From the Lab: Penryn powers MacBook Pro gains

Just as the hubbub over the MacBook Air has begun to quiet down, Apple has turned the spotlight on the rest of its laptop lineup. Last week the company introduced new MacBook and MacBook Pro models, replacing the Core 2 Duo processors with a new generation of faster chips and increasing the hard drive capacity.

We’ve put the new MacBook Pros through their paces and found that the changes add up to noticeable performance gains over the last-generation of Apple’s high-end laptop. More significant, the revamped MacBook Pro lineup is decidedly faster than the Core Duo-powered models that debuted two years ago.

The new MacBook Pros come with either a 2.4GHz Core 2 Duo processor (in the 15-inch model) or 2.5GHz Core 2 Duo chip (in the 15- and 17-inch configurations. The processors are part of Intel’s next-generation Core 2 Duo chip, code-named Penryn. Unveiled by Intel in January, Penryn chips use a 45-nanometer microprocessor architecture, which improves energy efficiency. The processors can also pack on up to 6MB of shared L2 cache.

Indeed, that’s exactly the amount of L2 cache you’ll find in the new 2.5GHz MacBook Pros—a 50-percent increase over the 4MB found in the previous generation. However, the new 2.4GHz MacBook Pro comes equipped with 3MB—1MB less L2 cache than those models.

The new MacBook Pros still use the same Nvidia GeForce 8600M GT graphics, but now come configured with twice the video RAM, with the new 2.5GHz models outfitted with 512MB and the 2.4GHz shipping with 256MB. All of the MacBook Pros ship with 2GB of DDR2 memory (upgradeable to 4GB). All configuration also get roomier hard drives, with 250GB drives replacing the 160GB hard drives in the previous 17-inch and higher-end 15-inch models, and a 200GB drive taking the place of the 120GB drive found in the last entry-level MacBook Pro.

So how do these internal improvements affect performance? Our Speedmark 5 benchmark suite shows some notable gains over the last generation of MacBook Pros. Aside from screen size, the two 2.5GHz MacBook Pros sport identical internal specifications. Yet, the 15-inch performed a bit faster overall than the 17-inch model, though not by much and not all the time.

Penryn-Based MacBook Pro Benchmarks

Speedmark 5 Adobe Photoshop CS3 Cinema 4D XL 10.5 Compressor iMovie HD iTunes 7.5 Unreal Tournament 2004 Finder HandBrake
OVERALL SCORE SUITE RENDER MPEG ENCODE AGED EFFECT MP3 ENCODE FRAME RATE ZIP ARCHIVE H.264 ENCODE
17-inch MacBook Pro/2.5GHz Core 2 Duo 219 1:00 0:52 1:42 0:45 1:02 81.6 4:32 2:37
15-inch MacBook Pro/2.5GHz Core 2 Duo 222 1:02 0:51 1:42 0:46 1:01 89.4 4:30 2:35
15-inch MacBook Pro/2.4GHz Core 2 Duo 204 1:05 0:53 1:51 0:49 1:03 73.4 4:46 2:57
15-inch MacBook Pro/2.6GHz Core 2 Duo * (Fall 2007) 205 1:20 0:51 1:57 0:48 1:03 74.1 4:50 2:37
15-inch MacBook Pro/2.2GHz Core 2 Duo 182 1:23 1:00 2:17 0:55 1:09 75.8 5:36 3:12
15-inch MacBook Pro/2GHz Core Duo 147 1:37 1:14 3:22 1:08 1:33 54.1 6:07 3:50
MacBook/2GHz Core 2 Duo (white 2007) 167 1:32 1:07 2:27 1:00 1:15 26.6 5:54 3:14
PowerBook G4/1.67GHz PowerPC G4 89 3:04 4:05 7:57 1:55 2:34 19.7 7:18 17:07
>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. 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. 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.—MACWORLD LAB TESTING BY JAMES GALBRAITH, JERRY JUNG, AND BRIAN CHEN

The new entry-level 2.4Ghz model bested the last entry-level system—a 2.2GHz MacBook Pro—by 10 percent in our Speedmark tests. In certain tests, like Photoshop, the improvement was even more dramatic, with the new 2.4GHz model finishing our Photoshop suite 23 percent faster than the older 2.2GHz system.

Even with less L2 cache, the new low-end MacBook Pro was able to compete head-to-head with last falls’s more expensive build-to-order MacBook Pro, posting a Speedmark score just one point less than the older system powered by as 2.6GHz Core 2 Duo chip.

The new 15-inch 2.5GHz MacBook Pro was quite a bit faster across the board than that build-to-order 2.6GHz system—more than 8 percent faster, in fact, in Speedmark, and 23 percent faster in Photoshop. Doubling the video memory also helped the new 2.5GHz MacBook Pro best the older build-to-order machine in our Unreal Tournament test by a whopping 34 percent.

While it’s certainly interesting to compare new models to the most recent releases to gauge the progression of Apple’s offerings, most people who bought a new MacBook Pro just last year are probably not looking to upgrade. Rather, it’s owners of even older laptops who have a stake in seeing just how much performance has improved with this latest release.

To provide a point of comparison, we also ran Speedmark tests on a 2GHz MacBook Pro Core Duo, a two-year-old machine that was among the first to ship with an Intel-built processor. The new 15-inch, 2.5GHz MacBook Pro scored around a 50-percent improvement over that older laptop in both Speedmark 5 and our Compressor tests. We also found the newer model to be 36 percent faster than the 2GHz MacBook Pro in both our Photoshop suite and Cinema 4D tests.

Users still holding on to their PowerPC-based PowerBooks have even more impetus to upgrade. Even the low-end 2.4GHz MacBook Pro had a Speedmark score twice as fast as the PowerBook G4. In other tests the 2.4GHz MacBook Pro finished tests in about a third of the time.

We’ll have a full review of the MacBook Pro shortly. Macworld Lab will now turn its attention to testing the new MacBooks that Apple released last week.

[James Galbraith is Macworld Lab director.]

Subscribe to the MacWeek Newsletter

Comments