From the Lab: Optimizing the MacBook Pro

We’ve seen what Intel’s next-generation of Penryn chips can do to the performance of both MacBook Pros and MacBooks. But that testing focused on the standard configurations of Apple’s revamped laptop offerings—there are also build-to-order configurations. And now we’ve gotten our hands on such a system, a customized MacBook Pro, to see how optimizing the hardware translates to performance gains.

Specifically, we received a 15-inch MacBook Pro with a speedier processor, faster (though smaller) hard drive, and more memory. Our build-to-order laptop sports a 2.6GHz Core 2 Duo processor; the standard MacBook Pro tops out at 2.5GHz. We’ve also swapped out the standard 250GB, 5,400-rpm hard drive for a 200GB model that runs at 7,200 rpm. And our customized MacBook Pro has been maxed out to 4GB of memory, up from the 2GB that ship with the standard version.

This souped-up MacBook Pro costs $3,199—$700 more than the 15-inch MacBook Pro with a 2.5GHz Core 2 Duo chip. But that extra money gets you the fastest portable Mac we’ve ever tested.

This custom MacBook Pro was nearly 8 percent faster than the standard configuration according to Speedmark 5, our overall system performance benchmark. Comparing this new system with the build-to-order MacBook Pro Apple offered in late 2007, and you’ll see an 18 percent increase in the new configure to order’s overall Speedmark score. Not only that, but the configure to order system also bested a 2.4GHz iMac meaning that using a portable Mac no longer means a necessary trade off in performance—as long as you’re willing to spend the extra money, that is. (It’s worth noting that all these comparisons involve systems that contain 2GB of RAM, versus the 4GB that shipped in our build-to-order unit.)

Not surprisingly, the Mac Pro, with its eight processing cores and 3.5-inch 7,200RPM hard drives, remains the top performer in the Mac lineup. But with the news that Intel plans on releasing quad-core chips for laptops in the near future, even that performance gap is likely to get much smaller.

2.6GHz MacBook Pro Benchmarks

Speedmark 5 Adobe Photoshop CS3 Cinema 4D XL 10.5 Compressor iMovie HD iTunes 7.5 Unreal Tournament 2004 Finder Finder Finder
OVERALL SCORE SUITE RENDER MPEG ENCODE AGED EFFECT MP3 ENCODE FRAME RATE ZIP ARCHIVE UNZIP ARCHIVE FILE DUPLICATE
15-inch MacBook Pro/2.6GHz Core 2 Duo with 4GB RAM and 7,200-rpm drive* 241 0:52 0:49 1:37 0:44 0:59 90.8 4:13 1:21 0:36
15-inch MacBook Pro/2.5GHz Core 2 Duo 222 1:02 0:51 1:42 0:46 1:01 89.4 4:30 1:34 0:46
15-inch MacBook Pro/2.6GHz Core 2 Duo (Nov. 2007)* 205 1:20 0:51 1:57 0:48 1:03 74.1 4:50 1:56 0:53
20-inch iMac/2.4GHz Core 2 Duo 239 0:54 0:54 1:56 0:49 0:58 90.2 4:14 1:08 0:31
Mac Pro/2.8GHz (8 cores) 301 0:49 0:15 0:51 0:32 0:48 109.8 3:51 1:12 0:31
>Better <Better <Better <Better <Better <Better >Better <Better <Better <Better

Best results in red. Reference systems in italics. * denotes build-to-order configuration.

Speedmark 5 scores are relative to those of a 1.5GHz Core Solo Mac mini, which is assigned a score of 100. Adobe Photoshop, Cinema 4D XL, iMovie, iTunes, and Finder scores are in minutes:seconds. All systems were running Mac OS X 10.5.2 with 2GB of RAM, unless otherwise indicated. 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 Cinema 4D XL. 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 Film effect from the Video FX. menu to a one minute movie. We converted 45 minutes of AAC audio files to MP3 using iTunes’ High Quality setting. We used Unreal Tournament 2004’s 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 2GB folder.—MACWORLD LAB TESTING BY JAMES GALBRAITH, JERRY JUNG, AND BRIAN CHEN

Taking a closer look at how some of the add-ons on our customized MacBook Pro affect performance in specific tasks, the build-to-order laptop was 16 percent faster than the standard 2.5GHz model in our Photoshop test suite. The increased RAM played a major role in this test. When we retested the new 2.6GHz configure to order MacBook Pro with the standard 2GB of RAM we saw the Photoshop test score slow by 6 seconds to 58 seconds—just 6.5 percent faster than the standard 2.5GHz system. We attribute that gain to the faster processor and hard drive in the 2.6GHz MacBook Pro.

When we bumped up the RAM in the standard configuration 2.5GHz MacBook Pro to the 4GB, that system took just 57 second to complete the test—an improvement of 8 percent over its old time. So, in the case of our Photoshop test, adding RAM to the standard 2.5GHz system helped that system edge past the faster processor and hard drive in the 2.6GHz system outfitted with just 2GB RAM.

Interestingly, running the rest of our tests with 2GB of RAM didn’t have any negative affect whatsoever on performance of the build-to-order 2.6GHz Penryn laptop in our individual tests.

Another optional feature, the 200GB, 7,200-rpm hard drive, proved to be a big help in our disk-intensive tests. For example, the customized MacBook Pro was 14 percent faster than the standard 2.5GHz system when unzipping a compressed 2GB file and 22 percent faster when duplicating a 1GB folder in the Finder. A faster hard drive will definitely help when copying and manipulating large files and folders, or if your system is running low on memory or working on projects too big to held in memory. The downside to this 7,200-rpm option is, of course, its lower capacity than the 250GB drive that comes standard on the MacBook Pro as well as its $50 boost to your price tag.

Processor speed plays a role in many tasks, but the one test we run that really isolates processing power is our Cinema 4D scene render test. The $250 2.6GHz option isn’t dramatically faster than the standard 2.5GHz processor—about 4 percent faster in fact. That also turns out to be the difference between the times turned in by the 2.6GHz and 2.5GHz Penryn MacBook Pros in the Cinema 4D test.

Worth noting is that the new build-to-order MacBook Pro beat last year’s 2.6GHz Merom-equipped model. Also, despite its slower clock speed, the 2.5GHz Penryn-based system tied that 2.6GHz Merom laptop in our Cinema 4D tests. That speaks to the improved performance in these next-generation Core 2 Duo chips.

All of our Speedmark tests are run one at a time. Often, though, the benefit of multiple processing cores and extra RAM shows up when running multiple tasks. To see how these models stacked up when working on multiple tasks simultaneously, we installed 4GB of RAM in each system and ran our Professional Application Multitask suite—timing a Photoshop action script while rendering a scene in Cinema 4D and encoding a movie in Compressor.

Multitask Testing

Multitask Suite Multitask Suite
4GB RAM 2GB RAM
15-inch MacBook Pro/2.6GHz Core 2 Duo (7,200-rpm drive)* 1:33 1:38
15-inch MacBook Pro/2.5GHz Core 2 Duo 1:41 1:48
15-inch MacBook Pro/2.6GHz Core 2 Duo (Nov. 2007)* 1:53 2:02
20-inch iMac/2.4GHz Core 2 Duo 1:39 1:43
Mac Pro/2.8GHz (8 cores) 1:17 1:28
<Better <Better

Best results in red. Reference systems in italics. * denotes build-to-order configuration.

For the Professional Application Multitasking suite, we recorded how long it took Photoshop to run our standard test suite while a longer Cinema4D task and our Compressor encode test ran in the background. Systems were tested with both 4GB and 2GB of RAM.—MACWORLD LAB TESTING BY JAMES GALBRAITH, JERRY JUNG, AND BRIAN CHEN

In the tests where systems had 4GB of memory installed, the customized MacBook Pro was 8 percent faster than the 2.5GHz MacBook Pro, 18 percent faster than the last year’s build-to-order laptop, and 6 percent faster than the iMac 2.4GHz system. It only trailed the Mac Pro, which was 17 percent faster than the 2.6GHz Penryn MacBook Pro. (The above chart also contains a column showing Multitask suite results with only 2GB of RAM, though the overall results are similar to what you’d see with 4GB.)

You can read Macworld’s full review of the MacBook Pro as well as our review of the Penryn-based MacBooks. Now Macworld Lab plans to turn its attention back to the Mac Pro and its many customization options.

[James Galbraith is Macworld Lab director.]

Subscribe to the MacWeek Newsletter

Comments