You obviously don't understand the war on terror or the goals it is attemping to achive.
What it's goals are? Power, pure and simple. It's easier to control population that lives in fear, and it's easier to make them accept acts that would otherwise be condemned. How exactly does War in Iraq fit in with "War on Terrorism"? Had USA tried something like that without "War on Terrorism", it would not ahve succeeded. But now most Americans believe that Saddam was behind 9/11, and war is therefore justified.
Or, as Hermann Goerin put it: ""Of course the people don't want war. But after all, it's the leaders of the country who determine the policy, and it's always a simple matter to drag the people along whether it's a democracy, a fascist dictatorship, or a parliament, or a communist dictatorship. Voice or no voice, the people can always be brought to the bidding of the leaders. That is easy. All you have to do is tell them they are being attacked, and denounce the pacifists for lack of patriotism, and exposing the country to greater danger.""
Goering was a smart man, and current US Administration follows his teachings to the letter.
Here is a news flash, most of the remaining insurgents are not iraqi freedom fighters. they are foreign terrorist that went to iraq with the intentions of killing iraqis in order to make the united states look like it is failing.
It seems that the brainwashing is working.
yes i am talking about this. Pulling troops from iraq right after a terrorist attack were they were claiming that no more attack would happen if they did pull out onlyn lends creditability to the terrorists.
Let's see... Before the election, the candidate that would win the election, made a promise that if he won, he would pull the troops out. And now that he *shock and horror* followed his campaign-promise you flame his for "caving in"? What should he have done? Told his voters that "sucks to be you! I promised to pull the troops out, but guess what? I'm not going to do it!". Hell, Spaniards have been dealing with terrorism alot longer than Americans have, and with greater success.
The idea of terrorism being a legitamate tool so that a minority of people can get thier way is kind of liek the playground bully punching every that wants to play in the nose to get at those that do not want to play his game. It is wrong then and it is wrong now.
And what about when it's USA that does it? Like through "School of the Americas"? Or replacing democratically elected leaders with military-dictators?
What makes you think that current vid-cards are "overkill"? I mean, it seems to me that they are already struggling with Doom3 and Half-Life2 when using higher resolutions together with FSAA and AF.
Well, I would guess that Valve made no guarantees that the product you purchased will work. So why would they owe you something, since they specifically said that the product might not work as advertised?
Just tell me then, are software publishers endtitled to delivering a half-eaten stale cookie in the box labeled "Game of the year?". According to you they are.
If the game doesn't work, take it back to the store for a full refund. Problem solved. No, you are not entitled to "compensation".
I just wasted several minutes of my life reading your comments. I was expecting insightful comments, but all I got was whining! And that means that you owe me money! When can I expect compensation from you? I would guess that 100e/hour would be suitable. I wasted maybe.... 15 minutes, so 25e would be enough. When can you pay?
HD-space is REALLY cheap these days. I'm running Gentoo on a 6.4 GB hard-disk with no problems. What was the size of your HD? 2 gigs? Seriously: get on with the times and get a bigger HD! It's not like you have to sell your soul in order to afford one!
The "prompt and full" refund does not take into account many hours of grief and frustration with the non-working non-product. That is the part that I am getting a remedy for.
you did not enter in to an agreement with Valve that states that you are "entitled to remedies". But hey, I'm sure judge would sympathize with your "need for immediate remedies".... not.
I just returned HL2 to EB and I am downloading the said cracked version. It is the first time ever I am pirating a game
you have no justification, moral or otherwise, to pirate the game. If you want moral justification for your actions, you could have kept the game you bought (hence, giving the developers their money) and then using a cracked version of the game. But you didn't do that, you returned the game (and got your money back). At that moment, you lost your rights to that game, pirated or otherwise. If you return the game, you do not pirate it, period. Had you kept the game, THEN you would (IMO) have the moral justification to pirate it (if the actual retail version does not work, for some reason or the other).
Me? I have waited for HL2 for a long time. I can wait for few days more until the worst rush is over. If you can't wait for a day or two, then that's your problem IMO.
Oh and by now it is you who ows me money since the cost of your "product" is far less then the expense of my time attempting to make it work.
No they don't. They didn't make an agreement with you, where they agree to pay you money for your troubles. So quit your whining! And that is what you are doing: whining. And no matter how much you whine, what you are doing is wrong. That does not change. Yes it sucks that the authentication-servers were overloaded after the release. Well boo-fucking-hoo! Can't you wait for a day or two? "No, I'm entitled to immediate satisfaction!". Give it a break already.
Yeh, with an order of magnitude more cash spent on making them do fine.
How do you explain AMD? AMD isn't that big of a company. IBM (for example) has more resources than AMD does. So, by your logic, G5 (made and designed by IBM) should walk all over Athlon64/Opteron (made and designed by AMD). Yet it does not, even though it has more resources at it's disposal. Again: why is that? Clearly it can't be due to resources, since IBM has more resources than AMD does.
If they didn't have to effectively convert x86 instructions into Alpha instructions in hardware (hence, inefficiently) they'd be able to leave a huge chunk of silicon and a bunch of pipeline stages off.
Just because they are decoded in to RISC, it does not mean that they are converted in to Alpha-instructionsa. And, like I said, x86-compatibility eats only tiny amount of die-space. And like I already told you, x86 does not mandate longer pipelines. 486 had very few stages, yet it was a x86-CPU. Just because P4 (one particular x86-CPU) has lots of stages, does not mean all x86-CPU's must have lots of stages.
I'm saying that if Intel was spending their money on an architecture that didn't suck, they would be building faster chips and they wouldn't be running into a performance wall right now.
And what about AMD? Their CPU's are even faster than Intel's CPU, and they aren't running in to a "performance-wall". And that's due to the fact that they designed their CPU's smarter than Intel did. It's not due to x86 being sucky, it's due to better CPU-design. P4 is not being held back by x86, it's being held back by the thermal characteristics of the CPU. And that problem is due to poor design-decisions, not x86.
I don't know about the weather forecast for hell, but you seem to have an unlimited ability to put words into my mouth, so no doubt you'll come back with yet another ludicrous rehash of something I didn't quite say. Please try and restrain yourself.
Well you ARE telling how these better CPU's don't have as much resources at their disposal, and that is why they are slower than x86-CPU's. But, like I already showed you, it doesn't quite work that way. AMD is a smallish company, yet their CPU's are among the fastest there are right now. And those CPU's are x86-CPU's! And up untill few years ago, Sun had the second biggest CPU design-team in the world (behind Intel). Yet their CPU's weren't much to write home about. Clearly superior resources do not automatically mean better CPU's. And limited resources don't automatically mean crappier CPU's. If that was the case, Intel would massacre AMD. Yet, for the last 1.5 years, AMD has been kicking Intel's ass. How is that possible?
The second sentence does not constitute support for the first sentence. ALL chip designs are getting faster as process technology improves, even the more-or-less abandoned Alpha has benefitted from that.
x86-CPUs just benefitted even more. But, since those "other" CPU's are so much better, they should still do OK, right? Too bad that G4 did not do so well in the end, eh....
The Power PC architecture is the low-end cousin to Power. Not only is it an older design than the Alpha, it's not strategic for either IBM or Motorola. You're right, it has not had nearly the same kind of resources thrown at it as the x86.
PowerPC has had lots of resources poured at it. IBM, Apple and Motorola have worked hard at it. IBM's POWER-series has ALOT of resources behind it. And since G5 is derived from it, it benefits as well. Yet, with all those resources and with that superior architecture, it does not massacre x86-CPU's.
It shows that your design might be technologically "pure", but that does not necessarily turn in to real-world benefits. Hell, the hi-end CPU's (POWER, SPARC etc.) are fast. But they seem to get their speed from their humungous caches, and those cost ALOT of money.
Seriously, what you are saying is that "if these other CPU's had infinite resources at their disposal, they would walk all over x86!". No shit Sherlock! But they don't. And neither does x86 for that matter. And yet, even with their technologal disadvantages, x86-CPU's are doing just fine. So it seems x86 is not that bad after all. Even if G5 and the like had less resources behind them (and G5 has ALOT of resources at it's disposal), it should still be superior to x86-CPU's, since it doesn't suffer from the "sucky" x86. Yet, it's not. It's competetive, but that's all.
But, I think we could argue about this untill hell freezes over....
complex stages can become a clock speed bottleneck, and how Intel's been able to push process technology and processor design to overcome the handicap of the lousy x86 architecture... so far.
x86 (the architecture) is not holding those CPU's back. Hell, they have been getting faster and faster all the time. Intel has been running in to problems recently when it comes to power-consumption and clock-speeds, but that's due to the design of P4. And that is not due to the architecture.
All of the oh-so-ironic questions you're asking here are answered there, if you could be bothered to read what I actually wrote instead of being arch.
Where do you answer my questions regarding Itanium? Where do you answer my question regarding G5? You just keep on whining about "if Alpha had similar resources as x86 had, it would have won!". Well, when we talk about x86 here, we are talking about the CPU's that use that instruction-set. Itanium has Intel's resources behind it and no x86 to carry around. G5 has IBM's resources behind it and no x86 to carry around. Yet those two chips do not massacre their x86-cousins.
Or are you claiming that G5 or Itanium do not have enough resources behind them? Seriously: just answer the damn question. G5 has a "superior" RISC-instruction-set, state-of-the-art process, lots and lots of resources behind it, no sucky x86 to carry around. Why doesn't it massacre x86-CPU's? According to you, it should walk all over P4/Athlon64/Opteron. But it doesn't. It's competetive, nothing more, nothing less. It doesn't massacre it's x86-cousins.
I was talking about pipeline-stages, not number of pipelines as such. I apoligize if I wasn't clear on that.
Actually, it doesn't.
As a rule of thumb: it does. Details may wary, of course.
At the same time you still want as few stages as you can, because the more instructions you have in flight the bigger the penalty when you're blocked on some dependency.
Maybe, but more pipeline-stages does not automatically mean less performance. Why did P4 beat G4, even though G4 had less stages than P4 did? Why did G4 beat G3, even though G3 had less stages than G4 did?
And that is why the architecture matters, and why an architecture can force an implementation to use a longer pipeline.
Then why did original Pentium have so few stages, while P4 has ALOT of stages? Architecture (x86) is the same on both, yet the pipeline-lengths are radically different. Clearly, the architecture does not determine the number of stages, that is up to the design of the CPU.
but on today's hardware the overhead it imposes is great enoug
AFAIK, on modern CPU's the "legacy overhead" x86 imposes on the CPU is about 1.5 million transistors. And that is not much.
You just keep on staring at the number of stages. Shouldn't you be staring at the end-result? Fact is that while Alpha was superior in the beginning, it kept on losing it's advantage, untill it was no longer the uber-chip it once was.
The situation today is that huge amounts of resources are being expended on making an instruction set that's a very poor match for todays processor technology run very fast. Given comparable resources, the Alpha (or any other RISC instruction set designed to execute on modern hardware) would go much faster.
And why wasn't Alpha given the same resources? Could it be that it didn't sell that well? Maybe it wasn't so good in the end, huh? And yes, compatibility with software IS an advantage. Just look at Itanium. It has HUGE amount of resources behind it, and it's architecture is written from scratch (so you can't complain about sucky x86), and it's not doing so well. Why do you assume that Alpha would have automatically done well?
you won't make it any truer by pointing to what superior process and bigger bankrolls can do to overcome the x86 handicap.
Itanium has lots of resources behind it. And it doesn't suffer from the x86-baggage. Yet it gets spanked by x86 on numerous occasions. Yes, it superior in some areas, but it's also order of magnitude more expensive.
Given comparable resources, the Alpha (or any other RISC instruction set designed to execute on modern hardware) would go much faster.
Or how about G5? It has state-of-the-art process-technology and no x86-legacy to carry around. And while it's a good chip, it does not mop the floor with contemporary x86-CPU's. Why is that? According to you, it should massacre x86, yet it does not. It performs well, but it's not the be-all end all CPU, like it should be according to you. Why is that?
A lesson that may soon come to the forefront again, since process and implementation seem to be running out of headroom.
I see no reason why we should ditch x86 or x86-64, do you? If x86 is so sucky, why is it still the fastest thing out there, even though there are alternatives that have "cleaner architecture" and lots of resources behind it?
The architecture doesn't say "you must have N pipeline stages" no, and I was obviously being flip, but to claim that the architecture has nothing to do with he number of pipeline stages necessary to efficiently implement it implies either extreme naivete or an attempt to muddy the waters.
let me repeat since you just don't "get it". The CPU can have any number of pipelines. The number of pipelines is up to the design of the CPU in question. Like I said, you can have x86-CPU's with VERY long pipelines (P4), or you can have x86-CPU's with shorter pipeline (A64 etc.). Hell, original Pentium had 5-stage integer-pipeline and 6-stage FP-pipeline (less than Alpha I might add). How does that fact fit in your "x86 has long pipelines!"-drivel? Or are you saying that Pentium was not a x86-CPU?
So, allow me to repeat: The architecture has nothing to do with the number of pipeline-stages. You can have CPU with long pipelines or short pipelines, and both of those could still belong to the same architecture (in this case, x86)
12-14 pipeline stages is still pretty high, when the next generation Alpha was only going to have nine, and when the Athlon is clock-limited by the complexity of its pipeline stages while Alpha had been able to stay ahead in both clock and performance throughout the '90s... with only seven.
Having less stages generally boosts the amount of work getting done per clock-cycle. But it usually makes it harder to ramp up clock-speed. True, Alpha WAS really really fast when compared to others. And it did have higher raw MHz in the beginning. But the fact remains that x86-CPU's first overtook it in raw Mhz and later in absolute performance as well.
Instead of staring at the number of stages, look at the performance. Alpha was good. But it has been overtaken long ago. I don't care what the situation was in the 90's, I care what the situation is today.
Since I am going to get flamed anyway, does linux support 64bit apps yet? Not just support for system memory above 4GB, but a full 64bit API set? Just curious as I don't know.
What would you consider to be a "64bit app"? On my Gentoo-machine (Athlon64 3200+) everything is compiled as 64bits. That includes Glibc, GCC, Kernel, KDE, KDE-apps etc. etc. There are some individual 32bit apps installed (Firefox for example, so I can use it with Flash (which only work on 32bits)), but for all intents and purposes, the system is 64bits.
Hell, Linux has supported 64bit apps for YEARS! Linux was ported to 64bit Alpha in 1994! And it was 64bit, not a 32bit OS running on 64bit CPU.
I'm well aware that Alpha was a kick-ass chip. Emphasis on the word "was". As time progressed, it's speed-advantage got smaller and smaller.
Maybe Alpha was "2-3 generations ahead when it was released". But the competition has released several several new generations since then. More than Alpha ever did. So it doesn't matter what the CPU WAS like, what matters is what it is today.
The Alpha design let them have high clock speeds without deep pipelines.
IIRC, in the later stages of it's life, Alpha-CPU's were having serious problems ramping up their clock-speed. Competition marched forward, but Alpha was standing still.
AFAIK, Fastest Alpha-CPU's achieved clock-speeds of 1.3GHz. And that was in August this year. Pray tell: how does 1.3Ghz translate in to "high clock-speeds without deep pipelines"? Athlon64 is currently at about 2.6GHz, twice the clock-speed on the Alpha, and it doesn't have uber-long pipeline (like P4 does).
In case you didn't know, those are up to individual CPU's, and not due to the architecture. Hell, P4 has what, 30 stages? A64 has about 12-14. And yet, both are x86-CPU's (A64 is also a x86-64-CPU).
Architecture (x86 etc.) has nothing to do with the number of pipeline-stages. So try to find better excuses, OK?
The US didn't blow up unarmed at distance individuals going to work (9/11).
Well, the 9/11 terrorists killed themselves while killing those americans, whereas Americans quite often rely on cruise-missiles and the like. So yes, you are "killing at distance". And besides, 9/11 claimed about 3.000 civilian casualties, civilian casualties in Iraq are ALOT bigger than that!
The US is not led by rich jerks like Bin Laden or Sadam who's sole purpose in life is to use religeon as an excuse to accumulate power and kill people who do not agree with his views.
Bush and Company are "rich jerks". And besides, Iraq was a secular state. Did you know that Tariq Azis (Iraq's foreign minister during the first Gulf War) is a Christian?
Your just ticked as the US founders has good sense to seperate church and state.
I guess that's why GWB tells people "God speaks through me"?
Of course you can buy any kind of ridiculous heatsink/fan/peltier/whatever for your CPU. Just because you CAN does not mean that you must have one. The regural OEM heatsink/fan that ships with 90nm Athlon64 is just that: a regural heatsink/fan-combo. It's not some ridiculous apparatus as shown on your pic. And it keeps the CPU cool, while not being loud. The fan on the heatsink automatically adjusts it speed according to the temperature of the CPU.
So you find the most ridiculous-looking aftermarket heatsink on the market, and somehow assume that 90nm A64 somehow "needs" something like that? Sorry to rain on your parade, but it does not. OEM a&4 does NOT ship heatsink/fan like the one shown on your picture.
Is it really so difficult to admit that G5 is not the uber-cool processor some people make it out to be? Are you people living in denial or something?
Well 90nm Athlon64 has a die-size of 83mm2. And since they must run hotter than G5 does, it must need insane cooling-system just to keep them cool, right? I mean, since the die-size is so small and all? Wrong! They manage just fine with regural heatsink/fan! But how can that be??
So let me ask you again: Why does "cool-running" G5 need liquid-cooling for, whereas "hotter" A64's do not? Yes, G5 has a bit smaller die-size (66mm2 vs. 83mm2), but since G5 "runs cooler" that shouldn't be a problem? But it is, why? Could it be because G5 is NOT the "cool-running" CPU some fanboys make it out to be?
Slashdot Mirror
What it's goals are? Power, pure and simple. It's easier to control population that lives in fear, and it's easier to make them accept acts that would otherwise be condemned. How exactly does War in Iraq fit in with "War on Terrorism"? Had USA tried something like that without "War on Terrorism", it would not ahve succeeded. But now most Americans believe that Saddam was behind 9/11, and war is therefore justified.
Or, as Hermann Goerin put it: ""Of course the people don't want war. But after all, it's the leaders of the country who determine the policy, and it's always a simple matter to drag the people along whether it's a democracy, a fascist dictatorship, or a parliament, or a communist dictatorship. Voice or no voice, the people can always be brought to the bidding of the leaders. That is easy. All you have to do is tell them they are being attacked, and denounce the pacifists for lack of patriotism, and exposing the country to greater danger.""
Goering was a smart man, and current US Administration follows his teachings to the letter.
It seems that the brainwashing is working.
Let's see... Before the election, the candidate that would win the election, made a promise that if he won, he would pull the troops out. And now that he *shock and horror* followed his campaign-promise you flame his for "caving in"? What should he have done? Told his voters that "sucks to be you! I promised to pull the troops out, but guess what? I'm not going to do it!". Hell, Spaniards have been dealing with terrorism alot longer than Americans have, and with greater success.
And what about when it's USA that does it? Like through "School of the Americas"? Or replacing democratically elected leaders with military-dictators?
What makes you think that current vid-cards are "overkill"? I mean, it seems to me that they are already struggling with Doom3 and Half-Life2 when using higher resolutions together with FSAA and AF.
IIRC, Blue Shift was made by Gearbox, not Valve, and Gearbox has not given their permission to use Blue Shift.
Well, I would guess that Valve made no guarantees that the product you purchased will work. So why would they owe you something, since they specifically said that the product might not work as advertised?
If the game doesn't work, take it back to the store for a full refund. Problem solved. No, you are not entitled to "compensation".
I just wasted several minutes of my life reading your comments. I was expecting insightful comments, but all I got was whining! And that means that you owe me money! When can I expect compensation from you? I would guess that 100e/hour would be suitable. I wasted maybe.... 15 minutes, so 25e would be enough. When can you pay?
HD-space is REALLY cheap these days. I'm running Gentoo on a 6.4 GB hard-disk with no problems. What was the size of your HD? 2 gigs? Seriously: get on with the times and get a bigger HD! It's not like you have to sell your soul in order to afford one!
Dude, "Guido" is not the preferred nomenclature. Italian-American, please.
you did not enter in to an agreement with Valve that states that you are "entitled to remedies". But hey, I'm sure judge would sympathize with your "need for immediate remedies".... not.
you have no justification, moral or otherwise, to pirate the game. If you want moral justification for your actions, you could have kept the game you bought (hence, giving the developers their money) and then using a cracked version of the game. But you didn't do that, you returned the game (and got your money back). At that moment, you lost your rights to that game, pirated or otherwise. If you return the game, you do not pirate it, period. Had you kept the game, THEN you would (IMO) have the moral justification to pirate it (if the actual retail version does not work, for some reason or the other).
Me? I have waited for HL2 for a long time. I can wait for few days more until the worst rush is over. If you can't wait for a day or two, then that's your problem IMO.
No they don't. They didn't make an agreement with you, where they agree to pay you money for your troubles. So quit your whining! And that is what you are doing: whining. And no matter how much you whine, what you are doing is wrong. That does not change. Yes it sucks that the authentication-servers were overloaded after the release. Well boo-fucking-hoo! Can't you wait for a day or two? "No, I'm entitled to immediate satisfaction!". Give it a break already.
How do you explain AMD? AMD isn't that big of a company. IBM (for example) has more resources than AMD does. So, by your logic, G5 (made and designed by IBM) should walk all over Athlon64/Opteron (made and designed by AMD). Yet it does not, even though it has more resources at it's disposal. Again: why is that? Clearly it can't be due to resources, since IBM has more resources than AMD does.
Just because they are decoded in to RISC, it does not mean that they are converted in to Alpha-instructionsa. And, like I said, x86-compatibility eats only tiny amount of die-space. And like I already told you, x86 does not mandate longer pipelines. 486 had very few stages, yet it was a x86-CPU. Just because P4 (one particular x86-CPU) has lots of stages, does not mean all x86-CPU's must have lots of stages.
And what about AMD? Their CPU's are even faster than Intel's CPU, and they aren't running in to a "performance-wall". And that's due to the fact that they designed their CPU's smarter than Intel did. It's not due to x86 being sucky, it's due to better CPU-design. P4 is not being held back by x86, it's being held back by the thermal characteristics of the CPU. And that problem is due to poor design-decisions, not x86.
Well you ARE telling how these better CPU's don't have as much resources at their disposal, and that is why they are slower than x86-CPU's. But, like I already showed you, it doesn't quite work that way. AMD is a smallish company, yet their CPU's are among the fastest there are right now. And those CPU's are x86-CPU's! And up untill few years ago, Sun had the second biggest CPU design-team in the world (behind Intel). Yet their CPU's weren't much to write home about. Clearly superior resources do not automatically mean better CPU's. And limited resources don't automatically mean crappier CPU's. If that was the case, Intel would massacre AMD. Yet, for the last 1.5 years, AMD has been kicking Intel's ass. How is that possible?
x86-CPUs just benefitted even more. But, since those "other" CPU's are so much better, they should still do OK, right? Too bad that G4 did not do so well in the end, eh....
PowerPC has had lots of resources poured at it. IBM, Apple and Motorola have worked hard at it. IBM's POWER-series has ALOT of resources behind it. And since G5 is derived from it, it benefits as well. Yet, with all those resources and with that superior architecture, it does not massacre x86-CPU's.
It shows that your design might be technologically "pure", but that does not necessarily turn in to real-world benefits. Hell, the hi-end CPU's (POWER, SPARC etc.) are fast. But they seem to get their speed from their humungous caches, and those cost ALOT of money.
Seriously, what you are saying is that "if these other CPU's had infinite resources at their disposal, they would walk all over x86!". No shit Sherlock! But they don't. And neither does x86 for that matter. And yet, even with their technologal disadvantages, x86-CPU's are doing just fine. So it seems x86 is not that bad after all. Even if G5 and the like had less resources behind them (and G5 has ALOT of resources at it's disposal), it should still be superior to x86-CPU's, since it doesn't suffer from the "sucky" x86. Yet, it's not. It's competetive, but that's all.
But, I think we could argue about this untill hell freezes over....
x86 (the architecture) is not holding those CPU's back. Hell, they have been getting faster and faster all the time. Intel has been running in to problems recently when it comes to power-consumption and clock-speeds, but that's due to the design of P4. And that is not due to the architecture.
Where do you answer my questions regarding Itanium? Where do you answer my question regarding G5? You just keep on whining about "if Alpha had similar resources as x86 had, it would have won!". Well, when we talk about x86 here, we are talking about the CPU's that use that instruction-set. Itanium has Intel's resources behind it and no x86 to carry around. G5 has IBM's resources behind it and no x86 to carry around. Yet those two chips do not massacre their x86-cousins.
Or are you claiming that G5 or Itanium do not have enough resources behind them? Seriously: just answer the damn question. G5 has a "superior" RISC-instruction-set, state-of-the-art process, lots and lots of resources behind it, no sucky x86 to carry around. Why doesn't it massacre x86-CPU's? According to you, it should walk all over P4/Athlon64/Opteron. But it doesn't. It's competetive, nothing more, nothing less. It doesn't massacre it's x86-cousins.
Answer me that.
I was talking about pipeline-stages, not number of pipelines as such. I apoligize if I wasn't clear on that.
As a rule of thumb: it does. Details may wary, of course.
Maybe, but more pipeline-stages does not automatically mean less performance. Why did P4 beat G4, even though G4 had less stages than P4 did? Why did G4 beat G3, even though G3 had less stages than G4 did?
Then why did original Pentium have so few stages, while P4 has ALOT of stages? Architecture (x86) is the same on both, yet the pipeline-lengths are radically different. Clearly, the architecture does not determine the number of stages, that is up to the design of the CPU.
AFAIK, on modern CPU's the "legacy overhead" x86 imposes on the CPU is about 1.5 million transistors. And that is not much.
You just keep on staring at the number of stages. Shouldn't you be staring at the end-result? Fact is that while Alpha was superior in the beginning, it kept on losing it's advantage, untill it was no longer the uber-chip it once was.
And why wasn't Alpha given the same resources? Could it be that it didn't sell that well? Maybe it wasn't so good in the end, huh? And yes, compatibility with software IS an advantage. Just look at Itanium. It has HUGE amount of resources behind it, and it's architecture is written from scratch (so you can't complain about sucky x86), and it's not doing so well. Why do you assume that Alpha would have automatically done well?
Itanium has lots of resources behind it. And it doesn't suffer from the x86-baggage. Yet it gets spanked by x86 on numerous occasions. Yes, it superior in some areas, but it's also order of magnitude more expensive.
Or how about G5? It has state-of-the-art process-technology and no x86-legacy to carry around. And while it's a good chip, it does not mop the floor with contemporary x86-CPU's. Why is that? According to you, it should massacre x86, yet it does not. It performs well, but it's not the be-all end all CPU, like it should be according to you. Why is that?
I see no reason why we should ditch x86 or x86-64, do you? If x86 is so sucky, why is it still the fastest thing out there, even though there are alternatives that have "cleaner architecture" and lots of resources behind it?
let me repeat since you just don't "get it". The CPU can have any number of pipelines. The number of pipelines is up to the design of the CPU in question. Like I said, you can have x86-CPU's with VERY long pipelines (P4), or you can have x86-CPU's with shorter pipeline (A64 etc.). Hell, original Pentium had 5-stage integer-pipeline and 6-stage FP-pipeline (less than Alpha I might add). How does that fact fit in your "x86 has long pipelines!"-drivel? Or are you saying that Pentium was not a x86-CPU?
So, allow me to repeat: The architecture has nothing to do with the number of pipeline-stages. You can have CPU with long pipelines or short pipelines, and both of those could still belong to the same architecture (in this case, x86)
Having less stages generally boosts the amount of work getting done per clock-cycle. But it usually makes it harder to ramp up clock-speed. True, Alpha WAS really really fast when compared to others. And it did have higher raw MHz in the beginning. But the fact remains that x86-CPU's first overtook it in raw Mhz and later in absolute performance as well.
Instead of staring at the number of stages, look at the performance. Alpha was good. But it has been overtaken long ago. I don't care what the situation was in the 90's, I care what the situation is today.
What would you consider to be a "64bit app"? On my Gentoo-machine (Athlon64 3200+) everything is compiled as 64bits. That includes Glibc, GCC, Kernel, KDE, KDE-apps etc. etc. There are some individual 32bit apps installed (Firefox for example, so I can use it with Flash (which only work on 32bits)), but for all intents and purposes, the system is 64bits.
Hell, Linux has supported 64bit apps for YEARS! Linux was ported to 64bit Alpha in 1994! And it was 64bit, not a 32bit OS running on 64bit CPU.
I'm well aware that Alpha was a kick-ass chip. Emphasis on the word "was". As time progressed, it's speed-advantage got smaller and smaller.
Maybe Alpha was "2-3 generations ahead when it was released". But the competition has released several several new generations since then. More than Alpha ever did. So it doesn't matter what the CPU WAS like, what matters is what it is today.
IIRC, in the later stages of it's life, Alpha-CPU's were having serious problems ramping up their clock-speed. Competition marched forward, but Alpha was standing still.
AFAIK, Fastest Alpha-CPU's achieved clock-speeds of 1.3GHz. And that was in August this year. Pray tell: how does 1.3Ghz translate in to "high clock-speeds without deep pipelines"? Athlon64 is currently at about 2.6GHz, twice the clock-speed on the Alpha, and it doesn't have uber-long pipeline (like P4 does).
In case you didn't know, those are up to individual CPU's, and not due to the architecture. Hell, P4 has what, 30 stages? A64 has about 12-14. And yet, both are x86-CPU's (A64 is also a x86-64-CPU).
Architecture (x86 etc.) has nothing to do with the number of pipeline-stages. So try to find better excuses, OK?
No, but I know that it was a kick-ass chip in the year sword and shield. Modern CPU's would mop the floor with it.
Yes: x86-64 at least. Seriously: what's wrong with x86? And x86-64?
Alpha? I though you wanted "next generation" chips, not chips from yesteryear.
Well, the 9/11 terrorists killed themselves while killing those americans, whereas Americans quite often rely on cruise-missiles and the like. So yes, you are "killing at distance". And besides, 9/11 claimed about 3.000 civilian casualties, civilian casualties in Iraq are ALOT bigger than that!
Bush and Company are "rich jerks". And besides, Iraq was a secular state. Did you know that Tariq Azis (Iraq's foreign minister during the first Gulf War) is a Christian?
I guess that's why GWB tells people "God speaks through me"?
Why do you need an alternative? Is Winamp going to mysteriously vanish from your hard-drive now that Nullsoft has closed their doors?
Of course you can buy any kind of ridiculous heatsink/fan/peltier/whatever for your CPU. Just because you CAN does not mean that you must have one. The regural OEM heatsink/fan that ships with 90nm Athlon64 is just that: a regural heatsink/fan-combo. It's not some ridiculous apparatus as shown on your pic. And it keeps the CPU cool, while not being loud. The fan on the heatsink automatically adjusts it speed according to the temperature of the CPU.
So you find the most ridiculous-looking aftermarket heatsink on the market, and somehow assume that 90nm A64 somehow "needs" something like that? Sorry to rain on your parade, but it does not. OEM a&4 does NOT ship heatsink/fan like the one shown on your picture.
Is it really so difficult to admit that G5 is not the uber-cool processor some people make it out to be? Are you people living in denial or something?
here, here, here and here.
Well 90nm Athlon64 has a die-size of 83mm2. And since they must run hotter than G5 does, it must need insane cooling-system just to keep them cool, right? I mean, since the die-size is so small and all? Wrong! They manage just fine with regural heatsink/fan! But how can that be??
So let me ask you again: Why does "cool-running" G5 need liquid-cooling for, whereas "hotter" A64's do not? Yes, G5 has a bit smaller die-size (66mm2 vs. 83mm2), but since G5 "runs cooler" that shouldn't be a problem? But it is, why? Could it be because G5 is NOT the "cool-running" CPU some fanboys make it out to be?