The Source for Mac Performance News and Reviews

Review: Giga Designs G4 1.25GHz CPU Upgrade By Mike Published: 3/14/2003

Benchmark Test Results

Intro | Benchmarks  | Apps Tests | Game Tests | Installation | Specs/Design

Benchmark Tests

Benchmark tests were run with Altivec Fractal Carbon demo 1.1.3 and CineBench 2000 and 2003. I stopped using Xbench some time back due to previous complaints about its repeatability. (The current 1.0 version may be improved in that regard - I did run tests with it for the DP533 and Giga Designs 1.33GHz CPUs, I'll try to add those scores here next week.) I reboot between all tests to ensure as clean/consistent a cache/memory state as possible. Of course benchmarks are far less important than real-world applications and game tests, but many want to see them regardless. (The Apps tests page has results of tests with iMovie2, iTunes3 (OS X), Photoshop 7.0 and MPEG4 movie conversion. The game tests page includes results with popular 3D games like Quake3, Unreal Tournament, and Return to Castle Wolfenstein.) In all but the Cinebench 2003 tests, Benchmark tests compared: A Mirror Drive Door (MDD) Dual 1GHz G4 system A Digital Audio (DA) G4/533 Dual CPU The DA system w/Powerlogix dual 1GHz upgrade The DA system w/Giga Designs G4/800 (7451 with no L3 cache), The DA system w/Giga Designs 1GHz (7455 CPU w/2MB L3 cache) The DA system w/Giga Designs 1GHz model set to 800MHz (to compare 800MHz w/L3, although it's not a perfect comparison since the 800MHz G4 w/o L3 cache is a 7451 CPU) The DA system w/Giga Designs 1.25GHz (7455A w/2MB L3 cache) set to 1.33GHz. Fractal FPU Benchmark: I used the freeware Altivec Fractal (Carbon) demo v1.1.3 program (available here) to compare FPU performance of the original Dual G4/533 system, with the Dual G4/1GHz Powerlogix upgrade, and a G4 Dual 1GHz Mirrored Drive Door (MDD) System. Default settings were used. (Note: MegaFlops/sec = Millions of Floating Point Operations per Second.) This is basically a FPU test (Altivec boosted of course), and L3 cache doesn't have any significant effect on the scores really (MHz/MHz with the same CPU). CineBench 2003 Results: Since probably less than 1% of Mac users own Maxon's Cinema4D application, I use their freely available CineBench benchmarks. (Which does more than just a simple timed render of a scene file - it also does shaded and wireframe model spins, "fly-throughs" of a scene, etc. to show graphics card and cpu performance, not just rendering times.) The Feb. 28th news page here noted that Maxon had released an updated version of their Cinebench 3D/rendering benchmark. Here's maxon's comments on the 2003 benchmark: " CINEBENCH 2003 is the free benchmarking tool for Windows and Mac OS based on the powerful 3D software CINEMA 4D R8. The tool is set to deliver accurate benchmarks by testing not only a computer's raw processing speed but also all other areas that affect system performance such as OpenGL, multithreading, multiprocessors and Intel's new HT Technology. CINEBENCH 2003 includes render tasks that test the performance of up to 16 multiprocessors on the same computer as well as software-only shading tests and OpenGL shading tests on huge numbers of animated polygons that will push any computer to its limits. " CineBench 2003 is available at http://www.maxon.net/jumps/cinebench.html. Cinebench 2003 is totally revised from the previous 2000 version and is now OS X native as well (but can still be run in OS 9). All Cinebench 2003 tests were run at 1600x1200 (desktop), millions color mode. Cinebench 2003 was released after my previous upgrade review tests so the results below compare the Digital Audio original G4/533 Dual CPU module with the Giga Designs 1.33GHz single CPU module (in the same system). The only Dual 1GHz system I had access to was a MDD system running 10.2.4 with a GeForce4 Ti graphics card. I've included MDD tests with both an ATI 8500 and Geforce4 Ti. Legend: CB 1 CPU = Single CPU render score CB X CPU = Dual CPU render score CPU Ratio = Gain from 2nd CPU (N/A for single CPUs) GFX C4D = Graphics performance using Cinema's software mode OGL SL = Graphics performance using OpenGL Software Lighting mode OGL HL = Graphics performance using OpenGL Hardware Lighting mode SL Ratio = Gain from OpenGL Software Lighting over C4D non-GL mode HL Ratio = Gain from OpenGL Hardware Lighting over C4D non-GL mode CineBench 2000 Results: Since Cinebench 2003 was only recently released, I also ran CB 2000 to compare results of the 1.33GHz upgrade to previously tested upgrades in the same system. (After the release of the 2003 version, Cinebench2000 apparently has been removed from Maxon's site.) Tests with CB2000 were run at the originally recommended 1024x768, millions color mode. Longer bars are faster.

The next page has results from real world applications. Or you may use the links below to jump to a specific page. ( For comparisons to other CPU Card upgrades and systems see the site list of CPU Card Reviews and Systems page.)

Index of Giga Designs CPU Upgrade Review Pages Intro | Benchmarks  | Apps Tests | Game Tests | Installation | Specs/Design - or - Back to WWW.XLR8YOURMAC.COM

Copyright © 2003. No part of this sites content or images are to be reproduced or distributed in any form without written permission. All brand or product names mentioned here are properties of their respective companies. Users of the web site must read and are bound by the terms and conditions of use.