PDA

View Full Version : Dual 2.0GHz G5 PowerMac Pictures and Benchmarks




MacRumors
Sep 4, 2003, 04:12 PM
As followup to the previous report (http://www.macrumors.com/pages/2003/09/20030903184752.shtml) of one of the first Dual 2.0GHz G5 PowerMac being delivered, Xlr8yourmac.com has posted (http://www.xlr8yourmac.com/G5/Powermac_Dual_g5.html#storytop) photos and benchmarks from the brand new PowerMac.

Initial reports included are Cinebench 2003 scores, iMovie DV->QT Export times, iTunes AIFF->MP3/AAC conversion times.



arn
Sep 4, 2003, 04:17 PM
Some notes:

iMovie results may be disk limited.

Cinebench 2003 is not G5 aware/optimized.

arn

Tiauguinho
Sep 4, 2003, 04:20 PM
45x importing speed is simply insane! My Dual 1Ghz gets less then half of that!

From Win to Mac
Sep 4, 2003, 04:20 PM
i can't get XLR8 to load on my browser. Is anyone having the same problem ?

fred
Sep 4, 2003, 04:23 PM
URL is spelled wrong ....an "r" is missing in Xlr8

justytylor
Sep 4, 2003, 04:26 PM
Gotta say, that iTunes conversion stat is impressive, at around 45times realtime for mp3s and aac conversion. I think the iDVD clip conversion times were in minutes:seconds:frames; 40 seconds to convert those is pretty impressive as well (though they might be too small for a big difference to become apparent). Put it to work squeezing two hours of DV (at approx. 26 gigs) down to a 3.5 gig mpeg2 file, and then we've got a benchmark!

[edit]Looks like xlr8yourmac.com is getting hammered; I managed to load the page in question once, and now I can't get back to it. Slashdot effect?

arn
Sep 4, 2003, 04:27 PM
From http://www.xlr8yourmac.com/G5/Powermac_Dual_g5.html#storytop

Page seems to be loading now...


****************************************************
Cinebench 2003
Tester : EMM

Processor : PowerMac G5
MHz : 2000
Number of CPUs : 2
Operating System : 10.2.7

Graphics Card : Radeon9600Pro
Resolution : 1024 x 768
Color Depth : Millions

****************************************************

Rendering (Single CPU): 219 CB-CPU (Dual G4 1.25GHz/9800 = 120)
Rendering (Multiple CPU): 401 CB-CPU (Dual G4 1.25GHz/9800 = 220)

Multiprocessor Speedup: 1.83 (Dual G4 1.25GHz/9800 = 1.83)

Shading (CINEMA 4D) : 266 CB-GFX (Dual G4 1.25GHz/9800 = 149)
Shading (OpenGL Software Lighting) : 661 CB-GFX (Dual G4 1.25GHz/9800 = 411)
Shading (OpenGL Hardware Lighting) : 1168 CB-GFX (Dual G4 1.25GHz/9800 = 875)

OpenGL Speedup: 4.40 (Dual G4 1.25GHz/9800 = 5.87)

****************************************************




I work at a university, and our dual 2Ghz G5 just arrived. I just did a quick iTunes benchmark, converting "Moment's Notice" (Coltrane) from AIFF, on the hard drive:

I just watched for the highest reached conversion speed factor:

Dual 2Ghz G5:
converting to 160 MP3: 45.6x
converting to 160 AAC: 33.5x

My 12" PowerBook G4 867Mhz:
converting to 160 MP3: 11.5x
converting to 160 AAC: 8.8x

The G5 is standard factory configuration.
The PowerBook is running Panther 7B53.

Both systems had nothing but iTunes running, and were not playing the tracks while converting them.
Nick M."



The iMovie export test was 40 seconds, which was actually comparable to a Dual 1.42GHz G4 - which is why I said it may be disk-limited, rather than processor limited.

Freg3000
Sep 4, 2003, 04:30 PM
The site is REALLY slow. I only got 1 picture to load. I want to see the benchmarks, which (at least the iTunes one) seems impressive.

.a
Sep 4, 2003, 04:50 PM
yes, the xlr8 site is slow - but the dual 2ghz g5 is fast

quite impressive. would like to know the speedfactor to my dual 450 g4 :)

.a

seven5
Sep 4, 2003, 04:52 PM
Its pretty dumb that he is testing with Panther on his Powerbook. Having been using Panther, i can tell you its a lot faster over all.

So if you are impressed with the gap in encoding time, consider it even bigger.

rlreif
Sep 4, 2003, 04:59 PM
My 12" PB can encode mp3's at 10-11x at 192. Thought that was great after encoding almost 700 cd's at 2x with a CRT imac. Now I really wish I had waited to do that work.

dombi
Sep 4, 2003, 05:03 PM
how about some Xbench results too?

iLife
Sep 4, 2003, 05:05 PM
very impressive i must say. i'm still waiting for mine... i really need to go down to the apple store by me just to see what they have around for me to play with! :D

G4scott
Sep 4, 2003, 05:13 PM
I got to touch a dual 2ghz G5 today at my local campus computer store... That thing is beautiful... It's big, but beautiful...

Freg3000
Sep 4, 2003, 05:21 PM
Originally posted by dombi
how about some Xbench results too?

Personally, I really don't trust xBench anymore. Some of the results show the 1.8 GHz G5 is slower than the 1.6 G5. Not very accurate IMO.

I'd still like to see a nice high number, but if it is not, so what. 45x ripping speeds is good enough.

trilogic
Sep 4, 2003, 05:22 PM
the delivery status of my dual G5 order is beeing assembled, delivery sept 7th. Hope it stays like this.

can't load the xlr8 site either.

those iTunes specs are very impressive.

we'll have to buy the fastest cd-rom available to benefit the cpu's speed.

or let the G5 render some 3D stuff while ripping cd's and play some games while rendering and ripping. :D

freaky57
Sep 4, 2003, 05:28 PM
I still cannot get in to see the pics. If someone does get in please copy them to a new link!:(

JtheLemur
Sep 4, 2003, 05:29 PM
Boy, looks like "shipping to education institutions first" really meant "shipping to college people first." I'm a huge K-12 customer, placed a bunch of Dual G5 orders right after the keynote, and man - got bumped from 9/2 to 9/23 like most people. Very lame. Well, at least they're starting to ship - I would have reallly like to have at least one for the first day of school (which was today). Blah!

panphage
Sep 4, 2003, 05:42 PM
Originally posted by JtheLemur
Boy, looks like "shipping to education institutions first" really meant "shipping to college people first." I'm a huge K-12 customer, placed a bunch of Dual G5 orders right after the keynote, and man - got bumped from 9/2 to 9/23 like most people. Very lame. Well, at least they're starting to ship - I would have reallly like to have at least one for the first day of school (which was today). Blah!

That blows.

EDIT: I could have sworn that xlr8 had mention that it was an institutional machine yesterday. Oh well, maybe it is his personal machine, in which case it don't make no sense. I still think it belongs to the college.

MOM
Sep 4, 2003, 06:14 PM
I just came from the computer store at the University of California San Francisco and they have 8 dualies and already last week they had about twice as many 1.6/1.8 units. They have a 1.8 on display, but there is not much on it for me to test it out with. Looks nice.

wrldwzrd89
Sep 4, 2003, 06:53 PM
I'm quite impressed with the benchmarks. I do understand that some of them don't stress the processor as much as other components. I am very much looking forward to getting a G5 of my own, perhaps by the end of this year.

york2600
Sep 4, 2003, 07:12 PM
I wish my school would hurry up and just order one. They said it would be a few months before they replaced their old G4 (not even MDD) with a G5.

Originally posted by G4scott
I got to touch a dual 2ghz G5 today at my local campus computer store... That thing is beautiful... It's big, but beautiful...

Hattig
Sep 4, 2003, 07:17 PM
Ah, when will someone post a nice hi resolution picture of the innards of the G5?

It looks like the PCI-X tunnel is mounted on the other side of the motherboard? But I can't really check because the image has been shrunk down.

Abstract
Sep 4, 2003, 07:26 PM
Holy ****, nice innards!!

ColoJohnBoy
Sep 4, 2003, 07:49 PM
Wow. The two Apple Stores in my area don't even have Dual 2.0 GHz machines. I was at the Cherry Creek store last playing around with the 1.8 though. The manager even unlocked the box and let me look at the insides. I'm still wiping up the drool.

*sigh* I might need to borrow some money.

tizza
Sep 4, 2003, 08:02 PM
hmmm prob be a while before the dualies get to Australia, but those stats are very impressive!

Analog Kid
Sep 4, 2003, 08:56 PM
Just making sure people noticed the iTunes rip is from an AIFF file on his hard drive.

Doesn't invalidate the benchmark, and may even be the better way to do it, but don't compare to ripping CD's...

NeXTCube
Sep 4, 2003, 09:31 PM
Barefeats.com has a couple of G5 benchmarks as well. Check out his comparison of the G5s with Xeons and Athlons (http://www.barefeats.com/g5sum02.html), and his Photoshop/Cinema 4D/Bryce (http://www.barefeats.com/g5.html) comparison...

tazznb
Sep 4, 2003, 10:14 PM
I hope this satisfies all.

tazznb
Sep 4, 2003, 10:16 PM
Originally posted by tazznb
I hope this satisfies all.

Sorry, but the site won't take file sizes larger than this. I have full size copies.

hayesk
Sep 4, 2003, 11:19 PM
Originally posted by Analog Kid
Just making sure people noticed the iTunes rip is from an AIFF file on his hard drive.

Doesn't invalidate the benchmark, and may even be the better way to do it, but don't compare to ripping CD's...

Good point - the CD only reads at 32x, so putting it on the disk eliminates the CD drive bottleneck. But that is probably a better test, since it is testing the G5 and not the drive.

mvc
Sep 5, 2003, 01:42 AM
Originally posted by tizza
hmmm prob be a while before the dualies get to Australia…

You think you've got a problem, try NZ!

SeaFox
Sep 5, 2003, 02:40 AM
Originally posted by Hattig
Ah, when will someone post a nice hi resolution picture of the innards of the G5?


Go here:

http://www.billnoll.com/g5/

MacBandit
Sep 5, 2003, 02:44 AM
Originally posted by tazznb
I hope this satisfies all.

Try using more jpeg compression and less scaling.

If you don't have a program to do this in I suggest Graphic Converter (http://www.lemkesoft.com/en/graphcon.htm).

tazznb
Sep 5, 2003, 06:43 AM
Originally posted by MacBandit
Try using more jpeg compression and less scaling.

If you don't have a program to do this in I suggest Graphic Converter (http://www.lemkesoft.com/en/graphcon.htm).

Here you go (no need for g-converter, though).

two_tail
Sep 5, 2003, 12:57 PM
This is kind of interesting. I placed a call in to ADC Support (800 793-9378 option 2) to see if anything has changed with my ADC order.

Instead of getting a person or an "everyone is busy" message, I got a recording telling me that all of the ADC Support staff was in a meeting that started at 11:30 central time and would last through the rest of the business day. I wonder what they're talking about?

MacBandit
Sep 5, 2003, 01:07 PM
Originally posted by two_tail
This is kind of interesting. I placed a call in to ADC Support (800 793-9378 option 2) to see if anything has changed with my ADC order.

Instead of getting a person or an "everyone is busy" message, I got a recording telling me that all of the ADC Support staff was in a meeting that started at 11:30 central time and would last through the rest of the business day. I wonder what they're talking about?

The angry customers calling in droves about there delayed G5 order most likely.

eatme8888
Sep 5, 2003, 02:09 PM
The fact that Cinebench gets about 400 when a dual Xeon gets well over 500 is very disappointing.

So from this, I would expect Lightwave and Maya to still be a tad slower on the Mac.

And I thought the G5 was going to be a lot faster. Now why would I think that?

two_tail
Sep 5, 2003, 02:17 PM
Originally posted by eatme8888
The fact that Cinebench gets about 400 when a dual Xeon gets well over 500 is very disappointing.

So from this, I would expect Lightwave and Maya to still be a tad slower on the Mac.

And I thought the G5 was going to be a lot faster. Now why would I think that?

Because once Cinebench and the other benchmark programs take the G5 into account, then the G5 just might be faster.

This is all similar to what happened when the PowerPC was originally released. Old 680x0 code ran really slow (until the emulator became more efficient), and eventually developers released "Fat" programs. The release of the G5 is similar, except there is not emulation mode for 32-bit PowerPC code.

MacBandit
Sep 5, 2003, 02:17 PM
Originally posted by eatme8888
The fact that Cinebench gets about 400 when a dual Xeon gets well over 500 is very disappointing.

So from this, I would expect Lightwave and Maya to still be a tad slower on the Mac.

And I thought the G5 was going to be a lot faster. Now why would I think that?

It's just a matter of the programs being rewritten to take advantage of the G5s advantages. Honestly the fact that it scores this well without code modifications is extremely impressive.

eatme8888
Sep 5, 2003, 02:36 PM
Because once Cinebench and the other benchmark programs take the G5 into account, then the G5 just might be faster.

This is all similar to what happened when the PowerPC was originally released. Old 680x0 code ran really slow (until the emulator became more efficient), and eventually developers released "Fat" programs. The release of the G5 is similar, except there is not emulation mode for 32-bit PowerPC code.

No, it's nothing like the move to PPC. The PowerPC was a completely different chip architecture, and software ran in emulation that made it think it was running on 680XX. Just like Windows emulators are slow, this emulation was slow, but not as noticeable because the first PPC processor was so much faster than the 680XX processor. So when software became PPC native, it wasn't operating under the emulation, so it was much faster.

The IBM 970 is a native PPC processor. There is no emulation here.

Software can be optimized for the G5's differences, but we won't see a speed increase on the level of 35-40%, which is what we would need to see in Cinebench for it to overtake the dual Xeon.

MacBandit
Sep 5, 2003, 02:39 PM
Originally posted by eatme8888
Because once Cinebench and the other benchmark programs take the G5 into account, then the G5 just might be faster.

This is all similar to what happened when the PowerPC was originally released. Old 680x0 code ran really slow (until the emulator became more efficient), and eventually developers released "Fat" programs. The release of the G5 is similar, except there is not emulation mode for 32-bit PowerPC code.

No, it's nothing like the move to PPC. The PowerPC was a completely different chip architecture, and software ran in emulation that made it think it was running on 680XX. Just like Windows emulators are slow, this emulation was slow, but not as noticeable because the first PPC processor was so much faster than the 680XX processor. So when software became PPC native, it wasn't operating under the emulation, so it was much faster.

The IBM 970 is a native PPC processor. There is no emulation here.

Software can be optimized for the G5's differences, but we won't see a speed increase on the level of 35-40%, which is what we would need to see in Cinebench for it to overtake the dual Xeon.

You're correct about the emulation but I don't believe so about the speed increase. The PPC970 has several advances over the current G4 or G3 line that are not being used by current apps and compilers. Once those are taken into account we could very well se a 25-50% increase in performance depending on the task.

eatme8888
Sep 5, 2003, 02:53 PM
Compiler, yes, optimizations, no. The developer of Cinema even states that with the optimizations it might reach 500. That's a quote. Dual Xeons are over 500.

With compilers, the question is which one do they use, and can they use the new one from IBM.

One thing, though, is I'm seeing results from Panther that are very impressive. So a dual G5 with applications that are heavily optimized running on Panther might be impressively fast. The problem is a lot of developers don't spend the time necessary to make a Mac version very well optimized. After Effects is a famous example from a developer that is supposedly one of the Mac's strongest.

I was under the impression that all software would be very, very fast on a G5 without all this "just wait for optimizations" talk. Apple's hype certainly implied that. So we are like we were with the G4 - a slower processor, but potentially faster with the right software optimizations.

MacBandit
Sep 5, 2003, 03:55 PM
Originally posted by eatme8888
Compiler, yes, optimizations, no. The developer of Cinema even states that with the optimizations it might reach 500. That's a quote. Dual Xeons are over 500.

With compilers, the question is which one do they use, and can they use the new one from IBM.

One thing, though, is I'm seeing results from Panther that are very impressive. So a dual G5 with applications that are heavily optimized running on Panther might be impressively fast. The problem is a lot of developers don't spend the time necessary to make a Mac version very well optimized. After Effects is a famous example from a developer that is supposedly one of the Mac's strongest.

I was under the impression that all software would be very, very fast on a G5 without all this "just wait for optimizations" talk. Apple's hype certainly implied that. So we are like we were with the G4 - a slower processor, but potentially faster with the right software optimizations.

Well it is a lot faster then a standard G4 but that's simply because it is a 2GHz processor. The only way to implement the additional FPU unit and the double precision math and all the other advantages the new G5 has is with a new compiler and maybe a code rewrite.

colinet
Sep 5, 2003, 06:09 PM
Originally posted by tizza
hmmm prob be a while before the dualies get to Australia, but those stats are very impressive!

The 1.8 has reached the Apple Dealer in Coff's Harbour I have seen it, got static off the alu case and looked inside which is a work of art. The Australian Apple site is still telling my dealer next week for the duals. I'm not holding my breath.

I've got my 23" cinema display frustratingly sitting in its box as even with a Mac Radeon card and the loan of a DVI to ADC, it won't work on my G4'd Beige Tower.

soggywulf
Sep 5, 2003, 07:13 PM
Originally posted by eatme8888
One thing, though, is I'm seeing results from Panther that are very impressive. So a dual G5 with applications that are heavily optimized running on Panther might be impressively fast.

Yes it probably will, but Panther won't help benchmarks like this Cinebench stuff. Which once again illustrates the general uselessness of benchmarks in determining real-world performance and useability. Running multiple Apps and making heavy concurrent use of OS/GUI functionality will be where Panther/G5 will shine, I think.

Originally posted by eatme8888
I was under the impression that all software would be very, very fast on a G5 without all this "just wait for optimizations" talk. Apple's hype certainly implied that.

That's true, and I am also somewhat disappointed with that. Although it is true that any new chip needs different instruction scheduling to make the most of it (even with the same native instruction set, and aside from the whole 32-64 question), I agree with you that the G5's raw CPU performance is probably still going to be generally a bit short of Intel--even with G5-optimized code. Still, it's nice that we are finally back in the same ballpark.

Originally posted by eatme8888
So we are like we were with the G4 - a slower processor, but potentially faster with the right software optimizations.

Not really. The G4 has other serious problems, like an absurdly slow memory bus. The G5 gets us away from that, and I think that is really one of the most important advantages of this chip for the Mac. The other major advantage is the seamlessness of the 64-bit transition, which needed to be done sooner or later as we approach the 4GB wall. So much the better that it is sooner, when most people haven't quite run into that wall yet. Code may be need to be recompiled for optimum scheduling, but we are not in a "32-bit emulation" situation.

jerrydog
Sep 5, 2003, 11:29 PM
itunes conversion on my 1.6 G5 from the hard drive is between 20 and 21. This is for an AAC file at 160. Pretty good speed, beats my dual 867 by about 5X to 6X.

porovaara
Sep 5, 2003, 11:48 PM
Originally posted by soggywulf
Yes it probably will, but Panther won't help benchmarks like this Cinebench stuff. Which once again illustrates the general uselessness of benchmarks in determining real-world performance and useability. Running multiple Apps and making heavy concurrent use of OS/GUI functionality will be where Panther/G5 will shine, I think.

Actually Panther will help a great deal with apps like this. Remember that Panther has a new optimized Math Lib and completely rewritten memory management which is significantly faster.

stingerman
Sep 6, 2003, 02:51 AM
Originally posted by eatme8888
Compiler, yes, optimizations, no. The developer of Cinema even states that with the optimizations it might reach 500. That's a quote. Dual Xeons are over 500.

With compilers, the question is which one do they use, and can they use the new one from IBM.

One thing, though, is I'm seeing results from Panther that are very impressive. So a dual G5 with applications that are heavily optimized running on Panther might be impressively fast. The problem is a lot of developers don't spend the time necessary to make a Mac version very well optimized. After Effects is a famous example from a developer that is supposedly one of the Mac's strongest.

I was under the impression that all software would be very, very fast on a G5 without all this "just wait for optimizations" talk. Apple's hype certainly implied that. So we are like we were with the G4 - a slower processor, but potentially faster with the right software optimizations.

Your wrong. Steve's WWDC keynote was very clear that with a simple and quick recompile Apps will do much better. Without a re-compile they will still do very well.

As far as performance comparisons, you're being ridiculous. Th 970's architecture and design outside of Altivec is radically different than the G4. The PPC architecture allows for binary compatibility though the implementations can be completely different, that is the beauty of the PPC architecture. By properly taking advantage the 970's internal parallelism and increased functional units, as well as its better prediction, Apps can be optimized significantly more than 30-40% as the Cinebench programmers stated. And that was before IBM's new xlC compiler which in some cases is showing over a 200% increase without any major changes.

To prejudge the 970's continued performance increases due to better software is premature. Why, OS X on the G4 is going to see another 30-40% speed increase with Panther. In fact, Apple has sped up some text functions by as much as 10x (1000%) with Panther on the G4.

Sun Baked
Sep 6, 2003, 05:38 PM
If you click on the link the PPC970 daughtercard is really packed in the G5 Mac...Originally posted by M.Isobe on Ars (http://arstechnica.infopop.net/OpenTopic/page?a=tpc&s=50009562&f=8300945231&m=9080959175&r=9460987385#9460987385):
_G5 processor module photo_

The photo was posted on some Japanese BBS. Maybe, it was leaked from Japanese MACPOWER magazine.

http://www.geocities.co.jp/SilkRoad/4512/970cpu1.jpg

barabics
Sep 7, 2003, 12:13 AM
Originally posted by trilogic
the delivery status of my dual G5 order is beeing assembled, delivery sept 7th. Hope it stays like this. :D

okay so i ordered a dual G5, where do i look and find when my G5 is being assembled?
i just wanna know.

MacBandit
Sep 7, 2003, 02:00 PM
Originally posted by barabics
okay so i ordered a dual G5, where do i look and find when my G5 is being assembled?
i just wanna know.

You go to your account in the Apple store and check the order status of the open order.

mark_wilkins
Sep 8, 2003, 04:40 AM
Originally posted by eatme8888
Software can be optimized for the G5's differences, but we won't see a speed increase on the level of 35-40%, which is what we would need to see in Cinebench for it to overtake the dual Xeon.

Actually, one of the developers of Cinebench posted on Ars Technica that they thought the dual 2 GHz G5 might end up "over 500" after optimization.

Note also that better optimization can yield tremendous performance improvements. One guy tested the same MP3 compression code compiled with GCC 3.3 and with IBM's 970-specific compiler for OS X (currently available as a public beta) and found that its execution doubled in speed when using IBM's compiler.

-- Mark

mark_wilkins
Sep 8, 2003, 04:44 AM
Originally posted by eatme8888
Compiler, yes, optimizations, no.

What do you think the difference between the compilers is, other than difference in optimization?

Take a look at the Shark tools described in the "Tuning for G5" technical note:

http://developer.apple.com/technotes/tn/tn2086.html

...and you'll see that they expose to the programmer all kinds of information about instruction issuing, where to expect pipeline stalls, and so on. With these kinds of tools, manual optimizations actually do have a reasonable hope of wringing out extremely strong performance improvements on top of what the compiler can achieve.

(Of course, that's a *hope* not a *guarantee.* :D)

-- Mark