All Macs In-Depth Tests
The Performance Edge: Hey Not So Fast! PowerBook G4/550 vs PowerBook G4/500 - Newer, Faster Clocked PowerBook Not Always Faster - A Performance Review Under OS X

Additional Related Resources

Friday, December 28, 2001

Below we provide a performance review of the PowerBook G4/550 compared to the PowerBook G4/500, when running OS 10.1.

The 550 MHz machine has a 100 MHz System Bus, a slightly higher processor clock speed, 256K of full processor speed,on-chip L2 cache and a faster graphics system, with 16 MB of dedicated graphics memory.

The 500 MHz machine also has a 100 MHz System Bus, in place of the on-chip cache it has a back-side cache of 1 MB running at half the processor speed. It also has a slower graphics system and only 8 MB of graphics memory.

As you will see from the scores below, the lack of a large back-side cache in the newer 550 MHz PowerBook, stunts its performance in some tests, when compared to the older 500 MHz PowerBook. However the smaller speedier on-chip cache seems to have made a big difference in one of our drive related tests, where faster calculations on smaller amounts of data were called for ... at least when running under Mac OS 10.1.

If you are a person that likes to play demanding games on your portable, the new 550 MHz PowerBooks really shines over its predecessor, turning in 130% better performance when running Quake III in 'Quality Mode.'

So the overall performance of the new low-end PowerBook is somewhat mixed, both when running under Mac OS X and when under OS 9. It is however Apple's budget professional portable. The previous 500 MHz machine was Apple's top of the line portable in its time. The 500 MHz machine cost $3,499 when it was first released. The PowerBook 550 MHz machine was $2,199. So you get slightly worse performance in some areas, much better performance in some areas, all for $1,300 less.

"Real World" Tests

The tests below are from our suite of real world application tests. These tests feature a diverse selection of applications commonly used by the Mac community. The test suite was designed to render an accurate and well rounded picture of a machine's performance. All of the tests below were timed with a stopwatch. The times are then converted to percentages relative to the PowerBook G4/500, which is set to 100%. For all scores, higher numbers are better.

Finder Tests

Drive performance is what probably makes the most difference in the above test

This was an interesting result because the perforrmance was almost the opposite when running under 9.2.1. Our feeling is that the fast 256K of on-chip cache is what is helping the score of the newer PowerBook. In some way OS X appears to be able to utilize this speedy memory better than OS 9

This result was similar under both OS's.

Why the smaller cache of the 550 MHz machine would be an issue hampering performance in this test is unclear.This test creates and destroys 1,000 windows. See the program site for more info

Large document is scrolled from one end to the other using Classic OS through OS 10.1

Large Document & Database Type Test

This test takes place in a large AppleWorks document. This results is also somewhat of a mystery. In past comparisons we have noted that a larger, but slower, L2 cache does better in this test than a faster smaller cache. Indeed when comparing these two machines under OS 9, this is the case ... by a wide margin. So why the newer PowerBook is doing better here, under OS X, is not clear.

 

Number Crunching & Rendering Tests

 

See iMovie

Obviously the newer PowerBook has a lot of processing punch, when it can be tapped. 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.

Encoding/Decoding Tests

This test gets movie files ready for Web streaming

Converting QuickTime movies to DV allows you to import them into iMovie

The above 3 test require a lot of data fetching and it appears that the larger cache trumps a faster processor... see iTunes

Pretty much a tie .. see StuffIt

Multitasking

A Sorenson encode and the AltiVec Fractal are performed at the same time... no clear lead means the slower clocked PowerBook is the winner.

Here the Sherlock Index Test and the AppleWorks Search and Replace tests are run at the same time. Curiously the 550 MHz machine beat the 500 MHz one when these two tests were run seperately.