I'll answer to everyone who replied to me in one big message:
G5 Specific instruction usage sounds suspicious. I really like the relaxed IEEE math operations.
These look like compiler optimisation routines, not benchmark optimisation. I agree that it DOES make a difference, but probably not such a big one.
As for the malloc special implementation, it's suspect, I admit, but I don't know enough about that to make a serious analysis, and it falls into the "of course they cheated in some places". I just don't think they cheated to the extent that's talked out in the posted article.
And yes, Altivec is in the G5, IBM incorporated the Motorola tech for them. Check here you can see the Velocity engine core.
Finally, as for the SMP bench, I tried to find them before but couldn't find my reference. Here's what I could find now for SMP and Single-CPU. The benchmark that the other guy posted are somewhat suspicious, as it shows a better increase from 2-way to 2-way with HT than from 1-way to 2 way. Not sure it makes much sense.
Apple has deliberately turned off processor features on the other platforms that would have led to their 'fastest in the world' claim being untrue. That's the point of the article. Cross-platform benchmarking IS hard, but deliberately crippling what you benchmark against in order to look better makes it seem that your software/hardware/whatever just isn't as good as what you're comparing it to...
OK, I mostly skimmed the article, but he's among other things complaining that they turned off SSE2. May I mention that from what I could gather, the benchmarks used on the Apple platforms had NO Altivec optimisation? With that in mind it seems that disabling SSE2 was simply done to level the field. If there had been Altivec optimisations, then for comparison's sake it would make much better sense to use Altivec and SSE2. Actually, they might have chosen to disable SSE too, but they didn't!
The other feature he's complaining about is the disabling of hyperthreading. From other benchmarks I've seen before, hyperthreading in SMP systems usually results in equal or slower performance, or at most a 10% addition in certain benchmarks. It was probably better to leave it off.
Finally, about the discrepancy between Veritest's/Dell's/Intel's benchmarks, this is to be expected. Veritest compiled the benchmarks with GCC 3.3, and certainly used different compiling options and different testing options than Dell used. Unless you use the same options and methodology on every test, comparing benchmarks is useless.
I'm not saying Veritest and Apple didn't do their best to look good, of course they did! But at least you have to give them credit for going with an independent firm with a full report (where everything is laid out), instead of absurd and evidently fabricated application benchmarks like they've done in the past.
As another poster mentioned, benchmarking is HARD, and harder across platforms, especially on a new CPU platform with no optimizations and no way to use some of the CPU features. When we get a benchmark version that allows for full use of al the features of the 970 (G5) and the x86 CPUs, then we might get a clearer picture. It also doesn't remove the fact that these machines are MUCH, MUCH better than the G4s, or that Apple also promised the processor would scale to at least 3GHz within a year.
Oh of course one of his arguments about his righteousness is "Look at all these Mac fanatics who flame me". He's not much better than them, from what I can see. One fanatic from one camp doesn't make all of them fanatics, and doesn't validate his points one iota (neither does flaming him destroy his points, which is why intelligent rebuttal would be better, but I have the feeling he would most likely not publish that).
Current jurisprudence appears to indicate that this'll get thrown unless unless the chip company caves and settles.
I'd be surprised to see them settle, since it's TSMC, one of the biggest chip manufacturer in the world, their products are found in everything from computers to toasters...
No, really, it looks like the plaintiff is trying to pull a SCO.
They made it standard, yes, by making it exclusive on the iMacs. But they were late to adopt it compared to other manufacturers, I'd been seeing and had USB on PCs for quite some time before Apple put it in. It hadn't yet reached much momentum yet, as peripherals were still rare, and Apple's adoption was helpful in that regard.
My list isn't going to be exhaustive but should provide some pointers:
Software:
1- Nicer Interface. Admit that Aqua looks much better than Luna.
2- Unix-based. You can run pretty much any Unix software on OS X with X11.
3- Stability. I have to say WinXP and OS X are pretty much similar there, but better than other Windows versions.
4- The Apple iApps. Nothing beats iTunes, iMovie, iPhoto, and iDVD.
5- Ease of install and software update/upgrade. Much easier to install OS X than Windows, software updates are much more reliable (and rarer) than MS. Updating to a new OS version or reinstalling if necessary is painless, whereas XP almost forces you to reformat.
6- Security. Most security-conscious tools and applications in OS X are open-source and/or Unix-based, and as we all know security failures are rarer for those, and patching is faster and more reliable.
7- You don't support Microsoft unless...
8- You can still run a recent version of Office if you need to, OpenOffice or Appleworks work well otherwise.
Hardware:
1- Although Apple sometimes is late to adopt certain standards (USB and USB 2 are examples), they are still the only manufacturer to implement firewire across their entire product line, and have firewire 800 on all high-end machines, as well as (now) serial ATA.
2- They're nicer to look at, and STILL easier to work inside than most PCs I've seen (exception for the iBooks, they're an horror to work in).
3- They're very robust, mostly apply to the laptops but still an important factor for some.
4- You just KNOW it's all gonna work together.
Note that I like PCs too, not just Macs, but you mostly asked for the Mac's strong points, so I'm not gonna be PC's advocates now.
Yes, a boycott. That way, RIAA sales will go even further down, and they'll continue to blame piracy
"See it's rampant, and increasing, our sales are even lower than they were! We must have the right to destroy those evil pirates' computers"
Which will not help at all until EVERYONE gets in, and that won't happen very soon. And we still need to enjoy music, and some mainstream music is good, it's just that most of it is so identical to the last one out.
The real problem is the power of corporate america, how they can bully through legal system, how they can bully politicians and buy laws in their favor, how it takes a superhuman effort from the populace to defeat such lawsuits or stop such laws from being passed. Congressmen do not really bother listening to their own constituents (as they understand their re-election is more dependent on the cash they get from corporations than on the votes of the people they're supposed to represent), and it takes a LOT of noise to make them do so.
So you either need changes in the legal and electoral system, or you need changes in the rights of corporations. Take your pick. I'd go for some of all three. One, it's forbidden for one party to spend more on defense than the other party can afford, unless you agree to pay for both defenses upfront and cannot get it back later. THAT would deter frivolous lawsuits. Two, No more soft money and contributions are limited in proportion to the number of people living in the area, and donations from a single person is also severely limited. A corporation cannot give more than a single individual could. Three, corporations cannot bring lawsuits against individuals with whom they do not have a business relationship without prior approval from a judge.
Re:Linux, BSD. How about Minix?
on
My Visit to SCO
·
· Score: 1
I don't think you realize yet that SCO wants to sue EVERYONE on the planet who has ever written an OS or even uses one. All they care about is how much cash they wring out of everyone until some people get fed up and stops them, along with all the IP lawyers out there. Their sickness is a mental problem akin to rabies, I think.
Someone has been posting this AND got modded up to at least 3 on every SCO discussion ever since the real circus started a few weeks ago. get a clue, Moderators!
And of course, we all know that Microsoft's Licence is much better than the GPL, and its terms are so much more reasonable. After all, giving away all your rights away to Bill Gates is the natural thing to do, no?/sarcasm
I mean, if you want to use Windows applications, just install the Windows that came free with your computer.
Free? as in beer or as in speech?
On a related note, how come there are no Linux emulators for Windows?
Probably because the point in using Linux is in leaving the Windows world behind as much as possible. Using a Windows emulator in Linux is a small concession to the need to run specific software, it's only running when absolutely necessary, and you know it's not a real Windows. Running a Linux emulator in Windows would be essentially useless since you wouldn't gain what Linux gives you: stability, security, and openness. The underlying reality would still be Windows.
Oh yeah, and most emulators require a functional install of Windows anyway. So it's also about the convenience of not having to restart all the time, or having to use several computers.
Not a good idea. Especially if the cable is plugged in and the system is running. Not for your possible death, oh no, anyone stupid enough to do that merits his fate as a possible Darwin Award winner, but for the poor system that might have had Linux installed on it and gotten a new life...
But remember, there are no documents ever written to this effect. No emails that can be found or memos to be brought forward. No one even knows what is going on except the people at the top. No one has actually said "Linux must die". But this is the ultimate goal.
Me thinks you've watched JFK too often. But it's not unreasonable to believe the possibility either.
Come on, there's no, I repeat, no form of energy production/transformation, whether it's fossil fuel, hydrogen, or burning human waste, that's 100% efficient and that will have no effect on the environment.
Living beings are exothermic and release all sorts of gases and heat and waste byproducts. What's important at this point is not to attempt to remove all of those from the energy-conversion systems we use, but to minimize their amount and possibly make sure they affect less critical portions of the environment.
What's worse? Fossil fuel or hydrogen? And to those that argue that producing hydrogen will require fossil-fuel energy are mistaken. Hydro-power and other sources can be used even more effectively.
Yeah, I did before posting. I tried it again, typed "ls -Al |more" and the output was pretty much what you'd expect on a unix/linux box. I've got a jpg of the output here.
The story notes that this book is about power tips for Mac OS X, "amazingly enough". As a Mac OS X user, this is upsetting... it seems to me that the poster finds it unusual or ironic that ORA would release a book of "power tips" for OS X?
Euh no, the poster finds it funny that anyone wouldn't be able to figure out that the hints are about OS X since it's in the NAME of the book.
How can they know of a margin of error when they made up the numbers? Reliable margin of errors come from knowing how the tools you use (physical or mathematical) are good at measuring whatever you are measuring.
You know your ruler is precise up to 1 mm or so, and that to get more precise you need a better instrument. Same with statistics: reliable statistical mathematical tools exist to evaluate how precise your measurement is. The BSA didn't use any of those to do their measurements, they instead used the patented "Nose-o-meter" which has no margin of error at all, since it gives them exactly the numbers they need.
You don't know much about how the BSA thinks or about their past history if you think that.
Actually, they DO tabulate Free Software, and it's included in their "pirated software" category. You see, the way they "make up" their statistics, if you don't buy a piece of software, it's pirated. Since you didn't have to pay for all that free software, then it goes into the "piracy" category.
So you see, they do calculate it, just not in the way we'd do it or in the way most intelligent, sensible people would. They use free software figures to inflate the piracy figures.
It is consistent with their mindset and their own internal logic, which makes people pirates by default and anyone who uses free software a communist.
Doesn't recorded history start a few thousand years ago? We have some records from the Sumerians, and history became a science in the Greco-Roman period.
Astronomy and astronomical records are known to have existed during that period, although reliable ones can be said to exist only since Copernicus, Kepler and Galileo.
Maybe you should have said "in recent history", or "in modern history". That would have been a lot more accurate!
Slashdot Mirror
That's bullshit and you know it! Really, EVERY company does this. It's called marketing, and marketing is nothing else than institutionalized lying.
I'll answer to everyone who replied to me in one big message:
These look like compiler optimisation routines, not benchmark optimisation. I agree that it DOES make a difference, but probably not such a big one.
As for the malloc special implementation, it's suspect, I admit, but I don't know enough about that to make a serious analysis, and it falls into the "of course they cheated in some places". I just don't think they cheated to the extent that's talked out in the posted article.
And yes, Altivec is in the G5, IBM incorporated the Motorola tech for them. Check here you can see the Velocity engine core.
Finally, as for the SMP bench, I tried to find them before but couldn't find my reference. Here's what I could find now for SMP and Single-CPU. The benchmark that the other guy posted are somewhat suspicious, as it shows a better increase from 2-way to 2-way with HT than from 1-way to 2 way. Not sure it makes much sense.
OK, I mostly skimmed the article, but he's among other things complaining that they turned off SSE2. May I mention that from what I could gather, the benchmarks used on the Apple platforms had NO Altivec optimisation? With that in mind it seems that disabling SSE2 was simply done to level the field. If there had been Altivec optimisations, then for comparison's sake it would make much better sense to use Altivec and SSE2. Actually, they might have chosen to disable SSE too, but they didn't!
The other feature he's complaining about is the disabling of hyperthreading. From other benchmarks I've seen before, hyperthreading in SMP systems usually results in equal or slower performance, or at most a 10% addition in certain benchmarks. It was probably better to leave it off.
Finally, about the discrepancy between Veritest's/Dell's/Intel's benchmarks, this is to be expected. Veritest compiled the benchmarks with GCC 3.3, and certainly used different compiling options and different testing options than Dell used. Unless you use the same options and methodology on every test, comparing benchmarks is useless.
I'm not saying Veritest and Apple didn't do their best to look good, of course they did! But at least you have to give them credit for going with an independent firm with a full report (where everything is laid out), instead of absurd and evidently fabricated application benchmarks like they've done in the past.
As another poster mentioned, benchmarking is HARD, and harder across platforms, especially on a new CPU platform with no optimizations and no way to use some of the CPU features. When we get a benchmark version that allows for full use of al the features of the 970 (G5) and the x86 CPUs, then we might get a clearer picture. It also doesn't remove the fact that these machines are MUCH, MUCH better than the G4s, or that Apple also promised the processor would scale to at least 3GHz within a year.
Oh of course one of his arguments about his righteousness is "Look at all these Mac fanatics who flame me". He's not much better than them, from what I can see. One fanatic from one camp doesn't make all of them fanatics, and doesn't validate his points one iota (neither does flaming him destroy his points, which is why intelligent rebuttal would be better, but I have the feeling he would most likely not publish that).
I'd be surprised to see them settle, since it's TSMC, one of the biggest chip manufacturer in the world, their products are found in everything from computers to toasters...
No, really, it looks like the plaintiff is trying to pull a SCO.
They made it standard, yes, by making it exclusive on the iMacs. But they were late to adopt it compared to other manufacturers, I'd been seeing and had USB on PCs for quite some time before Apple put it in. It hadn't yet reached much momentum yet, as peripherals were still rare, and Apple's adoption was helpful in that regard.
My list isn't going to be exhaustive but should provide some pointers:
Software:
1- Nicer Interface. Admit that Aqua looks much better than Luna.
2- Unix-based. You can run pretty much any Unix software on OS X with X11.
3- Stability. I have to say WinXP and OS X are pretty much similar there, but better than other Windows versions.
4- The Apple iApps. Nothing beats iTunes, iMovie, iPhoto, and iDVD.
5- Ease of install and software update/upgrade. Much easier to install OS X than Windows, software updates are much more reliable (and rarer) than MS. Updating to a new OS version or reinstalling if necessary is painless, whereas XP almost forces you to reformat.
6- Security. Most security-conscious tools and applications in OS X are open-source and/or Unix-based, and as we all know security failures are rarer for those, and patching is faster and more reliable.
7- You don't support Microsoft unless...
8- You can still run a recent version of Office if you need to, OpenOffice or Appleworks work well otherwise.
Hardware:
1- Although Apple sometimes is late to adopt certain standards (USB and USB 2 are examples), they are still the only manufacturer to implement firewire across their entire product line, and have firewire 800 on all high-end machines, as well as (now) serial ATA.
2- They're nicer to look at, and STILL easier to work inside than most PCs I've seen (exception for the iBooks, they're an horror to work in).
3- They're very robust, mostly apply to the laptops but still an important factor for some.
4- You just KNOW it's all gonna work together.
Note that I like PCs too, not just Macs, but you mostly asked for the Mac's strong points, so I'm not gonna be PC's advocates now.
"See it's rampant, and increasing, our sales are even lower than they were! We must have the right to destroy those evil pirates' computers"
Which will not help at all until EVERYONE gets in, and that won't happen very soon. And we still need to enjoy music, and some mainstream music is good, it's just that most of it is so identical to the last one out.
The real problem is the power of corporate america, how they can bully through legal system, how they can bully politicians and buy laws in their favor, how it takes a superhuman effort from the populace to defeat such lawsuits or stop such laws from being passed. Congressmen do not really bother listening to their own constituents (as they understand their re-election is more dependent on the cash they get from corporations than on the votes of the people they're supposed to represent), and it takes a LOT of noise to make them do so.
So you either need changes in the legal and electoral system, or you need changes in the rights of corporations. Take your pick. I'd go for some of all three. One, it's forbidden for one party to spend more on defense than the other party can afford, unless you agree to pay for both defenses upfront and cannot get it back later. THAT would deter frivolous lawsuits. Two, No more soft money and contributions are limited in proportion to the number of people living in the area, and donations from a single person is also severely limited. A corporation cannot give more than a single individual could. Three, corporations cannot bring lawsuits against individuals with whom they do not have a business relationship without prior approval from a judge.
I don't think you realize yet that SCO wants to sue EVERYONE on the planet who has ever written an OS or even uses one. All they care about is how much cash they wring out of everyone until some people get fed up and stops them, along with all the IP lawyers out there. Their sickness is a mental problem akin to rabies, I think.
Someone has been posting this AND got modded up to at least 3 on every SCO discussion ever since the real circus started a few weeks ago. get a clue, Moderators!
And of course, we all know that Microsoft's Licence is much better than the GPL, and its terms are so much more reasonable. After all, giving away all your rights away to Bill Gates is the natural thing to do, no? /sarcasm
Free? as in beer or as in speech?
Probably because the point in using Linux is in leaving the Windows world behind as much as possible. Using a Windows emulator in Linux is a small concession to the need to run specific software, it's only running when absolutely necessary, and you know it's not a real Windows. Running a Linux emulator in Windows would be essentially useless since you wouldn't gain what Linux gives you: stability, security, and openness. The underlying reality would still be Windows.
Oh yeah, and most emulators require a functional install of Windows anyway. So it's also about the convenience of not having to restart all the time, or having to use several computers.
I always preferred this interview
Not a good idea. Especially if the cable is plugged in and the system is running. Not for your possible death, oh no, anyone stupid enough to do that merits his fate as a possible Darwin Award winner, but for the poor system that might have had Linux installed on it and gotten a new life...
Me thinks you've watched JFK too often. But it's not unreasonable to believe the possibility either.
Living beings are exothermic and release all sorts of gases and heat and waste byproducts. What's important at this point is not to attempt to remove all of those from the energy-conversion systems we use, but to minimize their amount and possibly make sure they affect less critical portions of the environment.
What's worse? Fossil fuel or hydrogen? And to those that argue that producing hydrogen will require fossil-fuel energy are mistaken. Hydro-power and other sources can be used even more effectively.
I'm gonna regret this link though...
Start your Windows box, or anyone else's Windows box that's running Windows XP. Type ls, enter. Are you using Unix then?
Since Darwin is really a BSD-offshoot, shouldn't it have the same rights?
You mean companies like Rambus and SCO?
Euh no, the poster finds it funny that anyone wouldn't be able to figure out that the hints are about OS X since it's in the NAME of the book.
You know your ruler is precise up to 1 mm or so, and that to get more precise you need a better instrument. Same with statistics: reliable statistical mathematical tools exist to evaluate how precise your measurement is. The BSA didn't use any of those to do their measurements, they instead used the patented "Nose-o-meter" which has no margin of error at all, since it gives them exactly the numbers they need.
Actually, they DO tabulate Free Software, and it's included in their "pirated software" category. You see, the way they "make up" their statistics, if you don't buy a piece of software, it's pirated. Since you didn't have to pay for all that free software, then it goes into the "piracy" category.
So you see, they do calculate it, just not in the way we'd do it or in the way most intelligent, sensible people would. They use free software figures to inflate the piracy figures.
It is consistent with their mindset and their own internal logic, which makes people pirates by default and anyone who uses free software a communist.
3. Profit!
Astronomy and astronomical records are known to have existed during that period, although reliable ones can be said to exist only since Copernicus, Kepler and Galileo.
Maybe you should have said "in recent history", or "in modern history". That would have been a lot more accurate!
PPC970 Benchmarks
Quite impressive, I'm eager to see them in action.