Sidebar Sidebar
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.

Power Mac G5 Quad Benchmarks

For the first time in Apple's history we are looking at a regression in chip technology over the next year from this point on - assuming Intel can even get something usable out next year.

Massively cheaper and faster quad systems and it is all being thrown out the door. Thank you Jobs you idiot. Go play with your iPods and find someone competent to run the desktop hardware side of the company.

It is going to be embarrassing to have to listen to him try to spin his was through the performance and feature drop that will come when the first garbage Intel desktops show up. Sickening.
 
rlwimi said:
For the first time in Apple's history we are looking at a regression in chip technology over the next year from this point on - assuming Intel can even get something usable out next year.

Massively cheaper and faster quad systems and it is all being thrown out the door. Thank you Jobs you idiot. Go play with your iPods and find someone competent to run the desktop hardware side of the company.

It is going to be embarrassing to have to listen to him try to spin his was through the performance and feature drop that will come when the first garbage Intel desktops show up. Sickening.
Click to expand...


where has this come from ???

if dual 2.0 is benchmark of 100 then this is pretty dam quick !

whats the problem:eek:
 
My hope is that they back-pedal from the intel only stance, and take on both chips in the long term plans.

that would require a massive swallowing of pride and probably other business factors, so it probably won't happen.

Anyways, I can't wait to buy some used quad g5's on the cheap in a couple years...

-- J.
 
The ULTIMATE Quad TEST

Load MacOS 7.6 running Photoshop 3, PageMaker, and Simpletext at full throttle, all the while printing several Finder windows.

What could a poor Quad do?
Butts
 
My Cinebench scores

jiggie2g said:
Xbench should just crawl in some hole and die.

I think a cross platform benchmakr should be used such as Cinebench , or a Photoshop Filter/Render test.

for the Record My X2 3800 @ 2ghz scores 532 in Cinebench
@ 2.5ghz scores 659 in Cinebench.

I'd like to see some Post!!!!
Click to expand...

Wow, multi-processors kick @$$ in that benchie! I just downloaded and ran Cinebench 2003 for kicks, with all my typical processes running and without a restart, and got a 283 for single CPU (on my Inspiron XPS Gen 2 with Pentium-M at 2.13GHz).

CINEBENCH 2003 v1
****************************************************

Tester : Josh Barrie

Processor : Inspiron XPS Gen 2
MHz : 2130
Number of CPUs : 1
Operating System : WIndows XP Pro SP2

Graphics Card : Nvidia Geforce 6800 Ultra Go OC'ed
Resolution : 1920x1200
Color Depth : 32-bit

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

Rendering (Single CPU): 283 CB-CPU
Rendering (Multiple CPU): --- CB-CPU


Shading (CINEMA 4D) : 335 CB-GFX
Shading (OpenGL Software Lighting) : 1489 CB-GFX
Shading (OpenGL Hardware Lighting) : 4281 CB-GFX

OpenGL Speedup: 12.80

****************************************************
 
this look suspicious...

Bartleby84 said:
I'm surprised nobody's pointed out the bench marks from the other Dual Core G5s out there now. Check out Mac360's results here. Specifically, I'm amazed (although maybe not too surprised) at the thread test results-
  • Dualcore 2.0: 96.91
  • Dualcore 2.3: 113.74
  • Dual Dualcore 2.5: 246.38!
Oh, I can't wait for those MP aware Photoshop benchmarks. *drool*
Click to expand...

if my Rev.B dual processor 2.0 is the base (i assume Rev.B) then that means that it is actually FASTER than the dualcore 2.0.???
 
b.k.jackson said:
For comparison, my PowerBook (15" Alu) 1.25 G4 got a 102.80

Brian
Click to expand...
It may have gotten a 102.80 on an older version of XBench, but the new XBench shows 1.25GHz PB with >1GB of RAM scoring around 43.

For comparison, a dual 2GHz G5 scores about 100.

Check for yourself: http://www.xbench.com
 
That's a very impressive result overall for the dual dual (taking into account of course that the scale has been recalibrated). My mini (1.42, gig ram, 7200rpm external fw boot drive) now scores in the high 43's. 4x that seems pretty good to me :D

TM
 
Kicks butt on my "new" iBook
(Using latest xbench version)
Results 34.44
System Info
Xbench Version 1.2
System Version 10.4.3 (8F46)
Physical RAM 512 MB
Model PowerBook6,7
Processor PowerPC G4 @ 1.33 GHz
L1 Cache 32K (instruction), 32K (data)
L2 Cache 512K @ 1.33 GHz
Bus Frequency 134 MHz
Video Card ATY,M12
Drive Type FUJITSU MHV2060AT
CPU Test 46.13
GCD Loop 106.43 5.61 Mops/sec
Floating Point Basic 30.76 730.88 Mflop/sec
vecLib FFT 76.15 2.51 Gflop/sec
Floating Point Library 31.58 5.50 Mops/sec
Thread Test 54.36
Computation 50.17 1.02 Mops/sec, 4 threads
Lock Contention 59.32 2.55 Mlocks/sec, 4 threads
Memory Test 22.86
System 24.77
Allocate 93.11 341.94 Kalloc/sec
Fill 25.19 1224.92 MB/sec
Copy 14.15 292.28 MB/sec
Stream 21.22
Copy 21.04 434.48 MB/sec [altivec]
Scale 20.81 429.90 MB/sec [altivec]
Add 21.48 457.47 MB/sec [altivec]
Triad 21.57 461.41 MB/sec [altivec]
Quartz Graphics Test 48.84
Line 44.89 2.99 Klines/sec [50% alpha]
Rectangle 46.64 13.93 Krects/sec [50% alpha]
Circle 46.25 3.77 Kcircles/sec [50% alpha]
Bezier 60.14 1.52 Kbeziers/sec [50% alpha]
Text 48.97 3.06 Kchars/sec
OpenGL Graphics Test 62.76
Spinning Squares 62.76 79.62 frames/sec
User Interface Test 21.24
Elements 21.24 97.46 refresh/sec
Disk Test 27.83
Sequential 43.83
Uncached Write 38.01 23.34 MB/sec [4K blocks]
Uncached Write 36.97 20.92 MB/sec [256K blocks]
Uncached Read 70.55 20.65 MB/sec [4K blocks]
Uncached Read 42.14 21.18 MB/sec [256K blocks]
Random 20.39
Uncached Write 7.03 0.74 MB/sec [4K blocks]
Uncached Write 55.04 17.62 MB/sec [256K blocks]
Uncached Read 50.72 0.36 MB/sec [4K blocks]
Uncached Read 62.31 11.56 MB/sec [256K blocks]

Seems like I'm one of the slow pokes to this benchmark. If the quad scores THAT much higher, than it must be like lightning, my lappy seems pretty fast to me... (OK my lappy is faster than my other computers and my bro's PB (1ghz), but not as fast as his new iMac 17" g5)
 
It's DUAL, not duel.

AoWolf said:
Yeah I would like to see it next to a duel 2.7
Click to expand...

This is one of my pet peeves.

All together now...... DUAL DUAL DUAL DUAL DUAL DUAL
 
Lacero said:
Not sure how fast 151.86 on Xbench is. Any real world tests using everyday apps such as Shake?

Sounds great if the quads can run 70-80% faster than the dual-cores.
Click to expand...
The quads ARE dual-core.
 
Kills the xServe

You'd think the xServe Cluster Node would be all over a desktop machine, but with half the L2 cache, only 2 cores vs. 4, and a slower frontside bus it's way behind. Surely the Powermacs must be canabalising the xServe market for those who need true high performance? The xServe only starts to make sense if you start having space problems, and then the xServe is a winner.

Hopefully Quad Core xServes aren't far off!
 
imnoah said:
This is one of my pet peeves.

All together now...... DUAL DUAL DUAL DUAL DUAL DUAL
Click to expand...

Yeh... but the shoot out would be a duel!

XBench results for the dual 2.7 are median ~120.

If the quad is clocking 151.6, then we've got about a 25% boost from the 2.7...

That said, the dual 2.5's average around a 105. A 50% boost...

If we apply that same jump... the quad 2.7 would jump a 180.

I dunno... but the results are pretty much what I expected.. but not what I had hoped.

:)
 
the real deal

rlwimi said:
For the first time in Apple's history we are looking at a regression in chip technology over the next year from this point on - assuming Intel can even get something usable out next year.

Massively cheaper and faster quad systems and it is all being thrown out the door. Thank you Jobs you idiot. Go play with your iPods and find someone competent to run the desktop hardware side of the company.

It is going to be embarrassing to have to listen to him try to spin his was through the performance and feature drop that will come when the first garbage Intel desktops show up. Sickening.
Click to expand...


There is no doubt that desktop computers will keep getting faster and more powerful regardless of the cpu manufacturer.
Apple has always adopted new technology , and dragged the entire market after them. (scsi, firewire, pci-e, ...)
(how about an AMD mac ? sounds cool to me)

The real deal has been, and will forever be Software !

I think we should give Jobs credit for constantly keeping Apple's desktop operating systems a quantum leap ahead of their competetors.

If you need more processing power, you can always use J.D Lowry's solution :D
http://www.apple.com/pro/film/lowry/index2.html
 
eAspenwood said:
My hope is that they back-pedal from the intel only stance, and take on both chips in the long term plans.

that would require a massive swallowing of pride and probably other business factors, so it probably won't happen.

Anyways, I can't wait to buy some used quad g5's on the cheap in a couple years...

-- J.
Click to expand...


have you noticed apple has stopped comparing powermacs to intels and are comparing new G5s to old G5s.

please Stevo use the pentium Ms for laptops but let us keep the G5.
 
camomac said:
if my Rev.B dual processor 2.0 is the base (i assume Rev.B) then that means that it is actually FASTER than the dualcore 2.0.???
Click to expand...

I sure hope that isn't true... I'm getting a new dual core 2. I don't see how it can get a slower score when all the tests that I've seen show the new Dual Core 2 beating the old Dual Processor 2. (not by a whole lot, but still beating it)
 
Tupring said:
The quads ARE dual-core.
Click to expand...
Yeah, dual dual-cores. :D

But we like to call them quads, less confusing.


//the word DUAL has lost all meaning!!!
///*hides in corner sobbing.
 
Photoshop test results

Using Photoshop CS or CS2 (or PS 7)
==================================================
1.) Download the test image from http://www.quicklance.com/test.jpg
2.) Save it to the computer and then open it up in Photoshop
3.) From there please apply a ‘radial blur’ with the settings at:
Amount = 100
Blur Method = Spin
Quality = Best
Using a stop watch / ps timer see how long it takes to apply this filter
I just want to see what these new cpu’s can really do.

Results:
iMac G5 1.8GHz, 1GB - 2:00
Athlon XP3200+, 1GB - 2:15
Athlon64 4000+, 1GB - 1:25
Dual 2.5 Running 10.4.2 with 2.5 GB RAM 40 seconds
PowerMac Dual 2.7 Dell 2405 FPW, 2.5 gigs of ram, Radeon 9650 42 seconds
Dual Core 2.0 GHz G5 with 2.5GB ram Photoshop CS2 47.4 seconds

Quad 2.5GHz G5 2.5GB RAM 10.4.3 22 seconds !!!!! It's an amazing huh??!!!
 
Ecc

macorama said:
You'd think the xServe Cluster Node would be all over a desktop machine, but with half the L2 cache, only 2 cores vs. 4, and a slower frontside bus it's way behind. Surely the Powermacs must be canabalising the xServe market for those who need true high performance? The xServe only starts to make sense if you start having space problems, and then the xServe is a winner.

Hopefully Quad Core xServes aren't far off!
Click to expand...

Nope with out the ECC mem that a powermac is lacking a Powermac will be suxy against a xserver in a cluster. And clusters are true high preformance.
 
jiggie2g said:
Xbench should just crawl in some hole and die.

I think a cross platform benchmakr should be used such as Cinebench , or a Photoshop Filter/Render test.

for the Record My X2 3800 @ 2ghz scores 532 in Cinebench
@ 2.5ghz scores 659 in Cinebench.

I'd like to see some Post!!!!
Click to expand...


Nice thing about those is that they use real apps for the test. The guys with the Quads should download Cinebench and take it for a spin - that would say something, I imagine.

http://www.cinebench.com/

there is a PC, OSX and OSX G5 Optimized - someone should do this.

D
 
nick007 said:
Using Photoshop CS or CS2 (or PS 7)
Results:
iMac G5 1.8GHz, 1GB - 2:00
Athlon XP3200+, 1GB - 2:15
Athlon64 4000+, 1GB - 1:25
Dual 2.5 Running 10.4.2 with 2.5 GB RAM 40 seconds
PowerMac Dual 2.7 Dell 2405 FPW, 2.5 gigs of ram, Radeon 9650 42 seconds
Dual Core 2.0 GHz G5 with 2.5GB ram Photoshop CS2 47.4 seconds

Quad 2.5GHz G5 2.5GB RAM 10.4.3 22 seconds !!!!! It's an amazing huh??!!!
Click to expand...

How do you know all this? Do you have a Quad? If these results are true.. my God. :eek:
 
Ecc

PPC970FX said:
Nope with out the ECC mem that a powermac is lacking a Powermac will be suxy against a xserver in a cluster. And clusters are true high preformance.
Click to expand...

If you go to the Apple store, you will see the ECC mem for the Express PMac's.
 
PPC970FX said:
Nope with out the ECC mem that a powermac is lacking a Powermac will be suxy against a xserver in a cluster. And clusters are true high preformance.
Click to expand...
The new PowerMacs can be ordered with ECC memory as an option.
 
You must log in or register to reply here.
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.
Top Bottom
Back