Early Benchmarks: Dual 1GHz [Archive]

deepkid

Aug 16, 2002, 09:06 AM

As we've wondered in another thread..

1. What OS and version was used? Jaguar would probably be the best gauge.

2. How much RAM was in each machine?

3. What type of hard drives and what were their speeds? Were these identical?

Also, in the diagram it says that these are Apollo (7455) chips?? Not 7470, huh?
Notice that on the roadmap below..the Apollo chips weren't expected to scale past 1 Ghz.

So 7455 chips would sorta make sense in th low and mid-range machines.

However...

It should make you wonder if Apple will ship the top-end, dual-1.25 powermacs with a different chip.. maybe the 7470, which would make things very interesting. According to the roadmap, those are projected to reach 1.25 Ghz.

I don't know how close real world chip output compares with this roadmap, but maybe there's still a chance that the top end machine might be a different beast all together. (Unless someone can factually say that Apple won't be using anything different.)

http://www.geek.com/procspec/apple/g4.htm

soilchmst

Aug 16, 2002, 10:17 AM

Originally posted by deepkid
As we've wondered in another thread..

1. What OS and version was used? Jaguar would probably be the best gauge.

2. How much RAM was in each machine?

3. What type of hard drives and what were their speeds? Were these identical?[/url]

This test seems highly spuspect with no listing of the equipment in the computers tested. Maybe they only tested a standard model with the slower Radeon 9000 vs. the old dual 1 Ghz Geforce 4 Ti.

Also, I noticed on Mac centrals link to the tests that a reader ran these tests. Is that Barefeet's normal practice?

ryan

Aug 16, 2002, 10:18 AM

While I guess it is nice to see that the current middle-of-the-line PM G4 is as fast as the former top-of-the-line PM G4 it seems to me that there shouldn't have to be tests designed specifically to stress the machine to show how the (hacked) implementation of DDR is of benefit to the new machines. The new machines should simply be faster, regardless of what they're doing, than the machines they're replacing, period.

ImAlwaysRight

Aug 16, 2002, 10:54 AM

It seems to me this is another case of trying to boost number of hits at a site (barefeats.com). These 4 tests are all CPU tests, and do not stress the system. Being CPU tests, the L3 cache will make a difference. Where are 2D scroll tests? Where are 3D game tests? These are part of his normal testing as given in his "how I test", yet he either chose not to run them, or ran them and didn't like the faster results so didn't report them. It seems to me the "reviewer" is biased and probably upset we didn't see 1.2/1.4/1.6 G4's so is going to get back at Apple. OK, I'm reading a lot into it, but publishing results like this are LAME. Also, if you've been around a while, you know that barefeats results have been suspect in the past.

The only accurate test would be to have the same amount of RAM and move the hard drive and video card from one machine to the other, or AT LEAST report what the differences are. We don't have any of this here, so I'd ignore these tests for the time being.

But if you choose not to, then also relish the fact that a dual 867MHz is 45% faster than a 2.54GHz Pentium 4 computer.

http://a772.g.akamai.net/7/772/51/931148a5497b7f/www.apple.com/powermac/images/graphphotoshop08132002.gif

oranjdisc

Aug 16, 2002, 10:57 AM

Truth is, I'm actually kind of glad to see Bare Feat's results popping up on all these news sites. Apple lowered the PowerMac's prices, but they purposely crippled the machines to maintain their bloated profit margins.

ImAlwaysRight

Aug 16, 2002, 10:59 AM

Originally posted by ryan
While I guess it is nice to see that the current middle-of-the-line PM G4 is as fast as the former top-of-the-line PM G4 it seems to me that there shouldn't have to be tests designed specifically to stress the machine to show how the (hacked) implementation of DDR is of benefit to the new machines. The new machines should simply be faster, regardless of what they're doing, than the machines they're replacing, period. Ryan, not necessarily so. If you have a CPU bound task, then putting a dual 1GHz vs. a dual 1GHz isn't going to change much. The only difference here is old gig has 2MB L3 cache, and new gig has 167MHz bus, so based on these 4 CPU tests, these two seem about a wash with the slight edge going to L3 cache.

But, when you consider the other improvements to the new dual G4, like case design (dual CD/audio in/front headphone/4 RAM slots/3 ATA buses/etc), and the fact that in other tests like games and 2D scrolling the new stock G4 dual 1GHz will beat the old dual 1GHz, and comes with Jaguar, and costs $500 less, I think that is a pretty good upgrade. However, considering the old dual gig is now $2199, that makes it a pretty good buy, considering more RAM and 2MB L3 cache/processor. That is a tough choice for prospective buyers. But, if you want an old gual gig, you better act fast, as once they are gone, they are gone.

I'm eligible for Apple edu discount, so picked up a new dual gig for $2249 shipped (no tax). After paying shipping at a mail order house, it is about the same price as the old dual gig, and I like the newer better.

Timothy

Aug 16, 2002, 11:02 AM

The denigration of Bare Feats is getting ridiculous. He has posted some results that I find interesting and of themselves, dissapointing. Clearly, it is early, and he doesn't have a new box in his own hands. But to ascribe some conspiracy theory to him is a bit over-the-top.

I agree with the earlier poster who stated that you shouldn't need to craft a perfect task in order to find the manner in which this new machine is faster; according to the Apple Hype, this machine should simply be faster across the board. That it is not is troubling.

I always become worried when Apple Zealots turn into apologists; I thought I had left the dogmatic religion of my childhood, but wonder sometimes If I didn't merely replace it with my devotion to Apple. Reading some of the comments here and elsewhere make me believe that dogmatism is alive and well in the Apple community.

ibjoshua

Aug 16, 2002, 11:06 AM

Originally posted by oranjdisc
Truth is, I'm actually kind of glad to see Bare Feat's results popping up on all these news sites. Apple lowered the PowerMac's prices, but they purposely crippled the machines to maintain their bloated profit margins.

huh?

why would you 'cripple' a machine to maintain a profit margin. using cheap parts maybe, but actually 'crippling'? do you understand the meaning of the word?

j

Timothy

Aug 16, 2002, 11:07 AM

However, considering the old dual gig is now $2199, that makes it a pretty good buy, considering more RAM and 2MB L3 cache/processor.

Where is the old 1 gig being sold?

ImAlwaysRight

Aug 16, 2002, 11:13 AM

Originally posted by Timothy
The denigration of Bare Feats is getting ridiculous. He has posted some results that I find interesting and of themselves, dissapointing. Clearly, it is early, and he doesn't have a new box in his own hands. But to ascribe some conspiracy theory to him is a bit over-the-top.

I agree with the earlier poster who stated that you shouldn't need to craft a perfect task in order to find the manner in which this new machine is faster; according to the Apple Hype, this machine should simply be faster across the board. That it is not is troubling. Folks, stop and think about this a minute. You have two dual gig Powermacs, the main difference being the old has 2MB L3 cache per processor, the new has 1MB L3 cache per processor. The old has 133MHz system bus, the new 167MHz system bus. Why do you expect much of a performance difference between the two?

Also, some seem to be forgetting the new dual gig IS THE MID-RANGE POWERMAC. As such, compare it to the former mid-range PowerMac, a single 933Mhz G4 w/133MHz bus. The new mid-range will tear up the old. Why is everyone so anal on comparing the new dual gig vs. the old? When in Apple's history has so much grief been given over the new mid-range Powermac? The thing got a speed bump, dual processors, many other improvements with the redesigned PowerMacs, and yet all this disappointment. I understand the 1.25 isn't shipping yet, but when it does, then compare the old dual gig to the new 1.25 which HAS 2MB L3 cache per processor and then we'll see what's going on.

Why are people complaining so? Some have come out and said they are disappointed we didn't get 1.2/1.4/1.6GHz processors. But 1.25 is consistent with what Apple has done in the past. Get over it already. Don't bash the new Macs because of your perception that Apple has short-changed us. It is a good upgrade consistent with what Apple has done in the past.

And Timothy, my comments have more to do with common sense than dogmatism. I know you're still fuming over the "failure of Apple to produce" because of the 1.2/1.4/1.6 G5 rumors of several MacWorlds ago, but get over it already.

ImAlwaysRight

Aug 16, 2002, 11:31 AM

Originally posted by i_b_joshua

huh?

why would you 'cripple' a machine to maintain a profit margin. using cheap parts maybe, but actually 'crippling'? do you understand the meaning of the word?

j Exactly. I want to make this point very clear, since many might have missed it in my last post. THE NEW DUAL 1GHz IS THE MID-LEVEL POWERMAC. Repeat after me. THE NEW DUAL 1GHz IS THE MID-LEVEL POWERMAC. Compare it to the Quicksilver 933MHz with one processor and 133MHz bus. Because this is the upgrade we got. PLEASE NOTE THE 1.25GHz with 2MB L3 cache per processor is the new high end model.

Now maybe some won't feel so cheated. :-)

You shouldn't expect a huge perfomance difference comparing two dual 1GHz models against each other. Sure, too bad Apple didn't put 2MB L3 cache in the mid-level Mac, as then it would have been faster with the faster bus, but the new mid level is a LOT faster than the old mid-level. I'm glad I waited to purchase until now.

For those who want to see another test, (again, from Apple's propaganda), also note a new dual 867 beats a 2.54GHz Pentium 4 in DVD decoding.
http://a772.g.akamai.net/7/772/51/931148a5497b7f/www.apple.com/powermac/images/graphphotoshop08132002.gif
Geez, since two tests results from Apple's website I've posted to this thread alone show the dual 867 G4 to be faster than a single 2.54 Pentium 4, I wonder if all Pentium 4 owners are going to jump ship and run out and buy the dual 867Mhz PowerMac which not only "performs better" but costs less, too. Shouldn't the Pentium "simply be faster across the board?"

nero007

Aug 16, 2002, 11:35 AM

colewave

Aug 16, 2002, 11:41 AM

Testing the old dual 1ghz against the new dual 1ghz is the best way to judge the other changes in architecture Apple is touting. If the results are "no difference", then you might as well find an old dual 1ghz on deep discount instead of paying up for the new architecture. I agree that the barefeats test doesn't prove anything yet, so I'll wait and see.

ImAlwaysRight

Aug 16, 2002, 11:56 AM

Originally posted by colewave
Testing the old dual 1ghz against the new dual 1ghz is the best way to judge the other changes in architecture Apple is touting. If the results are "no difference", then you might as well find an old dual 1ghz on deep discount instead of paying up for the new architecture. I agree that the barefeats test doesn't prove anything yet, so I'll wait and see. (I can't seem to get off this topic for some reason...)

I suppose I'm just a fan of accurate, responsible testing. Let's see the whole picture. If you purport to be objectively testing two systems against each other, then do it. It just doesn't seem like this is what is going on at Barefeats.com.

If you want to judge the changes in architecture then you need to move the same hard drive and video card from one machine to the next. Have the same amount of RAM installed. This is the only way to give an accurate result. Barefeats.com did not do this.

There is some merit in testing the stock configurations of new and previous generations against each other. How much better is the new video card? What difference does the reduction of L3 cache make? But these kind of comparisons should only be done between the same class level, like low-end vs. low-end, and high-end vs. high-end.

It seems the point between comparing the former high end dual 1GHz vs. the now mid-level dual 1GHz IS architecture. So do it right. That's all I'm saying.

I'd be very interested to see tests showing the performance difference between new and old generation PowerMacs IN THEIR OWN CLASS LEVEL. Put the following against each other:

Stock Quicksilver 800MHz vs. new dual 867Mhz
Stock QS 933 vs. new dual 1GHz
Stock QS dual 1GHz vs. new dual 1.25 GHz

EDIT: The largest performance increase would come in the low end system. You have a combination of faster MHz, addition of a second processor, AND additon of L3 cache. The mid-level is a big improvement with faster MHz, faster system bus (166 vs. 133), and addition of second processor, but the 933 had 2MB L3 cache while the dual 1GHz has 1MB L3 cache, although taking all upgrades into consideration, the new will still pummel the old. The new dual 1.25 has the biggest speed jump, 250MHz per processor. It also benefits from faster 166MHz bus. Not to mention all new systems sport ATA/100 and the DDR RAM, which, it seems, doesn't add a whole lot to system performance, but should offer a slight improvement with some tasks. LOOKS TO ME LIKE THESE ARE GOOD UPGRADES.

porovaara

Aug 16, 2002, 12:01 PM

I'm suprised at the ignorance being shown here and touted as the gospel. The simple fact is barefeats does pathetic benchmarks. They have been shown in the past to be of poor methology and with the tasks chosen to "give" a result the tester wanted.

In real world interactive usage the new dual gig blows away the old dual gig. On things like encoding video, making mp3s, and other cpu bound intensive tasks the performance is almost identical. This is amazing considering the g4 really needs that extra L3 cache... amazing because the new dual gig has half the cache and manages to keep up.

Compared to last week the apple world is a lot better. Still not great but the entry level machine is awesome and the dual gig for the midrange is pretty sweet as well as long as you stay in the apple world.

AmbitiousLemon

Aug 16, 2002, 12:22 PM

i think some of you need to actually LOOK at barefeats.com before attacking the benchmarks. you are screaming and yelling about things that are flat out wrong. he does say very specifically how each machine is configured and he also says very specifically how he set up the tests. as for claiming these are cooked. BS. they dont say what you like so you attack it. claiming he would do this on purpose is completely wrong. barefeats.com is in no need of pulling a stunt to get hits. his benchmarks in the past have been very reliable, and have been very fair.

comparing all the dual 1ghz machines is the best way to test whether the new bus and ddr improve performance. if you can not understand basic scientific method then please dont criticize (putting your response in bold does nothing to convince others yo are right). apple has been telling us that the new dual 1ghz is faster than the previous by between 20 and 50% (in various tasks), thats why he compared it. Also Apple has even claimed the new dual 867 is faster than the previous dual 1ghz. Apple says this is because of the new architecture. Also i am sure as soon as the dual 1.25ghz ships he will add it, he is working with what he can get.

btw more tests ARE on the way aimed at proping the new architecture even more are on the way.

yadmonkey

Aug 16, 2002, 12:22 PM

Originally posted by ImAlwaysRight
Folks, stop and think about this a minute. You have two dual gig Powermacs, the main difference being the old has 2MB L3 cache per processor, the new has 1MB L3 cache per processor. The old has 133MHz system bus, the new 167MHz system bus. Why do you expect much of a performance difference between the two?

Also, some seem to be forgetting the new dual gig IS THE MID-RANGE POWERMAC. As such, compare it to the former mid-range PowerMac, a single 933Mhz G4 w/133MHz bus. The new mid-range will tear up the old. Why is everyone so anal on comparing the new dual gig vs. the old? When in Apple's history has so much grief been given over the new mid-range Powermac? The thing got a speed bump, dual processors, many other improvements with the redesigned PowerMacs, and yet all this disappointment. I understand the 1.25 isn't shipping yet, but when it does, then compare the old dual gig to the new 1.25 which HAS 2MB L3 cache per processor and then we'll see what's going on.

Why are people complaining so? Some have come out and said they are disappointed we didn't get 1.2/1.4/1.6GHz processors. But 1.25 is consistent with what Apple has done in the past. Get over it already. Don't bash the new Macs because of your perception that Apple has short-changed us. It is a good upgrade consistent with what Apple has done in the past.

And Timothy, my comments have more to do with common sense than dogmatism. I know you're still fuming over the "failure of Apple to produce" because of the 1.2/1.4/1.6 G5 rumors of several MacWorlds ago, but get over it already.

Good show ol' bean! I agree that these benchmarks are questionable at best. But even the believers seem to be missing out on two points, one of which you mentioned and one of which you hinted at:

1) The new "Faster" (dual-1ghz) Mac is much faster than the old "Faster" (single 933mhz) Mac. Likewise, the new "Faster" Mac has about the same performance as the old "Fastest" (dual 1ghz) Mac. In other words, if you want the previous top performer, it is much cheaper now. Everything is about as it should be.

2) If you believe in these benchmarks, they do indicate one important thing: That the new "Faster" (dual-1ghz) Mac does seem to get some performance boost from the new faster bus and DDR RAM. Why? Well, despite being crippled by a smaller L3 cache than the previous "Fastest" (dual 1-ghz) Mac, it performs about the same. Something is obviously making up for the half-sized L3 cache!!!

It stands to reason that the new "Fastest" Mac (dual-1.25 ghz) will see quite a performance boost over the others, since it combines the 2MB L3 cache with the DDR RAM and faster bus. The moral: If you want to have your cake and eat it too, you must pay Apple for the new "Fastest" Mac. Now who can argue with that? :D

ElRayOX

Aug 16, 2002, 12:27 PM

[QUOTE]Originally posted by deepkid
[B]As we've wondered in another thread..

but maybe there's still a chance that the top end machine might be a different beast all together. (Unless someone can factually say that Apple won't be using anything different.)

Deepkid makes a real good point. Maybe the September machines will be completely different beasts...

Pin-Fisher

Aug 16, 2002, 12:29 PM

Originally posted by ImAlwaysRight
I wonder if all Pentium 4 owners are going to jump ship and run out and buy the dual 867Mhz PowerMac which not only "performs better" but costs less, too. Shouldn't the Pentium "simply be faster across the board?"

Costs less??? How to you figure that the dual 867 costs less? Give me your breakdown of costs between the two system. I'm not talking complete Pentium system vs bare G4 system, Im talking soup to nuts. Monitor , speakers (why the heck Apple doesn't include the speakers Ill never know) If I had a nickle for every time I have heard someone at CompUsa say "Speakers are extra??" then walk over to the InSmell computers I could buy a Porsche.

yadmonkey

Aug 16, 2002, 12:32 PM

A 25% (at least) performance increase on the top model is damn good! So is an $800 price drop on the previous top model. I work in a multi-platform environment and I have multi-platforms (2 macs and 2 PCs) at home, so I have no reason to be partial to a platform other than preference. I can honestly say that these new Dells we got with the really fast bus (533 mhz, I think) and super-over-clocked P4s are overcompensating for something. Why do you use a Mac?

Get you mind out of the numbers game and just look at what is out there - a dual-1ghz Powermac, last-gen or this-gen is a great value for the $$, as is the dual 867. If you can afford the dual-1.25ghz powermac, all the better.

Ask yourself what you need and what you are willing to spend. When you consider the new models and the sales on the previous ones, you should come out with a great deal. I can't remember a better time to pick up a Mac.

deepkid

Aug 16, 2002, 12:33 PM

Originally posted by Timothy

I agree with the earlier poster who stated that you shouldn't need to craft a perfect task in order to find the manner in which this new machine is faster; according to the Apple Hype, this machine should simply be faster across the board. That it is not is troubling.

That is a very troubling statement. It is as scary as some court of law simply glancing at an accused person who "might" look guilty and charging them so without due process. Isn't that a bit like witch hunting?

If the tests that Barefeats performed are suspect, they should be not be held in such high regard. It does not matter what Apple's or Barefeats' opinions are, the results should be based upon sound benchmarking.

AmbitiousLemon

Aug 16, 2002, 12:38 PM

Originally posted by deepkid

That is a very troubling statement. It is as scary as some court of law simply glancing at an accused person who "might" look guilty and charging them so without due process.

If the tests that Barefeats performed are suspect, they should be not be held in such high regard. It does not matter what Apple's or Barefeats' opinions are, the results should be based upon sound benchmarking.

the ONLY reason these benchmarks are 'suspect' is that 1) it doesnt say what some of you want it to say, and 2) you are too lazy to go to barefeats.com yourself and read hwo they were performed.

dont get me wrong, i think this is a great update. but its important to have this info because it is contrary to what apple has told us. apple tells us the new 867 and new 1ghz are faster than the old 1ghz. this does not seem to be the case. but more benchmarks are on the way, and we cant test the new 1.25ghz until the thing ships. This is information. it should help people make purchasing decisions. all the info isnt in yet, so hold off on making any drastic decisions. but throwing this out just because you dont like what it says is childish and not in your best interests.

eric_n_dfw

Aug 16, 2002, 12:40 PM

Originally posted by ImAlwaysRight
I'm eligible for Apple edu discount, so picked up a new dual gig for $2249 shipped (no tax). After paying shipping at a mail order house, it is about the same price as the old dual gig, and I like the newer better.
What mail order house is offering you edu discount? (I haven't found one that will yet)

deepkid

Aug 16, 2002, 12:49 PM

Originally posted by AmbitiousLemon

the ONLY reason these benchmarks are 'suspect' is that 1) it doesnt say what some of you want it to say, and 2) you are too lazy to go to barefeats.com yourself and read hwo they were performed.

Was this a direct response to me?

I can't speak for the other forum members, but I looked at the Barefeats data several times -- and its too muddy.

Before getting into the specific tests, he should have given the OS and versions used for all machines...RAM and HD types and speeds. You have to perform this test using Jaguar, because that is the OS of today, not OS 9.2.

That would have exacted more credibility for him.

I personally don't have an emotional tie to the results. I own/use several macs and I'm pretty happy with them. I will replace my older powermac, so its not a matter of wanting the results to verify some pipe dream.

I simply have an interest, like many of us, in receiving the most sound benchmarks possible in order to make a better purchasing decision. It does not matter who performs these, just that they are as accurate as possible.

It appears that we will have to wait a while longer to get them.

Thanks.

carta

Aug 16, 2002, 12:53 PM

I visited the Barefeats site for the first time because they reviewed an eMac and the new iMac, both with 700 MHz processors. In the conclusion, the tester said that both machines were similar, but that he gave the nod to the new iMac because it had a significantly faster hard drive seek time.

While Apple's tech specs are only so informative, the eMac and new iMac appear to have the same 40 GB ultra ATA hard drive.

So the Barefeats conclusion really should be that the machines are equal (given equal hardware) and that they really comparable. But he goes on to bash the eMac's "flimsy" hard shell, suggesting that the machine is less rugged than its LCD cousin.

ImAlwaysRight

Aug 16, 2002, 12:55 PM

Originally posted by AmbitiousLemon
i think some of you need to actually LOOK at barefeats.com before attacking the benchmarks. you are screaming and yelling about things that are flat out wrong. he does say very specifically how each machine is configured and he also says very specifically how he set up the tests.Umm, two things. First, he does NOT say how each machine is configured. Where do you see how much RAM is in each system? Where do you see what video card was used? He lists system specs like max RAM, available video cards, but it does not say how much RAM is in each system. LOL - who needs to LOOK. The new dual gig only ships with 256MB RAM, and the old dual gig has 512MB. Assuming he just used stock configs, that RAM amount would make a difference in tests. Second, I just looked again, and now the barefeats website has been updated. I can't control the fact that the guy revised his website after I viewed it and made my remarks.
Originally posted by AmbitiousLemon
his benchmarks in the past have been very reliable, and have been very fair. Most of his tests seem fine. He's had some questionable test results in the past though. Perhaps search www.xlr8yourmac.com if you want to find discussion on it (that's probably where I was tipped off to it, but its been a while).

Originally posted by AmbitiousLemon
comparing all the dual 1ghz machines is the best way to test whether the new bus and ddr improve performance. if you can not understand basic scientific method then please dont criticize. If you want to judge the changes in architecture then you need to move the same hard drive and video card from one machine to the next. Have the same amount of RAM installed. This is the only way to give an accurate result. I suppose I can put this in bold, italic, or even 72 point font, yet some people will still fail to understand... Just because you claim to be more intelligent does not make it so.

And remember. ImAlwaysRight (heh-heh)

QuiteSure

Aug 16, 2002, 12:56 PM

Originally posted by yadmonkey
I can honestly say that these new Dells we got with the really fast bus (533 mhz, I think) and super-over-clocked P4s are overcompensating for something.

What does this mean, "overcompensating?"

Timothy

Aug 16, 2002, 01:02 PM

IAMRIGHT...

I agree that these benchmarks are preliminary; I suspect that BareFeats will update as time and information allows.

I'm curious, however, you don't seem to be as scrutinizing of the benchmarks that Apple has put out. Why? For example, I don't think it's fair to put dual processors against single processors. Do you?

BTW, again I'll ask, where is the Old Dual 1 gig being sold for $2199?

FatTony

Aug 16, 2002, 01:07 PM

Originally posted by QuiteSure

What does this mean, "overcompensating?"

o·ver·com·pen·sa·tion n.

Excessive compensation, especially the exertion of effort in excess of that needed to compensate for a physical or psychological characteristic or defect.
Source: The American Heritage® Dictionary of the English Language, Fourth Edition
Copyright © 2000 by Houghton Mifflin Company.
Published by Houghton Mifflin Company. All rights reserved.

Uragon

Aug 16, 2002, 01:09 PM

Originally posted by AmbitiousLemon

..... more benchmarks are on the way, and we cant test the new 1.25ghz until the thing ships. This is information. it should help people make purchasing decisions. all the info isnt in yet, so hold off on making any drastic decisions. but throwing this out just because you dont like what it says is childish and not in your best interests.

I agree...this is just a preliminary information.... I'am waiting for other benchmark before deciding whether to buy the new ones...

eirik

Aug 16, 2002, 01:11 PM

Does the size of L3 cache, 1 MB versus 2 MB, always make a difference for all performance tests?

I suspect that it doesn't.

Is it not conceivable that 1 MB of L3 cache is more than enough cache for application instruction, static data, frequently repeated data, and intermediate data (?)?

In time, I hope some performance tests can be run such that the testers alter the size of the L3 cache so that they're the same in both machines, affording us a more focused comparison of the architectural changes. Is there some reason that this cannot be done by a skilled individual (other than warranty issues)?

Eirik

Sun Baked

Aug 16, 2002, 01:11 PM

Overcompensation

The Porsche effect?

ImAlwaysRight

Aug 16, 2002, 01:12 PM

Originally posted by Timothy
IAMRIGHT...
Are you trying to get my attention or are you saying that you are always right. Because only one of us can always be right, and that is me. Look at my name. It says so, so you can't dispute that. :-)

Originally posted by Timothy
I'm curious, however, you don't seem to be as scrutinizing of the benchmarks that Apple has put out. Why? For example, I don't think it's fair to put dual processors against single processors. Do you?
Actually, I'm being sarcastic. The Apple results, although no doubt accurate when tested, are definitely biased. I wonder how many hundreds of tests Apple performed just to put these two graphs I reproduced on their website. For the record, I do NOT believe a dual G4 867 to be faster than a single 2.54MHz Pentium 4, other than maybe 1% of the time.
Originally posted by Timothy
BTW, again I'll ask, where is the Old Dual 1 gig being sold for $2199? I think I saw it at MacMall.com. Any place that has it in stock should have it at $2199, including your local CompUSA or other. MacWarehouse even had refurb duals for $2099, but for $100, I'd go with the new sealed box if you can still find it.

yadmonkey

Aug 16, 2002, 01:12 PM

Originally posted by QuiteSure

What does this mean, "overcompensating?"

Perhaps I should have simply said "compensating" for accuracy. What it means is that through my very unscientific tests (general usage, including Photoshop), they don't seem to perform much better or worse than the Quicksilver dual-1ghz I use. Therefore, there must be some flaw in the overall architecture or system software (XP in this case) which requires them to boost the bus and clock speeds so high.

BTW, XP ain't half-bad.

soosy

Aug 16, 2002, 01:13 PM

The criticism of barefeats tests seems a little harsh and unwarranted to me. If the new dual-1Ghz aren't any faster than the older dual-1Ghz's then that is a little dissapointing to me. I wouldn't normally expect old and new machines using the same chip to perform differently, but apple is very much stressing the benefits of the new architecture (which is understandable, they would want to have something more than the chip speed increase to make these machines seem "all new")

The "crippling" someone else was referring to is that the new dual-1Ghz has a smaller L3 cache than the old one. So if barefeats results are accurate, then maybe the new architecture is helping, while the smaller cache is hindering. They could have kept the cache the same, but it probably wouldn't have given as big a performance difference between the new 1Gz and the 1.25Ghz machines. I'm pretty sure they've done similar things before when speedbumping machines, so it's understandable, even if I don't exactly like it. I also don't like it when they "manufacture" limitations to seperate product lines. (for example, preventing external display spanning on the ibook when the graphics card is perfectly capable.)

Anyway, I think the new powermacs are a good step forward, even if lack a certain amount of the "wow" factor. It's certainly great that the high-end dual 1ghz are now in the middle at a significantly cheaper price. More bang for the buck.

I do like knowing the difference the between Apple Hype and reality. It's bothered me lately that they claim to "invent" things that are already out there. (e.g. Not acknowledging O'Meara's G-Force as the inspiration for iTunes visualization. Instead they were like "We asked ourselves what would it be like if you could see music"). Uh, okay, I'm off topic now.

yadmonkey

Aug 16, 2002, 01:16 PM

Originally posted by Timothy
BTW, again I'll ask, where is the Old Dual 1 gig being sold for $2199?

oops...

http://www.clubmac.com/clubmac/families/powermac/default.asp?estore=41147000

AmbitiousLemon

Aug 16, 2002, 01:23 PM

Originally posted by deepkid

Was this a direct response to me?

I can't speak for the other forum members, but I looked at the Barefeats data several times -- and its too muddy.

Before getting into the specific tests, he should have given the OS and versions used for all machines...RAM and HD types and speeds. You have to perform this test using Jaguar, because that is the OS of today, not OS 9.2.

That would have exacted more credibility for him.

I personally don't have an emotional tie to the results. I own/use several macs and I'm pretty happy with them. I will replace my older powermac, so its not a matter of wanting the results to verify some pipe dream.

I simply have an interest, like many of us, in receiving the most sound benchmarks possible in order to make a better purchasing decision. It does not matter who performs these, just that they are as accurate as possible.

It appears that we will have to wait a while longer to get them.

Thanks.

not a direct response to anyone. just to the general crowd all saying the benchmarks are questionable. he does list the info you mention is missing. since you missed it i assumed you didnt look at the page. he clearly says what os he used and what the specs are on the machine (including RAM etc). he can post all this info but if you refuse to look... not his fault. if you cant read a table...sorry but that makes your intelligence suspect not his tests. not trying to get personal or anything, but i mean the info is there. attacking him based on faulty info isnt fair. try to take more than a cursory look at the data before launching into your attacks. the reason he didnt put the same amount of ram/hard drive etc is because these things are changes that have been made between the models. these are just parts of the thing he is testing. the max ram has been changed, the ata controllers have been changed. we want to see if all this makes a difference.

I suppose I can put this in bold, italic, or even 72 point font, yet some people will still fail to understand... Just because you claim to be more intelligent does not make it so.

wow what great logic. i cans ee why you were unable to understand a simple table showing the specs of the machines.

ImAlwaysRight

Aug 16, 2002, 01:33 PM

I'll chime in about the use of the term "crippled" associated with the new dual gig. How is it crippled? Maybe because the former mid-range had 2MB L3 cache, while the new mid-range has L3 cache. Yes, if our new mid-range were a 933MHz single processor with 1MB L3 cache, 256MB RAM, and the other specs as the former mid-range 933, then I would call our new mid-range crippled.

But, what did Apple do here? We have a whole new computer here. They gave us a speed increase from 933MHZ to 1GHz. Wait, what? They added a second processor? Since when? Sweet. Now dual processors in the mid-range when there was only one. L3 cache is 1MB. Awww, com'on, the previous mid-range had 2MB L3. But, considering the other improvements, like DDR RAM, ATA/100 controller, 166MHz front side bus, yes, this is a good upgrade. Nothin' crippled here.

THE NEW DUAL GIG IS NOT THE OLD DUAL GIG. IT IS A REDESIGNED COMPUTER. THINK OUT OF THE BOX. This is not a hand-me-down. You've got new clothes, kid. "Aww, but dad, my suit only has two buttons on the front and brother John's had three!" "Dangit, kid, you got the wool instead of polyester, and we had yours tailored while John's doesn't fit quite right. Quit yer bitchin'!"

Or something like that.

It seems in the effort to test the ARCHITECTURE of the new Powermacs, people want to take the two models that have the same MHz speed and compare them. But they are taking the high-end and comparing it with the mid-range. But in reality, I'm not sure this is fair, EVEN BY USING THE SAME HARD DRIVE AND VIDEO CARD BETWEEN SYSTEMS, AND HAVING THE SAME AMOUNT OF RAM, to put the old G4 dual gig vs. the new, because of the L3 cache disparity. To me, this is not a true test of the architecture. We need a dual gig processor with 2MB L3 cache to properly test the architecture of the new system bus, ATA/100, and DDR RAM, don't we?

whatever

Aug 16, 2002, 01:36 PM

Alright here are my two cents. If you want to compare the old dual 1 GHz PM against the new, then one of the key metrics, which is missing is cost. Like one person mentioned several times, you're comparing a High End machine to a Mid Range machine. So one of the factors which make these machines either High End or Mid are their costs.
The trick here is some way including the price into the equation. And then we can determine the true worth of these machines. Once that fomula is compete run it against the old and new high end machines.

Bottom line is that many of you are hung up on hardware specs, but how many of you are actually using new machines, for the most part older Macs depreciate much better than anything else out there and that's the problem, they just don't die!

Timothy

Aug 16, 2002, 01:38 PM

Thanks for the link to ClubMac and the pricing on the Old 1 gig.

It is selling there for $2129. For those who think that the dual 867 on Apple's site is a great deal...if you add ram, larger hard drive and superdrive to match the old 1 gig...you'll get a price of $2099. Only $30 less than the original 1 gig is selling at ClubMac. That's a pretty good deal for the old 1 gig.

:-)

Sun Baked

Aug 16, 2002, 01:41 PM

Hello McFly, (TAP, TAP) anyone home?

Here's a chart comparing the features and specs of the three Dual 1GHz systems:

CHART/TABLE

Unless my brain is still asleep, this is only a copy of the data from Apple - not an as tested table.

When I compiled my list above it's what I used.

However I neglected to mention that 2 of machines should boot into OS 9 - which should give better access to hardware than OS X - and there are still people who need to boot OS 9, so some OS 9 testing may be of interest to people.

Frobozz

Aug 16, 2002, 01:42 PM

No matter how taxing these tests were, they were test used to show real world usage. Most users will not be doing Cinema4D renders for 24 hours straight, even though I may do things like this.

The point is that, for the average user, these systems are not faster. They are an excellent glimpse of what is to come-- either the 7470's or the Power4. The architecture improvements are very welcome, but my 2 x 1 GHz Mac from February is lookin' like it was a great investment.

Apple's gotta get a new PowerPC processor-- but otherwise it's doing just fine.

porovaara

Aug 16, 2002, 01:42 PM

Originally posted by AmbitiousLemon

saying the benchmarks are questionable. he does list the info you mention is missing. since you missed it i assumed you didnt look at the page. he clearly says what os he used and what the specs are on the machine (including RAM etc).

Where?

soosy

Aug 16, 2002, 01:42 PM

THE NEW DUAL GIG IS NOT THE OLD DUAL GIG. IT IS A REDESIGNED COMPUTER. THINK OUT OF THE BOX.

Yes it is a new system, which is why I would expect it to perform better than the old systems. :)

...people want to take the two models that have the same MHz speed and compare them

Yes that's exactly what we are doing. I guess we just have a difference of opinion here. I think it is perfectly reasonable to compare the two.

And like I said before, the new model is great if only for the price reduction. :)

ImAlwaysRight

Aug 16, 2002, 01:43 PM

Originally posted by AmbitiousLemon
he does list the info you mention is missing. since you missed it i assumed you didnt look at the page. he clearly says what os he used and what the specs are on the machine (including RAM etc). he can post all this info but if you refuse to look... not his fault. if you cant read a table...sorry but that makes your intelligence suspect not his tests.
Let's talk about looking at pages for a minute. In fact, go back to the barefeats site. It says: "Here's a chart comparing the features and specs of the three Dual 1GHz systems:" He then goes on to give Maximum Memory, Standard Graphics Card, and Optional Graphics.

So do you believe he had each system maxed out for memory? Which video card was in the test systems, the standard card, or the optional? Rob Morgan is simply stating the specifications of the machine, he's not telling you how his test systems are configured.

EDIT:OK, I'll be nice. I won't say anything about intelligence.

kenohki

Aug 16, 2002, 01:51 PM

Originally posted by ImAlwaysRight

Hah! Let's talk about looking at pages for a minute. In fact, go back to the barefeats site. It says: "Here's a chart comparing the features and specs of the three Dual 1GHz systems:" He then goes on to give Maximum Memory, Standard Graphics Card, and Optional Graphics.

So do you believe he had each system maxed out for memory? Which video card was in the test systems, the standard card, or the optional? Rob Morgan is simply stating the specifications of the machine, he's not telling you how his test systems are configured.

I can see why you misunderstand what I have to say when you can't even get this right.

So, please look, think, and then write, in that order.

And remember. ImAlwaysRight! (woooo-hoooooo!) (can you tell I play RTCW?)

Yeah, those are just the max specs. He doesn't list configuration on any of the machines tested...not even under the "How I Test" page. You can take these benchmarks with a grain of salt.

giovanni

Aug 16, 2002, 01:59 PM

ImAlwaysRight I hope by now you have stopped your completely idiotic posting ! ask Apple if they can replace your brain may be then we'll see better posts !!!!

ImAlwaysRight

Aug 16, 2002, 02:16 PM

Originally posted by giovanni
ImAlwaysRight I hope by now you have stopped your completely idiotic posting ! ask Apple if they can replace your brain may be then we'll see better posts !!!! I did ask, but they lowered the cache, which, although I got a faster bus, didn't make any difference in the end...

Edit: Did you read all my posts? I may have made a few rebuttal smart-ass remarks, and thrown in a little sarcasm with Apple's benchmarks on their website on the PowerMacs vs. Pentium 4, but for the most part I thought I raised some good points.

Can you tell it is my day off today? And I'm anxiously waiting my new DDR dual gig G4? I've spent waaaayyy to much time on this forum today. When the new Mac comes you won't have to worry about me placing a dozen posts in one thread.

yadmonkey

Aug 16, 2002, 02:22 PM

There are some seriously whiney people in this thread. I think everyone is so caught up in numbers and comparing Quicksilvers to whatever-the-heck-the-new-ones-are-called that they have forgotten the single most important thing: If you buy a Powermac today, you will get a seriously better value than you would have a week ago.

If you are disenchanted by the new dual-1ghz based on some early benchmarks, then get a dual-1ghz Quicksilver for $800 less than you would have paid last week. If you have the money, get the top model this year - 25% clock speed increase ain't shabby and overall performance just might be better than 25% better with the new architecture. If you're smart, you'll wait a little for some more benchmarks.

I don't care if you get an Apple or a Dell, the machine won't ever quite match the company's hype. That is what advertisers and marketers are paid for. Take a deep breath, decide what you need, decide what you are willing to pay, and I am certain you will find a great deal.

There's just no pleasing some people - sheesh!

ratph!nk

Aug 16, 2002, 02:44 PM

More info to chew on... The previous generation DP 1 GHz tower, the L3 cache was DDR memory running at 1/2 the processor speed, the new machines however have DDR memory running at full processor speed.(867MHz, 1GHz, 1.25 GHz) Now, I am sure most of you could imagine how expensive DDR RAM running at 1GHz or more would cost.
Yet another improvement in the architecture.

That could help explain some points about same performance with less L3 cache.

kenohki

Aug 16, 2002, 02:48 PM

Originally posted by yadmonkey
There are some seriously whiney people in this thread. I think everyone is so caught up in numbers and comparing Quicksilvers to whatever-the-heck-the-new-ones-are-called that they have forgotten the single most important thing: If you buy a Powermac today, you will get a seriously better value than you would have a week ago.

If you are disenchanted by the new dual-1ghz based on some early benchmarks, then get a dual-1ghz Quicksilver for $800 less than you would have paid last week. If you have the money, get the top model this year - 25% clock speed increase ain't shabby and overall performance just might be better than 25% better with the new architecture. If you're smart, you'll wait a little for some more benchmarks.

I don't care if you get an Apple or a Dell, the machine won't ever quite match the company's hype. That is what advertisers and marketers are paid for. Take a deep breath, decide what you need, decide what you are willing to pay, and I am certain you will find a great deal.

There's just no pleasing some people - sheesh!

Oh please. That's appologist rhetoric if I ever heard it. You're paying considerably more for the 25% clock speed boost (because there are considerably less chips available that can be overclocked 25%). With all these wild claims about bottlenecks being removed and such, people just want to know how these new machines stack up to the old. They're consumers trying to make an educated purchase.

You can't blame them either. Mac users are hungry for more power right now. Benchmarking is the only way to find out if these new machines provide it. If they don't, why waste my money. I'll stick to my already depreciated SDR RAM dual GHz.

deepkid

Aug 16, 2002, 02:57 PM

Originally posted by AmbitiousLemon

not a direct response to anyone. just to the general crowd all saying the benchmarks are questionable. he does list the info you mention is missing. since you missed it i assumed you didnt look at the page. he clearly says what os he used and what the specs are on the machine (including RAM etc). he can post all this info but if you refuse to look... not his fault. if you cant read a table...sorry but that makes your intelligence suspect not his tests. not trying to get personal or anything, but i mean the info is there. attacking him based on faulty info isnt fair. try to take more than a cursory look at the data before launching into your attacks. the reason he didnt put the same amount of ram/hard drive etc is because these things are changes that have been made between the models. these are just parts of the thing he is testing. the max ram has been changed, the ata controllers have been changed. we want to see if all this makes a difference.

wow what great logic. i cans ee why you were unable to understand a simple table showing the specs of the machines.

I believe that you should go back to the page and carefully study it. Unless Barefeats has greatly revised the manner in which it's reported the test results as of this writing, there are quite a few holes in the presentation.

BTW, the info isn't all there. Stating the exact OS/version, RAM, video cards, etc. should be clear, concise and upfront in such a critical study.

You say:

the reason he didnt put the same amount of ram/hard drive etc is because these things are changes that have been made between the models.

Huh??? That's about as clear as the hanging chad explanations in Fla.

Anyway, if the tests are haphazardly-performed and reported, then they are of no use to anyone. They are more of a disservice.

About personal attacks... I won't get into that. I only care about sound benchmarking, as I mentioned before. It does not matter who performs/reports.

soilchmst

Aug 16, 2002, 03:07 PM

AmbitiousLemon has some things in common with the guy at Barefeats. One missed that all the specs listed were just the available options, and the other forgot to notice that he did not 4D xl results, just a second copy of the Photoshop 7 results. That is what happens to people who rag on other intelligence.:cool:

Sun Baked

Aug 16, 2002, 03:23 PM

Originally posted by ratph!nk
More info to chew on... The previous generation DP 1 GHz tower, the L3 cache was DDR memory running at 1/2 the processor speed, the new machines however have DDR memory running at full processor speed.(867MHz, 1GHz, 1.25 GHz) Now, I am sure most of you could imagine how expensive DDR RAM running at 1GHz or more would cost.
Yet another improvement in the architecture.

That could help explain some points about same performance with less L3 cache.

L3 cache is clocked at 1/4 of the CPU clock speed.

Look at the Dual 1GHz Mirror Mac with 166MHz bus example

MaxBus - 166 MHz clock -> 166 MHz effective -> 1.3 GBps
DDR - 166 MHz clock -> 333 MHz effective -> 2.7 GBps
L3 Cache - 250 MHz clock -> 500 MHz effective -> 4 GBps

If the L3 cache was clocked at 1/2 the CPU's frequency, the bandwidth would double, and Apple claims 4 GBps to L3 cache.

Note that L3 is 1/4 clock, L2 1/2 clock, and L1 at full CPU clock speed.

cooper13

Aug 16, 2002, 03:37 PM

Originally posted by AmbitiousLemon

comparing all the dual 1ghz machines is the best way to test whether the new bus and ddr improve performance. if you can not understand basic scientific method then please dont criticize (putting your response in bold does nothing to convince others yo are right). apple has been telling us that the new dual 1ghz is faster than the previous by between 20 and 50% (in various tasks), thats why he compared it. Also Apple has even claimed the new dual 867 is faster than the previous dual 1ghz. Apple says this is because of the new architecture.

and

Originally posted by AmbitiousLemon

the reason he didnt put the same amount of ram/hard drive etc is because these things are changes that have been made between the models. these are just parts of the thing he is testing. the max ram has been changed, the ata controllers have been changed. we want to see if all this makes a difference

Okay, you can't have it both ways. Either the test is intended to see how the new DDR/bus architecture performs or it is to see how the systems perform as a whole. In the former case, ImAlwaysRight is right (well, with that name, duh... :)), and the RAM amount, OS version, hard drive, etc. need to be the same so that the isolated variable is the DDR/bus architecture (ok, throw L3 into the pot too). Then you will have the scientific test you were trumpeting in your first post.

If however you want to defend the different amounts of RAM/hard drive models instead, then you are talking about system vs. system tests and not scientifically comparing architecture components. In this case it is very important to note that the current mid-range system is being compared to the old high-end system, along with the attendant price difference.

In either case, these tests (as others have noted) point out the fact that for CPU intensive tasks the systems are very similar, which should surprise no one since they use the same CPUs! For other types of tasks we can't compare the systems because the tests don't stress the other parts of the machine as much. In this you are correct that we need to wait for more tests.

topicolo

Aug 16, 2002, 03:41 PM

Originally posted by Sun Baked

L3 cache is clocked at 1/4 of the CPU clock speed.

Look at the Dual 1GHz Mirror Mac with 166MHz bus example

MaxBus - 166 MHz clock -> 166 MHz effective -> 1.3 GBps
DDR - 166 MHz clock -> 333 MHz effective -> 2.7 GBps
L3 Cache - 250 MHz clock -> 500 MHz effective -> 4 GBps

If the L3 cache was clocked at 1/2 the CPU's frequency, the bandwidth would double, and Apple claims 4 GBps to L3 cache.

Note that L3 is 1/4 clock, L2 1/2 clock, and L1 at full CPU clock speed.

yeah, that was sooo obvious on Apple's powermac page. I was wondering, where did u get your info Ratph!nk?

iH8Quark

Aug 16, 2002, 03:57 PM

The test are likely to become even _more_ skewed when the processors are _really_ taxed. From what I can see, the DDR PowerMac is actually SLOWER than the SDRAM model. That situation is unlikely to improve. In subsequent testing, it will likely widen the DDR Mac's disadvantage.

IMHO.

SonnyCA

Aug 16, 2002, 04:07 PM

To all of those who think higher GHz means faster and superior, I suppose you think we should all drive higher HP Mustangs and Camaros and Corvettes? Having a faster engine under the hood, and a really big and loud muffler (an oxymoron) doesn't mean that you'll get across town any faster than someone in a Lexus or Mercedes or Audi. You'll just make more noise.

I spend 8 hours a day, sometimes more, working with my computer to accomplish a variety of tasks. I'd rather do it with a computer that works *with* me rather than against me. Why not enjoy the process? Windows gets in my way, and even with a billion GHz, I'll still get more done on my Mac because the OS makes more sense. I'll spend far less time jumping through the hoops the OS puts in front of me.

With the combination of Jaguar and SMP-aware apps, Apple is fully justified comparing its dual 1.25 GHz systems to 2.5+ GHz single-processor Pentium systems. What Apple doesn't have an answer to is dual processor Intel and AMD systems, but I suspect those types of systems comprise a very small part of the Wintel market.

Overall, the situation isn't as grim as people seem to think. The doom-and-gloom camp is caught up in the GHz numbers game, and not real-world use.

kenohki

Aug 16, 2002, 04:50 PM

Originally posted by SonnyCA
With the combination of Jaguar and SMP-aware apps, Apple is fully justified comparing its dual 1.25 GHz systems to 2.5+ GHz single-processor Pentium systems. What Apple doesn't have an answer to is dual processor Intel and AMD systems, but I suspect those types of systems comprise a very small part of the Wintel market.

But they do comprise a very LARGE part of the vertical markets Apple is trying to target (3D, effects, video compositing...the general Hollywood markets).

Apple isn't justified at all in comparing their hardware to top end Intel hardware. In a render farm, all the fancy schmancy Aqua goodness doesn't matter because it's not used. Linux on x86 works just fine. Cost effective performance matters and Apple simply isn't providing it with this iteration of the PowerMac line.

Gelfin

Aug 16, 2002, 04:52 PM

Originally posted by kenohki
You can't blame them either. Mac users are hungry for more power right now. Benchmarking is the only way to find out if these new machines provide it.

You're absolutely right. But that's also why it's so important to have responsible benchmarks performed by knowledgeable people. Good benchmarks are hard to design and the results are often tricky to interpret. BareFeats' documented testing procedure (http://www.barefeats.com/how.html) is strictly amateur. There's no sophistication, no evidence of any training in performance analysis.

Compare this with analyzing the performance of an automobile. An uninformed consumer is going to ask, "is car A faster than car B?" An uninformed tester is going to make up a test he thinks is significant and say "yes" or "no." More informed people are going to ask whether you mean low-end acceleration or top-end speed. Even more informed people are going to want to know at what RPM the peak torque and horsepower are reached, what the transmission gear ratios are and so forth. A more informed analyst will be able to compile multiple sources of data and tell you under what circumstances car A might be expected to outperform car B and vice versa. This requires a detailed knowledge of how a car works and how the different elements affect performance. It's a very complicated proposition, beyond the capabilities of an untrained enthusiast with a stopwatch to measure.

You guys, the uninformed consumers on these boards (not everyone falls into this category, of course) have proven on multiple occasions that you are very susceptible to getting worked up over irresponsible performance claims because you just don't know any better. I've done this stuff for a living, and I'm telling you those numbers are neither surprising nor meaningful. Switching over to a DDR architecture is only going to produce a distinct difference in a very limited set of cases, none of which were isolated and tested in BareFeats' results. The slight performance decrease in certain MP tasks could indicate an unexpected side-effect of the architecture change, but the tests do not eliminate enough alternate possibilities to say for certain.

Most notable is that the guy is soliciting possible explanations for the speed discrepancy from his reader base. Anyone with training in performance analysis knows that isolating and explaining bottlenecks can be 3/4 of the job, and that's what he is supposed to know how to do, preferably before releasing numbers to an audience that doesn't understand the implications.

MacArtist

Aug 16, 2002, 07:13 PM

Just for S&G I ran the Unreal Tournament benchmark on my system.

Test system:
QS G4 933Mhz
OS X 10.1.5
1.25GB ram
60GB 7200RPM HD

UT set-up:
res= 1024x768, color depth= 32bit, world texture= high
skin detail= high, min frame rate= 0, decals= on, dynamic light= on
sound quality= high, gore level= normal, game speed= 100%
dodging= on, weapons flash= on, ngStats Local= off, hud= all checked

results from Wicked400 demo= 23.62fps average

real game play:
all UT prefs the same
practice session DM-Fractal
7 bots set at godlike

real world results = 41.05fps average
real world game play is about 74% better than the benchmark.

You can take it or leave it.

While we all know the wicked400.dem to be one of the de facto benchmarks for gamers, I have found that my average fps during real game play is considerably higher than what the benchmark says.

Barefeats may or may not have accurate benchmarks for the machines, that point should be moot by now.

I for one don’t care.

You really shouldn’t base your desission to buy a computer solely on benchmarks because your real world usage will not be the same as the benchmark.

And regaurdless whether the new dual 1GHz is faster/slower/equal than the old dual 1GHz, it is a better deal now than it was before. And I'll bet in real world performace will be faster (maybe not by much) than the old dual 1GHz.

We live in the real world not in benchmarks.

Choppaface

Aug 16, 2002, 08:12 PM

Originally posted by Sun Baked
Looking at the 133 MHz bus diagram for the DDR tower that Arcady kindly left here
http://forums.macrumors.com/showthread.php?s=&postid=130228#post130228

and marking up the diagram a little, you see that on a 133 MHz bus, even if you give the MaxBus everything it wants, you still have memory bandwidth left over for video and storage. And the same would still be the case on the 166 MHz bus.

So why on all these 3 multitasking/SMP machines should all the benchmarks be so similar?

Especially when 2 are DDR, 2 have 133 MHz buses, 2 have 2 MB/CPU of L3 cache, 2 have ATA-100, and 2 have G4 Ti video ;)
http://forums.macrumors.com/attachment.php?postid=130241

why can't there be special pathways from the memory to the processors, gfx card, hard disk, etc that run at higher speed than the bus? wouldn't it be possible to create special high-speed pathways where they're needed?

macidiot

Aug 16, 2002, 09:10 PM

Originally posted by yadmonkey
A 25% (at least) performance increase on the top model is damn good!

Actually, no its not. You need at least a 30% increase in performance to notice any difference in normal use. Where you would see the most immediate difference is in cpu intensive tasks. And it would have to be a time consuming one at that. However, there are so many factors regarding performance(disk speed, bus, ram, video, i/o) that simply increasing the cpu by 25% is about the least important thing you could do. Better to increase drive-i/o speed if you ask me.

And in case your wondering, I have a new ddr dual 1Ghz(does anyone know of a name for this box to distinguish it from the last dual 1Ghz?? Its a real mouthful to say "new powermac g4 dual 1Ghz with DDR). I'm still in the process of transferring files(first time I've gone X to X). No matter how fast this new machine is compared to my old one, 3GB of file transfer still takes a loooong time. And I'd ahve to say, I'm somewhat disappointed in the performance. Its faster, sure, but in a lot of ways it feels about as fast as my old B&W running 9. Kind of annoying that I had to spend 2700 just to upgrade to jaguar...

Liske

Aug 16, 2002, 09:10 PM

Originally posted by soosy
I do like knowing the difference the between Apple Hype and reality. It's bothered me lately that they claim to "invent" things that are already out there. (e.g. Not acknowledging O'Meara's G-Force as the inspiration for iTunes visualization. Instead they were like "We asked ourselves what would it be like if you could see music"). Uh, okay, I'm off topic now.

I am 100% behind this concern as all Mac Users should be. It is the writing on the wall. Case in point at the recent MacWorld Expo in New York, they presented this great new technology they created - "Rendevous" - when in fact that technology was created by others and has been in development for some time.

Apple also has released aspects of their OS that mimic shareware features created by independent developers with often times no royalties for the original developer. I suppose the capitalistic engine is getting the better of them and they are becoming more the lesser of two evils [Microsoft], and less about thinking different. All we can do is support the independent developer as much as possible because this is what is driving the mac platform now more than ever. Apple will have its hands full just trying to copy all of the creativity out there.

Liske

Aug 16, 2002, 09:17 PM

Originally posted by Timothy
Thanks for the link to ClubMac and the pricing on the Old 1 gig.

It is selling there for $2129. For those who think that the dual 867 on Apple's site is a great deal...if you add ram, larger hard drive and superdrive to match the old 1 gig...you'll get a price of $2099. Only $30 less than the original 1 gig is selling at ClubMac. That's a pretty good deal for the old 1 gig.

:-)

OK NOW ADD OSX 10.2 and you have blown your wad, no?

Liske

Aug 16, 2002, 09:20 PM

Originally posted by ImAlwaysRight

Let's talk about looking at pages for a minute. In fact, go back to the barefeats site. It says: "Here's a chart comparing the features and specs of the three Dual 1GHz systems:" He then goes on to give Maximum Memory, Standard Graphics Card, and Optional Graphics.

So do you believe he had each system maxed out for memory? Which video card was in the test systems, the standard card, or the optional? Rob Morgan is simply stating the specifications of the machine, he's not telling you how his test systems are configured.

EDIT:OK, I'll be nice. I won't say anything about intelligence.

Aren't things getting a bit dirty in here? He probably has the older test page cahced in his browser. What about benefit of the doubt? I mean aren't we all giving apple that these days :)

oldMac

Aug 16, 2002, 09:25 PM

Not to toot my own horn, but check out my pre-introduction post about DDR and L3 cache here... (down the page a bit)

http://forums.macrumors.com/showthread.php?threadid=7591&highlight=ddr

Sun Baked

Aug 16, 2002, 09:32 PM

There's a good chance that Beano will cure that horn tootin' problem. :p

--- Added a :p yes a :P

eric_n_dfw

Aug 16, 2002, 11:50 PM

Originally posted by Liske
I am 100% behind this concern as all Mac Users should be. It is the writing on the wall. Case in point at the recent MacWorld Expo in New York, they presented this great new technology they created - "Rendevous" - when in fact that technology was created by others and has been in development for some time.

Apple also has released aspects of their OS that mimic shareware features created by independent developers with often times no royalties for the original developer. I suppose the capitalistic engine is getting the better of them and they are becoming more the lesser of two evils [Microsoft], and less about thinking different. All we can do is support the independent developer as much as possible because this is what is driving the mac platform now more than ever. Apple will have its hands full just trying to copy all of the creativity out there.
You may have a point, but pick your battles better, Apple has repeatedly stated that Rendezvous is based on open standards. They have included it because that's the way they want the market to go.
from http://www.apple.com/macosx/jaguar/rendezvous.html
Indeed, all of the technologies driving Rendezvous are open and standard, and it is itself a proposed IETF standard. Meanwhile, we’ll push for widespread adoption of the standard just as we did with FireWire. Major players are already jumping on board like printer vendors Epson, HP and Lexmark. More are sure to follow. We’ll build it into what we make, and let the superior user experience it delivers move the market forward.

and, from the first paragraph of the Rendezvous Developers Page:
from http://developer.apple.com/macosx/rendezvous/index.html
Rendezvous is Apple's proposed new industry standard for automatic discovery of computers, devices, and services on IP networks. Also known as Zero Configuration networking or Zeroconf, Rendezvous uses industry standard IP protocols to allow devices to automatically find each other without the need to enter IP addresses or configure DNS servers.
That same page has a link to http://www.zeroconf.org/ , the official site of the whole standard.

Now, if you want to argue about iPhoto, iTunes or iDVD swallowing up developers, then you might have some points. Rendezvous, however, is not pushing anybody out of anything or taking money from the pockets of anyone.

hardchemist

Aug 17, 2002, 08:14 AM

Noooobie here...

I just dropped Rob at Barefeats a note suggesting that he install 10.2 on all the tested systems (you know, the $199 Apple family discount for 5 copies of OS X 10.2!). There may be an issue with Jaguar default install having more CPU background applications open for one reason or another (Rendevoux, etc.). Also I suggested that he run Norton defrag on all the systems, as I have read on other forums that Apples software can come fragmented and unoptimized from the factory.

And I saw no indication of the exact memory configuration of the machines. *If* the default was used the SDRAM PowerMac has 512MB of RAM and the DDR PowerMac has 256MB.

I am excited though...I ordered a dual 1GHz from Apple store on the web 5 minutes after the product was announced! Paid the $100 for the 120GB upgrade, and have since received a 2nd 120GB HD (IBM Deskstar 7200RPM 8.5ms) and another GB of RAM from Googleware.com. BTW those aforementioned 3 items (HD + RAM) cost $391 delivered! :D

Unfortunately it's Saturday morning, and the order progress page on the Applestore site still says "being assembled." I guess that's what happens when custom configs are specified (3 - 5 days to get it out the door).

Cheers

BobVB

Aug 17, 2002, 01:00 PM

Originally posted by hardchemist
Unfortunately it's Saturday morning, and the order progress page on the Applestore site still says "being assembled." I guess that's what happens when custom configs are specified (3 - 5 days to get it out the door).

Not just custom configurations. I placed my order for the stock dual 1 GHz immediately after they were available too - mine is still 'being assembled' too.

Why do they say 1-3 days when they know there is no chance of them actually shipping it in that time frame?

Raye

Aug 17, 2002, 03:32 PM

think, think

not even bill gates on amd, relase a new cpu, chip, or anything slower than it's predecessor, well, maybe bill on windows, but not APPLE.

chetwilliams

Aug 18, 2002, 03:17 AM

I bought a dualie 1 Ghz from the Miami store on Wednesday (they got them a day late because they are on the East Coast). Everyone at the store was very apologetic because I came in the day before and they weren't there yet. I do have to say that the new box hauls ass. I previously had an 867 Mhz box and still have a 667 TiBook and this new Mac rocks. I don't know how it compares to the previous dualie 1 Ghz, but I have run Warcraft III and Max Payne with all settings set to maximum at full Cinema HD resolution (I took the $500 rebate) and they didn't skip a beat. Not to mention this is with the ATI and not the GeForce Ti.

I do want to add my comment on the PC vs. Mac debate. I have had several multi Ghz processor PC machines. However, none have reliably done what I have been able to do with this baby out of the box. I have hooked it up to a Cinema HD display and a 1600x1200 monitor (dual display setup). I have had it playing LOTR in the DVD player, playing a 384kbps RealPlayer stream, AND running VirtualPC full screen on the second monitor. There were no performance hits... it ran like a dream.

I just kicked all of these programs off and expected them to work. I would never do this on a PC because I would be afraid some of the stuff would crash. If I was on a PC, I probably would have closed some of the stuff. Now, you might say why would I do that. Well, I'll tell you. I bought the first 1 Ghz PC ever released (this was a couple of years ago). I also got the best gfx card ever available at the time. I figured I would be able to do all kinds of stuff with that power. Well, guess what I could do a lot. But, many things were slower than they had to be (MP3 encoding especially). Also, the damn machine crashed quite a bit (every other day). Now, my Macs (including the one I bought a couple of days ago), don't have this problem. They have the hugest advantage over the PC ************. They KNOW the hardware. They can take advantage of it. It doesn't crash all the time because of some weird incompatibity.

The problem with PC hardware is everyone has to program to the lowest common denominator. I don't mean the slow stuff either. I mean that everybody has to program for "compatibility." I have custom built many cutting edge PCs in my lifetime. You know the ones that everybody talks about when they talk benchmarks. But these boxes always seem to have problems. They crash with certain programs or they refuse to recognice certain CDs or something goes wrong. In other words, the custom built speed demon I built with the 2 AMD processors, the fast RAM, the ultimate GfX card, and the big shiny ***** runs Warcraft III at 30 fps for 15 minutes but then crashes with no explanation. When, at the same time, the Apple with less Mhz, less Gfx card, less RAM, and less shiny *****, runs faster and does not crash. Why. Because of hardware integration. This is more important than clock speed, DDR, or whatever. All of you people who complain about Apple having a slower CPU are missing the big picture. The big picture is that Apple hardware is so well integrated that everyting can take advantage of everything. The other guys have to go with the LCD (lowest common denominator).

Originally posted by BobVB

Not just custom configurations. I placed my order for the stock dual 1 GHz immediately after they were available too - mine is still 'being assembled' too.

Why do they say 1-3 days when they know there is no chance of them actually shipping it in that time frame?

naumann

Aug 18, 2002, 02:38 PM

I ordered a dual 1Ghtz on Feburary 2nd with an upgrade to the Nvidia Geforce Ti and it never shipped. Then the new ones came out and and Apple sent me an email saying "Hey we got these new ones you should cancel your order and get one of these." No problem. I ordered the new 1 Ghtz, upgraded the graphics card and tacked on the 120 GB hard drive but I STILL DON'T HAVE A MAC!

Apple, ship us our Macs, please. I'm an impatient man running Photoshop, Illustrator, After Effects, Cubase, Finale, and a video game or two on a 5 GB hard drive PC laptop (Dell), not to mention the 800 MB of MP3s I've got on there.

I'm ready to make the switch! But my new 10 GB iPod already collecting dust.

LET'S GO APPLE! SHIP THOSE BAD BOYS!

madamimadam

Aug 18, 2002, 10:42 PM

I do not have time to read all the posts before I make my reply... sorry if I talk about something already resolved.

I have, for a long time, distasted the tests done by BareFeats. One wonders why they continue to use macs when all they ever want to do is show off the areas that they lack in.

Saying this, as someone who usually believes that slagging off Apple because you did not get what you want is rediculous and not thought through, I think the latest release was ****E.

A lot of people have said "compare faster to faster and fastest to fastest" ect. BUT you have to remember that usually Apple takes the high end machines processor and puts it in the low end model.

I can understand that Apple would NOT have wanted to make the low end models processor too fast because the new low end should never be faster than the old high end but adding 67MHz is pretty piss poor, even in a DP situation.

Why does the Xserve have 66/33Mhz PCI but the PowerMac only 33MHz.

Why bother using DDR if you are going to choke it?

To tell you the truth, I would be happy with a DP867 IF it was on the 7470 because the DDR would be being used effectively.

2 CD drives is GREAT but why can't I have a Super/Combo Drive and a DVD-ROM??? I am NEVER going to burn to 2 CDs at the same time so why pay for 2 burners?

Where is the ATA133... the demand for more bigger drives is still growing at the same pace it always had and soon the average PowerMac Pro user will be crying out for hard disks they can't have?

Now, I will point out that I am NOT one who is asking for this 1.2/1.4/1.6 people have spoken about... I am not interested in the M/GHz for M/GHz sake... I want OVERALL power upgrade that will allow for new technologies to be incorporated for at least 3 years and I really think that:

1) this was not supplied; and
2) this should have been when the mentioned add-ons should have been added... the time was perfect.

I don't know about anywhere else but here in Australia the prices of the PowerMacs has gone up, significantly in the case of the 1.25GHz, but the performace increase was quite small.

Looks like Apple has gone back to its rediculous RAM pricing again.... just emphasises that you should NEVER configure a machine before you get it if you can... it is cheaper to buy Apple RAM seperate than in a configure to order machine.

To leave on an up note, I LOVE the idea of a headphone port on the front of the machine. It is not a new idea but one that should be across the board.

mdurg

Aug 18, 2002, 11:25 PM

Where is the ATA133... the demand for more bigger drives is still growing at the same pace it always had and soon the average PowerMac Pro user will be crying out for hard disks they can't have?

ATA133 has nothing to do with drive size.

madamimadam

Aug 19, 2002, 12:19 AM

Originally posted by mdurg
Where is the ATA133... the demand for more bigger drives is still growing at the same pace it always had and soon the average PowerMac Pro user will be crying out for hard disks they can't have?

ATA133 has nothing to do with drive size.

I might be mistaken but I was sure that some of the new 200+GB drives will only work on a 133 bus. I have no idea why this is, esp. since the drives max out at about 55MB/s but that is what they require.

What is the HD company starting with W?

daveg5

Aug 19, 2002, 01:07 AM

all ata/100 and ata/66 controllers are limited to 137GB
You must have ata/133 or ata/serial to have access to more
You can check www.sonnettech.com, www.siig.com etc.
the way around it is to put it in a firewire case
www.westerndigital.com has the new 200 dives on there websight
Someone before thought if you partition are 137GB+ drive it might work but I dont know.

madamimadam

Aug 19, 2002, 01:31 AM

Originally posted by daveg5
all ata/100 and ata/66 controllers are limited to 137GB
You must have ata/133 or ata/serial to have access to more
You can check www.sonnettech.com, www.siig.com etc.
the way around it is to put it in a firewire case
www.westerndigital.com has the new 200 dives on there websight
Someone before thought if you partition are 137GB+ drive it might work but I dont know.

Thanks... I knew someone could expain it in the detail needed.
:)

mdurg

Aug 19, 2002, 07:13 AM

Like I said, ATA133 has nothing to do with hard drive size. That Western Digital 200GB is an ATA100 drive. It's probably a MacOS limitation or a limitation with the Sonnet cards.

ATA100 or ATA133 is the interface for how fast the disk cache talks to the system. Once you have used the disk cache, it's all up to the rotational speed of the disk.

As far as I know only Maxtor has ATA133 drives. They are the ones who created the spec and I don't think anyone else bought into it (yet.)

daveg5

Aug 19, 2002, 07:24 AM

technically you are correct
However (please correct me if I am wrong} according to all the ata100, ata/66, ata/133 card makers-sonnet-acard-siig-alchemy etc both pc and macs most have a ata/133 card to access more than 137GB. ata/66-ata/100 controllers are limited to 128 GB max.
Western Digital even acknowledges this on thier website and includes a ata/133 card with there 200GB drive.
The interface standard on the drive dosnt' really matter much!
What matters is what type of controller you are using if you want access to more than 137GB. all the ata controller sites acknowledge this.

soilchmst

Aug 19, 2002, 11:35 AM

This is why the Barefeats resluts are the same:

"The "SDR" Power Mac 1GHz MP had 1GB of PC133 CL2 SDRAM.
The "DDR" Power Mac 1GHz MP had 768MB of PC2700 CL2.5 DDR RAM
The "DDR" Xserve 1GHz MP had 1.5GB of PC2100 CL2.5 DDR RAM
All three were running from an IBM 120GXP drive.

They each had a different graphics card but none of the tests listed on this page are graphics intensive. The DDR Power Mac had a Radeon 9000 while the SDR Power Mac had a GeForce4 MX. "

If the DDR computer runs programs at the same speed and requires 25 % less ram, well then, it sounds like the better computer to me. ;)

There has been speculation that the Radeon card is actually very slow compared to the GeForece cards. And, the tests conducted in Jaguar are graphics intensive because of Quartz Extreme.
:rolleyes:

TMJ1974

Aug 19, 2002, 12:32 PM

I had a chance to play around with some of the new PowerMacs at the Apple Store over the weekend.

Of course, I wasn't doing any "official" benchmarking or anything like that, however the new PowerMacs didn't seem any faster than the Quicksilvers. I'm sure they have a few tricks up their sleeves, but my 733Mhz Quicksilver seems to hold its own, for now. Granted, I'm not doing any "pro" applications.

The silver bay doors showed all of the customers fingerprints real well. At home, they'd look cool because we'd not be putting fingerprints all over them.

A really big plus for the new PMs, they seem to have alot of great software. I don't know if they come with it, or it was only on there for demo purposes.

Everyone who ordered one should be pleased. :) I'll have to wait for the next round to get a new one.

Tim

eric_n_dfw

Aug 19, 2002, 02:49 PM

I'd like to try some FCP stuff on all three of the new Mac's and see what the speed diferences are. Do the stores actually have the 1.25 Ghz machines on the tables to play with?

Omad0n

Aug 19, 2002, 04:18 PM

Unfortunettly they don't have the 1.25's at the store to play with.

yadmonkey

Aug 19, 2002, 05:17 PM

Have you noticed in Apple's write-up about the new line of PMs, how much they emphasize the L3 cache's contribution to performance? Because of that, I am quite torn in my decision of which PM to buy. It would be an easy choice if Apple didn't cut the L3 cache in half on the dual 1ghz model. I guess they figured most folks wouldn't notice. I like some of the improvements, but I can't help but suspect that they will be offset by the smaller L3 cache size, making me tempted to get a Quicksilver dual-1ghz, with the good ol' 2MB L3 cache.

I shouldn't complain, because either way, I am getting that power for much less money than I would have a week ago, but I want to make the most informed decision.

How would you weigh the smaller L3 cache vs. DDR/faster bus/new architecture?

Any ideas when/where we might see some more benchmarks?

Dignan

Aug 19, 2002, 05:26 PM

Would apple have any with maxed out ram on display?

daveg5

Aug 19, 2002, 05:36 PM

I think the old dual will beat the new old dual any day on anything when equipped the same.
But it cant always be equipped the same
That said its the other things that make the new one an intriging buy
dual 51/4 bays dual hard drive controllers, 4 count them 4 hard drives. 10.2 for free, sound in , headphone up front, slightly better looking to me, 2GB of memory instead of 1.5 this will probably help it win some benchmarks if maxed out. Giant power supply will keep all those hard drives humming better.
The faster bus will come in handy on upgrades with small multipliers and on 3d games
thats just my take on it.
but I only have $300 dollars
Help
You cant go wrong with either it really depends on how much you plan to upgrade the insides and how much you want to pay

Sun Baked

Aug 19, 2002, 05:59 PM

Originally posted by yadmonkey
Have you noticed in Apple's write-up about the new line of PMs, how much they emphasize the L3 cache's contribution to performance? Because of that, I am quite torn in my decision of which PM to buy.

Buy the new one, it's a "major" architectural change - one of the first of this level in quite awhile (last B&W to AGP/MaxBus Sawtooth) - and betting on the newest versions has usually paid off it better long-term flexibility than those they have replaced.

While many may consider this an interim step on the road to the next processor generation, bus change, and full DDR support coming hopefully soon - you also have this to think about...

With the introduction of QE, the video is really starting to play a "key" role in the Mac's daily usefullness - the extra bandwidth with DDR will allow you to take better advantage of this than the QS machine will.

The Mirror Mac also has more internal storage space, better cooling, a second optical bay, bigger power supply, etc.

It's still your choice...

madamimadam

Aug 19, 2002, 08:48 PM

Originally posted by soilchmst
This is why the Barefeats resluts are the same:

"The "SDR" Power Mac 1GHz MP had 1GB of PC133 CL2 SDRAM.
The "DDR" Power Mac 1GHz MP had 768MB of PC2700 CL2.5 DDR RAM
The "DDR" Xserve 1GHz MP had 1.5GB of PC2100 CL2.5 DDR RAM
All three were running from an IBM 120GXP drive.

They each had a different graphics card but none of the tests listed on this page are graphics intensive. The DDR Power Mac had a Radeon 9000 while the SDR Power Mac had a GeForce4 MX. "

If the DDR computer runs programs at the same speed and requires 25 % less ram, well then, it sounds like the better computer to me. ;)

There has been speculation that the Radeon card is actually very slow compared to the GeForece cards. And, the tests conducted in Jaguar are graphics intensive because of Quartz Extreme.
:rolleyes:

You have to remember that once you get up to 768MB of RAM, most of these programs used for testing are getting more than their fair share of RAM anyway so there is no difference. Also, on the topic of Quartz Extreme, it only needs 32MB of VRAM PLUS it takes the weight off the processor so if QE was to make any difference it would be in the favour of the new machine. The old machines were running on Puma so the old 1GHz could have a GeForce4 MX but that means nothing when it is not being used to any significant level.

Sun Baked

Aug 19, 2002, 09:00 PM

His new test is done. :rolleyes:

I do like his new picture, very pretty ... not very useful.

http://www.barefeats.com/images/load_perf.gif

Somehow, I think if this guy was ask to compare and contrast the market for full-sized cars sold in the US by looking at and testing three of them, he'd end up choosing the Crown Victoria, Grand Maquis, and Lincoln Town Car.

soilchmst

Aug 19, 2002, 10:52 PM

Originally posted by madamimadamtimallen

... on the topic of Quartz Extreme, it only needs 32MB of VRAM PLUS it takes the weight off the processor so if QE was to make any difference it would be in the favour of the new machine. The old machines were running on Puma so the old 1GHz could have a GeForce4 MX but that means nothing when it is not being used to any significant level.

Check the stats, the tests are using 10.2 on the old macine :rolleyes: What I am getting at is that the photoshop 7 and export quicktime tests are faster on the old dual. This could be because less cache, or it could be because of the old dual having a much faster video card and having better support from the OS X. Anyway, my point is that systems do need to have the same options to yeild valid tests :cool:

When looking at real world performance, the key is "snappier," which can be a very small benchmark number and can be affected by the amount of RAM and type of videio card.

madamimadam

Aug 20, 2002, 12:15 AM

Originally posted by soilchmst

Check the stats, the tests are using 10.2 on the old macine :rolleyes: What I am getting at is that the photoshop 7 and export quicktime tests are faster on the old dual. This could be because less cache, or it could be because of the old dual having a much faster video card and having better support from the OS X. Anyway, my point is that systems do need to have the same options to yeild valid tests :cool:

When looking at real world performance, the key is "snappier," which can be a very small benchmark number and can be affected by the amount of RAM and type of videio card.

Doh! It he was using 10.1.5 on the SDR when I looked at it the first time but it has been updated since then.

The Xserve is still on Puma though and it wins out on some tests but overall all 3 machines come in about the same. I think the RAM and graphics cards mean nothing in these tests BUT the tests should be re-done with the same configurations when it is possible for such a test to be done.

It is time to realise the facts.... 7455 and DDR = a product that SOUNDS better than one with SDR. The real test will be the 7470

groovebuster

Aug 20, 2002, 03:56 AM

... the benchmarks may be not that professional, but face the truth, the new machines are not faster than the old ones.

I was testing the new DP1000 yesterday at an Apple dealer side by side with the old DP Quicksilver, both running 10.2, same amount of RAM, etc... pp...

The dealer was doing the set up himself to be able to compare the machines (he doesn't want to tell the people just what is written by Apple marketing).

And what I can tell you? :eek:

You almost don't notice any difference in real life... it was kinda disappointing!

No new Mac before the next update of the PowerMacs, it's not worth the money, when you already have a DP800 or DP1000 Quicksilver.

I think the best deal ist still the little DP867... it is a good deal compared to the former low-end model...

groovebuster