Menu
Connect3D Radeon 9700 Pro in the test: performance leap at high resolutions

Connect3D Radeon 9700 Pro in the test: performance leap at high resolutions

Table of contents
  1. 1 Introduction
  2. 2 The card
  3. Scope of delivery
  4. 3 Drivers
  5. 4 Specs and technology
    1. 5 FSAA and AF
  6. 6 Benchmarks
  7. Test system
  8. 7 Synthetic tests
    1. 3DMark2001 SE
    2. 8 3DMark Detail
    3. 9 Villagemark D3D
    4. 10 Villagemark Detail
    5. 11 TempleMark D3D
    6. TempleMark D3D detail
    7. 12 Codecreatures Bench
    8. 13 Codecreatures Detail
    9. 14 Aquamark D3D
    10. 15 Aquamark D3D detail
  9. 16 Game benchmarks
    1. Ultima IX D3D
    2. 17 Ultim a IX D3D Detail
    3. 18 Comanche4 D3D
    4. 19 Comanche4 D3D Detail
    5. 20 Dungeon Siege
    6. 21 Dungeon Siege Detail
    7. 22 Aquanox
    8. 23 Aquanox in detail
    9. 24 Jedi Knight II
    10. 25 Jedi Knight II Detail
    11. 26 Max Payne
    12. 27 Max Payne detail
    13. 28 Serious Sam SE D3D
    14. 29 SeSam SE D3D Detail
    15. 30 Serious Sam SE OGL
    16. 31 SeSam SE OGL Detail
    17. 32 UT2003 Demo FlyBy
    18. UT2003 Demo Botmatch
    19. 33 UT2003 FlyBy Detail
    20. UT2003 Botmatch Detail
    21. 34 Alice
    22. 35 Alice Detail
  10. 36 Conclusion

Alice Detail

Let's see if our thesis from Alice's strong bandwidth dependency. If so, the frame rate should go pretty much towards the basement with FSAA, while the AF should remain largely stable (at least on the Radeon).

Alice OGL -FSAA
  • 1024x768x32:
    • R9700pro (default)
      105,1
    • R9700pro (2xAA)
      103,3
    • GF4 Ti4600 (default)
      97, 5
    • R9700pro (4xAA)
      86,9
    • R9700pro (6xAA)
      64,5
    • GF4 Ti4600 (2xAA)
      58.0
    • GF4 Ti4600 (4xAA)
      33.0
  • 1280x1024x32:
    • R9700pro (default)
      94.4
    • R9700pro (2xAA)
      83.0
  • GF4 Ti4600 (default)
    61.8
  • R9700pro (4xAA)
    56.0
  • R9700pro (6xAA)
    41,6
  • GF4 Ti4600 (2xAA)
    35,6
  • GF4 Ti4600 (4xAA)
    18.4
  • 1600x1200x32:
    • R9700pro (default)
      69.4
    • R9700pro (2xAA)
      55,6
    • GF4 Ti4600 (default)
      42,4
    • R9700pro (4xAA)
      37,6
    • R9700pro(6xAA)
      26,3
    • GF4 Ti4600 (2xAA)
      23,0
    • GF4 Ti4600 (4xAA)
      11.6
  • Voilà, the Radeon still has enough bandwidth in store for 2xFSAA. The 4x and 6x modes break in compared to the 2xFSAA and also compared to many other games much more than it has become the norm.

    The GeForce is just capable of playing things in 1024 with 2xFSAA to render to the screen. The Radeon can literally only laugh about that ...

    Alice OGL -AF
    • 1024x768x32:
      • R9700pro (default)
        105.1
      • R9700pro (16xAF bilinear)
        104.7
      • R9700pro (2xAF trilinear)
        103,6
      • R9700pro (4xAF trilinear)
        102.4
      • R9700pro ( 8xAF trilinear)
        101,3
      • R9700pro (16xAF trilinear)
        100,7
      • GF4 Ti4600 (default)
        97.5
      • GF4 Ti4600 (2xAF trilinear)
        75.7
      • GF4 Ti4600 (4xAF trilinear)
        63.1
      • GF4 Ti4600 (8xAF trilinear)
        57,5
    • 1280x1024x32:
      • R9700pro (default)
        94,4
      • R9700pro (16xAF bilinear)
        90,9
      • R9700pro (2xAF trilinear)
        81,5
      • R9700pro (4xAFtrilinear)
        77,3
      • R9700pro (8xAF trilinear)
        75.7
      • R9700pro (16xAF trilinear)
        75.4
      • GF4 Ti4600 (default)
        61.8
      • GF4 Ti4600 (2xAF trilinear)
        47.7
      • GF4 Ti4600 (4xAF trilinear)
        40,6
      • GF4 Ti4600 (8xAF trilinear)
        36,6
    • 1600x1200x32:
      • R9700pro (16xAF bilinear)
        65.9
      • R9700pro (2xAF trilinear)
        60.1
      • R9700pro (4xAF trilinear)
        57.0
      • R9700pro (8xAF trilinear)
        55,8
      • R9700pro (16xAF trilinear )
        55,4
      • GF4 Ti4600 (2xAF trilinear)
        33,2
      • GF4 Ti4600 (4xAF trilinear)
        28 , 0
      • GF4 Ti4600 (8xAF trilinear)
        26.1

    The Radeon makes it clear again here that there is no lack of fill and texel fetch rate once impressive. In contrast to the GeForce, you can also afford high levels of anisotropic filtering without sacrificing performance.

    On the next page: Conclusion