The standard configuration of the Mac Pro outperforms its PowerPC-based G5 predecessors by a wide margin, helping to justify Apple’s 2005 decision to switch to processors from Intel. What’s more, the system powered by two dual-core 2.66GHz Xeon chips narrowly missed becoming the first machine to ever record a Speedmark score of over 300.
Still, tallying a Speedmark 4.5 score of 299 in Macworld Lab testing is nothing to sneeze at—especially in light of the fact that a few of the tests that make up Speedmark involve applications that don’t yet run natively on Intel chips. That means the Mac Pro was able to improve upon the Speedmark score of the Power Mac G5 Quad by 14 percent, even though the collection of tests that comprises Speedmark includes several which require Apple’s Rosetta code-translation technology.
Apple unveiled the Mac Pro at this week’s Worldwide Developers Conference. Using two dual-core Intel Xeon “Woodcrest” processors, the new Mac Pro comes in just one standard configuration, although Apple lets you configure everything from the processor speed to the installed RAM to the graphics card to the number of hard drives and optical drives that ship in your model—there’s around five million possible configurations, according to Apple’s marketing material.
We’ve ordered Mac Pros in a few different configurations and will test them as they arrive. The first machine to come in was the standard configuration—the $2,499 Dual-Core Mac Pro with two 2.66GHz Xeon processors, 1GB of Fully-Buffered DDR2 RAM, a 250GB hard drive, a 16X SuperDrive with double-layer support, and an Nvidia GeForce 7300GT graphics card. This out-of-the-box Mac Pro configuration earned the highest Speedmark score ever recorded in our tests.
Mac Pro Benchmarks
| Speedmark 4.5 | Adobe Photoshop CS2 | Cinema 4D XL 9.5.21 | Compressor 2.1 | iMovie 6.0.1 | iTunes 6.0.4 | Unreal Tournament 2004 | Finder | |
|---|---|---|---|---|---|---|---|---|
| OVERALL SCORE | SUITE | RENDER | MPEG2 Encode | AGED EFFECT | MP3 ENCODE | FRAME RATE | ZIP ARCHIVE | |
| Mac Pro/2.66GHz dual-core Intel Xeon x2 | 299 | 1:25 | 0:28 | 1:47 | 0:38 | 0:48 | 91.3 | 2:01 |
| Power Mac G5 Quad/2.5GHz dual-core G5 x 2) | 262 | 0:45 | 0:30 | 1:52 | 0:39 | 0:43 | 62.2 | 2:22 |
| Power Mac G5 Dual/2.7GHz single-core G5 x2 | 267 | 0:48 | 0:52 | 2:17 | 0:43 | 0:46 | 44.3 | 2:15 |
| 20-inch iMac/2GHz Intel Core Duo | 210 | 2:31 | 1:11 | 3:21 | 1:03 | 1:26 | 54.1 | 2:34 |
| >Better | <Better | <Better | <Better | <Better | <Better | >Better | <Better |
Best results in bold. Reference system in italics .
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 Finder scores are in minutes:seconds. All systems were running Mac OS X 10.4.7 with 1GB of RAM, 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 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 video effect to a 1-minute movie. 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. To compare Speedmark 4.5 scores for various Mac systems, visit our Apple Hardware Guide .—Macworld Lab testing by James Galbraith and Jerry Jung
As the results chart shows, in addition to having our highest Speedmark score, the Mac Pro posted the best results in five of the seven individual tests we’ve listed here. On some tests, such as rendering a scene in Cinema 4D, applying a video effect in iMovie, or using Compressor to encode a movie into MPEG2, the Mac Pro beat out its predecessor by just a few seconds. Other tests, such as creating a Zip archive and running the Unreal Tournament 2004 Botmatch, the Mac Pro’s lead widened—10 percent faster at archiving and 47 percent more frames per second in UT2004 than the fastest Power Mac G5.
Of the two tests the Mac Pro didn’t win, one involved the yet-to-be-Intel-native Photoshop CS 2. Even there, the Mac Pro showed plenty of improvement over other Intel-based Macs; it took about one-third the time of a 2GHz iMac Core Duo to run through our Photoshop test suite. The Mac Pro also cut the time it took to encode a CD’s worth of MP3s by half compared to the iMac’s performance.
We expect more new Mac Pros to keep arriving in our lab for similar testing. We plan to continue testing this standard configuration, installing more memory to see how that affects performance; using Boot Camp to install and run Windows, we also plan to test the Mac Pro with PC World’s WorldBench 5. With the impressive results of this off-the-shelf model, I can’t wait to get my hands on the new 3GHz system and finally blow past the 300-score level on Speedmark.
[ James Galbraith is the Macworld Lab director. ]