Testbed configurations:

• Athlon XP 3000+ based computer
  • AMD Athlon XP 3000+ CPU (2166 MHz)
  • MSI KT7 Ultra-2 mainboard based on VIA KT333
  • RAM: 1 GB DDR SDRAM PC 3200
  • Seagate Barracuda 7200.7 80GB SATA HDD

• Operating system – Windows XP SP2; DirectX 9.0c
• Monitor: Mitsubishi Diamond Pro 2070sb (22").
• Drivers:
  • ATI v6.476 (CATALYST 4.9)
  • NVIDIA v65.76
  • for Voodoo4 - Amiga 3.0
  • for Savage4 - 8.40.02
  • for Savage2000 - 9.21.01
  • PowerVR - 21.00.07
  • Matrox G550 - 5.92.006; Parhelia - 1.07.00.
  • for DeltaChromeS8 - 15.10.11

VSync is disabled.

ATTENTION! In games using shader technologies the test results ARE SPLIT INTO SEVERAL DIAGRAMS: without shaders, Shaders 1.1 and 2.0. ZEROS in SOME VIDEO CARDS mean that THIS TEST (GAME) COULD NOT BE RUN ON THIS CARD, or AN ERROR OCCURRED.

Test results: performance comparison

We used the following test applications:

• Serious Sam: The Second Encounter v.1.05 (Croteam/GodGames) – OpenGL, multitexturing, ixbt0703-demo, test settings: quality, S3TC OFF
  
  
• Unreal Tournament 2003 v.2225 (Digital Extreme/Epic Games) – Direct3D, Vertex Shaders, Hardware T&L, Dot3, cube texturing, default quality
  
  
• Code Creatures Benchmark Pro (CodeCult) – gaming test demonstrating how the video card works with DirectX 8.1, Shaders, HW T&L.
  
  
• Unreal II: The Awakening (Legend Ent./Epic Games) – Direct3D, Vertex Shaders, Hardware T&L, Dot3, cube texturing, default quality
  
  
• RightMark 3D v.0.4 (one of game scenes) – DirectX 8.1, Dot3, cube texturing, shadow buffers, vertex and pixel shaders (1.1, 1.4).
  
  
• Tomb Raider: Angel of Darkness v.49 (Core Design/Eldos Software) – DirectX 9.0, Paris5_4 demo. The tests were conducted with the quality set to maximum, only Depth of Fields PS20 was disabled.
  
  
• HALO: Combat Evolved (Microsoft) – Direct3D, Vertex/Pixel Shaders 1.1/2.0, Hardware T&L, maximum quality
  
  
• PainKiller v.1.31(People Can Fly/Dreamcatcher) – DirectX 9.0, multitexturing, maximum possible test settings. Integrated benchmark was used.
  
  
• Tom Clancy's Splinter Cell v.1.2b (UbiSoft) – Direct3D, Vertex/Pixel Shaders 1.1/2.0, Hardware T&L, Very High settings; demo 1_1_2_Tbilisi
  
  
• Call of Duty (MultiPlayer) (Infinity Ward/Activision) – OpenGL, multitexturing, ixbt0104demo, test settings – maximum, S3TC ON
  
  
• FarCry 1.2 (Crytek/UbiSoft), DirectX 9.0, multitexturing, demo01 (research) (the game was started with the -DEVMODE option), test settings – Very High.
  
  
• Quake3 Arena v.1.17 (id Software/Activision) – OpenGL, multitexturing, ixbt0703-demo, all test settings to maximum: detailing level – High, texture details – #4, S3TC OFF, curved surfaces are strongly smoothed using variables r_subdivisions "1" and r_lodCurveError "30000" (note that by default it's r_lodCurveError «250» !),
  
  
• Return to Castle Wolfenstein (MultiPlayer) (id Software/Activision) – OpenGL, multitexturing, ixbt0703-demo, test settings – all to maximum, S3TC OFF,
  
  
• DOOM III (id Software/Activision) – OpenGL, multitexturing, test settings – Low Quality,
  
  

If you want to get the demo-benchmarks, which we use, contact me at my e-mail.

You can download the summary table of results in Excel 2003 format here.

ALL DIAGRAMS ON ONE PAGE (4.5MB)

In our 3DiGest you can find more detailed comparisons of various video cards.

Conclusions

The bottom line is simple: we used the most powerful of the existing platforms, which supports all AGP 1.0-3.0 video cards. That's why we managed to test this number of accelerators. By the way, it should be noted that our readers also learned how the outdated accelerators deal with new games (as we can see, the majority of video cards produced in 1999-2000 simply refuse to operate).

And the choice is up to the readers. :) You've got the info. Plenty of it. :)