Rubbish. I don't use anything from Microsoft, and haven't for at least 4 years. You and everyone can do the same. Fact is, most people don't care enough about the issue to do the necessary investigation to take this step.
The suit against Microsoft is tripe and nonsense. The only way anyone can have a monopoly is if people choose - yes, choose - to do business with them. Sorry, you lose on this one because the argument is irrefutable. No business, no profits, no market share. There is a choice. There is always a choice.
I could care less if Microsoft is a monopoly... this bundling/tying/integration crap must stop for exactly this freakin reason!
It is your attitude that allows them to engage in monopolistic business practices. If you don't like their products - and it's obvious that you have serious issues with them - then instead of whining about it on/. just stop doing business with Microsoft. It's really just that simple. Corporate profit whores are the easiest entities in the world to manipulate. All you have to do to change their ways is to choke off their profits.
If you stick a fork in your eye, I will neither help you get it out nor sympathize with you; you stuck it in there and it's your own damn fault. Using Microsoft products is the same way. Anyone who does so is just asking for problems. I'm not claiming nobody else's products have flaws, only that Microsoft's have many more flaws than anyone else's, and as you mention their fundamental strategy merely worsens the situation. If you use them, you deserve what you get.
Finally, I end virtually every post this way: if your employer "forces" you to use this stuff, just remember that in most countries you can always quit. So either stop whining about it or quit your job and go work elsewhere. "Whoring: Just don't do it!"
Now hear this: All Linux-related product reviews are fixed. The Linux Cabal, led by Red Hat and VA (parent of Slashdot, they're the ones targeting the satellites on you - don't forget your tinfoil hat!), fresh from their huge stock market gains (oops, they've all lost their shirts), are conspiring to make sure you never hear anything bad about Linux or Linux-related products! So run out and support the good, kind-hearted honest folk at Microsoft (home of the Mindcraft benchmark) and your favourite multibillion-dollar proprietary software houses.
Or maybe they really are fixed. Who cares anyway? Only suits read software reviews in trade rags, and only idiots put any faith in them. At the end of the day, does it make one bit of difference to anyone? NO! The idiotic suits who base their purchasing decisions on reviews are always going to end up with crap, because, well, they're idiots. People who use Free software for various reasons, including but not limited to issues of freedom and quality, but don't spend their lives talking about it, aren't affected either. They use the same software in the same ways they always have. The only people who care are the self-proclaimed "Open Source Evangelists" who seem bound and determined to piss off everyone within earshot by harping on how much better Linux is than [whatever]. These people know nothing about technology, nor about business. They cannot write a line of code, nor can they run a successful enterprise. They are mindless drones caught up in the whirlpool of excitement that the magic word "Linux" generates today.
In a few years, when all this calms down, Linux will be just another option for business types, and it'll be the same software with the same license the geeks have always used. The loudmouthed advocates will have to spend their time on other things. God forbid, Slashdot might not even be profitable any more.
We don't care. Review is fixed, review isn't fixed. You want to know how something works? The only way you'll ever know is to evaluate it in the context of your specific application. No thinking human gives a rat's ass what any reviewer writes, or what motivates him or her to write it. Get a fucking life.
First of all, the Sun Ultra 10 machines I was talking about aren't PCs, I am not sure where do you get that from.
Open one up sometime. Look at the chips. You will see that they use standard peecee components like ATI graphics, IDE, and Goldstar (yes, Goldstar) CD drives. In my book, that makes it a peecee.
I wonder if you use Matlab, which doesn't seem you do.
It's not my primary application, no. I use my systems for development. Since I know for a fact that matlab does not run on sparc-sun-linux (I do admin matlab, I just don't normally use it), I would strongly suggest that your disappointment with your Suns is the fault of your choice of operating systems, not hardware. Solaris has a reputation, backed up by benchmarks for whatever they're worth, for offering poor performance, especially on fewer than 16 processors.
I once worked on a project to translate a matlab program into C. I do not know whether the original program played to matlab's strengths or weaknesses, but I can say that my portable ISO C program averaged 23 times the performance of the matlab version. The point? I don't think matlab is a very good benchmark. Obviously, it's your application so it's the only benchmark you care about, but I suspect that in the grand scheme of things matlab doesn't necessarily mean much. It also has no way whatever to test things like disk I/O and internal bandwidth which are nearly irrelevant to matlab but of critical importance for virtually every other application, areas in which peecees lose to any real workstation, often by a factor of 5 or more.
My point is if I have an Alpha or Sun with a 500 Mhz processor and they cost 5000 and I can buy an Athlon 900Mhz for 2500 I pefer the Athlon and I KNOW it has very good chances of outperforming the others.
Good for you. I'm glad you've found systems that work well for your application. I'm sure you'll enjoy repairing them numerous times in the six months before they stop working completely. *shrug* It's your maintenance nightmare, not mine.
The U5 and U10 are not deserving of the name they carry. They are peecees with a different CPU. I won't consider discussing the merits of these machines separately from peecees, since they are identical. Someone at Sun loaded up on crack cocaine and the 5/10 resulted. End of story. Let's hope he got the help he needed.
And you're welcome to spend $1000+ for a Creator 3D card that's probably no faster than a $200 PC video card.
I paid $80 for mine. FFB2+. Very nice.
And then you can get screwed when you need a patch for Solaris that's only available to contract customers.
So don't use Solaris. It isn't very good anyway. Linux runs exceptionally well on Sun hardware, much faster and more reliable than on peecee hardware.
You think everyone would rather spend 3 times as much because you're too lazy to work inside a computer for a few minutes longer?
Laziness has nothing to do with it. I was discussing cost. If something takes longer, it costs more. In an environment where you're paid to do so, the costs are immediate and direct. In other environments you must evaluate the worth of your time. Personally, I'd rather just use my computers to do the work I want to do and not spend lots of time screwing around trying to get broken, misdesigned hardware to function. YMMV of course.
I don't know what planet you're from if you consider US$5k for a workstation (even a high-end workstation) "surprisingly inexpensive" either.
Look, I really hate to use buzzwords (is it ok if they have fallen out of use?) but you need to think about total cost of ownership. If you have to pay someone $50 an hour plus benefits and taxes to fix things when they break that $3500 peecee suddenly looks pretty expensive. Real workstations are much more reliable, and when they do break it's just a matter of pulling out the broken piece and popping in the new one. If you've ever worked in real hardware you know what I mean. Any repair job is 2 minutes, and there are no bloody hands and extra screws to deal with. If we're talking about individual use systems, then the TCO depends on how much you value your time. I consider playing around in cramped, cable-rat's-nest-ified, sharp-edged, poorly labeled peecee cases to be a complete waste of my time. It's well worth the extra money to have a machine that always works; and even if it doesn't, it's trivial to fix it. If you've never owned a real workstation, you can't really argue with me. Try it; you'll never go back.
I argued that x86 is the "open-source ISA" since anyone can use it, while Intel and HP will demand steep royalties for anyone wanting to do IA64 processors.
Anyone remember Intel's lawsuits against AMD for implementing this open ISA? Huh. How quickly we forget. The only reason Intel gave up is that they have something supposedly better now. On the other hand you can buy a license to manufacture as many SPARC chips as you like for $99. Total, not each. SPARC is an open ISA. x86 is only open because Intel no longer cares to defend it.
which according to Ars Technica only adds about 1% penalty to the processor's speed.
While I doubt this number, I have no other so I will not contest it. Regardless of the performance penalty, there are most certainly much larger a) power penalty - power consumption is proportional to dies size, b) heat output penalty - ditto, and c) elegance penalty. To me, the elegance penalty is the killer. It's cruft. It's a nasty hack to try and get performance from something that was never designed for it. It's a marketing decision laid down in silicon. Even if you don't care about elegance, consider this: how much faster would the CPU be if the extra silicon were a) cache, or b) logic directly related to processing, not translation. It's inexcusable.
Fuck elegance, give me just as fast for half the price and I'll take x86 ugliness any day.
I'm sorry you feel this way. I don't think I could live without an appreciation for beauty.
If you need those big caches, the 500MHz Xeon with 2MB cache goes for between $700 and $900
Uh...the street on a 2MB Xeon 500 is $3000-4000. That is, higher than a 400 MHz 4MB UltraSparc II and significantly lower in performance as well.
Unfortunately, AMD is still behind with its multiprocessor solutions...
As is Intel. The practical effects of inelegance.
Most PC platform problems could be cured by moving to faster and wider buses, and a Unified Memory Architecture like SGI used on its short-lived line of Wintel workstaions.
Sure. But that's where all the cost is, not the CPU. And if you're going to spend the money on a nice architecture, why not put in the extra $100 for a better CPU as well? Then you can kick Intel's kiester for their anticompetitive behaviour as well.
And, most existing operating systems and the software which run on them would work fine with just a minor OS patch, like the one SGI used to get NT 4.0 to run on its UMA Visual Workstations.
The operating systems that are used to actually get things done already run on the CPUs that don't suck. Linux runs on virtually everything. As does NetBSD (no SMP though). You can get realtime OSs for nearly every CPU, and there are vendor Unix OSs that work fine for most platforms. Who cares about enntee? Nobody who values his job uses it anyway. And all the useful OSs already have code to handle the I/O architectures. Why patch when useful OSs are already available?
I don't know how it's insightful. I'm not a karma whore, so I don't give a rat's ass what happens to my posts. My argument is based on technical merit - anyone doing something with less technical merit than they are capable of is evil. I'm not a businessman, so I don't care whether someone makes a profit or not. Making a profit from good technology is not evil. Making a profit (or losing your shirt) on lousy technology is always evil. You don't have to like it, but that's my point of view.
If you bought your machines directly from Sun, that's your own fault. You can buy them elsewhere for a fraction of the cost. The Ultra 10 is a peecee, so I don't see how it fits into the comparison. Of course it sucks, it's a peecee. Go buy a used dual CPU ultra 2. It's elegant, fast, and inexpensive. The performance of peecees compared with real computers depends, as always, on application. If you want to spin your cpu in a tight loop of integer instructions, then a real computer is not necessary. If you actually want to get anything done, you need some I/O bandwidth and floating point performance, things that aren't available in anything with a BIOS in it.
I fail to see your argument for AMD. I agree with your entire position on Intel, but logically you cannot exempt AMD from your ire. While they are surely less evil than Intel, they are still evil for contributing to the continued existence of x86. And any proportion of evil makes for complete evil. And to get right down to it, x86 itself is nowhere near as bad as the peecee architecture in general. The product of 20 years of non-design and corner-cutting cheapness, this architecture offers atrocious performance, maintenance nightmares, and outrageous total cost of ownership. So if you really want to make a difference, stop buying peecees altogether. Your case for AMD is weak at best. If Intel is evil, so is AMD.
There are plenty of options out there; many are surprisingly inexpensive. Quality, high-performance workstations from Sun, SGI, and Decompaq can be had for less than USD 5000, often less than half of that, which do not use x86 nor the peecee architecture. You'd better hurry, though, before everyone drops their quality architectures for IA64 and gives Intel the market chokehold it has been lusting after for years.
Fight the power; insist on quality; boycott the peecee!
you won't convince Windows users to come to the Linux/BSD,etc. World if you don't offer them a way to execute any of the application they are used to.
*sigh* I think I need to put this statement in my signature: I am not interested in convincing anyone to use anything. What does it matter what people use? If they are stupid enough to use winDOS, let them. Our objective should be to maximize freedom and quality, not to convince people to use our stuff. Everyone says derogatory things about "marketdroids" but if you look closely you'll see that the function of marketing is to convince people to use your product. In other words, you've become marketdroids without even realizing it.
What a great debate this is. It's clear that you can't marshal any arguments to counter my position (because, really, there aren't any - you want support for a closed-source product, you have to pay for it) but are bitter about the delays. Doing business with people like that sucks, doesn't it? Hope you learned your lesson. Closed source isn't evil, but you have to know what you're getting into. And in a Free Software development effort, closed source modules always lag behind in both quality and currency. Live with it, or pick a different vendor.
If nvidia wanted their drivers to work they would release the source just like everyone else, and they'd track development. Since they don't give a shiot about being a part of the community, the community feels no obligation to help them. If you buy their crap, you get what you deserve - frustration and delays. Seems fair enough to me...
unless it's a Microsoft server. Like the bitchy woman behind the desk at the DMV, an NT/IIS server can serve only one person at a time, does so only grudgingly, and takes frequent breaks. It even mumbles incoherently from time to time. Now that's progress.
n32 tools are better, vendiors love to ship o32... sound familiar
Of course. Proof that IRIX-targeting proprietary vendors are just as idiotic as Linux-targeting ones (libc5, yeah that'll make me buy your shit).
This is _not_ a single machine image. O2k machines have only been implemented upto 256 cpus with a single image, althoug the O2k architecture should support 4096
I'm familiar with the architecture. 256 is still four times as many as Sun offers. The Craylink technology used to link partial SGIs is also highly impressive. It's really a blazing-fast network, with hubs and so forth. Quite flexible.
These sorts of things tend to not happen with solaris. It's not nearly as esoteric, so it doesn't have the bleeding edge performance of IRIX.
IRIX 6.5, which has been around for quite a while really, is rock solid. I've had plenty of annoying problems with earlier versions, just like you. 6.2 and 6.3 would lock up, 6.1 was complete garbage, NFS had issues, and so on. But you have to compare equivalent systems - we're not comparing Solaris 2.8 with IRIX 6.2. Solaris versions less than 2.4 had a number of serious problems; it's generally conceded today that Solaris < 2.4 is effectively unusable. I'm not recommending that anyone use IRIX 5.3 any more than that they use Solaris 2.3. When comparing IRIX 6.5.[5-8] with Solaris 2.8, IOW contemporaneous operating systems, I think you'll find that IRIX comes out looking quite good for stability, ease of use, and feature set. Naturally YMMV but I'm disinclined to allow problems with earlier versions of IRIX to bew brought up in a comparison with more recent versions of (something else).
since you can pick up an O2 for about the same amount as a mid to high end powermac
A reasonably configured used O2 in perfect condition can be had for under US$1500, about the same price as a midrange peecee. An R10k High Impact Indigo2 can be had for about $1300-$1700 as well. That's a fully 64-bit system with a 200 MHz processor (faster than it sounds) and graphics faster than all but the high-end peecee offerings. Even Sun Ultra 2 systems, which are also fully 64-bit and offer dual CPU capability, are less than $3000 in reasonable configurations today, and it's even possible to get them new. You can say what you like about high workstation prices, but in the real world, clever individuals can get nice, if slightly out of date, systems that offer good to excellent performance for prices comparable with peecees.
On top of that, the only unix box hardware I really appreciate is SGI, but the only commercial unix I would run is Solaris - Which is a fundamental incompatibility.
That seems odd. Both SGI and Sun build great machines, but I'd rather put a fork in my eye than have to use Solaris. IRIX is ok most of the time though. IMO the only acceptable OS for Sun boxes is Linux. Try it; you'll like it.
Feel free to feel like you have a larger penis because you've left the PC platform
[Looks down] Looks pretty standard to me. A refusal to compromise with idiocy doesn't come from the penis, it comes from the brain, and I'm pretty sure ours are within 20% in size.
Until the cost of systems based on other processors drops
It has. See above.
the number of available applications must increase...
I don't know about you, but I have solid applications - we're talking about things that actually work reliably here - for every task I might possibly want to do on a Unix box. I challenge you to name a task I can't do on a Unix box. That Turd or whatever other flavor of the month isn't available isn't important - what matters is what tasks you can do, and how easily you can do them. I've found that Unix systems offer more applications than I could ever find a use for.
Re:x86 is popular to hate, but not that bad really
on
Is The x86 Obsolete?
·
· Score: 2
Never critize those who came before you. They didn't have the benefit of your knowledge.
The 8086 is not what I'm criticizing. Yes it sucked but so did everything else at that time. What I'm criticizing is the decision of the engineers to let the marketdroids run Intel and thereby prolong the life of a design that had no business surviving past 1988 or so. In the mid-80s the SPARC and MIPS projects were starting to produce marketable CPUs. These CPUs were well-designed and well-implemented, and fast. Intel's engineers are more than capable of competing with such offerings, but they chose instead to allow non-technical idiots to dictate technical policy. Specifically, the 486, Pentium,... are mistakes and deserve to be treated as such. These CPUs should never have existed because Intel should have abandoned an architecture that by the time of the 386 was already aging very badly. I will gladly excuse technical mistakes made in the absence of information we have today. I will not excuse bad policy decisions which should have been made by engineers, made instead by braindead marketdroids.
In legal-speak, I'm saying that Intel knew, or should have known, that their current product offerings were technically inferior to those of their competitors, and should have adjusted their product line accordingly.
The i860 and i960, along with the ability to manufacture x86 CPUs that offer any performance at all, prove that Intel has a great many competent, if not brilliant, engineers. Their mistake was in giving up control of the product line. When Intel's marketdroids announced the 486, every Intel engineer should have either demanded a change, or cut and run. There is no excuse for the continuing existence of the x86.
Re:x86 is popular to hate, but not that bad really
on
Is The x86 Obsolete?
·
· Score: 1
I use the term to mean factor of 2. Adjust accordingly if your definition is different.
Re:x86 is popular to hate, but not that bad really
on
Is The x86 Obsolete?
·
· Score: 2
Non-linear memory model is true of any system that uses paging, and is a very VERY good thing.
I was referring to the "segment" concept, the fact that physical memory is nonlinear (or however you prefer to describe it. The point is that pointers require two registers.) Thankfully protected mode helps somewhat and makes it possible for an OS to offer virtual memory and a linear address space, but the fact that 16-bit real-mode segmented address spaces still have to be dealt with at all, ever, is obnoxious and stupid.
Your point is? WinDOS has almost 90% market share. Does that mean it doesn't suck? Solaris takes a beautifully-designed lightning-fast million dollar system and makes it run like a 386 with a flaky memory module. IMHO, that qualifies as "sucks." I guess your definition is different. Just remember me when you're trading up your expensive Sun box again to make up for the failings of Solaris; I'll buy the old system from you, put UltraLinux on it, and get the same performance you will at half the price. I wish BSD had SMP support, but it's still worth using if you have a UP system lying around. Linux on SMP UltraSPARC, however, is a thing of beauty.
From SGI of course.. makers of IRIX.. the most universally loathed UNIX amongst free unix/BSD zealots.
Too bad for them. I like IRIX. And BSD. And Linux, sometimes. Solaris, however, sucks my ass. IRIX has all the features you attribute to solaris, but it's actually fast. XFS is infinitely better than Solaris standard UFS, and you get it out of the box without paying extra. IRIX's thread implementation is functional, fast, and standards-compliant. NFS, including v3, works great. Intelligent SMP support? Well, IRIX runs on the 8k+-CPU nuke simulators and other massive Origin 2000 systems. Solaris can do 64 CPUs, but slowly (well, it can't do any number of CPUs quickly). I could go on, but I'm convinced the world is blind to Solaris's failings, which are many and severe.
Slashdot Mirror
Rubbish. I don't use anything from Microsoft, and haven't for at least 4 years. You and everyone can do the same. Fact is, most people don't care enough about the issue to do the necessary investigation to take this step.
The suit against Microsoft is tripe and nonsense. The only way anyone can have a monopoly is if people choose - yes, choose - to do business with them. Sorry, you lose on this one because the argument is irrefutable. No business, no profits, no market share. There is a choice. There is always a choice.
Whoring: just don't do it.
It is your attitude that allows them to engage in monopolistic business practices. If you don't like their products - and it's obvious that you have serious issues with them - then instead of whining about it on /. just stop doing business with Microsoft. It's really just that simple. Corporate profit whores are the easiest entities in the world to manipulate. All you have to do to change their ways is to choke off their profits.
If you stick a fork in your eye, I will neither help you get it out nor sympathize with you; you stuck it in there and it's your own damn fault. Using Microsoft products is the same way. Anyone who does so is just asking for problems. I'm not claiming nobody else's products have flaws, only that Microsoft's have many more flaws than anyone else's, and as you mention their fundamental strategy merely worsens the situation. If you use them, you deserve what you get.
Finally, I end virtually every post this way: if your employer "forces" you to use this stuff, just remember that in most countries you can always quit. So either stop whining about it or quit your job and go work elsewhere. "Whoring: Just don't do it!"
"Just don't do it!"
Or maybe they really are fixed. Who cares anyway? Only suits read software reviews in trade rags, and only idiots put any faith in them. At the end of the day, does it make one bit of difference to anyone? NO! The idiotic suits who base their purchasing decisions on reviews are always going to end up with crap, because, well, they're idiots. People who use Free software for various reasons, including but not limited to issues of freedom and quality, but don't spend their lives talking about it, aren't affected either. They use the same software in the same ways they always have. The only people who care are the self-proclaimed "Open Source Evangelists" who seem bound and determined to piss off everyone within earshot by harping on how much better Linux is than [whatever]. These people know nothing about technology, nor about business. They cannot write a line of code, nor can they run a successful enterprise. They are mindless drones caught up in the whirlpool of excitement that the magic word "Linux" generates today.
In a few years, when all this calms down, Linux will be just another option for business types, and it'll be the same software with the same license the geeks have always used. The loudmouthed advocates will have to spend their time on other things. God forbid, Slashdot might not even be profitable any more.
We don't care. Review is fixed, review isn't fixed. You want to know how something works? The only way you'll ever know is to evaluate it in the context of your specific application. No thinking human gives a rat's ass what any reviewer writes, or what motivates him or her to write it. Get a fucking life.
Open one up sometime. Look at the chips. You will see that they use standard peecee components like ATI graphics, IDE, and Goldstar (yes, Goldstar) CD drives. In my book, that makes it a peecee.
I wonder if you use Matlab, which doesn't seem you do.
It's not my primary application, no. I use my systems for development. Since I know for a fact that matlab does not run on sparc-sun-linux (I do admin matlab, I just don't normally use it), I would strongly suggest that your disappointment with your Suns is the fault of your choice of operating systems, not hardware. Solaris has a reputation, backed up by benchmarks for whatever they're worth, for offering poor performance, especially on fewer than 16 processors.
I once worked on a project to translate a matlab program into C. I do not know whether the original program played to matlab's strengths or weaknesses, but I can say that my portable ISO C program averaged 23 times the performance of the matlab version. The point? I don't think matlab is a very good benchmark. Obviously, it's your application so it's the only benchmark you care about, but I suspect that in the grand scheme of things matlab doesn't necessarily mean much. It also has no way whatever to test things like disk I/O and internal bandwidth which are nearly irrelevant to matlab but of critical importance for virtually every other application, areas in which peecees lose to any real workstation, often by a factor of 5 or more.
My point is if I have an Alpha or Sun with a 500 Mhz processor and they cost 5000 and I can buy an Athlon 900Mhz for 2500 I pefer the Athlon and I KNOW it has very good chances of outperforming the others.
Good for you. I'm glad you've found systems that work well for your application. I'm sure you'll enjoy repairing them numerous times in the six months before they stop working completely. *shrug* It's your maintenance nightmare, not mine.
And you're welcome to spend $1000+ for a Creator 3D card that's probably no faster than a $200 PC video card.
I paid $80 for mine. FFB2+. Very nice.
And then you can get screwed when you need a patch for Solaris that's only available to contract customers.
So don't use Solaris. It isn't very good anyway. Linux runs exceptionally well on Sun hardware, much faster and more reliable than on peecee hardware.
You think everyone would rather spend 3 times as much because you're too lazy to work inside a computer for a few minutes longer?
Laziness has nothing to do with it. I was discussing cost. If something takes longer, it costs more. In an environment where you're paid to do so, the costs are immediate and direct. In other environments you must evaluate the worth of your time. Personally, I'd rather just use my computers to do the work I want to do and not spend lots of time screwing around trying to get broken, misdesigned hardware to function. YMMV of course.
Look, I really hate to use buzzwords (is it ok if they have fallen out of use?) but you need to think about total cost of ownership. If you have to pay someone $50 an hour plus benefits and taxes to fix things when they break that $3500 peecee suddenly looks pretty expensive. Real workstations are much more reliable, and when they do break it's just a matter of pulling out the broken piece and popping in the new one. If you've ever worked in real hardware you know what I mean. Any repair job is 2 minutes, and there are no bloody hands and extra screws to deal with. If we're talking about individual use systems, then the TCO depends on how much you value your time. I consider playing around in cramped, cable-rat's-nest-ified, sharp-edged, poorly labeled peecee cases to be a complete waste of my time. It's well worth the extra money to have a machine that always works; and even if it doesn't, it's trivial to fix it. If you've never owned a real workstation, you can't really argue with me. Try it; you'll never go back.
Anyone remember Intel's lawsuits against AMD for implementing this open ISA? Huh. How quickly we forget. The only reason Intel gave up is that they have something supposedly better now. On the other hand you can buy a license to manufacture as many SPARC chips as you like for $99. Total, not each. SPARC is an open ISA. x86 is only open because Intel no longer cares to defend it.
which according to Ars Technica only adds about 1% penalty to the processor's speed.
While I doubt this number, I have no other so I will not contest it. Regardless of the performance penalty, there are most certainly much larger a) power penalty - power consumption is proportional to dies size, b) heat output penalty - ditto, and c) elegance penalty. To me, the elegance penalty is the killer. It's cruft. It's a nasty hack to try and get performance from something that was never designed for it. It's a marketing decision laid down in silicon. Even if you don't care about elegance, consider this: how much faster would the CPU be if the extra silicon were a) cache, or b) logic directly related to processing, not translation. It's inexcusable.
Fuck elegance, give me just as fast for half the price and I'll take x86 ugliness any day.
I'm sorry you feel this way. I don't think I could live without an appreciation for beauty.
If you need those big caches, the 500MHz Xeon with 2MB cache goes for between $700 and $900
Uh...the street on a 2MB Xeon 500 is $3000-4000. That is, higher than a 400 MHz 4MB UltraSparc II and significantly lower in performance as well.
Unfortunately, AMD is still behind with its multiprocessor solutions...
As is Intel. The practical effects of inelegance.
Most PC platform problems could be cured by moving to faster and wider buses, and a Unified Memory Architecture like SGI used on its short-lived line of Wintel workstaions.
Sure. But that's where all the cost is, not the CPU. And if you're going to spend the money on a nice architecture, why not put in the extra $100 for a better CPU as well? Then you can kick Intel's kiester for their anticompetitive behaviour as well.
And, most existing operating systems and the software which run on them would work fine with just a minor OS patch, like the one SGI used to get NT 4.0 to run on its UMA Visual Workstations.
The operating systems that are used to actually get things done already run on the CPUs that don't suck. Linux runs on virtually everything. As does NetBSD (no SMP though). You can get realtime OSs for nearly every CPU, and there are vendor Unix OSs that work fine for most platforms. Who cares about enntee? Nobody who values his job uses it anyway. And all the useful OSs already have code to handle the I/O architectures. Why patch when useful OSs are already available?
I don't know how it's insightful. I'm not a karma whore, so I don't give a rat's ass what happens to my posts. My argument is based on technical merit - anyone doing something with less technical merit than they are capable of is evil. I'm not a businessman, so I don't care whether someone makes a profit or not. Making a profit from good technology is not evil. Making a profit (or losing your shirt) on lousy technology is always evil. You don't have to like it, but that's my point of view.
If you bought your machines directly from Sun, that's your own fault. You can buy them elsewhere for a fraction of the cost. The Ultra 10 is a peecee, so I don't see how it fits into the comparison. Of course it sucks, it's a peecee. Go buy a used dual CPU ultra 2. It's elegant, fast, and inexpensive. The performance of peecees compared with real computers depends, as always, on application. If you want to spin your cpu in a tight loop of integer instructions, then a real computer is not necessary. If you actually want to get anything done, you need some I/O bandwidth and floating point performance, things that aren't available in anything with a BIOS in it.
There are plenty of options out there; many are surprisingly inexpensive. Quality, high-performance workstations from Sun, SGI, and Decompaq can be had for less than USD 5000, often less than half of that, which do not use x86 nor the peecee architecture. You'd better hurry, though, before everyone drops their quality architectures for IA64 and gives Intel the market chokehold it has been lusting after for years.
Fight the power; insist on quality; boycott the peecee!
*sigh* I think I need to put this statement in my signature: I am not interested in convincing anyone to use anything. What does it matter what people use? If they are stupid enough to use winDOS, let them. Our objective should be to maximize freedom and quality, not to convince people to use our stuff. Everyone says derogatory things about "marketdroids" but if you look closely you'll see that the function of marketing is to convince people to use your product. In other words, you've become marketdroids without even realizing it.
What a great debate this is. It's clear that you can't marshal any arguments to counter my position (because, really, there aren't any - you want support for a closed-source product, you have to pay for it) but are bitter about the delays. Doing business with people like that sucks, doesn't it? Hope you learned your lesson. Closed source isn't evil, but you have to know what you're getting into. And in a Free Software development effort, closed source modules always lag behind in both quality and currency. Live with it, or pick a different vendor.
If nvidia wanted their drivers to work they would release the source just like everyone else, and they'd track development. Since they don't give a shiot about being a part of the community, the community feels no obligation to help them. If you buy their crap, you get what you deserve - frustration and delays. Seems fair enough to me...
It would certainly be possible to make it street legal. The description even mentions the possibility of modifications.
Because he was paid to do so.
Who would be dumb enough to buy it?
Speed Racer fans and/or car collectors who have too much money, obviously.
Lighten up.
unless it's a Microsoft server. Like the bitchy woman behind the desk at the DMV, an NT/IIS server can serve only one person at a time, does so only grudgingly, and takes frequent breaks. It even mumbles incoherently from time to time. Now that's progress.
"Napster: tired of the w4r3z scene? Steal music instead!"
"At Napster, we don't break the law. We make breaking the law easier."
"Napster: Our protocol is proprietary, but music isn't."
"FTP is better, but your friends at school will think you're cooler if you use Napster."
"Napster: redefining lameness for the next generation of children."
Of course. Proof that IRIX-targeting proprietary vendors are just as idiotic as Linux-targeting ones (libc5, yeah that'll make me buy your shit).
This is _not_ a single machine image. O2k machines have only been implemented upto 256 cpus with a single image, althoug the O2k architecture should support 4096
I'm familiar with the architecture. 256 is still four times as many as Sun offers. The Craylink technology used to link partial SGIs is also highly impressive. It's really a blazing-fast network, with hubs and so forth. Quite flexible.
These sorts of things tend to not happen with solaris. It's not nearly as esoteric, so it doesn't have the bleeding edge performance of IRIX.
IRIX 6.5, which has been around for quite a while really, is rock solid. I've had plenty of annoying problems with earlier versions, just like you. 6.2 and 6.3 would lock up, 6.1 was complete garbage, NFS had issues, and so on. But you have to compare equivalent systems - we're not comparing Solaris 2.8 with IRIX 6.2. Solaris versions less than 2.4 had a number of serious problems; it's generally conceded today that Solaris < 2.4 is effectively unusable. I'm not recommending that anyone use IRIX 5.3 any more than that they use Solaris 2.3. When comparing IRIX 6.5.[5-8] with Solaris 2.8, IOW contemporaneous operating systems, I think you'll find that IRIX comes out looking quite good for stability, ease of use, and feature set. Naturally YMMV but I'm disinclined to allow problems with earlier versions of IRIX to bew brought up in a comparison with more recent versions of (something else).
A reasonably configured used O2 in perfect condition can be had for under US$1500, about the same price as a midrange peecee. An R10k High Impact Indigo2 can be had for about $1300-$1700 as well. That's a fully 64-bit system with a 200 MHz processor (faster than it sounds) and graphics faster than all but the high-end peecee offerings. Even Sun Ultra 2 systems, which are also fully 64-bit and offer dual CPU capability, are less than $3000 in reasonable configurations today, and it's even possible to get them new. You can say what you like about high workstation prices, but in the real world, clever individuals can get nice, if slightly out of date, systems that offer good to excellent performance for prices comparable with peecees.
On top of that, the only unix box hardware I really appreciate is SGI, but the only commercial unix I would run is Solaris - Which is a fundamental incompatibility.
That seems odd. Both SGI and Sun build great machines, but I'd rather put a fork in my eye than have to use Solaris. IRIX is ok most of the time though. IMO the only acceptable OS for Sun boxes is Linux. Try it; you'll like it.
Feel free to feel like you have a larger penis because you've left the PC platform
[Looks down] Looks pretty standard to me. A refusal to compromise with idiocy doesn't come from the penis, it comes from the brain, and I'm pretty sure ours are within 20% in size.
Until the cost of systems based on other processors drops
It has. See above.
the number of available applications must increase...
I don't know about you, but I have solid applications - we're talking about things that actually work reliably here - for every task I might possibly want to do on a Unix box. I challenge you to name a task I can't do on a Unix box. That Turd or whatever other flavor of the month isn't available isn't important - what matters is what tasks you can do, and how easily you can do them. I've found that Unix systems offer more applications than I could ever find a use for.
The 8086 is not what I'm criticizing. Yes it sucked but so did everything else at that time. What I'm criticizing is the decision of the engineers to let the marketdroids run Intel and thereby prolong the life of a design that had no business surviving past 1988 or so. In the mid-80s the SPARC and MIPS projects were starting to produce marketable CPUs. These CPUs were well-designed and well-implemented, and fast. Intel's engineers are more than capable of competing with such offerings, but they chose instead to allow non-technical idiots to dictate technical policy. Specifically, the 486, Pentium, ... are mistakes and deserve to be treated as such. These CPUs should never have existed because Intel should have abandoned an architecture that by the time of the 386 was already aging very badly. I will gladly excuse technical mistakes made in the absence of information we have today. I will not excuse bad policy decisions which should have been made by engineers, made instead by braindead marketdroids.
In legal-speak, I'm saying that Intel knew, or should have known, that their current product offerings were technically inferior to those of their competitors, and should have adjusted their product line accordingly.
The i860 and i960, along with the ability to manufacture x86 CPUs that offer any performance at all, prove that Intel has a great many competent, if not brilliant, engineers. Their mistake was in giving up control of the product line. When Intel's marketdroids announced the 486, every Intel engineer should have either demanded a change, or cut and run. There is no excuse for the continuing existence of the x86.
I use the term to mean factor of 2. Adjust accordingly if your definition is different.
I was referring to the "segment" concept, the fact that physical memory is nonlinear (or however you prefer to describe it. The point is that pointers require two registers.) Thankfully protected mode helps somewhat and makes it possible for an OS to offer virtual memory and a linear address space, but the fact that 16-bit real-mode segmented address spaces still have to be dealt with at all, ever, is obnoxious and stupid.
Your point is? WinDOS has almost 90% market share. Does that mean it doesn't suck? Solaris takes a beautifully-designed lightning-fast million dollar system and makes it run like a 386 with a flaky memory module. IMHO, that qualifies as "sucks." I guess your definition is different. Just remember me when you're trading up your expensive Sun box again to make up for the failings of Solaris; I'll buy the old system from you, put UltraLinux on it, and get the same performance you will at half the price. I wish BSD had SMP support, but it's still worth using if you have a UP system lying around. Linux on SMP UltraSPARC, however, is a thing of beauty.
Too bad for them. I like IRIX. And BSD. And Linux, sometimes. Solaris, however, sucks my ass. IRIX has all the features you attribute to solaris, but it's actually fast. XFS is infinitely better than Solaris standard UFS, and you get it out of the box without paying extra. IRIX's thread implementation is functional, fast, and standards-compliant. NFS, including v3, works great. Intelligent SMP support? Well, IRIX runs on the 8k+-CPU nuke simulators and other massive Origin 2000 systems. Solaris can do 64 CPUs, but slowly (well, it can't do any number of CPUs quickly). I could go on, but I'm convinced the world is blind to Solaris's failings, which are many and severe.