T
he discussion concerning the speed claims of Appleis new Power Mac G5 continues to churn on the Internet. Apple introduced the Power Mac G4 replacement last Monday during the WWDC keynote. During the presentation, Apple CEO Steve Jobs announced the new architecture by calling the Dual 2 GHz Power Mac G5 the "worldis fastest personal computer," a description used by the company on its Web site, as well.
To back up that claim, Apple released benchmark results compiled by an independent company, VeriTest, which was hired by Apple. Steve Jobs and Apple VP Phil Schiller also brought out company execs from Adobe, Wolfram Research, eMagic, and Luxology to do some old fashioned bake-offs that pitted a Windows XP system against the PowerMac G5, with the Apple machine crushing the Windows machines by wide margins in each case.
This has set off all manner of controversy, as some people began to question the testing methods as documented by VeriTest (see TMOis full coverage for more information). Though Apple VP Greg Joswiak has publicly attempted to answer those questions, there hasnit been much response to Appleis response from the companyis critics, leaving the controversy in full swing. In the middle of that, however, Luxology, one of the companies that participated in the WWDCis bake-offs, has come out swinging for Apple.
Luxology has posted a letter to its Web site titled "G5 Performance Response." That letter was signed by Brad Peebler, president of Luxology, LLC, and the man who demonstrated his software on stage. Luxology makes 3D software, and is a new company founded by Lightwave veterans.
The demonstration centered around 3D motion-capture information being displayed on the screen. In the tests, the G5 performed at real-time, or nearly so, while the PC stuttered along at a much slower pace. According to Mr. Peebler, the code base was the same for the two platforms. It should be noted that Luxology does not yet have a shipping commercial product..
[Editoris Note: During his WWDC presentation, Brad Peebler touted a 15 minute recompile time for moving the companyis code to a 64-bit version for the G5 (12 minutes to get the code, 3 minutes to recompile was what he quipped on stage). As Observer Hank pointed out in the comments below, that was not a port from Wintel to OS X as we originally stated in this article, but rather a recompile from a 32-bit version to a 64-bit version "using Appleis tools," according to Mr. Peebler. See the keynote for more information. To stress our original point, according to the letter posted on the companyis site, the code base used on the Windows and Mac version is identical.].
In his letter to the public, Mr. Peebler explains that his company is largely a Windows company, and that most of their engineers work on Windows machines, though "many of us simply prefer OS X for its attention to detail and workflow for everyday use," to use his words. He describes Luxology as "platform agnostic," but defends the real-world results he demonstrated on-stage at the WWDC. From that letter:
The impressive SPEC benchmark results presented at the Apple G5 launch have been greeted with skepticism and a host of questions about their validity and methodology.
Luxology was one of the “real world” applications used to showcase the speed of the new processor. We would like to outline a few key facts about our development practices and how we went about putting the demo together. We hope this will shed some light on the performance users can expect from the G5, and clear up some confusion surrounding the various speed measurements.
[…]
Luxology uses a custom-built cross platform toolkit to handle all platform-specific operations such as mousing and windowing. All the good bits in our app, the 3D engines, etc, are made up of identical code that is simply recompiled on the various platforms and linked with the appropriate toolkit. It is for this reason that our code is actually quite perfect for a cross platform performance test. It also allows us to support multiple platforms with a relatively small development team. Huzzah.
The performance demo made with Luxology technology shows our animation playback tools utilizing motion capture data. Typically with 3D animation playback the application taxes the GPU (graphics processor) using Open GL or Direct 3D to handle the hardcore 3D computations. In the case of our demonstration we actually moved many of those functions to go through the CPU and stated as much in the presentation. After all, this was a test of raw CPU power, and not the graphics cards in the box (which were identical Radeon 9800s, by the way). We did quite a bit of performance tuning during the preparation for the demo. However, we did absolutely no AltiVec, or SSE coding. In fact, the performance tuning was done on Windows and OSX. We used Intelis vTune, AMDis CodeAnalyst and Appleis Shark. Again, 75% of our engineers were on Windows boxes and 25% working on the Mac, not to mention the fact that we only had one engineer with access and security clearance for the G5 prototype. That is hardly relevant, however, as any optimization done on one system is implicitly passed on to the other, as these were general optimizations to our raw 3D engines. The demo set up itself was designed to require a large number of computes and to push a large amount of data in and out of the chip to show both processor speed and bandwidth. I believe the demo accomplished this in an effective and very fair manner.
Read the full letter at Luxologyis Web site. Thanks to Observer Lester for pointing us to the Luxology letter.