Follow Slashdot blog updates by subscribing to our blog RSS feed


Forgot your password?
Check out the new SourceForge HTML5 internet speed test! No Flash necessary and runs on all devices. ×
Sun Microsystems

64-bit Solaris Tests Successful 108

mulan writes "Following a successful email sent from a Solaris64 box, Sun announced today that the Solaris Operating Environment is running on engineering prototype systems based on Intel's Itanium processor. The press release is on line, while meatier details, white papers and documentation are available at the Solaris64 developer center. "
This discussion has been archived. No new comments can be posted.

64-bit Solaris Tests Successful

Comments Filter:
  • by Fizgig ( 16368 ) on Monday October 25, 1999 @11:37AM (#1588720)
    I don't doubt that, Bruce, but I seriously doubt you got a Xeon with 2MB cache. I'm seeing $3680 as the minimum price on the net.
  • The American Revolution has a lot of similarities- we fought the English Empire, won our freedom, and went on to forge our own little empire. The sun has set on England, but it shines on America 24/7. The rebels have become the establishment.

    Revolution is a fine idea, but what happens when the empire is overthrown? If you don't like Solaris then quit bitching and be constructive. The only thing Zealotry proves is that you''re a Follower, not a Leader. The fact that you haven't thought things through enough to realize that if it involves computers, it's news to SOMEBODY, speaks of a high degree of self-centeredness and possible egotism. Unless your nick is CmndrTaco or Hemos, you don't speak for Slashdot (and no one speaks for the users). You speak only for your own narrow little mind- and who wants to hear an uninformed opinion, anyway?

    You can be right, but at the bottom line the people are going to believe the man with the better delivery, not some arrogant loudmouth.

    Case proven and closed. Try using your mind, if you have one. Being trendy isn't all there is to life.
  • Well, I'll have to get rid of any Ultra Sparcs that I run across - silly attempts at an 8-way box that scales better than NT or Linux on an x86. Don't get me wrong, SMP on Linux is getting better, but my personal experience with Solaris on multi-proc Sparc boxes tells a story of a more mature SMP implementation. Solaris x86 isn't nearly as cool overall as it is for the Sparcs, but that should be somewhat expected - more of an afterthought...

    The rest of your post reeks too much of moldy trolls and flamebait, so I won't qualify it with much of a response, aside from this: I think Linux is the Greatest Thing(tm) since sliced bread, but I have to admit that it isn't perfect (and certainly far more hackable by default than OpenBSD). Advocate all you want, but the position you are taking sounds pretty uniformed and inflammatory to me...

  • Roll the wayback machine back to 1991. Some little O/S called OSF/1 was booted on an Alpha.


    there are 3 kinds of people:
    * those who can count

  • > as the "32" suggests, don't support a 64-bit flat address space

    My point was that their code was already architected for both memory models (can you say "#ifdef"? I knew you could).

    As for the instruction set, take a quick look at the site. They emphasize backwards compatibility with existing Solaris x86 binaries. They probably only "ported" the essentials (memory manager, program loader, etc.) and ran everything else in IA32 compatibility mode.

    For a commercial system like Solaris, the backwards compatibility is more interesting than anything else. Remember, IS manager types are easily spooked. Demoing a mix of IA-32 and -64 binaries would be in their favor.
  • Is that people who are less versed in the arts of Dry Comedy may take it as wrote and reply accordingly. I think a lot of bonfires on slashdot get started this way- someone makes a snide remark like "MacOS can't multitask" (for example), and bring your marshmallows: even if it was a joke, the Macheads are going to get hurt and start spouting back. No one wins. This is why I try to keep humor out of my posts and respond to everything as if what is written is an opinion the poster would die for.
    What makes each of us laugh or cry is relative to our experience. Personally, I find all of this flaming and bitching over operating systems and hardware to be truly sad, and not something I want to be a part of. If someone makes a product better than Photoshop that runs on Linux, then I'll think about converting. Until then I'm sticking with the Mac. It's my belief (to the death, dammit) that your OS shouldn'tbe an issue, should be easy to use and FUN, dammit. It shouldn't get in the way of workflow. If PS and other products worked half as well on a Wintel box I'd be there, but you wouldn't see me rattling my saber for M$. Linux is too big a headache for me to concern myself with.
    Potentially aggravating comments, on the other hand, are in need of being dealt with for the good of the individual and the community.
  • First of all Solaris x86, is horrible when compared to Solaris/Sparc

    I'm at a loss to explain why the general /. opinion is that Solaris/x86 sucks so hard. Certainly Sparc hardware is nicer than Intel hardware, but Intel hardware is good enough for Linux for most of you.

    Sparc hardware is nicer than most Intel hardware...if you remove cost from the equation. But mostly I've found that Solaris users who dump on Intel Solaris are either just blind Sparc bigots, or formulated their opinion on an ancient version of Intel Solaris when it really was a terrible product. The Sparc bigots are really reflecting on Intel hardware, not the Solaris product. When pressed, I've found they will generally admit that there isn't really anything wrong with Intel Solaris. The past-bad-experience people just need to get with the program and realize that Intel Solaris has matured considerably and is every bit as capable as Sparc Solaris if you don't try to go beyond what the underlying hardware can handle. Just don't use IDE disks with it and expect to use a third-party X server, if you need an X server.

    So that is the story with Sparc Solaris users. Linux/BSD users might reject it for ideological reasons, cost (it is free only for non-commercial use), baseline system requirements, and the painfully short hardware compatibility list. In my opinion, anything less than 128MB of RAM just doesn't cut it for a Solaris desktop system. FreeBSD is quite usable in the same capacity with half that.

    Along many dimensions, FreeBSD does outperform Intel Solaris on the same hardware (I haven't done many comparisons with linux), but not by a huge margin (except metadata intensive filesystem I/O but rumor has it that Solaris 8 will include FreeBSD's softupdates code). FreeBSD generally has a snappier feel too it for interactive use, but I'm hard pressed to explain that through the synthetic and real world benchmarks I've run.

    SMP is the one area where Solaris is the clear leader. Both Linux and BSD need same major internal reworking to get where Solaris is now. Intel Solaris also supports Intel's new address extension thingy so you can have truly staggering amounts of real RAM...if you can find the hardware that supports it.

  • Minor point: HP-UX on PA-RISC 64 has only been available on servers up until like next month, when HP-UX 11 debuts. 10.20 isn't really a 64-bit OS.

    But point taken :) (BTW--I have always felt that Mr. Packard should have demanded that his name be first :)

  • Yes, they can and they will it seems. I can't find it anymore, but there was something on a while ago from a SUN engineer about Perl 5 shipping with Solaris 8...
  • Anyway, the real question is: "what's the critical mass of itantium". Is it fissionable?

    Ok, so maybe Itanium is fissionable, but I think Pentium must be certainly FUSIONABLE: As you know, the best known fusion materials are deuterium and tritium, which is actually hydrogene with respectively one or two added netrons in their core. So, Pentium would be a hydrogene isotope with four neutrons in the core!? (and you wonder what happened with quartium)

    Did this interesting chemical analogy occur to anyone before?

  • The reason RISC is damn fast is that the philosophy of RISC is one (however simple) instruction executed per clock cycle. CISC, by contrast, execute an instruction over multiple cycles.
    With ultrascalar design and pipelines the CISC have catched up nicely, though.

  • Thank you, that was my point!

  • From what you quoted, I took it to mean that several OEM's are sticking with intel's 32-bit line.

    Unless I read it wrong the article specifically said that they announced they were planning on sticking with their *own* chips. Instead of the (more logical path of dropping their 64bit chips for) Intel 64bit chips.

    It was a bogus argument that Intel's chip were better then current 64bit chips.

  • UNICOS first I can believe, though at that point Cray was a long, long way from being sold to SGI.

    IRIX surely wasn't second. At the time of the 64-bit CDC machines (mid 80s), Silicon Graphics was building M68K boxes.

  • Really? Well, I stand corrected! Thanks for the info
  • Yep, you got that right. Like Fizgig said, it's a Xeon /w 2MB cache. Those chips are MUCH more expensive. Plus, I kinda doubt the $6500 list quoted on IBM's web page is for the "raw" chip. Probably includes a CPU "board" that plugs into the Netfinity much like Compaq's SMP servers do.

    I was a little surprised also, because I had to spec out a E450 running Solaris vs an Intel box running WindowsNT. Much to my surprise the Intel/Windows "solution" was more expensive than the SPARC/Solaris option. It was great to see because I don't think the apps that we were going to run on it would have faired too well with the NT server.

    And I did try to be "fair" to the Intel/Windows box by spec'ng out "comparable" equipment. I could have spec'd out the 8-way Netfinity which would have really cost more than the SPARC, but that wouldn't be too fair now, would it?

  • it's the 4 pound heat-sink.

    That fucker's expensive!

    I wish I had a nickel for every time someone said "Information wants to be free".
  • Ah, you can bet that Windows 2000 will be labelled "64-bit", but it will really just have like a 64-bit "notepad.exe". Then after a service-pack or two, we'll get a 64-bit calculator, and someday in 2002, we'll have a 64-bit explorer, and some goofy shim that allows 64-bit SQL database servers to run on it. And by 2003, we'll have a 64-bit Exchange server. That's when Windows 2004 comes out, and by then, all Unix will be dead, so MS won't have to finish up with a real 64-bit kernel.

    I wish I had a nickel for every time someone said "Information wants to be free".
  • Sun has been runing 64bit for over 3 years

    More like one year, given that this press release [] has Sun announcing Solaris 7 on October 27, 1998, and given that Solaris 7 was the first fully 64-bit OS from Sun (Solaris 2.6 supports 64-bit file offsets, but that's it).

    The title of the original article was a bit misleading, as "64-bit Solaris" has been running for about a year on Sun's SPARC V9 systems; however, I suspect at least some nerds consider it news that it also now boots on Raseodymium or Echnetium or Odium or whatever the hell that name was that Intel presumably spent lots of money to get somebody to come up with....

  • Well sun has always had the ability to make binarys for ther current x86 platform just by telling the compiler to do so. I see no reson as to why they would change that now.
  • You'll find most GNU stuff in

    GNOME, E were compiled & packaged by a Sun engineer and they are in: ome-1.0.5.solx86.bin.bz2 ip2

  • I would more consiter it to be news if Sun did NOT port ther OS to rhododendron or irritating or what ever the hell they are going to call it.
  • I recently read Neal Stephenson's In the Beginning was the Command Line [] (good read, I wonder if that link is a legal copy?) and can't help but think about the probability that without support from Windows' home edition (whenever and whatever it may be), the IA-64 won't become a commodity chip and may be just as out of reach for Joe Hacker as the rest of the chip world (with the notable exception of PPC, of course.)

    I'd hate to see that happen. I would love to ditch bloat on my CPUs as much as I loved ditching bloat in my OS :-)

  • by Guy Harris ( 3803 ) <> on Monday October 25, 1999 @12:34PM (#1588752)
    What's more likely is that Sun is going to make damn sure that Solaris runs better on Sun IA-64 stuff...

    This presumes that there will be "Sun IA-64 stuff", rather than just Sun SPARC hardware. That isn't necessarily going to be the case.

  • But mostly I've found that Solaris users who dump on Intel Solaris are either just blind Sparc bigots, or formulated their opinion on an ancient version of Intel Solaris when it really was a terrible product.

    Just don't use IDE disks with it and expect to use a third-party X server, if you need an X server.

    It may not have occured to you that most Intel PCs use IDE disks and that most people need an X server - both of which is no problem with Linux and *BSD. This means that for most of the hardware and most of the people Intel/Solaris is a bad deal.


    PS: Sure you can buy an extra X server, but (1) I would expect that to be included and (2) I have personally had bad experiences with Xi's servers (on two different chip sets).

  • All marketing. They would have to admit that free software is better than their closed products and they would have to start the free software discussion with their more conservative customers.

    They of course hide this behind arguments of liability etc, but I think, it in the end it boils down to the above.


  • What is it that on a Solaris news everybody keeps talking about Linux?

    I bet people can't realize what the next wave.

    Behold, brothers and sisters. There will be a time when there will be no Linux, no Solaris, no AIX, no FreeBSD, no more Unices, just one whole, monolithic, united, big, UNIX (R) called something like HPSCOLinarisBSDIX (tm). Then everybody will be happy forever (except for Bill Gates and his minions, of course).

    Or maybe we could stick with a hybrid version... Maybe WINE gets so big that it makes it possible to hybridize Unix with Windows, so we would have WINHPSCOLinarisBSDIX. Wouldn't that be great?

    I Wonder how much time will it take for my message to be moderated out of existence.


  • Correct. The title of this entire discussion is especially misleading, as if Solaris had been 32bit until yesterday.

    What's even worse is the latest print copy of _ent_magazine_ (The Independent Newspaper for Windows NT Computing) has a front page article on Intel's 64bit chip where they quote: "Intel announced its newest chip, Itanium, which was previously known as Merced. Several OEMs, however, are sticking with their current architecture."

    They seem to imply that the OEMs are foolish for continuing to use their own 64bit chips when now Intel has a *real* 64bit processor. As if for some reason Intel is a saviour. Yes, we can now replace our crummy 64bit chips with superior Intel ones. Oh, wow!

    I predict we'll see this kind of argument more in the future. "Well, you'll want to use Intel's chip because they are better then others that have been out longer. Nonsense. However, this will make other chips cheaper, thank goodness.

    Of course, by the time 64bit chips are common-place the other "OEM's" will be using 128bit chips...

  • It may not have occured to you that most Intel PCs use IDE disks

    It most certainly did occur to me. If you are trying to retrofit old Windows machines to run Unix, this is a problem. If you are building a machine specificly for Unix, not a problem. Even if Linux or BSD which squeeze amazing performance out of IDE hardware are slated for installation, there are compelling reasons to go SCSI. With Solaris it is a necessity because the IDE drivers are terrible (in terms of performance that is; they are reliable).

    and that most people need an X server - both of which is no problem with Linux and *BSD.

    Well, good thing that XFree86 works. Incidentally, this is the exact same X server that Linux and *BSD typically use. The only hassle here is that it isn't conveniently bundled.

  • As a late follow-up, the ZDNet story has this mysterious addendum:

    Sun reports no change in its strategy toward Linux -- Linux applications run on Solaris -- but the company does include an Open Source Software Toolkit with Solaris 7 that offers tools and applications optimized for ISPs running Solaris on Intel.
  • And to think HP could be behind, but one of the key developers to IA-64, and forced Intel to add PA-RISC compatability. If that's true.. that's just a bit sad.
  • When I buy a Sun, I want the hardware and in some cases the Solaris kernel. For example, I don't want their crappy tar, so they can ship GNU tar as well.

    Second what is more disgusting with Sun selling GNU tools than with RedHat selling GNU tools?


  • This really isn't a departure from what they've done in the past; Solaris runs on IA32 hardware as well. Perhaps the intent is to make it easier for people to try out Solaris on their current hardware, hoping that next time they buy hardware it will be from Sun.
    As for W2K performing best on Sun hardware, I would be quite surprised if it runs on Sun hardware at all. NT has never run on Sparc before, and last I checked Sun and Microsoft weren't exactly sleeping together.
  • Sun has been runing 64bit for over 3 years, just becauls Intel has finaly gotten on the band wagen (Which by not I think that we all know) is not news worthy. Unless you are surprised thatsun is continuing to make x86 solaris?
  • Sun has been runing 64bit for over 3 years, just becauls Intel has finaly gotten on the band wagen (Which by now I think that we all know) is not news worthy. Unless you are surprised thatsun is continuing to make x86 solaris?
  • I guess in the end, I have to ask - what the hell does it all mean? I am a fairly technical guy and if you ask me what's better - shuffling around 32 bits at a time or 64, I would say 64. However, I also know that nearly all (if not all) of the applications today are optimized for the current psuedo-32 bit environment that we "live" in. Who is willing to go back and rewrite all this code to be 64 bit happy? And if someone does that, who is to say that the time in development would pan out to be worth the increase in speed or flexability.

    So, I wonder.. what does it mean to me? Fun to toy with for the next, say... 3 years? Or will I really be running a 64-bit machine 3 years (or less) from now on my desktop?
  • by RNG ( 35225 ) on Monday October 25, 1999 @09:08AM (#1588770)
    Having tried a SPARC based personal workstation a while ago, I can only say that this is good news for Sun. Their systems may deliver nice I/O throughput, but their processors seem to be outclassed by Intel, especially so when taking into account the price tag of SPARC hardware.

    I think Sun has 2 problems: Linux, which from a free download gives you a much more polished software install than the factory pre-installed Suns have (and which is certainly good enough unless you're doing realy high-end stuff) and of course the ix86 chips. Intel and AMD might not be there for the really high-end market yet, but for the workstation market they are dirt cheap at similar (or in my case even better) performance than Sun could provide for twice (or even more) the price. Sun's success is increasingly mysterious to me ...

  • I understand that there are a number of OS components involved in sending Internet e-mail, but it's not like they teleported a tangerine to Pluto. It's just e-mail.

    And how does this indicate that " ready for the Itanium processor"? Unless you want to send a few e-mails, which most of us can do just fine with a non-Itanium processor...

    Technology milestones are great, but I don't see that this means that I should plan on running my business (or anything else, necessarily) on Solaris IA-64.

  • The OS architects have said for a long time that moving an OS from 16 -> 32 -> 64 bits is significantly more difficult than moving it between 2 CPUs at the same bandwidth. In other words porting Solaris from Spark to IA64 should be fairly simple and this announcement pretty much proves that.

    Linux ( how could I leave it out ? ) has been tested on IA64 and that too was not surprising since Linux has run as a 64 bit CPU on Spark and Alpha machines for some time.

    PS : Yes you read correctly. The Linux port started from the Alpha branch of the Kernel source rather than the i386 branch.

  • Hmmm...lets see... Solaris/UltraSparc is 64 bit; IA64 supports IA32 instructions. Why am I not surprised that they managed to get this to run. It's still a good thing, though.

    Anyway, the real question is: "what's the critical mass of itantium". Is it fissionable?
  • I'm really curious as to how this affects the Linux port to Itanium. Anybody working with the port care to comment?
    It seems that this is giving Sun quite a jump and headstart in the 64bit realm. I don't think that Linux's goal is to complete with other commercial vendors -- but it is inevitable. Course I think that Solaris should just replace it's kernel with Linux or (open|free)BSD. Just my humble opinion.
    -= Making the world a better place =-
  • I don't get it. The only reason I can think of, is that Sun's primary objective is to try and harm Microsoft.

    I know very little about IT marketing, but somehow from a business point of view, it seems to me that they would have more to gain by making sure Windows2000 performs best on Sun hardware, instead of supporting the flagship of a major competitor.

    Does this mean that Sun now concedes that intel cannot be beaten?
  • by Anonymous Coward
    Why does Sun care so much to port Solaris to the Itanium?

    It is clear that OS *nix will eventually erode all vanilla commercial unices from the low end up, and Sun has stated that they are a hardware company and do not care if consumers run Linux or *BSD on their machines, as long as it is _their_ machines. But in this case it is not a Sparc.

    The i386 is poorly supported by Solaris, and I do not remember any excitement about it.

    Does Sun plan on manufacturing/selling Itanium boxen? Is this where they think the market is going?

    Or are they just messing with Microsoft, showing how easily they can port Solaris?

    n'th post :)
  • A prediction, yes?

    Now as soon as this stuff starts blowing up in a big way, Linux will be one of the first OSes to get booted on Itanium as well.
  • It's debatable. We have some of the vew SPARC V9 chips here where I admin, and they are verra verra nice. Also verra verra pricey.

    Sun's biggest problem (and has been for some time) is that their hardware is way the hell overpriced, and their industry-standard stuff lags behind (e.g., their latest CDROM drives are a third the speed of a generic Plextor drive, but cost five times as much). Their custom hardware (UltraSPARC processors, say) is nice, but equally pricey.

    There are some very handy things that you can do under Solaris/SPARC but not Solaris/x86. Even so, running on Intel whytanium will be a boost to Sun.

  • Uh... there's been people working on Linux-on-Itanium for a while now, so, no matter what happens with Solaris, Linux will be running 64-bit on Itanium early on.
  • by Guy Harris ( 3803 ) <> on Monday October 25, 1999 @12:38PM (#1588780)
    Solaris/UltraSparc is 64 bit; IA64 supports IA32 instructions.

    But IA-32 instructions, as the "32" suggests, don't support a 64-bit flat address space, so, to run Solaris 7 on IA-64, Sun has to treat Tterbium or Otassium or whatever the heck it's called as an IA-64 processor; the fact that it runs IA-32 instructions doesn't help (unless you boot Solaris x86 on it, but all that would demonstrate is "yup, Adium's IA-32 mode works").

  • How exciting! Intel has a new 64-bit OS for its new bloatware processor!!! (can you detect my sarcasm).

    Seriously now, I've been using Linux on Alpha for a long time now and Tru64 (formerly Digital (formerly OSF/1)) UNIX as been around for a even LONGER time! The very first Alpha, released to the public in 1992, was 64bit! Why would ANYONE want to try out a new platform that's going to cost as much as a house and doesn't even have any compilers yet?

    rbf who is typing this on a Alpha running Debian GNU/Linux 2.1 with Linux 2.2.13.


  • I know that you can get GNU binaries easily for Solaris, however not getting them out-of-the-box is a big complaint from Linux users.

  • Good point. Sun's probably likely to stick with Sparc hardware for now, but *if* Intel manages to scale IA-64 way beyond Sparc, I wouldn't think that Sun would have any problem switching over.
  • by Guy Harris ( 3803 ) <> on Monday October 25, 1999 @01:05PM (#1588786)
    ...and where there are no file size limitations.

    The address-space limitations may require a 64-bit processor, but the file size limitations don't, as long as you're not mapping the entire file into your address space - plenty of OSes running on 32-bit processors allow files bigger than 4GB.

    Not to mention native support for double precision floating point math in both hardware AND software.

    If by "double precision" you mean "64-bit floating-point numbers", with the exponent+mantissa+sign taking 64 bits total, what current 32-bit processors don't support 64 or more bits of floating-point number in hardware (and/or don't run software that supports them as well)?

    Integer arithmetic instructions that handle at most 32 bits at a time, and 32-bit pointers, don't limit file sizes to 32 bits (one can synthesize 64-bit or bigger arithmetic operations from the integer arithmetic instructions - and most C compilers, these days, will do it for you, and compilers for other languages may do the same); they only limit how big a file you can map into your address space all at once.

    They also don't limit the width of floating-point numbers.

    The key limitation of 32-bit processors is the address space limitation you noted; that one is a bit more of a pain to work around (e.g., by mapping stuff into and out of your address space manually).

    Remember, the Playstation2 is what, 128bit?

    64-bit, or 64-bit with some 128-bit instructions. The Emotion Engine is, according to a Microprocessor Report article, a processor that implements the MIPS III instruction set plus some MIPS IV stuff, with some additional vector and MPEG-2 decoding support added. The operand bus for the vector stuff is 128 bits, but that's not enough to make it a full-blown 128-bit processor (any more than the SIMD stuff in MMX/SSE, or AltiVec, or..., make processors that implement those wider everywhere).

  • I didn't say that they shouldn't be bought. I said that they are overpriced. I think houses and cars are overpriced too, but I'm not advocating that we live in tents and walk thirty miles to work. I am definitely not saying that we should all go out and purchase cheaper IBMs.

    We have a finite but nondeterministic number of Ultras here at work; four at the moment. I am well pleased with them. Occasionally there's an SGI machine, which is also nice but has a wacked-out library layout. But that's a different rant.

  • but *if* Intel manages to scale IA-64 way beyond Sparc, I wouldn't think that Sun would have any problem switching over.

    At least not any technical problem. :-) There might be a corporate pride problem (look how long it took Scott McNealy to publicly use that "M" word :-)).

  • by Alan Cox ( 27532 ) on Monday October 25, 1999 @01:12PM (#1588791) Homepage
    Someone taking my name in vain ? Thats certainly
    not my quotes

    Solaris scales to 64CPUs (partly because of their
    kickass memory bus on the ultrasparc). We beat them flat low end but believe me, for a lot of
    things on 8+ cpus it has us hammered. On 32+ cpus
    Id be willing to bet it wins aginst 2.4 once we
    have it finshed

    I wouldnt buy a Xeon for most things either. A
    quad Xeon costs the same as a rack of 2U celeron
    boxes and ethernet switch. 20 celerons versus 4
    xeons, 20 celerons with a total of about 8 times
    the memory bandwidth of the xeon box

  • From what you quoted, I took it to mean that several OEM's are sticking with intel's 32-bit line.
  • Who is willing to go back and rewrite all this code to be 64 bit happy?

    A couple of points:

    • If the code is well written, porting to 64-bits is simply a matter of recompiling. Sure, much code around today isn't well written, but the changes needed aren't usually that great.
    • 64-bit OSes almost invariably allow 32-bit apps to run unmodified anyway, so you can carry on using your old apps. There will be certain classes of application (e.g., large databases, scientific number crunching, rendering etc.) that will be better off as native 64-bit apps, and those will have to be made 64-bit friendly to make best use of the hardware, but most programs will not benefit significantly.
  • We're talking about a PIII Xeon here, Bruce, not a regular PIII. With the Xeon, you're paying extra for two things:
    1. Large amounts of on-chip cache
    2. Intel's extra profit margin. Since the competitors (UltraSPARC, MIPS, high-end Alpha) all have 4-figure price tags, Intel does the same too, to give themselves a large profit margin.
  • Sorry but you are wrong: we are using HP UX 11.0 since may at least. Even I was on an admin course for HP UX 11.0. I compiled a lot of freeware stuff on a HP Apollo workstation where I installed HP UX 11.0. So, it is here.
  • 1) solaris SMP is a 3rd rate hack, its been proven by alan cox

    Do you have any links or more information about Solaris's "third rate" SMP. I was under the (marketing?) impression that Solaris had kick-ass SMP. I'm particularly curious as to what Alan Cox had to Solaris's SMP. I've been following the linux-kernel mailing list and I'm very excited about Linux 2.4's SMP improvements.

  • Correct. The title of this entire discussion is especially misleading, as if Solaris had been 32bit until yesterday. I wish we could moderate/influence titles and intros also.

    That said, the news itself is great and is one of the (many) significant milestones on the way to viable IA64 systems.

    Now we need to hear great things about compilers (actually, more about the code they produce) for IA64. Can we really reap the benefits of the EPIC architecture in practice any time soon?
  • > "Since its inception in 1982, a singular vision,
    > "The Network is the ComputerTM," has propelled
    > Sun Microsystems, Inc."

    Oh really? I thought marketing only thought up that slogan a year or two ago..

    SunOS (sorry, Solaris Operating Environment) is ready for the Merced (sorry, Itanium) in exactly the same way as a wheel is ready for a car..
  • Basically, intel's merced (or whatever they've renamed it to) has two operating modes: a "native" or VLIW-style mode that takes raw EPIC instructions, and an x86 "emulation" mode that translates x86 style instructions on the fly. Merced actually has a special opcode just for switching between these modes. When merced starts up, so to speak, it starts in x86 emulation mode, so if your binaries are old, they'll work ok. Native code can be intermingled with x86 code simply by bracketing it with these opcodes telling it to switch to the proper mode.

    Naturally, if you are just trying to use x86 binaries, this processor won't do much for you as far as horsepower, because it has to translate all those instructions, schedule them, etc.

    However, by recompiling your code to run using "native" IA-64 instructions, you can get tremendous performance advantages. Native code basically goes straight into the pipeline. Due to the many advantages inherent in VLIW architectures, like (supposedly better) software scheduling, more functional units, etc., I think any native code should run quite well.
  • Are you guys crazy?

    Look at an IBM Netfinity 7000 M10 3SY. It's a 4 CPU Pentium III Xeon 550Mhz /w 2MB Cache server. The base system, with one CPU, cost $15,053.35. The CPU's for this guy are $6,521.74 according to IBM's web site.

    Look at a Sun Enterprise 450. It's a 4 CPU UltraSPARC-II 400Mhz /w 4MB Cache server. The base system, with one CPU, cost $15945. The CPU's for this guy are $5600 according to SUN's web site.

    Let's see:

    * 32 bit CPU vs 64 bit CPU.

    * 2MB Cache vs 4MB cache.

    * $15K vs $16K.

    * 550MHz CISC vs 400MHz RISC.

    Which would you rather have, given that they are approximately the same price (and the UltraSparc-II CPU's are much less)?

    I think it's a no-brainer.

  • I used to think like you, but after 3+ years working with 64bit Irix 6.x I have changed my mind.

    You'd be surprised by the number of scientific number-crunching apps that port relatively easily (if not trivially) to 64bit. The list keeps growing at a very rapid pace. To me it doesn't look like porting to 64 bits is that much of an issue in practice.

    In the life sciences, which is where I live, systems under study are growing very quickly, and we have reached the point where it makes a lot of sense to be able to address gobs of memory without hacks and where there are no file size limitations. Not to mention native support for double precision floating point math in both hardware AND software.

    I am sure that for apps in the engineering and physics fields this is even more pronounced.

    It will be far less than 3 years until all that high-end stuff trickles down to everyday computing. Remember, the Playstation2 is what, 128bit? The future is already here, just not on your PC. ;-)
  • I'm curious; how many 64-bit UNIX(-alike) systems were there before the first port to an Intel part, and exactly how long ago was the first? (Indeed, how many other 64-bit operating systems and architectures predate IA-64?)

    Was UNICOS first? Then SysV on the ETA-10, VX/VE and the native port (name?) on the Cyber 180, ... after that I can't think of any more for several years. Then the micros (in what order?): OSF/1 (alias DU, Tru64) on Alpha, IRIX on MIPS, Solaris on Sparc, AIX on Power, HP/UX on HPPA, and....? And of course NetBSD and Linux both on Alpha and Sparc.

    A dozen at least. But get ready for the "First 64-bit Computer!" news reports once Intel finally ships.

  • by Alan Cox ( 27532 ) on Monday October 25, 1999 @01:16PM (#1588811) Homepage
    Dear me. Believing a slashdot poster. Want to buy
    a bridge, or some dehydrated water ?

    Solaris Ultrasparc SMP is very good.

    Thats a real quote from me.

  • by Mr. Piccolo ( 18045 ) on Monday October 25, 1999 @01:31PM (#1588813) Homepage
    Proof that not only MS creates FUD...

    1. I think you got the two Oses reversed here, as Solaris scales to 64 processors I believe. Anyway, show me where Alan Cox says this.

    2. Say it with me, folks:


    NO sane administrator would use anything (except perhaps OpenBSD) out of the box. At the very minimum most of /etc/inetd.conf gets commented out. And not starting daemons you don't need helps too.

    3. The focus shouldn't be "is it Open Source?", but rather "is it the best program that I can use now to fit my needs?"

    Linux is a nice system for the "average" PC. But the BSDs are probably best for Web servers, and Solaris is probably best if you need a huge file server or database machine.

    Solaris is definitely the wrong choice for home PCs, which have no SCSI and 1 processor, but it's not intended for that. Linux is.

    4. The actual situation is more like this: Once the server machine gets big enough to warrant using Solaris on it, the price of the OS is a small fraction of the price of the entire system. And yes, for those machines (4 processors or more) Solaris may perform better (gasp!) than Linux.

    5. I must be part of a different revolution than you. My revolution is against Microsoft. My revolution does not say, "Use GNU/Linux OR DIE!!!" My revolution says, "There is more to life than Microsoft products. There are better ways to compute. It's up to you to use the best product for you. It's just that we think you can do better than Microsoft products and would encourage you to research the alternatives."

    Open Source is nice, but you have to figure a lot of people just won't _care_ whether they get source code or not, as long as the program works properly.
  • ... Tterbium or Otassium or whatever the heck it's called ...

    Na. Hs. Au.

  • There is nothing in the world more disheartening as when your sarcasm shoots right over someone head.

    I laughed when i read it, then nearly lost it when i saw serious replies!

    Good times.
  • Is that true?
    Can't they ship free software with their OS? I've had the impression that the GPL allows this, as long as no proprietary code is mixed in their source.

    If I were an OS developer like Sun or IBM, I'd put at least some of the best free software products we have today - including the wonderful GNU rewritten UNIX utilities, like grep, ps, bash, awk and so on. I am an Unix worker, and it really annoys seeing these UNIX commands with lack of options - e.g, I tried to use grep on AIX with the -b (before) option some day, and realised the AIX version didn't have it.

    It's a shame. Big companies like IBM, who already gives much to the free software world, can't leave the fear of their OS being superceded by Free Software.


  • by Jarvo ( 70205 )
    I have had the unfortunate experience of using SLOaris on and off over the last two years. I am not impressed with any part of Sun's OS. Why on earth would anyone want to inflict this on an x86?
  • Yes, you're right ... I should probably have mentioned that I'm really happy with an 8CPU server we have; it makes Oracle databases faster than any other machine I've ever seen (although having seen it's price tag I would expect no less); the only machine that come close (or equaled it) was a recent AIX box I installed on ...

    I think Sun's coolest product is Java, which ironically is probably what they make the least direct money off (although indirectly it probably payed for itself quite handily by turning quite a few heads/minds their way) ...

  • It would be a strange world where Sun offers support for Windows 2000 on it's hardware! Especially since Sun touts it's position as the only major computer company without some deal with Microsoft.

    What's more likely is that Sun is going to make damn sure that Solaris runs better on Sun IA-64 stuff than on your commodity Dell or Compaq. Some of this will be due to just plain better hardware from Sun, but I'll bet that Solaris will have a few hooks in it that will disimprove performance when running on a non-Sun box.
  • $6K for a Pentium III 550? I just paid around $200 for a Pentium III 450. The 550 would have been more, but not that much more.


  • First of all Solaris x86, is horrible when compared to Solaris/Sparc

    I'm at a loss to explain why the general /. opinion is that Solaris/x86 sucks so hard. Certainly Sparc hardware is nicer than Intel hardware, but Intel hardware is good enough for Linux for most of you.

    Certainly Solaris/x86's hardware support is much thinner than Linux's, and the distribution is pretty thin compared to Linux, but from what I've seen, Solaris on Intel is a very solid operating system once you have it up and running.

    Furthermore, in the PC Week "NOS Shootout" a few months ago (which got everyone here up-in-arms), Solaris/Intel was faster and scaled better than either NT or Linux.

    Perhaps if Sun wrote a few more device drivers, and shipped Gnome, KDE, the GNU toolset, XFree, and so on, Linux folks would have a little more respect for the OS....

Build a system that even a fool can use and only a fool will want to use it.