Apple Hardware VP Defends Benchmarks 1081
He said Veritest used gcc for both platforms, instead of Intel's compiler, simply because the benchmarks measure two things at the same time: compiler, and hardware. To test the hardware alone, you must normalize the compiler out of the equation -- using the same version and similar settings -- and, if anything, Joswiak said, gcc has been available on the Intel platform for a lot longer and is more optimized for Intel than for PowerPC.
He conceded readily that the Dell numbers would be higher with the Intel compiler, but that the Apple numbers could be higher with a different compiler too.
Joswiak added that in the Intel modifications for the tests, they chose the option that provided higher scores for the Intel machine, not lower. The scores were higher under Linux than under Windows, and in the rate test, the scores were higher with hyperthreading disabled than enabled. He also said they would be happy to do the tests on Windows and with hyperthreading enabled, if people wanted it, as it would only make the G5 look better.
In the G5 modifications, they were made because shipping systems will have those options available. For example, memory read bypass was turned on, for even though it is not on by default in the tested prototypes, it will be on by default for the shipping systems. Software-based prefetching was turned off and a high-performance malloc was used because those options will be available on the shipping systems (Joswiak did not know whether this malloc, which is faster but less memory efficient, will be the default in the shipping systems).
As to not using SSE2, Joswiak said they enabled the correct flags for it, as documented on the gcc web site, so that SSE2 was enabled (the Veritest report lists the options used for each test, which appears to include the appropriate flags).
Who cares? (Score:5, Insightful)
If you want OSX, you'll need to get the PPC.
If you want Windows, you'll get the x86.
If you want Linux, you can pick up 10 [slashdot.org] and build yourself a cluster for the price of one of these new machines.
Honesty (Score:5, Insightful)
I found that to be refresing especially in light of all the recent benchmark tests that have not been so forthright with all their methods and procedures.
Benchmarks (Score:1, Insightful)
Everyone should benchmark with GCC (Score:5, Insightful)
And that's not to mention the benefits for OSS compilers. Imagine the kind of resources and funding processor companies would dump into open source compiler projects if they were going to be the basis for their benchmark scores instead of their closed source proprietary compilers.
Separate compiler from hardware? (Score:4, Insightful)
Removed one of the processors for the SPEC CPU 200 (Score:5, Insightful)
It really seems like they tried to do a pretty even evaluation. And again, if the benchmarks were so off then why was the performance on the G5 apps so good? And that was without G5 tuning most likely.
Compiler's should be included (Score:3, Insightful)
So, the correct SPEC results for the 3GHz Intel CPU (from the www.spec.org website) should be 1200 SPECInt and 1229 SPECFp, vs. 800 SPECInt and 840 SPECFp for the PowerPC 970.
The Intel CPU wins (by a lot!)
Re:Separate compiler from hardware? (Score:5, Insightful)
However, the IMPORTANT benchmarks are the ones that test the whole system. The stuff up on stage during the keynote is the proof of that, I think. The architecture of the G5 gives it a big win. Getting data to the processor is almost as important as having a fast processor itself.
Does this mean.. (Score:4, Insightful)
regarding the malloc.... (Score:3, Insightful)
Personally I don't care very much about synthetic benchmarks, day-to-day apps are a much better test: OTOH if it comes out that this 'tweaked' malloc library was used for PhotoShop (with, say, side effects of making PS taking up 2 gigs of RAM and it crashing every 2 hours) then my feelings of this would change...
Re:Who cares? (Score:5, Insightful)
This means 3 things:
People just have a hard time dealing with this whole "choice" thing.
Other Benchmarks? (Score:5, Insightful)
Further I notice he didn't mention the problem of not doing comparisions to AMD.
While I can understand his reasoning, the fact is that most software on the PC runs under VC or Intel's compiler. It doesn't run under gcc. The benchmark might be a fair Linux/OSX comparison but implies something about Windows/OSX that is incorrect.
I'd also like to see the tests done under Mathematica and Photoshop discussed more. Apple's had a history with photoshop so there is prima facie reasons to distrust it. But the Mathematica test, which seemed the most exciting to me, is what I'd really like to see.
Realistically though the tools for Apple, including graphics drivers, are all very beta. So we should see improvements with time. And realistically benchmarks are typically kind of deceiving as an indicator of real world performance.
So any word on these other questions?
PS - I love OSX and would love to make a Mac my primary machine. If only Project Builder was up to the task so I could abandon Visual Studio. But I am excited about the G5, but I think Apple's "questionable" tactics have brought a lot of unfavorable press that more honesty would have avoided. Personally I think being within 10% - 15% of the top end PC would have been fine.
More Data Good (Score:3, Insightful)
I think that Apple should benchmark every case, especially the ones that the Wintel boosters are whining about, and post ALL the results. It certainly can't hurt if the G5 wins them all anyway. And even if it does not, it will bolster the argument that Apple's trying to be a straight shooter with these tests, which will help their credibility. Which is important, because that's at least as much at stake here, as the arguably temporary "bragging rights" of being the fastest.
Honesty (Score:4, Insightful)
Perhaps a case of ineffective thoroughness? (Score:5, Insightful)
I have to say, this puts things in an interesting light.
Does a company, in trying to be fair as it seems in this case, get penalized for choosing the best optimization and not testing with the worst optimizations(as per their views)?
In looking at other sites like Tom's Hardware and Anantech, I think the answer is simple: Show all of the results, both the good and the bad. That way, it removes the spectre of doubt in peoples' minds that fairness wasn't present during testing.
Personally, I don't have the funds to get a G5 based system. It just isn't in the budget. But then again, the only reason I would buy a G5 system over an x86(Opteron or P4) would be to run Mac OSX. :)
I'm guessing that tests will be conducted by various groups over the next few days to either validate or invalidate the tests. Sounds alike like that whole MS/cost analysis/web server speed fiasco all over again.
Despite the tests, for Mac users who wish to stick with Mac OS X, the G5s are as fast as they come.
Re:Compiler's should be included (Score:3, Insightful)
Re:I love Apple (Score:5, Insightful)
Q: You know what a $750 dual 3gHz Xeon PC is called?
A: "Stolen Goods"
Really, the point for Mac users is not so much whether or not the G5 wipes the floor with the Pentium, but whether or not the long period of performance stagnation is coming to an end, and whether or not top-end Mac performance will once again be reasonably comparable to top-end PC performance. And it looks like the answer to both questions is YES! (FINALLY!!!)
compilers do matter (Score:3, Insightful)
I use the Intel compilers on all the x86 boxes (including Athlons) I run on, because they give me the best performance on my application code (a computational fluid dynamics code). When evaluating a machine, the only thing that matters to me is how fast it runs my code. I will use whatever compilers give me the best performance (while still giving the right answer).
For people not doing high-performance computing, none of this matters. Nor, for that matter, does any chip from the last year or so -- they are all fast enough. But when looking for the fastest platform to run your specialized codes on, everything must be taken into account.
An interesting benchmark I'd like to see if for Intel and Apple to agree on some codes/benchmarks, and then they should be free to trick out machines however they seem fit, and run the codes at the maximum speed (without outright cheating, and still making sure they get the right answer), and submit those numbers for comparison. In the end though, it is whatever code you run personally, and how that performs that matters the most.
benchmarks and real apps (Score:2, Insightful)
What I do like is the real-world application performance. I was much more impressed by the photoshop, etc. comparisons (Mathematica: comparison to higher end unix-workstations!) than those silly benchmark numbers. Real tests that finish twice as fast are more impressive and less deceptive (well, a bit anyways).
So now we wait...for panther, for the G5's and for the G5 powermac (could be some time though...sigh). I am already happy that apple is back on track, if their product is even any faster than other platforms: good for them...and us. Even other platforms must welcome some competition, right?
Re:Removed one of the processors for the SPEC CPU (Score:5, Insightful)
Oh, yeah. Steve probably said "hey, vendors, come on over and do a little demo. Yeah, it'll be a duel, but don't worry about recompiling for the G5 (which is supposed to be trivial). We'll just see what happens."
Look -- they spent every last minute they could optimizing the builds they used for the demo - don't doubt it for a minute. On the other hand, every last minute probably wasn't all that long, and the demos did kick ass.
But let's call an Apple an Apple. This was a DEMO. Smoke and mirrors were involved. But I drank the cool-aid; I believe it's faster. Dunno how much, but I don't really care. Mostly I'm just happy it kicks the crap outta the systems they're shipping now.
Re:compilers do matter (Score:3, Insightful)
Benchmarking (Score:5, Insightful)
Correct in the sense that he wasn't necessarily being unfair. I don't think Apple was raelly cooking the books here. OTOH benchamarking is quite difficult.
No, it would not be fair to compare intel compilers to gcc compilers. But what about, say, another non-hardware tied compiler? Look at it this way - 3dmark scores on graphics cards. Theoretically it should give a good impression on thier relative hardware - but we all know that it doesn't necessarily. It may do something bad on one system, great on another, one system may cheat and have special code to work better with that particular test.
Same here. Ideally you would find many benchmarks, not just gcc, but both with all optimizations on, with all off, both with the best compilers, worst compilers, and middle of the road. You also need memory intensive, processor intensive, grpahics intensive, floating point, integer, and many others to get the full idea and compare it to what you need to do with the computer. For many of the crowd that worries over this stuff overclocking can become an issue also.
This is why benchmarking is as much art as science. I care about all those numbers - I have code compiled specifically for my athlon-mp's, some generic, and some optimized for p4's for the consumer tasks. On our computation cluster we use specialised compilers. I care how it runs on all of it for real world use. But no hardware manufacturer does those extensive of a tests - they pick the best of the ones they can claim "fair" on usually.
And lastly, in the end, who cares? Unless you are regularly running 4 hour jobs from a console it is irrelevent. It is more important that you are productive with the interface and that is personal choice. Few consumer tasks (and even programming tasks) require that power - and the stuff that does is generally handled by specialised hardware. Then if they have the fastests today they won't tomorrow.
...but is gcc equal across architectures? (Score:5, Insightful)
In this case, performance will in part be a function of how mature and optimized the generation of code for the advantages of that particular chip is.
Because there is no guaruntee at all of fairness by using gcc for both processors, except of course if we had the expert opinion of someone intimately familiar with gcc's code generation for both processors, using gcc for both processors would seem to be little more than a marketing tactic to give the appearance of fairness and credibility.
It seems to me that a better test is to take the best compiler widely available for each chip, and then run your tests with the produced code. Now, this isn't necessarily real world application testing, but that isn't what we are necessarily looking for here.
How well the processor performs with code generated by the best generally available compiler, is, apart from extraordinary measures, the best prediction we have of how generally the processors will compare for any given well-written, production quality code.
Re:Separate compiler from hardware? (Score:4, Insightful)
The important thing is to test the processors on an even playing field, as much as anything could possibly exist.
Apple using GCC is the fairest way to test, for both systems. I'm sure that a specific IBM compiler would ALSO make the PPC970 look good, as much as an Intel compiler would make the Xeon looks good. But that's like testing cars by putting me in one and Schumacher in another. It doesn't really matter how good the car is I'm driving, Schumacher is going to wipe the floor with me, and you'd then conclude that the car Schumacher was driving was better? Probably not. It's not a fair test. For results that are even close to scientific, you have to eliminate as many variables as possible, including the compiler.
This situation needs to be abstracted a little (Score:4, Insightful)
What seems to be missing in all of this is the big picture. Whether or not the G5 is 1.2% faster or slower than the Xeon/P4/Opteron is not a uniform answer. Different apps are going to perform differently on different platforms. Not only that, but there are a million possible variations of benchmarks that could make both sides the winner. Like Greg said in the interview, if Apple was looking to cheat they wouldn't have hired an independent company and provided full disclosure.
Processor speed notwithstanding, most Mac users are so because of Apple's OS not their hardware. Windows would slow me down much more than 6 extra cycles of processor speed. For my circumstances, the fact that Apple now has hardware fast enough that it can even attempt to make the 'fastest' claim is far more important.
Of courser the Dell benchmarks..... (Score:4, Insightful)
I have this theory. A 2Ghz twin G5 system is really fast. And if you have some money to spend and you want a really fast system and you'd like to run OSX then you could do worse than buy one.
gcc a constant, that is naive (Score:5, Insightful)
If everyone benchmarked with open source compilers, there would be none of the shady benchmark-specific optimizations you'd expect to see in proprietary compilers. Everything would be above the table.
No. Benchmarks would become less realistic. There is nothing wrong with proprietary compilers. If they use proprietary techniques not available to gcc, so what. The only consideration is whether the compiler is available to other developers. The Intel compiler is available under Windows and Linux so it would be completely fair to try it and gcc and pick the faster of the two.
Re:Compiler's should be included (Score:3, Insightful)
You mean to use it for everything? No, that's not the point. You use the malloc that is right for your application. In this case, it is fast FPU or whatever, so they use that one, which is what you would use for Mathematica or a similar application.
Re:Compiler's should be included (Score:2, Insightful)
Re:More marketing games. (Score:2, Insightful)
b/c we all know that no one uses SPEC for marketing purposes! Everyone uses SPEC benchmarks for evaluating the purchase of a personal computer. Why, just the other day my mom called me up to say, "Hey Bill, your father and i were just about to buy a new PC so that we can send digital pictures to grandma. what's the spec CPU2000 numbers on that little Lindows number you keep on talking about?"
Re:Honesty (Score:3, Insightful)
I found that to be refresing especially in light of all the recent benchmark tests that have not been so forthright with all their methods and procedures.
If it wasn't amply documented, it would violate the terms of the SPEC benchmark. Give them credit where it's due, but really, the only reason why there's more information about these benchmarks than they normally give is because it's required of them by the benchmark they chose to use.
Re:yeah right (Score:4, Insightful)
The earlier discussion on the tests blew up at 1000+ comments and after a careful read (of both the article _and_ the discussion) even i, a confessed mac zealot, was wondering how true the tests were. having joswiak (i love that name) immediately come out and justify apples claims is as big of a PR move as spending a few undred thousand on advertising while costing less and telling us more.
just my 2c but i dont recall nvida immediately coming out to diprove any claims of cheating and thats why there are numerous nvida jokes in the origianl thread.
Re:Curious (Score:5, Insightful)
You know, I always thought that this would be a good idea for Slashdot. I mean, you guys must have some pretty interesting contacts by now, use some of them to do a "news" article or two on your own. I'd still keep the old Slashdot question/answer interview around because they are interesting and good for the people who don't have time to do a traditional interview.
Compiliers built to cheat at SPEC (Score:2, Insightful)
Re:...but is gcc equal across architectures? (Score:4, Insightful)
Re:Who cares? (Score:5, Insightful)
Does either of those questions alone determine whether you should get a G5 based system or not? No, but that doesn't mean the question isn't worth discussing.
I'm curious how fast the G5 is at certain kinds of tasks. Not because it helps me make a purchasing decision, but because I'm a geek and I'm interested in that kind of thing. This being slashdot, I'm sure I'm not the only one. Does superior floating point performance mean "better for photoshop"? Maybe not, but I'm more intersted in FP performance that PS performance.
I thought the original article was worth a read. I thought some of the comments are interesting. I thought this follow up was interesting. People like me are the ones who care. People who just want to know what kind of computer to buy, well yes, they are totally missing the point.
Re:Separate compiler from hardware? (Score:3, Insightful)
In any case, you want to eliminate as many variables as possible, as best you can. Testing Photoshop on the Mac and UT2K3 on the PC tells you nothing about which machine is faster. It only tells you that Photoshop runs fast on the Mac and UT2K3 runs fast on the PC. Different compilers - as different as they'd be when made by completely different vendors - are just another variable that ruin the scientific process.
In the end, there's no good way to test which machine is better at the processor level. In the end, it's not really even the biggest deal. Objective performance on real-world applications is the big deal. Let Apple and Dell duke it out over Mathematica or Photoshop. In the past, the fastest machine always did win. P4s are faster than G4s at doing Photoshop filters, and that's what matters more to people in the end, I think. This SPEC stuff is just for us geeks to mumble over.
Re:Who cares? (Score:4, Insightful)
Apple may be a hardware company, but it isn't the hardware that is attracting customers. It's the software, stupid. If anything, Apple should be talking up the benefits of the OS and the "Apple System" (where everything works seamlessly) rather than the raw speed of the processor and leaving the benchmarking to review sites.
Apple's core competence is in making systems that are easy to set up and easy to administer and easy to use. It has never been in making "the fastest machine".
Re:Compiler's should be included (Score:2, Insightful)
No, actually SPEC CPU was designed as a benchmark for a CPU (hence the name). It's openly acknowledged that it is influenced by other components in the system, so it is, in practice more of a measure of how all those components peform under high CPU load.
It is actually quite common to control the various variables in the system in order to compare how specific components improve performance (my god! using scientific methods!!!! it's crazy!!!). For example, SPEC is a good way to measure the relative performance of various Intel compilers. It's also helpful for measuring performance of various heap implementations. It's also a very good way to compare chipsets.
Honestly, everyone on this list soaks up similar style benchmarks that Anandtech and Tomshardware do. Why people choose to decide the process in this particular benchmark is flawed is beyond me.
It's money that matters. (Score:5, Insightful)
Forget about Serial ATA - (Apple is the first top-tier manufacturer to make this interface stardard across their high-end machines.)
Forget about the new motherboard featuring HyperTransport, PCI-X, and the IBM-fabbed 1GHz northbridge chip. Oh, and 802.11G, USB 2.0, FireWire 400 and 800, and Bluetooth, too.
Forget about the imagination and creativity that goes into making a project like this go from concept to reality in eighteen months.
Why support a company like that? Bunch of dirty liars - there's no way a 2GHz chip could be faster than my Intel/AMD/whatever86!
Maybe it's not ultimately faster (although Greg's comments seem to indicate that the playing field was pretty equal). I don't buy "fast". I buy well-integrated tools that help me get work done, and in turn, bill clients. So I (still) use a Mac.
Jeez - to hear people around here, you'd think that innovation, style, performance, and the courage to move forward agressively and definitively with new technologies doesn't come at a price.
What other comapny would develop all these technologies to hardware and software maturity as part of a new hardware platform, then bring it all to market with system software already written (by the same vendor, I might add) to take advantage of new hardware features?
Those things DO come at a price. The price begins at $1999.00 for the 1.6GHz G5, or $799.00 for an eMac.
As long as there are people who just want to get work done on their computers without hiring an IT department or worrying about who is responsible for which component of the system, Apple will still be around.
I bill around eight hours a day with my Macintosh - the $400.00 price premium over PC hardware at the time I bought my G4/800 simply isn't an issue - over the lifetime of the machine, I'll probably bill at least two hundred times that amount for work made possible by its existence.
That $400.00 up-front cost means that I don't have to spend my time - my extremely expensive and finite time - having to deal with at least two vendors just to get a system with competitive hardware, a competitive OS, and support for them both. If your time isn't valuable, by all means cheap out and build your oft-touted (and perfectly capable) PC from parts you buy at Frys. $400.00 means nothing to professionals - it's cheap support insurance.
I hope Apple sells a TON of these machines - because they're practically the only personal computer company willing to take the initiative and responsibility for supporting hardware and operating system on equal terms.
Perhaps if Apple stressed the cost of ownership point to more people, they'd have higher sales. Our small business has nearly thirty Macs. I'm the lone IT person, spending an entire hour a week on supporting a bunch of artists and their Macs. What similarly-sized Windows-based business can make that claim?
Re:Apple: innovation or catch up? (Score:5, Insightful)
While I appreciate the opinions and arguments of the author, I am dismayed by the constant references back to the BeBox. Yes the BeBox and Amiga (similar case) were excellent platforms when they were introduced. Yes, each had quite revolutionary ideas. Unfortunately, neither caught on. Both were targeted at geeks - a niche market with questionable budgets, based on the "$1k is TOO much to pay for a box" posts.
Apple does not invent everything, although historically they tried! Apple is clever at evaluating technologies, combining them into their existing product, and making the results available to the mass audience. I agree that many of the individual accomplishments are unremarkable, packaging all these into a new release is impressive. And doing this three times (10.0, 10.1, and 10.2) in about three years is amazing for any product. Doing this with an operating system is unparalled*.
Take a step back and evaluate Apple's announcement in the broader industry context. You may not be amazed, but I think you'll be impressed.
.
* I suggested that Apple's OS release schedule was unparalled based on the number of features being introduced. This isn't an achievement driven entirely by the programmars in Cupertino. With the Mach / BSD underpinnings, open source software can be easily ported over to the new machine (see: fink, apt-get, etc.). In many cases (e.g. Safari, ProjectBuilder, etc.), Apple is applying a flashly UI on top of standard source. The result is a relatively small number of programmers producing a large number of features. Compare this to Microsoft which uses entirely custom code and where you need a large number of programmers to get a small number of features. Compare this to the Linux model where you need a large number of programmers (as most are part-time), to get a moderate number of features. Solaris and other commercial Unixes also have this advantage, but neither has been quite as driven; I don't understand why this is so.
If this analysis is correct, OS X should have an impressive feature and Microsoft will need to change their OS development model. Linux / BSD, if they can avoid fragmentation, will continue to provide much of the R&D that the other OSes rely on.
Re:Honesty (Score:5, Insightful)
How dare Apple! But then they only had the G5 2GHz. Maybe they should wait for the 3GHz, then the comparison will be fairer?
The fact that everyone is nitpicking these benchmarks shows how close the performance is. And with such a huge "megahertz" disparity between the Xeon and the G5 shows how much power the G5 has to offer.
Re:Honesty (Score:5, Insightful)
Considering that you couldn't get either system yesterday (G5 or 3.2GHz Xeon (I hate it when slashdotters write 'zeon')), I see the whole thing as moot.
It's marketing, folks, not the bible. Greg backed up the test parameters with his data. I think the world would be a less stressful place if Windows went away, but I'm not stressing over a minute saved over a week of Photoshop work.
We spend more time thinking about what to do next in Photoshop than could possibly be saved by a faster processor/architecture/whatever.
That being said, I'll continue to buy Macs because the extra up front cost is well worth the knowledge that one company (and a rather well-run one these days) is responsible and capable enough to develop and market botht he hardware and the OS. They do a rather good job of it for a small premium.
Put another way: If I lose an hour a month because of a hardware vendor who refers me to an OS vendor to resolve a problem, I've lost an hour. I can't get that time back. If my Mac emits smoke and kernel panics at the same time, I know I can get resolution to both problems by calling Apple.
Re:Everyone should benchmark with GCC (Score:2, Insightful)
Everyone should benchmark with the actual compiler that most developers are really going to use. If that's the same between platforms, so be it. If that's different between platforms, so be it.
Sure, nothing else but using the same compiler will factor out the compiler when comparing hardware platforms. But who cares? Actual raw hardware speed is not what users care about at all. The actually speed that people are going to get out of the whole platform in real life is what people care about. And the fact is, nobody who seriously cares about performance uses GCC on x86.
The benchmarks were downright deceptive, period. And that's even without taking into account the fact that there's no such thing as a mac with more than 2 processors, while there are x86 boxes with more than 2 processors.
Here's the way I look at it:
With the benchmark results that were reported, it basically amounts to "if things were fair, we'd be almost but not quite as fast as the Intel chip -- we've almost caught up, if you ignore the high-end x86 boxes that have more than 2 CPUs".
Then on top of that, they said that they'll be at 3GHz in a year. That's a 50% speed increase in 12 months. Notice something? That's slower than Moore's law. So, what this amounts to is "we're slower than x86, and over the next year that gap will widen".
They should have just left raw computational speed out of the keynote entirely. They'd have looked less silly.
Mind you, I'm typing this on my 1GHz TiBook running OS X 10.2.6. I am a mac user myself. There's no way you'd get me to use x86 hardware for my desktop system, whether you're talking about Windows or Linux or BeOS or whatever. None the less, Apple has almost no credibility with me when they talk about system performance now.
Vindication? Or more fuel for the fire? (Score:5, Insightful)
While surprising and most certainly refreshing to see that apple is serious about their claims, serious enough to publicly rebuke the claims almost certainly first brought to the big light by /.'s earlier article, this may only be leading into a circle of prooving and disprooving.
I believe it would be best for apple to answer with a full fury of tests to truly show the full range of operating prowness of the G5's vs the P4's, etc.... at least initialy, and to from there LEAVE IT ALONE. Cause no matter how many tests they do, no matter how much proof ... there will always be people out there ready to bring flames over nothing.... For instance this guys claims that FP isn't all that important, and that int tests are basicly all that matters for the majority of users.
He and others will stick too their guns even if they have only a couple benchmarks to cite as being supirior (kinda like the G4's and their altivec/photoshop optimizations of yester-year).
Apple needs to make sure that they have a clean image of being flatly open on their claims, and then to move on without being bogged down in an obvious quagmire of platform evangalism. The truth is, their strongest advantage remains the OS and not their hardware's direct horse-power. Of course the G5 along with all the goodies they come with are incredibly great, but this isn't apple's mainstay... it's simply another selling point.
If they become entrapped in having to proove themselves through benchmarking every new release, it won't be long before their entire image would have to live up to being ahead at all costs.... and guess what... they ARE going to fall behind again.... and then they'll leap ahead again.... and then they'll fall behind... etc.... And every down cycle will be worse, since the specs will be much more associated with their image.
keep your strong point in innovation apple, and if youve got the great hardware... great.... but don't get stuck in the mind-less mhz/spec race that has stagnated computer innovation for the love of ego's.
just my 2 cents.... I develop ASP, and love win 2k adv srv, ill never use anything but unix/linux for my networking gear, and OSX keeps me damn happy when i want to do anything not mind-numbing. Cisco IOS is arcane but makes me feel good. I am biased towards all platforms.
Re:Even if Apple is faster (Score:5, Insightful)
2xCPUs would cost around $1400
Motherboard $300
'Cos everyone knows all you need is a motherboard and processors. Didn't you work in IT at a company I used to work for? You're the one who took the RAM out of my computer and said you'd be "right back", aren't you?
Excercise for you:
Add the cost of Bluetooth, PCI-X, 802.11G, Gigabit ethernet, SATA hard drives and controllers, DVD-R drive, power supply, all the other hardware stuff I've forgotten, plus iTunes, iDVD, iMovie, and the ten or so other bundled applications on the G5s, a Unix-based operating system with superior usability, and one year of free warranty and support for ALL of that stuff.
How much does your dual Xeon cost now?
Re:Everyone should benchmark with GCC (Score:2, Insightful)
That's why using the best compiler on the platform is beneficial. It's the difference between saying that the apps generically suck or they run as best they can, given the current compiler technology. Get new compilers that optimize better and recompile.
As I stated in another thread, on one project I participated in, the choice of compiler made a difference of 100% performance difference. On our simulations, that meant using the right compiler shaved *days* off the runtime. Days = several people's salaries and rapid turnaround time for the simulations. Telling my boss that because using GCC in our case was the right thing to do because it was the same across all platforms although it took 2X as long (and therefore cost 2X as much to do each job), would have been foolish for our careers.
But G5's lost in SPECint_base2000! (Score:4, Insightful)
Is the PowerMac G5 the "world's fastest personal computer"? Probably not, but it may be the first 64-bit personal computer to ship to the masses (ie. bought in a store like CompUSA). I wonder if AMD will move up the Opteron release now or if Intel will drop the price on their Itanium. If so, then people who want 64-bit x86-compat CPU's should thank Apple for bringing them their CPU's faster. =)
Anthony
Re:It's money that matters. (Score:4, Insightful)
For example:
Troll: "If I had a way to download a MP3 for a very small payment, I wouldn't steal them from KaZaA anymore"
www.emusic.com, the Apple Itunes Music Store...
Troll: "Emusic won't let me mirror the whole site, so I won't use it! Itunes doesn't use OGG, so I won't use it! So I'll still use KaZaA"
Troll: "When they make OS X that runs on Intel/AMD hardware, then I'll buy it!"
But you didn't buy your Windows XP either...
Troll: "Software should be Free!"
Same shit, different pile.
Re:gcc a constant, that is naive (Score:3, Insightful)
IMHO using gcc on both gives a false sense of security that the variable is minimized. Personally I believe using the best available to developers on the platform is the most realistic. As far as gcc being better optimizaed for x86 that is a debious assumption. Apple has been working on gcc for PowerPC for a while now. Apple had undisclosed info to guide such improvements being they worked with IBM on the PPC970. Intel does not work on gcc for x86, they have their own compiler that is free to use proprietary techniques. Some apps show a distinct improvement with Intel, results vary with app.
Re:Who cares? (Score:5, Insightful)
And that's not only thanks to the software, but also due to the great integration of software and hardware.
This integration ("it just works") is why people buy Apple. And therefore it's really hardware and software that attract customers (ey, and don't tell me I didn't buy my 17" PowerBook just for the software, I could have gotten an iBook if I only wanted to run OS X!)
Re:Compiler's should be included (Score:3, Insightful)
Also, Apple did not claim fastest desktop merely on the SPEC results, but on the real-world tests.
I don't have the inclination to continue this discussion with you, in light of this.
Re:Separate compiler from hardware? (Score:3, Insightful)
No, there is no way that a compiler for one platform can be 'the same' as a compiler for another platform. What GCC does when targeting PPC is totaly diffrent then what GCC does when targeting x86 or any other chip. The compiler 'cores' are totaly diffrent.
Apple uses that compiler as their dev compiler, and poors a lot of money into it.
Re:Everyone should benchmark with GCC (Score:5, Insightful)
Nonsense (to quote someone else in this discussion
The tests were designed to show raw hardware performance in the most fair way possible. It was NOT designed to show that the G5 is faster in real-world use. SPEC *sucks* for that, and is not designed for that. Using it in the real world, with real apps, is how you test real-world use. And Apple did that, too, though I am sure it is not the final word on the subject: for that, we wait until the machines get out into the real world.
You use it because of the OS (Score:3, Insightful)
Look, don't we all know by now that people use Macs because of the OS, not because of the speed?
As I see it, even if Apple fudged the numbers a bit (like what manufacturer hasn't), these new G5s are still the first time Apple can justifiably say that they are "comparable" (whatever that mean, and, like I care!) to Windows machines.
Frankly, I am not a computer guru (by any stretch of the imagination), but don't you all find it pretty lame that Apple needs a 64 bit processor to come close to the speeds of a 32 bit Pentium?
Still, I have a slow-assed 733 mhz G4 on my desk because I prefer OS X and because I prefer not to have MS's DRM and oppresive licening on my computer.
For running a webserver, NFS, Samba or whatever, I buy an x86 box and run Linux, because it is just cost-effective.
-A
My turn to bitch! (Score:5, Insightful)
I know I do, and that's why I'm writing this.
I can't figure out why so many people post to threads like this and
bash Apple, while saying that they would never buy a machine from them
anyway. What's the point in that? Would the industry be better off if Apple
didn't exist? Would you finally be happy if everyone went out of business
except for Dell, only selling boxes pre-loaded with Linux, for $299?
If that was true, Lindows should be
And those that say that they could build a machine themselves for way
less than a Mac, if Apple had a build it yourself, parts in a bag option for
$500 less, then people would still bitch that for that price, it should come
fully assembled.
Although yes, I am a "Mac guy" (but I've got Windows, Linux, Solaris, IRIX,
NeXT and a few other boxes on my home network), regardless of my
prejudice for the platform, you have to acknowledge what a beautiful
$3000 machine the G5 is. Clean inside and out, plenty, plenty fast for
the years that you'll have it in service, arguably a better OS than any
Linux variant and absolutely better planned out and cleanly feature
rich (and economical) than any Windows release. I was doing some
admin work on Win 2000 server today, what a disorganized, steaming
plie that thing is. Some say it's superior, I think it might be the absolutely
worst collection of software ever crammed into one box. Pheeeewwww!
But I digress. I have come here to praise the Power Mac G5....
One of my favorite things about the G5 (and I know that non-Mac users
think than Apple just makes pretty boxes), is indeed, the pretty box.
J. Ive did such a restrained design. So clean and minimal.
There's a guy with rare discipline and insight.
The new design language, aluminum and circular hole accents, also
seen in the iSight and hints of it in the line of new aluminum PowerBooks,
in my opinion is the best we've seen in the 2nd Jobs era at Apple.
I liked the clean white, crystal and chrome designs of the G4 iMac and the
iPod but this new design language is going to make for some other very
exciting products. The new display line will be beautiful, wrapped in a
thin sheath of aluminum. Will a future iPod have the look of a large-ish
Zippo lighter? What would an all-aluminum G5 iMac look like?
I'm just glad that Apple's still here, still thinking different, and still making
insanely great products.
Dell? HPQ? Gateway? Lindows? Sony? (Well, Sony's trying).
The parts bin at Frys? That little shop in the strip mall that sells cases and
motherboards? For the most part, all of that is commodity crap. Even if
you throw on your free homemade Linux on it, it's half-assed at best,
even after hours of effort.
Apple is the only computer company left that's doing anything that really matters.
Like it or not.
Here is the demo that sold me... (Score:4, Insightful)
###(My little bench mark bar graph)###
Dell Intel Xeon running Mac OS X
#
Mac OS X runs infinitely faster on the G5 than the Dell Intel XEON. Focus on that.
The G5 blows the G4 outta the water, so I really don't care how it performs to the Intel XEON.
Processor speeds aren't going to make people 'switch'. It's the User Experience / WTF can I do with this computer now? (Meaning does it run the apps I need it to run?)
I think it was Panther that stole the show for Apple, not the G5. That is an awesome OS, just the fast user switching alone sells it for me.
Compilers make a big difference but Apple was fair (Score:5, Insightful)
All in all I think this was a fair test of these CPUs, it was a level playing field. OTOH we know Intel can do much better with their compiler, but only some developers use their compiler. It would be interesting to see just how much of a benefit Apple could squeeze out of non gcc compilers, probably not as much as Intel, perhaps not anything, it depends on the work they or IBM et.al. have done on their compilers. You just know if it was to Apples advantage they'd have compiled with their best compiler and dont teh comparrison with those numbers vs Intel's so this situation has been contrived to an extent.
With Intel charging what they do for their compiler developers can be reluctant to pay extra for it, I expect almost everyone (on Windows) would use it if it were free. I know I would, but I can get by without it. I don't really have much sympathy for Intel here, they make billions of chipe, make significant performance claims based on their own compiler, yet charge for it to the point where many developers simply stick with Microsoft's compiler that they've already spend a fair bit on. Now Intel is upset that Apple used gcc, well more people might use Intel's compiler if it were easier to aquire, and clearly it would benefit Intel. If they want to run there business where everything is a profit center and they don't have to be smart enough to evaluate obvious but intangible benefits that's their business, but this is part of the price you pay for charging an arm and a leg for your compiler when you should be in the hardware business and giving your compiler away to help your customer gain the benefit of faster code from the applications they purchase. In the meantime specbench numbers for Intel are simply bogus for many applications.
Opteron = Workstation/Server (Score:4, Insightful)
a 64bit desktop computer for general use.
Certainly at $3000 the dual 2Ghz is pricey, but look at what you can do with it. This computer can work with video, audio and bitmaps NOW and it doesn't take Joe average weeks to figure out.
Only an idiot would use a shotgun to kill a fly, or a semi-trailer to bring home the groceries, but both have their place and purpose. I'm sick of idiots claiming you can create a Linux cluster to get the same power at the same price, but then not mentioning the applications they will run and more significantly their price.
Reality is MacOSX works, it works well on a G4 and even better on a G5. I'll bet no-one in your neighbourhood will buy a NEW Opteron workstation, but a few will buy a G5 Apple.
The less you know about computers and computing, the more appealing Apple's Products become.
There is something for everyone, BSD Unix for geeks, and a great interface for the rest. If only they cost a tad less!
Re:Removed one of the processors for the SPEC CPU (Score:2, Insightful)
Why would the Xeon machine crash? Perhaps:
* The Mac version of Mathematica got recompiled for a 64 bit architecture, so it could handle 64 bit memory space. The Xeon machine didn't have a 64 bit version of Mathematica, and therefore couldn't handle it.
* The Xeon version didn't handle PAE properly and had bugs.
* Any number of other reasons.
I sure took notice of Apple's benchmarks... (Score:3, Insightful)
As far as I am concerned if a dual G5 can outperform a dual Xeon under Linux using gcc then that is more "real-world" than Intel's spec results.
Re:Compiler's should be included (Score:3, Insightful)
It is incorrect to use a compiler other than the ones used,or which you will use on the applications for which you are purchasing a system.
Who cares how fast that Ferrari runs on nitro if you will only be putting Chevron gas in it for your drives around the block.
Re:Honesty (Score:5, Insightful)
This is unfortunately the problem with *all* benchmarks. Almost any two competitive systems can be measured to be faster than one another under certain conditions.
The point of Apple's benchmarks were to show that "in the general case", the G5 would be faster than an Intel workstation. The general case assumes either a) using photoshop, or b) using applications compiled with GCC.
Are either of these a large stretch? Well (b) might be, and a comparison with MSVC++ and/or ICC would be nice, but then Apple would probably just counter that with IBM's optimised G5 compiler.
If you want an honest benchmark, have Apple's system tweaked by Apple, Dell's system tweaked by Dell, and who gives a damn which complier is used? I'm a user, not a CPU. I don't care about the theoretical capacity of each computer, especially if the theory is tested using inefficient compliers.
Well then, frankly, you shouldn't be paying attention to SPEC benchmarks, you should be looking at the informal timed application benchmarks. These are more "user-centric" and "whole-system" measurements.
The point many on Slashdot are making is that SPEC benchmarks *are fundamentally* theoretical CPU capacity measurements, not intended for users.
Let Apple and Dell pick their own compliers, or even write their own compliers just for this test.
The amount of man hours that goes into an optimising compiler is arguably more than goes into an operating system kernel. It's a rough business, and usually why people tweak existing compilers to perform better on benchmarks such as SPEC.
Ok, get a grip people (Score:2, Insightful)
GCC mattered to ME (Score:3, Insightful)
So we've moved most users to OS X, a few special purpose Windows machines (Quickbooks, two designers that bring their own Windows machines, and one developer choosing between Linux and OS X).
If I cared about speed for my Unix workstations, it's a fair comparison. My OS + Applications would be run on Redhat 9 using GCC to compile under Linux.
In all honesty, the numbers aren't that meaningful, as we wouldn't consider a dual-G5 (or a dual-Xeon), but it is nice to know that Apple has "caught up." Maybe the P4 is faster or maybe the G5 is faster, but it's pretty similar.
To me, that matters, as the guy who is deciding played with an old G4 Cube with Jaguar, and it was too slow for him. Knowing that it will run OS X fast is critical in his decision.
If I run a Linux machine, the apps will be built with GCC. For Windows tests, they showed the Photoshop + Mathematica tests. For the pure crunching tests, they compared OS X to a Redhat workstation, not an unreasonable comparison.
Alex
Re:Honesty (Score:5, Insightful)
You've obviously never worked in a data center where cooling and power are a premium. In a room full of hundreds of Intel crap, you start to consider things like power consumption and heat dissipation. This is a fact: The higher the clock the more power and heat.
We started holding our data center manager accountable for his own electric bill. After that, efficiency (lower clocks to do the same work) started to take on a whole new meaning.
This particular criterion also got us to get the MS-weenies to shut up and we started to implement more Linux systems.
Real-World Performance (Score:4, Insightful)
I'm the head of a mid-sized consulting company that deals almost exclusively with digital media and digital arts firms. We have a few G5s on order, and because we're a solutions provider, we'll probably get them pretty early. I'm going to wait and see exactly how fast they are, not just in Photoshop, but also in Final Cut Pro -- which in my experience has a history of outrunning similar applications on faster hardware. It's going to be real-world performance that matters. Not SPECfp scores. And we won't know the real-world performance until people start getting their hands on some production units. End of story.
Compiler NOT constant (Score:5, Insightful)
What matters to a purchaser is "How much performance can *I* get out of this machine". If I am performing CPU-intensive scientific calculation that require the fastest CPU I can find (at least for a given number of kilodollars), I'll almost certainly spring a few hundred extra for the compiler that produces the fasted object code on that platform (if needed, there's nothing ruling out GCC automatically because it's free).
It happens that for a Xeon or P4 (or Opteron, for that matter), the compiler that produces the fastest object code is ICC. Intel has done an amazingly good job with their compiler.
Now, sure, I *could* get a similarly optimized 970 compiler for comparison.... if one existed, that is. It looks like right now, GCC is the best you can get on a 970. It doesn't do a buyer any good to know that IN PRINCIPLE a more optimized compiler could be written.
All that said, the 970 looks like a very respectable chip. And Apple is selling their new machines at a very competitive price; and Macs have extremely friendly and stable OSs. All that means that it is probably well worth buying a PowerMac even if it will crunch big computations a few percent slower than a more expensive Xeon. But still... the "GCC is the common element stuff is pretty darn bogus."
Why won't Apple just use the AIX C compiler? (Score:5, Insightful)
Let's face it: in their own way, Apple is being quite fair. Everybody in the free software community uses gcc, and publishing SPEC scores on x86 gcc is valid and useful.
However, IBM probably has C compilers for the POWER architecture that produce far more optimized code than gcc. Why hasn't Apple licensed and ported this technology?
Apple needn't resell such a C compiler, but critical system binaries (i.e. the kernel) could be recompiled for much better performance. Granted also that IBM is unlikely to support Objective C anytime soon, so such a compiler is only marginally useful.
However, Apple positively wastes these POWER chips without a vendor-optimized C compiler.
Re:Who cares?... Geeks do! (Score:5, Insightful)
Re:Honesty (Score:3, Insightful)
Yes, and I'm sure Intel would be so very helpful in getting one of their prime competitors pre-release sample versions of their chips.
Apple most likely did have to actually buy that Dell box just like the rest of us poor slobs (if us poor slobs were to buy a Dell, that is). Since they're a big competitor, I doubt they got any special favors about first ship or anything else.
Re:Who cares? (Score:4, Insightful)
I used to write image-processing software. I wrote it in C, because writing it in a higher-level language would have been absurd. These days, I write database and Web interfaces, and I use the "P" languages (PHP, Perl, and Python) because writing it in C, while certainly possible, would be a huge pain in the ass. I like all of these languages, but it's indisputable that each of them is the right tool for some tasks but not for others.
The same is true of computers in general -- processors, architectures, OS's, etc. It would be great if you could set up one system that was clearly better than all others, or even equally good, for all tasks you might want to use it for. But you can't. The difference might not be quite as dramatic as that between pliers and an axe, but it's real.
I'm very happy with my iBook. It does many things I want to do very very well, and everything else I want to do at least passably. But I'm well aware of its limitations, and chafe at them fairly often. And this would be true of any system -- laptop, desktop, handheld, whatever -- I could possibly buy. I chose it because overall it offered the best fit for what I want to do. If my requirements change, well, then, so will my computer.
Re:Why won't Apple just use the AIX C compiler? (Score:5, Insightful)
Re:Who cares?... Geeks do! (Score:5, Insightful)
RAM capacity is also not under challenge. So, for 23999 I can get a system that would permit up to 8GB of ram on the system.
Just those two unchallenged figures make this much more than just another boring speed bump hardware upgrade.
If they're providing the actual compiler flags they used and the flags used disprove one of the doubter's claims (no SSE2 use) then maybe Apple is *not* just making stuff up?
Re:Who cares? (Score:3, Insightful)
I was talking about software for personal use in my response to your post (which I did not make clear), so your exmaple is not relevant to that.
However, if someone believes in something as an ethical guideline, then they won't want to work for an employer that categorically violates that guideline. This applies not just for FS but also for any other moral stand. Someone who is anti-choice should not work for an abortion clinic.
In the case of Free Software, that is not, however, the only way to look at it. It is perfectly possible to view proprietary software as a social problem (and Free Software as the solution), yet still use significantly inferior (in terms of practical use) Free Software on the job, if you think you'll be fired for doing so. After all, an unemployed person is a person who cannot contribute to Free Software.
There are also practical reasons for using Free Software, even if it is an "inferior tool for the job that pays your bills". Before I get into those, taking a step backwards, if that "inferior tool" is one that you personally use to help you get your work done, then it doesn't matter -- as long as you get by with it (in which case, it's practical "inferiority" is highly subjective). Now, there is also justification for using those "inferior tools" even as parts of the final product, or for intra-business operations. Your company will not have to worry about the business that makes that tool going bankrupt, and having no possibility of upgrade for future needs, or bug-fixes. Your company will not have to worry about EULAs or audits from the BSA, nor bear the costs of keeping track of licenses and proofs of purchase. Your company will not be forced into mandatory upgrade schedules. Etc etc etc.
Btw, the ethical issues with FS have nothing to do with individuals not wanting to pay money to other developers. It has to do with the essential four freedoms that the FSF deems necessary to call something Free Software. None of them have anything to do with money, and I damn well suspect you knew that. So please stop confusing Free with free. There are many Free Software programs for which it is not practical to obtain the program for free ($0), and there are also many free ($0) programs that are most certainly not Free Software. Simply because most Free Software happens to be free ($0), does not mean that that is required.
Clouded judgement according to who, you? Sorry, buddy, but you are not the ultimate authority on that, nor does your example in any way provide evidence as to clouded judgement.
If someone chooses to use an inferior Free Software program due to their ethical considerations, that does not mean their judgement is clouded. It may not be the decision you would choose, nor the one that a business would choose, but that does not mean the person's judgement was clouded.
There are many cases where people choose a suboptimal solution because of their ethical considerations. For example, in labs, when mice are euthanized, they are first gassed with CO2, with 5 mice per cage, and other cages covered so that those mice can't witness the "distress of their fellows"; their necks are then snapped to ensure that they are dead, and they are then incinerated. This process takes up more time and uses more money (because of the CO2) than a faster cheaper alternative: simply putting all of the mice to be euthanized in a bag and incinerating them alive. If you believe in animal welfare (which I don't), then the more costly slower solution is better.
Ethics and morals are additional guidelines in individuals judgement. You can either agree with a person's ethics or not. It is obvious you don't agree with the ethics of Fre
big spender (Score:1, Insightful)
The $30 for the public beta was rebated on the purchase of the retail copy. So in reality you will have spent by end of year 2003, $406.95 give or take a bit cause you can find the OS cheaper at places like Outpost. Divide that amount by the 40 months between the release of the Public Beta in September 2000 and the release of Panther in December 2003 and you spent $10.17 a month or roughly 33 cents a day for OS upgrades.
Not an inconsequential sum but nothing compared to the cost of buying a latte grande at Starbucks every day.
The truth will be out soon (Score:4, Insightful)
Re:Separate compiler from hardware? (Score:3, Insightful)
Furthermore, Apple did not use the same compiler for both systems. The Xeon benchmark was compiled with a "plain vanilla" version of the compiler, with no special optimisations. The G5 version, on the other hand, was compiledwith Apple's custom version of GCC, and highly optimised for the G5.
See the section "manipulating the results", in this article [haxial.com].
Also rather conspicuous is the absence of any Opteron benchmarks. You see, even with GCC and without any special tweaking, SPEC results for the Opteron (dual 1.8 GHz) are about 60% better than Apple's proposed results for the G5 (dual 2 GHz). So they just pretend the Opteron doesn't exist.
As many people have pointed out throughout this discussion (and the ones before it - BTW, can we please have some articles not about Apple's paper launches?), this is not information and it's not a hardware review, it's marketing.
Anyone who belives this sort of thing must have a lot of disappointments in life.
RMN
~~~
Re:Why fight this fight? (Score:2, Insightful)
Yeah, but the Wintel zealots have been pooh-poohing those for years, if not outright dismissing the results as fraudulent. I've been to a few MacWorld keynotes and seen the Photoshop "bake-offs" with my own eyes. I watched the replay of the WWDC keynote video Monday evening and saw the dual 2GHz G5 totally smoke the dual 3GHz Xeon running a handful of 'real world' apps.
There's just no pleasing those assholes, there's always another complaint. I've just tuned them out, now all I hear is that noise like Charlie Brown's teacher makes.
I make my living supporting the shit that Microsoft sells-- I've seen all manner of Windows failures and shortcomings, and I've seen my share of that commodity hardware the Wintel zealots love so much fail horribly. That's why I happily spend my hard-earned money on a Mac, so I don't have to deal with those things when I come home after doing it all day at client sites. Besides, I can easily afford it because cleaning up Windows' messes is quite lucrative. Last year my end-of-year bonus (based on billable hours) was damn near $5,000.
Sure, there's a home-built PC running XP Pro sitting under the desk my G4 calls home, but I don't use it much-- it's mostly there for the occasions when I feel like tinkering for some reason. I actually turn it on maybe every other week just to download the latest handful of security updates.
This is really simple (Score:3, Insightful)
With the G5, Apple seems to be at an equivalent performance level with the PCs. With equivalent, I mean comparable, that is not extraordinarily faster or slower.
The message from these benchmarks are clearly targetet at their user base to turn their frustration / anxiety to exhilaration.
The Mac faithfuls will believe the message, even if the supporting evidence seems rather dubious, and deflect any rebuttal as coming from jalous / incompetents / trolls.
The rest of the crowd will not take Apple's words for granted and will wait for independant benchmarks when the G5 will be available, showing (my guess) that it is a very good CPU indeed, but certainly not significantly faster or slower than the best x86 offerings.
But Apple does not really care for the rest of the crowd. They passed the message to their base, it has strengthend their confidence and that is what mattered.
Re:Who cares? (Score:4, Insightful)
Not a flame, just a note on how things were when I knew physicists. Now I'm stuck with bio types :) Maybe things have changed and physicists are moving toward macs; I don't claim expertise in this area.
Re:Who cares? (Score:2, Insightful)
I beg to differ. Apple's core competence is in making systems that are sexy. :)
-Guanno
Re:Who cares? (Score:4, Insightful)
Actually, gcc is not so bad (Score:5, Insightful)
The gcc "Haifa" scheduler was donated by IBM Haifa, by the way, so I think it's not surprising that gcc produces good code on powerpc.
On Intel it's quite the same, except that gcc does not vectorize code. From what I have seen, however, icc's vectorizer is not very useful either. I recently tested ogg-vorbis (which is a plain C floating point intensive benchmark) with icc 7 and gcc 3.3 and the gcc version was actually faster than the icc version (on my Athlon XP, target CPU pentium3) despite icc having vectorized several loops.
So all this "vendor-optimized C compiler" stuff is really besides the point. No C compiler will ever be able to match the quality of hand optimized assembler code, and the most important code (ffmpeg MPEG-2 decoder and MPEG-4 codec) has already been hand-optimized. You might be able to squeeze anoter 5 percent out of your code by using a vendor C compiler with insane optimizer settings, but what good is that if the end user is only going to use gcc anyway. I know I am, so I find the numbers for gcc actually more useful for comparison purposes than some vendor C compiler comparison.
Also, we don't want to encourage vendors to produce super vendor optimizing compilers, we want them to optimize gcc (so that everyone benefits, not just their users). So the more benchmarks are done using gcc, the better!
Re:Mac users care =) (Score:3, Insightful)
So there are other 64bit PCs.
Itanium II costs 10x more and consumes 3x energy (Score:3, Insightful)
You also miss the point that GCC is much more optimized for the long established x86 platform than any other less commonly use CPU architectures such as SPARC or PowerPC and the least for the new born G5.
>> An Itanium II, btw, is 61% faster, running at half the clock speed. Incredible.
The Itanium II costs over $3000 per chip (more than the total cost of a dual 2 GHz Power Mac), consumes 3x more energy (130W vs 40W), and relies on massive on-chip cache to boost its SPEC numbers. In short, your comparison is just pure bullshit.
Re:Why won't Apple just use the AIX C compiler? (Score:3, Insightful)
That would make sense. After all, IBM are a hardware company first and foremost. Anything that makes it easier and cheaper for people to develop applications on their hardware is good for them. If you start with the assumption "lots of people use GCC on AIX anyway" (which may or may not be true) then enhancing GCC is a win-win.
Benchmark the user experience (Score:5, Insightful)
What it comes down to is the speed of the system, not the chip. The 1000+hp dragster is a useless vehicle to me because I don't need to go in a straight line at over 200 mph. What I do need is to be able to accelerate in traffic, handle corners, etc.
To me, a computer is a system. So I don't really care if the G5 is cranking out power I will never need. I feel like the G4 and the P3 are plenty powerful chips if the OS is built to be efficient and the supporting components to the system are configured correctly.
These days, my biggest reason to upgrade to a new computer is desire for faster system components. I wish my P3 had firewire (might go buy a card), I wish my PowerBook G4 (400mhz mind you) had BlueTooth (not 1600 extra mhz).
Benchmark the user experience, give a review that is more like Automobile or Road and Track. Tell us the zero to sixty and then move on the how the G5 handles in the turns. Tell us if the wind noise is less than a Xeon. Tell me if it has power windows. But don't spend 90% of your marketing materials telling me about the engine, that is only 10% of my buying criteria.
You just gotta TRY OS X!
Tests on Windows with hyperthreading. (Score:1, Insightful)
Well, why the hell not? I say 'do it'.
Although, I can see the trolls now: "Apple cheated! They used Windows!!!! of course the Mac looks better..."
Re:Apple is a Well Run Business? (Score:3, Insightful)
Dell and HP are about the only two players selling personal computers that are consistently profitable today - and HP's profits derive mainly from their high-margin servers and printer supplies - not from desktop computers. On the other hand, Apple's server business is a drop in the bucket, they only sell two real peripherals (one peripheral until this past Monday - the iPod), and have a minimal business selling boxed software. They make their profit based almost entirely on their ability to sell desktop and laptop computers.
To take one more benchmark, Gateway is the only other major manufacturer to run company stores. They've lost a bundle, locating in strip malls and out-of-the-way locations. Apple has opened over fifty stores, mainly in very high-rent locations, and is on the verge of break-even after less than two years in retail. So that's a pretty well-run business as well.
Intel/AMD? Not going to happen. Period. Same with becoming a software-only company. I posted a comment a while back [slashdot.org] explaining why that would be idiotic, and I'm sticking to it. I won't recap here in the interest of brevity, but look it up if you want to see my argument.
Re:Compiler NOT constant (Score:3, Insightful)
Re:Who cares? (Score:3, Insightful)
If I want a high-performance Web server, I'm going to use Apache. Since I'm using Apache, I'm going to be using something from the Unix/Linux world. If I need or want really badass administration tools and a good GUI, I'll grab an Xserve, which runs Jaguar Server. If all I really need is a headless box that serves up some pages, I'll build a Linux box for less than my six-month car insurance rate.
If I want to do some heavy video editing, I might consider a strong G4 or a G5. Final Cut Pro is excellent.
Games? I'll build a cheap Windows box. (Or buy a console.)
That's not saying that's all they're good for, but like with anything, there's an appropriate tool for a particular job.
Re:As usual, Apple handles this big fuss in style (Score:1, Insightful)
Re:Who cares? (Score:3, Insightful)
All you have to do is measure the performance of real-world apps on typical problems with stock hardware/software settings. Anandtech and Tom's Hardware do this all the time and nobody complains about their results. It could easily be done for the G5 vs. HP Dual Xeon 3.2's as well.
-Buy each machine stock from the factory.
-Load up Photoshop, Director, Lightwave and Maya
-Run common transforms and renders at common resolutions.
-Convert some CDs to MP3s and some AVIs and Quicktime movies to MPEG2 and MPEG4 files
-Measure the time it takes to perform the procedures.
-Report the results in a nice graph.
This is what real people do with high end Macs. It's what they buy faster machines for. How could anyone complain about such a test?
The fact is, people don't really care about which hardware is faster on "normalized" benchmarks, they care about whether the stuff they will be using it for is faster.
TW
Re:Why won't Apple just use the AIX C compiler? (Score:5, Insightful)
Most of the market wants to get their work done and doesn't care if it's x86, ppc, or some other chip that powers their computers. With Apple's unlimited client server licensing they're a cheaper solution for standard file and print servers than Windows. That's not as cheap as Linux but the hardware price difference very quickly gets swallowed up by Windows CAL costs. For small companies in the 10-100 employee range who don't want to have a full-time administrator Apple has a compelling enterprise product.
On KneeJerking (Score:4, Insightful)
I feel those shouting the loudest -scanned, rather than read the report.
Typical of the 'outrage':
http://news.com.com/2100-1042_3-10206
"It wasn't really a fair test," said Gartner analyst Martin Reynolds, who said that the Dell machines are capable of producing scores 30 percent to 40 percent higher than those produced under Apple's methodology [using the Intel compiler]...â
-Well DUH! I guess we then should have expected Intel to trot out a hand-coded/Spec optimized version of their compiler for the G5 too! Idiocy.
âoe...In response, an Apple representative said it wanted to compare hardware performance, so it made sense to use the same compiler on the Mac and the Dell. The SPEC benchmark tests measure the performance of the hardware and the compiler. âoe
-Lets get real here! NOT normalizing the compilers on each systems is nutso â"even to me (which isnâ(TM)t saying much.)
âoe...Joswiak said that the Power Mac settings were representative of how the final machines will ship, even though a few settings did differ from the way current prototypes are configured. As for the Intel-based PCs, he noted that some of the settings that have been criticized were chosen because they actually improved the performance.â
DUH again! Even I saw that! Hey people, the methodology rationale was even explained in the study! Read it!
The bottom line of most of the PC-lumpenproletariat out there seem to be: âoehey dude, ya needed to use the Intel compiler because the Specmarks are, like, soo-ooo much higher on the Dell. As for the G5, use whatever â"it sucks anyway.â
Another big moan out there was that the Dellâ(TM)s Hyperthreading was turned off. They donâ(TM)t seem to realize is (according to DELL) is that, re SpecMark, this was to Dellâ(TM)s advantage!!!!
http://www.dell.com/us/en/esg/topi
(...As was the fact that the Dellâ(TM)s were packing 512 MB more RAM than the G5! (Which NOONE seemes to have noticed. btw.)
âoe...Peter Glaskowsky, editor-in-chief of Microprocessor Report,
Damn right they do! To put it mildly.
Iâ(TM)ve read scads of articles on the various, ahem, Spec-specific âoptimizationsâ(TM) theyâ(TM)ve built into their compiler. Great too if youâ(TM)re comparing one Intel product against another â"but other than that, itâ(TM)s just marketing fluff, IHMO.
"...Jobs on Monday also showed demonstrations in which the new Power Macs outperformed the Dell by greater than 2-to-1 ratios on several programs...Reynolds says he has no reason to contest those claims. âoe...the application benchmarks look quite credible," Reynolds said.
Those usage tests may also be more important than synthetic benchmarks, he said. "The SPEC benchmarks aren't that relevant anymore. People now are looking for things like multimedia (performance) and content management."
Agreed. I also think there is just too much marketing driven Spec-chicanery going on out there for them to be considered meaningful benchmarks -if they ever were.
Anyway, the telling of the tale will be on actual boxed applications.
And although I may be surprised, I would place big bets (right now) that the G5 system -especially running Altivec-aware, 64bit recompiled applications, -will run (multiple) circles around the best MP PC versions that are out there (right now.)
But Intel and AMDâ(TM)s caldrons are busy bubbling â"and the landscape may change radically by October (doesnâ(TM)t Intel typically intro their new stuff in September and March?).
Even so, it will be interesting to see the price point any new uber-systems come in at. Right now, (unless you, brrrr...., 'roll your own'), theyâ(TM)re priced in the workstation stratosphere.
Re:Curious (Score:4, Insightful)
I hate to break it to you but many of the print reporters have very few qualifications to be covering the news but they are doing it anyways. Sure a Slashdot "professional" interview won't be extremely professional but I'm sure most people don't want it to be. I, for one, think I would enjoy a more "geek-on-the-street" kind of interview and I think that a Slashdot interview would provide that.
I may be wrong but it's at least worth a shot. It seems to have worked out pretty well in this story we are commenting on.
Brand new features all of the time? Please... (Score:2, Insightful)
1. Metal. There are techniques to get rid of most of it, but a few apps like iTunes can't be converted to Aqua. If Apple wants to provide a themable interface and let me pick when and where I want the New Butch Look of Metal, by all means, but if I don't want it, don't force it on me.
2. Services and Context Menu. Make up your mind, Apple. Where should I look for shortcuts and new tools? Surely the context menu is supposed to provide a subset of (hopefully) frequently used commands, but there's things I can only do through the context menu, and things I can only do through the Services, and (now that I think of it) things I can only do through menu icons on the right side... and some seem only available through keyboard shortcuts. How about bringing all this together and giving us a "Shortcuts" preferences pane that lets us pick the keystrokes, chords, and menus that extensions use?
3. Where's my application menu? The dock is actually pretty nice, though I'd rather that iconified windows and docked folders and the trashcan weren't all mixed up in the same section. But it doesn't provide all the functionality of that old upper right button.
4. The say Safari handles FTP is really clever, but clever isn't the same as right. It breaks ftp-hosted web pages and it seems to break ftp access through http proxies (though perhaps there I'm missing something). Plus, this kind of browser-desktop integration is the kind of thing that's caused so many security problems in the Windows world. Please, Apple, back out of that and keep the browser separate from the OS.
5. Looking at that new finder in Panther, I'm filled with fear and trepidation. It's Metal. It's apparently iTunes-like, so it might end up being non-optional Metal like iTunes. And it's got all this extra junk in the Finder windows, taking up more of my precious real estate.
Meanwhile, there's a few things they seem to have lost from the old UNIX side that I'm starting to miss. Number one is tape drive support. I've got to keep my Intel UNIX system running because I can't use Mac OS X as an AMANDA server. Also, Darwin supports more older devices (like the Adaptec 2940) that OS X has given up on... they could at least keep up-to-date drivers in there. Finally, the remote file system support is very hard to get used to... if their automount is based on the traditional one, they ought to include the -hosts map. Or toss in amd...
Oh, and the default Sendmail configuration. It doesn't really work behind a non-routing firewall. And, well, sendmail on a personal computer? How about having another look at the options available... there are mailers that are less tricky to configure, safer, and if they don't have all the functionality you need to run a major ISP they're more than adequate for home use. And anyone who actually needs sendmail should have no trouble installing their own (most of them install all the servers and server-side applications from source anyway).