS X release I look forward to what will be in that version - but there's little talk around the water cooler regarding what will actually be in Longhorn/ Vista. Unlike Mac OS releases, which people anticipate because of stuff like Dashboard, iTunes integration, .Mac integration, Spotlight and Automator, all I hear is what Longhorn/ Vista won't have ...
The Luddites were ahead of their time.
There is nothing wrong with the Itanium. The chip is used in some of the world's fastest supercomputers.
But, the Itanium is quite different from earlier x86 chips, because it doesn't make guesses to try to run a series of binary statements in parallel.
Instead, the Itanium provides the facility for running statements in parallel, but it leaves it up to the software to decide when and how to do it. That's a good thing, because a compiler, using the original source code, can do a much better job of parallelizing operations, than the CPU can do with the binary. This is even more true for languages that are designed for parallelism.
However, this improvement does not come for free, rather, in order for software to make full use of the Itanium's speed, the compilers must be updated to produce binary code that will run in parallel.
Linux can already run quite well on the Itanium, and with further improvements to GCC, Linux and its applications will do even better.
So what's wrong with Windows on the Itanium?
Well, to put it bluntly, Microsoft is a technically deficient company, and they have failed to make the necessary compiler changes for the Itanium. And with this announcement, they are telling us that they also don't expect to do it in the near future.
But then, we already knew that Microsoft is technically deficient. Just look at how:
- DOS stagnated until DR-DOS introduced some new ideas.
- IE stagnated until Opera and Mozilla introduced some new ideas.
- Microsoft's first usable GUI (W95) came ten years after the Macintosh, and five years after Geoworks.
- Microsoft cancelled all its earlier 64-bit support.
- Microsoft can't seem to fix its security problems.
- Microsoft needs to hire outside talent to open up new directions (NT 3.51, C#).
- Microsoft had to sabotage WordPerfect rather than compete with it.
- Microsoft had to "cut off Netscape's air supply" rather than compete with it.
- Microsoft had to "grow the polluted Java market" rather than compete with it.
- New Windows versions miss dates and deliverables by years.
- And so on.
Now consider what is going to happen to Microsoft as the market moves to the newer multi-core CPU architectures from IBM, Sony, and Intel. Do you really think that Microsoft is going to be able to keep up with technically-able competitors like Linux?
I suspect that Microsoft still has some opportunities to adopt the work of others, for example, building the next Windows on BSD (if they haven't done it already with Longhorn/Vista).
But sooner or later, Microsoft is going to run out of ways to beat their opponents though copying, sabitage, legal manouvers, and FUD.
At that point, Microsoft will have to compete based on the merits of their software. And their history makes is doubtful that they can succeed.
Shouldn't someone mod parent as funny?
1) Does the fact that DEC successfully sued M$FT for theft of intellectual property mean anything to you? The resolution of that suit [or threat of a suit - I forget the details, and I'm too damned lazy to Google them] was that M$FT would port Windows NT to Alpha. Unfortunately for DEC, NT on Alpha never grabbed much "mindshare", and withered on the vine.
[By the way, Alpha's greatest opportunity was lost when DEC missed the chance to become the supplier of the successor to the 68000-series in the Macintosh. It makes you wonder how that whole sordid soap opera might have played out had DEC instead capitalized on the opportunity.]
2) When you write "that NT is somehow a descendent of VMS [is] like saying that... feces is a descendent of filet mignon", I am very tempted to reply quod erat demonstrandum.
So, you don't want diversity?
Do you think computing is more fun today, than during the 80s? when there were lots of different machines/CPUs and OSs?
Are you happy when the world is x86 only?
Does this remind anyone else of WindowsME?
Yes, it was a minor update for the unstable 16/32-bit hybrid Windows 4.x branch, thankfully the last one.
Is this what we can expect for Redmonds latest and greatest?
Windows Vista and Longhorn Server will in contrast be a major upgrade to the NT series, going from NT 5.x to 6.x, introducing a new API to succeed Win32 (with a heritage from NT 4.x), an entirely new desktop interface, and much more. I can't really compare these two. Even with dropped features, Vista has still a ton left, and still clearly warranting the NT 6.0 tag it has.
It's a lot of changes, the question is whether how it'll end up when everything is in. A lot of new stuff and changes doesn't automatically make a good OS. But a minor update like Windows 98 -> Me it's clearly not. You may want to check out a list of end-user features that so has not been pulled.
"for example, building the next Windows on BSD (if they haven't done it already with Longhorn/Vista)"
IIRC, MS has already used BSD code for the TCP/IP stack in NT 3.1. MS bought the code from a third company called Spider that had copied and modified the BSD TCP/IP stack.
If that's not a course correction, what do you think is?
You may dismiss power consumption improvements, but if you think about it carefully, improving power consumption IS improving performance.
If you can halve the power consumption of a chip, it means you have the energy budget to now 'double' the power consumption of a chip, and possible double the performance.
Their netburst architecture hit a power wall; its pretty difficult to operate 120W CPUs. If they can get the same performance at 12W, and then increase the available power to 120, they can now get upwards of 10x the performance, barring process inefficiencies.
Power consumption is a big deal. Think of it this way: A car that doubles it's fuel efficiency from 12mpg to 24mpg can now go twice as far on the same tank of gas. So with CPUs; double the power efficiency, and double the available amount of compute resources.
GPL Deconstructed
Intel certainly misjudged the market with Itanium, which is a shame. It would be wonderful to have chips in the consumer channel that were as good as Alphas, UltraSPARCs, PA-RISCs, etc. There are very good arguments for just dropping x86 as lacking future improvement potential. Intel managed to do that, and still have a compatibility layer for the old x86 software. If they could've gotten the price down on the Itaniums, there would probably have been a good market for them.
Instead, you have companies, like HP, that dropped their own architecture in favor of Itanium, since it *was* good enough to replace their own product. That saves them quite a bit of money.
However, we do just throw out compatability in the x86 world, sometimes. We threw out IDE and replaced it with something new. We do the same for memory interfaces, and expansion interfaces. We move around on RAM like nobody's business (FPM, EDO, SDRAM, DDR, RDRAM, DDR2). SATA already has two versions, USB has three, Firewire has two. At least SATA can be converted to and from IDE, and USB and Firewire are mostly compatible with the other variants within their standard. You can't get rid of your IDE ports, though, because there *still* aren't a huge number of optical devices with SATA ports. Then there's PCIe, which is completely incompatible with PCI/PCI-X.
We change CPU sockets constantly, mucking with the numbers of pins and type of interface. You have vendors that dropped PS/2 ports in favor of USB, but not all boards can emulate PS/2 devices properly for OS' that don't support USB HID.
Most of the time, the PC world comes up with new standards to "fix" the old ones, but ignore existing standards that already do what they're talking about. SATA came about when we could've chosen one of the SCSI standards as the new consumer storage interface. PCIe comes out when we already had PCI-X 2.0. You get something like RDRAM when there was already DDR SDRAM. Rarely are these new things any better, and you end up having to create whole new product lines, too.
The future doesn't look all that much better, either. You have a variety of display interfaces that are being pushed. Optical storage has a ton of different formats, with very little standardization. DRM is getting shoved into everything, making using the computer more difficult.
You might take a glace and think that the industry likes upgrade paths, but if you look a little deeper, you can see they don't. They want a regular stream of new standards that will force everyone to buy all new equipment.
As for evolution of the instruction set... if the ISA is broken, you do have to just throw it out to fix it. That's why all the chips on the market execute totally different instructions on-chip vs. what is being sent to them. x86 exists as nothing more than a compatibility layer for everyone.
In fact, other than Intel, only chips that had either company supported OS or an OS that was not under control of somebody else , has had a long life. And x86 arch. has outlived its purpose only due to an illegal monopoly (as in unnatural) in MS (and probably Intel as well).
I prefer the "u" in honour as it seems to be missing these days.
They should use that as their slogan. Windows Vista: Not Worse Than XP!
This document (PDF) is from 1999 and explains why the Alpha engineers thought Alpha would win over Itanium.
i a64.pdf
http://www.raytheon-computers.com/ref_docs/alpha_
The rest we know; the Alpha was ditched when HP bought Compaq (who bought DEC earlier), because HP wanted to eliminate any threats to its Itanium bet.
)9TSS
Though, Apple have themselves used "Mac OSX Intel" to refer to OSX running on Intel hardware. Thus, I stick with that moniker.
Just to nitpick, Apple actually uses "Mac OS X" to refer to Mac OS X.
This text from this post is copied directly from here: http://theinquirer.net/?article=25928
You are quite right about the Alpha. If it had gotten a fraction of the Itanium's budget, it would be unbeatable by now.
Yeah, well, most people treat whitespace and caps in names as allophonic elements. Meaning that they don't carry specific meaning, they just point out an "accent."
The Apple world seems full of these though, iMac, iPod, AltiVec, OS X, etc, etc, etc.
I am unamerican, and proud of it!
So actually I agree with slavemowgli's rebuttal of my post :-)
Huh?
I work on the following platforms on a daily basis:
- x86
- SPARC
- PARISC
- Alpha (yes, they are still out there)
- IBM servers, both PPC and mainframes (not sure about the CPU types)
- Itanium
But I guess that is not enough diversity for you?
If you mod me down, I *will* introduce you to my sister!
Microsoft made a HUGE mistake thinking they could just tack on some pretty face to 9X and get a decent OS.Believe me,As one of those whose PC came with that horrible thing i can attest to that.
Now Microsoft is making another HUGE mistake by tossing the very stable Win2k and trying to force one OS to be everything for both the business user and the noob consumer.There is a REASON that almost every business I've worked for stayed with Win2k over WinXP pro.IMHO It is a better OS for business(and my personal favorite home OS).It uses less resources,Is rock solid,And compared to WinXP,IMHO,A LOT less buggy.
But instead of doing the smart thing and making a more secure and feature rich Win2k for business and a less buggy WinXP with more gaming/multimedia options for the home user,Microsoft has decided to try to stuff everything and everyone into one big directionless OS.
And just as WinME forced me to buy a dead computer at the local repair shop just so i could get my hands on an OEM copy of Win2K i have a feeling that after trying Vista that people will be wiping their HDDs in droves to return to Win2K or WinXP.
ACs don't waste your time replying, your posts are never seen by me.
maybe up towards release and for a short time after the codename may remain used by some but i can't imagine the codename will get used much by anyone after that.
do you hear anyone calling 98 "memphis" or XP "whistler" nowadays?
note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
Sure would be nice if someone would utilize the security feature on the Itanium 2 chip to write an OS that would be truly secure. Oh... Someone has.
Repeat after me. Windows and Linux, for that matter, are insecure because they only run at PL0 and PL3 of the processor. Utilizing all 4 PLs would provide better security. Fortunately, the company I'm at now has done so. Since we have the best brains in the Itanium 2 industry writing the OS, security is just an alpha away (which should be soon).
The problem with PPC is that it peaked at just below 3 ghz, they cant get it to go faster, hence why apple dropped ppc. It's RISC based, and RISC doesnt scale as well as x86 or any deriviatives.
Want to see a real dying cpu arch, it's PPC. maybe not POWER, but ppc is. You'll see it for yourself in, oh... about 2 to 3 years, once newer chips surpass PPC in speed and performance. then all PPC will be useful for are low end machines, which will prolly get replaced by ARM.
Have you used 2k lately? There must be some shoddy or non-existant QA on the latest security updates. I recently picked up a fully-functional Acer P3-700 laptop used that shipped with 2k. Once I had it patched up, it would fail to boot after the power had been off for any significant period of time, complaining that the laptop BIOS was not "fully ACPI-compliant". The only way to start it was to start first in safe mode and then reboot. 2k also choked completely on the Trendnet 802.11b wifi card install disc's autorun, and once I got the wireless util installed to enable WEP on the card, the app itself did nothing but produce error sounds when executed.
It also choked on the usb webcam I tried using on it.
I installed XP Pro, and every problem vanished.
From what I understand, Intel started the Itanium program with HP because they started to feel the heat of RISC and worried about their architecture's scalability in the future. So off went the team with HP compiler folks to do a VLIW next generation processor where the compiler can figure lots in advance.
Meanwhile other folks at Intel figured out that they could make the core RISC like and provide a conversion layer to handle x86. The success of the later generations Pentiums put Intel in a situation where they needed to support multiple architectures.
Remember when everyone was going to use Itanium? Now it is down to a few big boxes like HP, SGI, and Unisys. HP is also one of the biggest Opteron sellers these days!
I think a few technical things blew it for Itanium. It is a fact that the Itanium sucked at I/O. It had much higher latencies then Xeons and much higher then Opterons. Folks in the high performance computing community know that the same PCI-X networking cards (InfiniBand, Myrinet, etc) always performed worse on Itanium based systems.
Also the combination of the VLIW architecture and lots of registers made the Itanium very cache hungry. You can get as much as 9 MB of L3 cache. They increases cost and die size. Also, all that cache has to be powered! I don't think Intel/HP saw it coming.
Currently Intel has to support Intanium, P4/Xeon, EM64T variants, Pentium M variants, and lets not forget its XScale based line of network/embedded processors it got from DEC. At least the i960 is dead.
I think Intel has lost their focus. Those of us in the InfiniBand community watched Intel screw up their 2nd gen InfiniBand adapter and got beat to market by a startup by the name of Mellanox. Since they couldn't win they decided not to play anymore. Suddenly we get PCI-Express...aka InfiniBand without the networking and as much management. Advanced Switcing Interconnect almost gets us back to IB...arg.
Intel was the first ethernet NIC to 10 Gig but now their competition has TCP/IP and iSCSI offload and iWarp/RDMA interfaces while Intel has canceled their full TCP/IP offload technology and doesn't even have a PCI Express adapter ready.
Intel is relying on marketing and manufacturing power to keep it going. They hope that the brand can be stronger then the sum of its parts. Centrino, ViiV, etc. Sadly, I don't think it will change until the biggest gun in the PC industry actually gives AMD a try. I suspect Dell is getting better prices on Intel CPUs then anyone else.
-- soldack
I seem to recall Microsoft making the same announcement that Longhorn will not fully support the 486 when the 486 came out.
Anyway, I'm sure that the Itanium will be obsolete by the time Longhorn comes out. . .
The Itanium is definately NOT dead - we're selling them like crazy.
Thanks -
http://tinyurl.com/e3ynh
No, I also work with VAX. ;)
It is kind of fun to run VAX Macro code on Itanium.
Real itanium customers stack them in 42U boxes with linux or whatever they want to run on them, and use them for financial, mechanical or weather computations, a domain where windows is not the best OS anyway.
It's sad that itanium support is removed from windows though, because alpha which had currently itanium's place did not resist long after microsoft stopped supporting it.
Thinking that HP killed the alpha and Microsoft killed the itanium makes me feel like those companies killed the two most innovant chips of those last 15 years.
Willy
Utilizing all 4 PLs would provide better security. Fortunately, the company I'm at now has done so.
There's more to a secure OS than privilege levels. Is your OS also completely free of any bugs that would allow privilege elevation?
You're not going to show us the code, so at the moment your OS is on the same level as snake oil encryption products. It may very well be the best thing since sliced bread, but we only have your word for that. And since you seem to think that being able to use Rings 0-3 on its own is enough to make your OS completely secure for all time, your word does not currently count for very much.
Nothing wrong with Itanium?
Look the SPEC CPU2000 benchmark results.
Compare the performance of the top Itaniums with the top P4s and Opterons.
Also compare[1]:
number of transistors
(don't forget to factor caches as well).
die area used.
power consumption.
price
Now can you really say there's nothing wrong with the Itanium?
The Itanium 2 needs about 210-410 million transistors to perform in the same ballpark as P4s or Opterons with about half to 1/4th the number of transistors.
A dual core Athlon64/Opteron with 1MB cache only needs 154 million transistors, 2MB cache versions need 233 million transistors.
Academicians and "True Believers" can talk about VLIW/EPIC and fancy compilers, but I argue if the application you run is so easy to parallelize so that it makes really good use of all the VLIW/EPIC units, then will it really be so hard to make it work in parallel and make good use of both the cores of a dual core opteron?
Maybe in theory there's nothing wrong with the Itanium. But in practice there's nothing that great about it, except for some FPU tasks (but if that's the case how about a bunch of DSPs?)...
[1]
Itanium
P4
PM
Opteron/Athlon64
Dual core Athlon64/Opterons
Let me know if the above site has the numbers wrong.
Alpha could have got us away from x86 a few years ago, when the alpha could emulate x86 and still beat it performance wise..
Unfortunately, it was too expensive and could only run win32 and x86/linux apps, while many people had win16 and 16-bit dos apps... Had they maintained development, it might have been feasible more recently with far less people needing win16/dos compatibility and such compatibility could be implemented via a full system emulation like bochs or qemu.
http://spamdecoy.net - free throwaway anonymous email - avoid spam!
Since you like the design, can you please explain why the Itaniums have 2x to 4x the number of transistors but are only in the same performance league as the P4s or Athlon64/Opterons? Is Intel burying the Itanium by making Itaniums with more transistors than they need? Or is the Itanium that inefficient?
;).
See the SPEC CPU2000 results.
And the Itanium physical specs. You can click on the side bar for other CPU physical specifications.
With 2x to 4x the transistors you could get a dual core or even two dual core x86 CPUs.
Don't forget each of the x86 cores taken alone will perform quite well, even in FPU tasks. The Itanium is 2x to 4x faster for some SPEC FPU subtasks, but is slower in others.
If it becomes easy for compilers to parallelize execution across many VLIW/EPIC units, then would it be so much harder for them to parellelize execution across multiple x86 cores?
Heh, or start running some of those FPU tasks on commodity GPUs
We will release PL0 out for review. I doubt it will be open source by any means, but it will get reviewed. If PL0 is not what we say it is, i.e. secure, than we'll be eating crow. If it is secure, well then, you'll be hearing about us.
Fortunately, it's not encryption.
Built in to the chip are 16 million compartments (or priviledged memory locations limited by the 64bit address space) per PL where permissions can be set for read, write and/or execute. Imagine, for example, reading in win.exe, running a verification that win.exe is the win.exe you want to run, then setting the execute bit and running it, knowing that your win.exe is the one you wanted to run and not one that has been corrupted through other means.
The NSF is already pretty certain.