The SpeedZone: Sure The New Dual G4/1.25 GHz Tower Is Faster Than The Single G4/1 GHz .. But By How Much? A Tale Of The Two Towers!

Below we take a look at the relative performances of the current low-end and middle of the road Power Mac Tower models from Apple. Aside from clock speed, the main difference between these two machines is that one comes with a single G4 processor and the other comes with two. Both machines have 256k of L2 cache (per processor), both have 1 MB of L3 cache (per processor). However the single processor Tower has a bus speed that clocks in at 133 MHz and the dual 1.25's bus runs at 167 MHz. This is not a great speed difference and probably had little, if any, effect on the performance results listed below.

The two machines also have different graphics cards. The single processor machine an NVIDIA card and the dual processor machine an ATI card. Both come with 64 MB of video memory.

What kind of effect do these differences have on performance? In most tests that required heavy processing activity, and that could take advantage of dual processors, the dual 1.25 GHz machine pulled significantly ahead. However the dual processor Tower left a lot of its processing power on the table, unused by the application that was running. For example in one of our Photoshop tests only 55% of the processing capability of the dual processor machine was used. 45% of the machine's data crunching ability was left idling, waiting for 1s and 0s that never came. This situation repeated itself in many of our other single application tests. Somewhere along the data feed chain there is a bottle neck that keeps data from arriving fast enough to keep the processors fed. Since it is possible to saturate the processors, both with specialized single applications, and when running multiple processes from more than one application, our guess is that the bottle neck is not at the hardware level, but the software level .. or perhaps at the level where the two meet. But we are speculating here. In any case, in environments where you want to be running multiple processes at once, a dual processor machine becomes much more attractive, perhaps even essential.

It also appears, at least from our testing, that, depending on the game, a dual processor machine will greatly out class a single processor machine when playing games.

Difference and similarities of each machine

"Real World" Tests

For the graphs below frame rates were converted to percentages, relative to the Power Mac Dual G4/1000, which is set to 100%. For all scores, higher numbers are better.

The copy folder test not only stresses drive performance but also takes advantage of faster processing capability & caching schemes.

In the single file test the the processor & caching capability of the machine is less of a factor. Drive performance is pretty evenly matched here

In this test only 55% of the processing power of the Dual 1.25 GHz Tower was being used, while 100% of the single processor machine's was. This is good news if you want to do other chores with your Tower while you import that 50 GB movie. It is bad news if you don't. There is some bottleneck in the process that keeps the dual processor machine from performing up to its potential .. wasting valuable processing capacity. Perhaps the drive is not feeding data quickly enough to the processor or there is some limiting factor in the software itself. Still if you are doing this type of work a dual processor machine makes a lot of sense.

Let 1K Windows Bloom is a simple carbon application that opens and closes 1,000 windows. This gauges how fast screen redraws are taking place. Though our stock machine and the dual 1.25 GHz have the same graphics card, the extra processing muscle puts the 1.25 over the top.

Large Document & Database Type Tests

Microsoft Office X Word Macro

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	94%	120%

A Macro (series of complex actions) was run in Microsoft's Excel spreadsheet program. Excel is part of Office X

Microsoft Office X Excel Macro

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	90%	114%

A Macro (series of complex actions) was run in Microsoft's Excel spreadsheet program. Excel is part of Office X

AppleWorks Search And Replace Test

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	95%	116%

This test takes place in a large AppleWorks document. Machines with larger chip caches usually do better in this test

Finder File Search

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	87%	112%

Mac OS X's new File Search function relies on both processor and drive performance

Number Crunching & Rendering Tests

Photoshop 7 - BareFeat's Test

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	77%	126%

BareFeats Photoshop Test Suite - mimics a production type workflow in Photoshop. In the single processor Tower, the processor was saturated with data. The 1.25 GHz machine had 25% left unused.

Photoshop 7 - AltiVec Tests

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	63%	114%

Certain of the functions of Photoshop can take special performance advantage of the G4 processor. A dual processor machine runs rings around a the single processor one, in this test.

Photoshop 7 - Normal Tests

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	94%	124%

The test above consists of Photoshop functions that do not take any particular advantage of the G4. The reason that the dual processor machines don't show more of a performance gap is that 45% to 50% of the processing power those machines was not being utilized. So having an extra processor was not much of an advantage ... unless you wanted to do something else at the same time.

iMovie - Effect Render

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	68%	126%

An Effect Render is run on an movie using iMovie. This tests takes advantage of dual processors.

AltiVec Fractal (Carbon)

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	50%	125%

The Fractal program has been highly tuned to take advantage of the G4 and is precisely the type of work that the G4 was made for. It will also gobble up whatever processing capability is present. This is a good test for assessing the fundamental processing potential of each machine. Really highlights the processing advantage of a dual processor machine

Encoding/Decoding Tests

QuickTime Encode

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	88%	112%

A QuickTime encode compresses a QuickTime movie for streaming on the Web. Only 50% of the processing power of the dual processor machines was used

QuickTime Convert To DV Stream

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	82%	126%

Converting QuickTime movies to DV allows you to import them into iMovie. 60% to 70% of the processing power of the dual processor machines was used.

iTunes - MP3 Encode From CD

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	101%	106%

During the encode 65% of the processing capacity of the dual processor machine was used. Is the CD drive speed a bottle neck?

StuffIt Expand

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	93%	126%

StuffIt does not take advantage of dual processors

Multitasking

iTunes MP3 Encode + AppleWorks Search & Replace + Finder Copy (Multitasking)

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	75%	116%

MP3 Encode, AppleWorks search & replace and folder copy are all carried out at the same time. In a production type environment the Dual Processor Towers make a lot of sense ... if you do some planning.

QuickTime Encode + Fractal (Multitasking)

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	52%	113%

QuickTime Encode and Fractal render are both carried out at the same time.

QuickTime DV + iMovie Effect Render (Multitasking)

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	56%	124%

QuickTime DV Encode and iMovie Effect are performed at the same time. Dual Processor machines rule the day

MP3 Encode + Photoshop Normal + Word Macro (Multitasking)

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Scores as percentage of Power Mac Dual G4/1 GHz	100%	96%	116%

The MP3 Encode, Photoshop Normal and Word Macro tests are all run at the same time

Gaming

Giants Highest Frame Rates

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Actual Frame Rates	105	62	133

Giants Average Frame Rates

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Actual Frame Rates	45	25.2	47

Giants Lowest Frame Rates

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Actual Frame Rates	21	13.9	25

4x4 EVO 2 Average Frame Rates- High Quality Setting

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Actual Frame Rates	18	17	25

4x4 EVO 2 Average Frame Rates- Medium Quality Setting

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Actual Frame Rates	30	26	39

4x4 EVO 2 Average Frame Rates- Low Quality Setting

Machine	Power Mac Dual 1 GHz	Power Mac Single G4/1 GHz	Power Mac Dual G4/1.25 GHz
Actual Frame Rates	42	36	52

For very demanding games you can't beat a Tower .. at least not yet