PHYSX NEWS PHYSX SDK
PROJECTS TABLE
GPU PHYSX
GAMES INFO
PHYSX
ARTICLES
PHYSX WIKI FORUM
РУССКИЙ ENGLISH


:: Back to news index ::

ATI HD 5870 + NV GT 220 PhysX Benchmarks

with 8 comments

Two questions may bother some people, interested in PhysX nowadays  – “Are those hybrid ATI+NV PhysX configurations really working ?” and “How new GeForce GT 220 can perform as dedicated PhysX card ?“. User soothepain from coolaler.com forums has performed a bunch of tests, that can answer both of those questions.

ati_nv

System, used for benchmarks includes Intel Core i7 975 Extreme CPU, 6GB DDR3 RAM, EVGA Classified X58 Motherboard, ATI HD 5870 and Nvidia GeForce GT 220 GPUs running on Windows 7 RC7100 64-bit OS.

Three setups were tested:

Single GT 220 (Both graphics and PhysX processing)

Single HD 5870 (CPU is calculating all PhysX effects in this case)

HD 5870 for graphics + GT 220 for PhysX (using GenL Mod)

Test results:

Nurien Benchmark

Min fps Avg fps Max fps
Single GT 220 16,5 33,1 93,4
Single HD 5870 18,8 42,3 148,5
HD 5870 + GT 220 64,7 101 183,6

Star Tales Benchmark (1280×1024, 4xAA, 8xAF)

Min fps Avg fps Max fps
Single GT 220 11,1 19,3 698,9
Single HD 5870 9,46 34,9 1213,5
HD 5870 + GT 220 38,39 125,7 2851,2

Cryostasis Techdemo (1280×1024, DX10)

Min fps Avg fps Max fps
Single GT 220 9,5 15,1 43,8
Single HD 5870 5,8 15,8 164,6
HD 5870 + GT 220 45,7 75,1 172,9

Batman Arkham Asylum built-in benchmark (1280×1024, PhysX High)

Min fps Avg fps Max fps
Single GT 220 12 23 42
Single HD 5870 13 21 57
HD 5870 + GT 220 41 88 132

As you may see, single GT 220, overwhelmed by simultaneous graphics and physics processing, can’t handle latest GPU PhysX games with appropriate fps (it’s obvious, GT 220 is low-end GPU). In most cases, Core i7 975 CPU is even faster. But moving GT 220 to a dedicated PhysX card boost framerate up to 4-5 times.

Written by Zogrim

October 21st, 2009 at 3:12 pm

Posted in Hybrid PhysX

Tagged with , , ,

8 Responses to 'ATI HD 5870 + NV GT 220 PhysX Benchmarks'

Subscribe to comments with RSS

  1. Since not everyone has a two slotted PCI-e 16x, what about dremeling the GT220 to fit it in a PCI-e 1x slot?
    How would that affect the results?

      

    Reboot

    3 Dec 09 at 3:54 am

  2. Reboot
    Certain tests indicates it won’t affects performance much

      

    Zogrim

    3 Dec 09 at 10:09 am

  3. The performance drawback from Pci-e 16x to 1x is only 4%, it’s ridiculous.

      

    Paul

    6 Jan 10 at 12:44 am

  4. What? why the hell the gt 220 beats the hd 5870?? even if the test are physx only..

      

    Justine

    22 Jan 10 at 1:58 pm

  5. Basically because when the CPU is doing the Phyxs processing is acting like a bottle neck for the ATI GPU.

      

    Pakin

    8 Feb 10 at 11:02 am

  6. i was just wondering does a 5870 + 9600 gt or 9800 gt(for physx) have a bigger improvement than a 5870 + 220 gt?

    I am debating should i buy a 9600 gt or 220 gt for physx

    thanks

      

    jasonl

    21 Feb 10 at 10:33 am

  7. jasonl
    Here are benchmarks with 5870 + GT220/9600GT
    9600 is slight faster.

      

    Zogrim

    21 Feb 10 at 2:05 pm

  8. FPS for 5870 are low because they’re run at 12×10 meaning the 5870 GPU isn’t even getting a work out at all. They run at this low resolution because the GT220 is a very low end GPU and so it cannot handle anything higher. None of the framerates it has produced are even playable.

      

    rUmX

    17 Sep 10 at 3:54 am


Leave a Reply

*
Copyright © 2009-2014. PhysXInfo.com | About PhysXInfo.com project | Privacy Policy
PhysX is trademark of NVIDIA Corporation