Books & Buyer's Guides

Books
Using iLife ... Books
Using iWork ... Books
Using The iPod ... Books
All Books On Apple Products ...

Information Hubs



Other Product Information


Site Supporters

send this page

Send to a friend

News Feed

Mailing list ...List information...


 
MacSpeedZone Gift Shop




Mac Performance In The Raw - Wow! The Intel iMac Is Almost As Fast As The Quad Core Power Mac - How Macworld Pulled A "Not So Fast" One ...

Wednesday, January 25, 2006

Request a Comparison between any two Macs
Computer Trade In Program


We are pleased to report that our testing results show that the new Dual Core Intel iMac, which clocks in at 2X 2.0GHz is almost as fast as the current high-end Power Mac that has two Dual Core G5 processors running at 2.5GHz.

How can this be, you ask ... An ostensibly 2 processor machine nearly keeping up with a faster, ostensibly 4 processor one? Easy, we used the same methodology employed in the Macworld "First Look" review of the new iMacs, and applied that to our comparison. (they found the Intel iMac, in general, only 10% to 25% faster than a similar speed single core processor G5 iMac)

But before we go any further, lets look at the astounding numbers, that prove our case ... the incredible performance, of the Intel iMac ....

We found the following

When running a QuickTime encode the Power Mac Quad G5/2.5GHz took 84.85 seconds.
The Intel iMac Core Duo 2.0GHz took 97.02 seconds
Advantage: Power Mac by 14% .... Nothing to write home about ... Not even keeping up with the clock-speed difference between the two machines

iMac
InfoZone
Performance
Performance vs Others
Buyer's Guide
Specs & Features
Discussision Thread
Reviews
Apple's iMac Page
Apple's Previous iMac Details

Not convinced .... I wasn't either ... Ok lets try something different. Lets run two encodes at the same time .... just for fun. It is easy to do, just duplicate the file and run the processes concurrently.

What scores did we get?

When running the QuickTime encodes the Power Mac Quad G5/2.5GHz took 86.25 seconds.
The Intel iMac Core Duo 2.0GHz took 176.60 seconds
Advantage: Power Mac by 105%

Ok let's get this straight when doing twice the work it only takes the Power Mac with its four processor cores, about 2 extra seconds, but takes the Intel iMac an extra whopping 79+ seconds - almost twice as long as in the single test?

What's wrong with this picture? What's wrong is processor capacity vs processor usage.

If you visit your Utilities folder, in the Application folder on your Mac (assuming you are running OSX), you will find a small application called "Activity Monitor". From the Window menu of Activity Monitor you can launch a window call CPU usage.

This will give you visual feedback about how much, of the processing capacity of your machine, is being utilized at any given time. When we speed trial any machine, we have the CPU usage window open while we go about our testing, making note during each test of how much of the processor(s) are put to use.

Guess what we found for the two tests outlined above?

In the first test, where there was just one file being encoded, the Intel iMac, on average, was using 87% of its processing capacity ... 13% was sitting around with nothing to do

On the other hand the Quad G5 Power Mac was using less than half its capacity, 42%. A full 58% was waiting for its dance card to be filled.

When we ran the two QuickTime encodes at the same time, processor usage moved to 87% for the Power Mac, and 100% for the Intel iMac. In other words the iMac was maxed out, and the Power Mac had 13% capacity left before it would really start to sweat.

This is where the Macworld "First Lab Tests" article falls a little flat ... obscuring the processor capacity vs processor usage problem inherent with mutiprocessor machines (or multi-core ... same difference). Using Macworld's logic we could argue, given the data above, the Quad G5 Power Mac is only 14% faster when running some of Apple's own applications. We think that this is misleading, as we pointed out.

There are precious few applications that take complete advantage of multiple processors, and of those only certain actions can use huge amounts of processing capacity. If you are using this type of application, you probably know it already.

We have long argued that, to really take full advantage of multiprocessor machines, you need to be in a production type of environment, and have a strategy for utilizing the significant resources these computers make available. It is possible to do this, and we fault the Macworld article for not pointing it out ... this was, after all, one of the reasons for OSX.

A multiprocessor machine will provide the user (even the casual user), with more flexibility. However, truth be told, for most of us, most of the time, it is over-kill. You need a kitten, and you're getting a tiger.

The Macworld article does say the machines have potential (we argue that potential is already there), and also makes the point that old applications, that do not run natively on the Intel processor, run about half as fast as they would run on a G5 machine (which is what we found also).

From our perspective we have established that the iMacs are at least twice as fast as their G5 counter parts, if you harness all the power. To us it appears that the hardware is up to the task, but that there is some bottleneck in the software (either at the application, or OS level), that prevents full utilization of multiprocessors by single applications (in most cases). Because you are able to max out the processors (even on the Quad machine), it seems like the hardware can get data fast enough to the processors, so the capacity is lacking elsewhere.

We have finished our extensive speed trials of the 2.0 GHz Intel iMac and will move on shortly to its slower sibling. We also have finished speed testing the 2.5 Quad Core Power Mac. So if you have any performance questions about these machines, drop us a line.

Below you will find our results of a comparison between an iMac G5/1.8GHz and the iMac Intel Core Duo 2.0GHz. Times are in seconds (except where noted), and the processor usage of each machine, for each test, is also given. Scores in dark orange are from applications that run natively on both Intel Macs and G5 Macs. The processor clock-speed difference between these two machines is 11%. The processor capacity difference is 122%.

Test iMac G5/1.8GHz Processor Usage iMac Intel Duo 2GHz Processor Usage Advantage
QuickTime
Encode
242.61
100%
97.02
87%
Intel 150% faster
iMovie Import
180.77
45%
108.02
7%
Intel 67% faster
Word Macro
178.48
97%
268.55
50%
G5 50% faster
iDVD import
95.60
97%
36.45
77%
Intel 162% faster
Altivec Fractal
233.51
100%
518.50
100%
G5 122% faster
Graphics - Interface
9.95
100%
11.97
50%
G5 20% faster
Copy Single Large File
79.84
15%
42.09
2%
Intel 90% faster
Game Performance
30 fps
-
32 fps
-
Intel 7% faster
Processor Dual
(2X QuickTime)
492.59
100%
176.60
100%
Intel 179% faster
Photoshop Filters
339.47
100%
608.25
90%
G5 79% faster
Photoshop Workflow
366.82
100%
532.24
80%
G5 45% faster
Fractographer
241.98
100%
82.27
100%
Intel 194% faster
CB 2003 Processor Single
189 points
100%
83 points
100%
G5 128% faster
CB 2003 Processor Dual
189 points
-
156 points
100%
G5 21% faster
CB 2003 Graphics Card
925 points
80%
543 points
75%
G5 70% faster
CB 2003 Graphics Processor
221 points
100%
111 points
100%
G5 99% faster

Fractographer is a new test application for us, that we are experimenting with . It appears to run significantly faster on the Intel processor, but perhaps this is explained by the much larger L2 cache in the Intel iMac.

We don't claim that our results here are the definitive word on the Intel iMac's performance, but we do present a different viewpoint, when looking at the performance of these machines, than was found in the Macworld article. We have, along with others, more fleshing out to do with the new machines, with their new processors. We hope to do that in the coming weeks, and to built a more complete picture of their comparative performance in relation to other Macs.

Top of page

 

Copyright 1996-2007 by Cider Press Publishing LLC all rights reserved. MacSpeedZone is not authorized, sponsored, or otherwise approved by Apple Computer. Apple, the Apple logo, Macintosh, iPod, iBook, iMac, eMac, and PowerBook are registered trademarks of Apple Computer, Inc. Additional company and product names may be trademarks or registered trademarks and are hereby acknowledged.

|