Performance

Benchmarking under OS X is a bit of a pain. There aren't many good standardized real world benchmarks, and unfortunately the synthetic tests are often over used.

General OS usage is a difficult thing to quantify, but one measure of performance has always been the number of bounces an icon in the dock makes before an application loads. I decided to take it to the next level and write a quick script to launch 15 applications in a row, timing how long the entire process takes.

I launched, in order: Mail, Safari, Activity Monitor, iTunes, iCal, DVD Player, iPhoto, Photo Booth, Quicktime Player, Disk Utility, Preview, iMovie, Front Row, Garage Band and Aperture.

The entire process stresses both the disk and CPU, which is why we see a huge improvement when going to an SSD as well as differences between CPU speeds.

The 13-inch MacBook Pro performs the worst here by a large margin, not just because of its lowly 2.26GHz Core 2 Duo, but also because it only has 2GB of memory. The 13-inch system takes nearly 30% longer to load all of the apps because of its limited amount of memory.

The 15-inch MacBook Pro uses a 2.53GHz Core 2 Duo instead of the 2.80GHz chip in the 17-inch by default. The result is a 7% longer load time on the 15-inch system, not huge, but not insignificant. As always, I recommend getting the fastest CPU you can afford if you're planning on keeping this machine for a while.

The fastest machine here is actually the MacBook Air, because it comes with an SSD. Your best bet to improve overall system responsiveness and launch times is to get a good SSD. Even with only 2GB of memory, the current gen MacBook Air finishes the script faster than the 17-inch MacBook Pro. Paired with an Intel X25-M G2 the 15-inch MacBook Pro can run through our script in 16 seconds.

Adobe Photoshop CS4 Performance

The Retouch Artists Speed Test we use for our CPU testing under Windows also works under OS X. We're running the exact same benchmark here, basically performing a bunch of image manipulations and filters and timing the entire process.

Despite limiting Photoshop to not keeping any history, the 2GB 13-inch MacBook Pro takes around 40% longer to complete the test than the 15-inch MacBook Pro. If you're planning on doing any Photoshop work you'll want to upgrade the 13-inch system to 4GB of memory.

The slower CPU in the 15-inch system penalizes it by around 10% compared to the 17-inch MacBook Pro. For any sort of real performance work, it looks like a 15-inch MacBook Pro with the 2.80GHz upgrade would be a good balance of price/performance.

As I alluded to earlier, there's not much of a performance improvement from the early 2008 MacBook Pro to the current generation. Drive speeds have improved a bit but overall performance hasn't really gone up, it's why Apple had to rely on updated looks and much better battery life to sell systems this time around. Not a bad tradeoff if you ask me, you'll see the performance improvement next year with Arrandale.

Aperture 2 RAW Import

For my Aperture test I simply timed how long it took to import 203 12MP RAW images into the library.

Once again, 2GB isn't enough, the 15-inch and 17-inch are indistinguishable but the 13-inch system takes much longer here.

Cinebench R10

3D rendering performance is mostly CPU bound so the 13-inch system isn't penalized by its memory limitations. Here the 2.53GHz Core 2 Duo is around 11% faster than the 2.26GHz in the 13-inch MBP. The 2.80GHz CPU is another 11% faster on top of that.

In the multithreaded bench the performance advantages are about the same, a bit closer to 12% between chips.

Again we see that CPU speed hasn't really improved much since early 2008, the two 15-inch systems are basically equal performers here.

Quicktime H.264 Video Encoding

Our final benchmark is more consumer focused. Here I'm taking an XviD and converting it to an iPhone-supported H.264 format.

We're CPU bound here so the 13-inch system only takes 14% longer to convert our video clip than the 15-inch. The difference between the 15-inch and 17-inch is about another 10%.

Still Better Battery Life Than Windows 7 Final Words
Comments Locked

115 Comments

View All Comments

  • Drakino - Wednesday, November 11, 2009 - link

    I'd be curious to know what battery life is like playing back H.264 content, since it should be accelerated by the GPU. Would help to know if it's worth the effort to encode to it over any other format.
  • Ram21 - Wednesday, November 11, 2009 - link

    You could do another benchmark on the Mac systems with Blender 3d. It would give you a comparison to the PCs with similar specs.

    Great Article, thank you.
  • drew952 - Wednesday, November 11, 2009 - link

    Could somebody clear up my confusion please...The article states "Both machines start at 7 lbs and don't offer higher than 1080p resolutions." However, in the specifications for said computers, the resolution is 1600 x 900.
    Isn't that comparable and/or better then 1080p?
  • slashbinslashbash - Wednesday, November 11, 2009 - link

    1080p is 1920x1080. So it is substantially higher resolution than 1600x900. (2.07 million pixels vs. 1.44 million pixels)

    FYI, 720p is 1280x720, so even the 13" MBP with the 1280x800 screen resolution handles 720p.
  • The0ne - Wednesday, November 11, 2009 - link

    Just wondering if you guys have a Droid 2 review coming for 2009? Would like you guys to do this so we can have the Pre, Droid and Iphone for comparison. Thanks.
  • crimson117 - Wednesday, November 11, 2009 - link

    "Jarred has seen similar results. One of his battery life tests involves leaving the laptop idle at the Windows desktop until it shuts off."

    That sounds like Anand caught Jarred napping at his workstation, and Jarred was like "no, really I'm, uh, testing battery life! See? It's my custom made Idle Windows Desktop Battery Life Test."

    I'm going to start testing my software designs by observing to make sure they don't alter themselves if left untouched on my computer for 6 hours ;)
  • DCstewieG - Wednesday, November 11, 2009 - link

    Anand, you say you want a more forward looking test for watching videos and then you use XviD? Surely you know how to use Handbrake. Then you could show battery life watching H.264 videos in QuickTime with GPU acceleration.

    Otherwise great article! You first Mac article way back when got me first seriously looking at Macs and now I've been a happy MBP owner for 2 years. Thanks!
  • Pneumothorax - Wednesday, November 11, 2009 - link

    It's about time somebody from the press brings up the cursed SSD Macbook Pro issue. Even some of the 15" MBP 2009 models with the 1.7 Sata II patch are still having random freezes with Intel 160gb G2 SSD's. It drove me so crazy that I returned a 2009 MBP and got a refub 2.53 MBP 2008 with the removable battery. Now my G2 runs flawlessly. Whenever there's a hardware issue, Apple likes to give us the silent treatment (which is MUCH WORSE than the spokesholes remarks that pc makers will at least give you) Shame on you Apple!
  • The0ne - Wednesday, November 11, 2009 - link

    You'll like their terminology of their latest patch for the OS then :)

    http://www.dailytech.com/Apple+Releases+OS+X+1062+...">http://www.dailytech.com/Apple+Releases+OS+X+1062+...
  • SmCaudata - Wednesday, November 11, 2009 - link

    I have an early 2008 MBP. I'll not buy an apple machine again. Their updates are so infrequent that when there is a problem like the terrible batter life or wireless issues with Snow Leopard you have to wait for a year for it to be fixed. Instead they spend time "fixing" iTunes to make it not work with the Palm Pre (I don't own a Pre...I just think them repeatedly disabling it is getting old).

    With new windows7 laptops like that 14" Acer Anand reviewed a few weeks ago, I expect Apple is going to have to stop being so closed off. What's more I could buy a new PC laptop every year for the same out of pocket cost to get a MacBook every 3 years. I still need boot camp on my MPB for some programs and there is nothing on my MacOS that I cannot have on Win7.

    So long Apple... Fool me once....

Log in

Don't have an account? Sign up now