First Look: Understanding our 17-inch MacBook Pro benchmarks

A 17-inch MacBook Pro powered by a next-generation Core 2 Duo chip performs as you might expect, generally matching the performance of a 15-inch MacBook Pro equipped with the same 2.33GHz processor—with one notable exception.

Apple announced a 17-inch 2.33GHz MacBook Pro Core 2 Duo along with the rest of the upgraded MacBook Pro line in October, though the 17-inch model didn’t ship until November. We finally got our hands on one just before Thanksgiving and began running our usual battery of tests. For the most part, we liked what we saw. Results from tests using applications such as Photoshop, Cinema 4D, Compressor, iMovie, iTunes, Unreal Tournament were all nearly identical on both the 15-inch and 17-inch 2.33GHz Core 2 Duo MacBook Pros. Other tests, like zipping and unzipping one Gigabyte archive files were not as close, but didn’t produce numbers that we consider eyebrow-raising.

Ah, but our iPhoto test results—those had us scratching our collective heads.

For some reason, the 17-inch model we bought from the San Francisco Apple Store was taking two-and-a-half times longer than the 15-inch MacBook Pro Core 2 Duo to import 100 photos from the hard drive into the iPhoto Library. (The 17-inch MacBook Pro uses a 160GB drive from Hitachi; the 15-inch model’s 120GB drive comes from Fujitsu.) The 2.33GHz Core 2 Duo-powered machine was even taking longer than a 1.67GHz PowerBook G4.

17-inch MacBook Pro Core 2 Duo Benchmarks

Speedmark 4.5 Adobe Photoshop CS2 Cinema 4D XL 9.5.21 Compressor 2.3 iMovie 6.0.2 iPhoto 6.0.5 iTunes 6.0.4 Unreal Tournament 2004 Zip Archive UnZip Archive
SUITE SUITE RENDER MPEG2 Encode AGED FILTER IMPORT PHOTOS MP3 ENCODE AVERAGE FRAME RATE 1GB FOLDER 1GB FILE
17-inch MacBook Pro Core 2 Duo/2.33GHz 211 1:12 0:57 2:02 0:50 2:55 0:58 72.6 2:18 1:34
17-inch MacBook Pro Core 2 Duo/2.33GHz (120GB drive) 218 1:11 0:57 2:07 0:51 1:21 0:58 72.4 2:24 1:33
15-inch MacBook Pro Core 2 Duo/2.16GHz (1GB RAM) 209 1:16 1:01 2:17 0:54 1:12 1:11 63.9 2:48 1:26
15-inch MacBook Pro Core 2 Duo/2.33GHz 226 1:10 0:57 2:07 0:51 1:10 0:58 72.9 2:22 1:19
15-inch MacBook Pro Core 2 Duo/2.33GHz (1GB RAM) 222 1:11 0:57 2:07 0:51 1:12 0:58 72.1 2:39 1:24
15-inch MacBook Pro Core Duo*/2.16GHz (1GB RAM) 190 1:40 1:06 3:02 0:58 1:51 1:38 59 2:37 1:17
MacBook Core 2 Duo/2GHz (White-1GB RAM) 178 1:25 1:14 2:41 0:59 1:15 1:13 17.8 2:53 1:40
15-inch PowerBook G4/1.67GHz (1GB RAM) 132 1:35 3:57 6:59 1:51 2:04 1:53 19.9 3:30 1:32
>Better <Better <Better <Better <Better <Better <Better >Better <Better <Better

Best results in bold. Reference system in italics . Asterisk (*) denotes model with build-to-order 7,200-rpm hard drive

Speedmark 4.5 scores are relative to those of a 1.25GHz Mac mini, which is assigned a score of 100. Adobe Photoshop, Cinema 4D XL, iMovie, iTunes, and Zip Archive scores are in minutes:seconds. All systems were running Mac OS X 10.4.8 with 2GB of RAM (except where indicated), with processor performance set to Highest in the Energy Saver preference pane when applicable. The Photoshop Suite test is a set of 14 scripted tasks using a 50MB file. Photoshop’s memory was set to 70 percent and History was set to Minimum. We recorded how long it took to render a scene in Cinema4D. We used Compressor to encode a 6minute:26second DV file using the DVD: Fastest Encode 120 minutes - 4:3 setting. In iMovie, we applied the Aged video effect to a 1-minute movie. We imported 100 jpeg images from the hard drive into iPhoto’s library. We converted 45 minutes of AAC audio files to MP3 using iTunes’ High Quality setting. We used Unreal Tournament 2004’ Antalus Botmatch average-frames-per-second score; we tested at a resolution of 1,024 by 768 pixels at the Maximum setting with both audio and graphics enabled. We created a Zip archive in the Finder from a 1GB folder and then Unzipped the same file. To compare Speedmark 4.5 scores for various Mac systems, visit our Apple Hardware Guide .—MACWORLD LAB TESTING BY JAMES GALBRAITH, JERRY JUNG AND BRIAN CHEN

We tried another batch of stock photos from a different source and found the same large performance gap. (We chose stock photos for the comfort of our testers—who wants to watch my life pass before their eyes day after day during testing?) Unable to resolve the issue, we alerted Apple, which loaned us another 17-inch MacBook Pro for testing—but the same problem popped up with that system.

I decided to try swapping the hard drive from the 15-inch model for the 17-inch’s drive. Though the process is relatively simple, it requires removing, keeping track of, and replacing approximately 24 screws per system. After the switch, I found that the 17-inch model gained considerable ground, posting a time just 11 seconds shy of its 15-inch 2.33GHz sibling. After going back to Apple representatives with our results, we decided to swap test photos. When I tried the tests using Apple’s photos, the problem disappeared. When the folks at Apple tried ours, they removed the ColorSync profiles from the images before running the tests using the “Remove profile from image” script found in /Library/Scripts/ColorSync. We ran the script and then ran the tests again.

What a difference a profile makes! The stock 17-inch 2.33GHz MacBook Pro went from taking nearly 3 minutes to complete the test to just one minute, as you can see in the chart below. Removing the profiles sped up the other systems as well, so using these new files in this version of Speedmark just isn’t possible. Apple isn’t sure why those profiles are making such a difference, but the company assured us that it’s working to get to the bottom of this and will keep us informed of any progress.

17-inch MacBook Pro Core 2 Duo And iPhoto

iPhoto 6.0.5 iPhoto 6.0.5
IMPORT PHOTOS IMPORT PHOTOS no color-sync profiles
17-inch MacBook Pro Core 2 Duo/2.33GHz 2:55 1:00
17-inch MacBook Pro Core 2 Duo/2.33GHz (120GB drive) 1:21 1:00
15-inch MacBook Pro Core 2 Duo/2.16GHz (1GB RAM) 1:12 1:01
15-inch MacBook Pro Core 2 Duo/2.33GHz 1:10 0:57
15-inch MacBook Pro Core 2 Duo/2.33GHz (1GB RAM) 1:12 0:59
15-inch MacBook Pro Core Duo*/2.16GHz (1GB RAM) 1:51 0:56
MacBook Core 2 Duo/2GHz (White-1GB RAM) 1:15 1:02
15-inch PowerBook G4/1.67GHz (1GB RAM) 2:04 1:59
<Better <Better

Best results in bold. Reference system in italics . Asterisk (*) denotes model with build-to-order 7,200-rpm hard drive

All systems were running Mac OS X 10.4.8 with 2GB of RAM (except where indicated), with processor performance set to Highest in the Energy Saver preference pane when applicable. We imported 100 jpeg images from the hard drive into iPhoto’s library. In the second column, we removed ColorSync profiles from the images before running the test.—MACWORLD LAB TESTING BY JAMES GALBRAITH, JERRY JUNG AND BRIAN CHEN

In the meantime, keep in mind that the stock 17-inch MacBook Pro’s Speedmark score is severely affected by this quirk we found in iPhoto. In fact, if we were to pull the iPhoto test out of the Speedmark calculation, the 15-inch 2.33 MacBook Pro would have scored just one point higher than the 17-inch model, compared to the current 15 point performance gap.

Though we stand by our results, we will likely change the test to use typical digital camera files in the next version of Speedmark, which we expect to debut early in 2007. We will also continue to follow up with Apple for an explanation of this quirky result.

Stay tuned for Macworld ’s full review of the 17-inch MacBook Pro, coming soon.

[ James Galbraith is Macworld Lab director. ]

Comments