Mac OS X 10.4.1--How Fast Is It?

2004–09May 23, 2005Macs Only!Reviews
On Monday afternoon, May 16, Apple released Mac OS X 10.4.1 Update to Tiger. The Server edition of 10.4.1 Update was released Thursday of last week. As frequent readers know, we have benchmarked virtually every release of Mac OS X from the original 10.0 release through 10.3.9 to keep track of the improvements in its speed, a major complaint initially about Mac OS X. With the evolution of Mac OS X, Apple has made great strides in speeding it up. That, along with the release of Apple's Power Mac G5 and iMac G5, have mostly eliminated any significant OS speed concerns for its desktop computers. Even on the remaining G4s (i.e. PowerBooks, iBooks and Mac mini) and many legacy G4s and G3s, Mac OS X runs very well these days. According to Apple, the improvements in 10.4.1 included core graphics and updated ATI and NVIDIA graphics drivers.

So how fast is it? Did 10.4.1 speed anything up? To determine this we ran our usual suite of speed tests on our two test-bed Macs and one other. The speed tests are composed of a series of "canned" benchmark applications and several so-called "real world" tests that anyone can repeat on their own Mac for comparison by following the steps that we perform.

Our long-term test Mac (since Mac OS X 10.0) has been a mostly-stock, year 2000-vintage 450 MHz Power Mac G4 Cube with 704MB RAM. With Mac OS X 10.3, Apple began including improvements that are aimed mainly at the G5 CPU and graphics cards with 32MB of video RAM or more (the Cube's has only 16MB) so we also began using our dual 2.5GHz Power Mac G5 with 1.5GB RAM and an Nvidia GeForce 6800 Ultra DDL graphics card in the speed tests. For Tiger, we also ran our speed tests on a 20" 1.8GHz iMac G5 so we have also included the results for 10.4.1 below.

The 10.4.1update also did not turn on by default Tiger's new Quartz 2D Extreme technology (not to be confused with Quartz Extreme), just as we found for Tiger. To turn it on, one has to install Apple's Developer Tools and use the Quartz Debug application. Why this new technlogy is not enabled is a mystery to us.

Here are the results for the G4 Cube using Mac OS X 10.4.1 and Mac OS X 10.4 (Tiger) plus the last update of each "cat" version, i.e. 10.3.9 (Panther) and 10.2.8 (Jaguar) and 10.1.5 (Puma). Other versions back to 10.0 can be found in our previous articles:

450MHz G4 Cube Speed Tests (average* scores or secs).
Test Cube 450 MHz
Mac OS X Version:
10.1.5
10.2.8
10.3.9
10.4
10.4.1
Benchmarks:
Altivec Fractal (GFLOPS)
-
1.5
1.5
1.5
1.5
Cinebench 2003 - Rendering
-
49
48
48
48
- OpenGL Hardware Lighting
-
92
91
90
97
Let1kWindowsBloom 1.0 (sec)
57
61
53
30
30
Xbench - CPU
-
52
54
54
53
- Threading
-
34
42
42
42
- Memory
-
64
76
77
77
- Quartz Graphics
-
63
74
73
73
- OpenGL Graphics
-
84
80
88
88
- User Interface Graphics
-
60
102
150
148
- Hard Disk
-
66
54
56
57
"Real World" Tests:
Startup (sec)
98
54
52
53
49
Shutdown (sec)
5
7
15
16
15
Launch Classic Mode (sec)
43
-
25
36
37
Dup. 700 MB Folder 3600 Files (sec)
-
131
152
128
129
Scroll 142p Acrobat Reader File (sec)
71
57
55
55
59
Encode MP3 in iTunes (sec)
-
105
105
104
104
Export QT FQDV Movie in iMovie (sec)
-
32
36
38
38
Quake III Arena 1.32 (frames/sec)
-
22
34
32
32
*Average of three runs. Green is much faster. Red is much slower.

There are no significant performance improvements in Mac OS X 10.4.1 for the G4 Cube, the oldest Mac tested. For the most part, the significant speed improvements that arrived in Tiger were maintained in 10.4.1. Startup averaged a few seconds faster but scrolling averaged a few seconds slower. All of the rest are virtually identical.

Here are the Power Mac G5's results, with Quartz 2D Extreme manually turned on using Quartz Debug, comparing 10.4.1 with 10.4 and several previous versions of Mac OS X 10.3.x:

Dual 2.5GHz Power Mac G5 Speed Tests (average* scores or secs).
Test Dual 2.5 GHz Power Mac G5
Mac OS X Version:
10.3.5
10.3.7
10.3.9
10.4+
10.4.1+
Benchmarks:
Altivec Fractal (GFLOPS)
12.7
12.7
12.9
12.9
12.9
Cinebench 2003 - Rendering
647
644
647
649
646
- OpenGL Hardware Lighting
1569
1579
1601
1797
1801
Let1kWindowsBloom 1.0 (sec)
11
11
11
6
7
Xbench - CPU
243
243
241
242
241
- Threading
241
260
262
268
268
- Memory
340
335
333
385
376
- Quartz Graphics
300
342
348
525
521
- OpenGL Graphics
209
178
202
233
234
- User Interface Graphics
374
410
415
521
517
- Hard Disk
110
108
106
105
107
"Real World" Tests:
Startup (sec)
45
38
40
35
37
Shutdown (sec)
9
9
10
8
11
Launch Classic Mode (sec)
9
9
10
11
10
Dup. 700 MB Folder 3600 Files (sec)
62
56
66
58
62
Scroll 142p Acrobat Reader File (sec)
13
12
11
12
12
Encode MP3 in iTunes (sec)
54
54
54
52
52
Export QT FQDV Movie in iMovie (sec)
20
19
20
22
24
Quake III Arena 1.32 (frames/sec)
417
407
411
405
401
Halo 1.0.5.3/1.5.1 (frames/sec)
57**
61***
63***
67***
67***
Call of Duty 1.4 (frames/sec)
n/a
84
85
86
86
*Average of 3 runs. **Halo 1.0.5.3 with ATI Pixel and Vertex Shaders. ***Halo 1.5.1 with Advanced Shaders. +With Quartz 2D Extreme enabled.Green is much faster. Red is much slower.

For the next-to-latest top Power Mac G5, the performance improvements of 10.4 were retained but there were no further gains. The greatest effect of Quartz 2D Extreme is on the benchmarks Cinebench 2003 (G5)'s OpenGL Hardware Lighting, Xbench Quartz Graphics and Xbench User Interface Graphics. Halo still benefitted from the faster OpenGL graphics but not by much. Perhaps, the updated Nvidia graphics drivers (v1.42) in 10.4.1 still need even more tweaking.

Here is a table comparing Tiger's 10.4.1 vs 10.4 and Panther (10.3.9) using the 20" iMac G5:

iMac G5 Speed Tests (average* scores or secs).
Test
20" iMac G5**
Mac OS X Version:
10.3.9
10.4
10.4.1
Benchmarks:
Altivec Fractal (GFLOPS)
2.6**
2.4**
2.3
Cinebench 2003 - Rendering
242
246
244
- OpenGL Hardware Lighting
680
936
946
Let1kWindowsBloom 1.0 (sec)
18
12
12
Xbench - CPU
88
114
128
- Threading
70
97
100
- Memory
154
240
234
- Quartz Graphics
171
202
209
- OpenGL Graphics
169
173
178
- User Interface Graphics
204
314
312
- Hard Disk
83
85
86
"Real World" Tests:
Startup (sec)
49
38
38
Shutdown (sec)
9
7
7
Launch Classic Mode (sec)
-
-
-
Dup. Britannica 2004 Folder (sec)**
84
80
80
Scroll 57p Acrobat Reader File (sec)**
99
105
113
*Average of 3 runs. **Run by a different person than the other tests using different but consistent within-iMac test files. -Not available. Green is much faster. Red is much slower.

The results from the iMac G5 are very similar to our usual test-bed computers. Only the Xbench CPU test is a little higher. Quartz 2D Extreme was not enabled.

Apparently, 10.4.1 has only security, compatibility and stability improvements. We found no speed improvements. Unfortunately, Quartz 2D Extreme is still not enabled but, anyway, it seems to affect only some of the canned benchmarks and not any of our "real world" tests. 10.4.1 updated both Mail and Safari but we still have the major issues introduced in those applications by Tiger--the speed of backups due to Mail's new file structure and Java problems in Safari (e.g. see Edmunds.com). [Bill Fox & Dana Baggett]



Saw something? Send a tip

The archive ran on reader tips. What did you see, where, and do you want the credit?

Read by the editor. Never published without your say.

More in Reviews · This month in the archive