The Test

For the launch of the Radeon HD 6900 series, AMD supplied us with a 6900-enabled version of the Catalyst 10.11 driver, version 8.79.6.2RC2. This is older than the Catalyst 10.12 preview released Monday, which was 8.8xx.

Otherwise our test setup has not significantly changed from the GTX 570 launch last week. For our existing AMD cards we’re still using the Catalyst 10.10e, while for NVIDIA it’s a mix of 262.99 and 263.09. Note that we do not have a 2nd GTX 570 yet for GTX 570 SLI comparisons; given the equality between the 570 and 480, the GTX 480 in SLI is a reasonable stand-in.

Finally, all tests were done with the default driver settings unless otherwise noted.

CPU: Intel Core i7-920 @ 3.33GHz
Motherboard: Asus Rampage II Extreme
Chipset Drivers: Intel 9.1.1.1015 (Intel)
Hard Disk: OCZ Summit (120GB)
Memory: Patriot Viper DDR3-1333 3 x 2GB (7-7-7-20)
Video Cards: AMD Radeon HD 6970
AMD Radeon HD 6950
AMD Radeon HD 6870
AMD Radeon HD 6850
AMD Radeon HD 5970
AMD Radeon HD 5870
AMD Radeon HD 5850
AMD Radeon HD 5770
AMD Radeon HD 4870
NVIDIA GeForce GTX 580
NVIDIA GeForce GTX 570
NVIDIA GeForce GTX 480
NVIDIA GeForce GTX 470
NVIDIA GeForce GTX 460 1GB
NVIDIA GeForce GTX 460 768MB
NVIDIA GeForce GTS 450
NVIDIA GeForce GTX 285
NVIDIA GeForce GTX 260 Core 216
Video Drivers: NVIDIA ForceWare 262.99
NVIDIA ForceWare 263.09
AMD Catalyst 10.10e
AMD Catalyst 8.79.6.2RC2
OS: Windows 7 Ultimate 64-bit
Meet the 6970 & 6950 Crysis: Warhead
Comments Locked

168 Comments

View All Comments

  • Ryan Smith - Wednesday, December 15, 2010 - link

    Exactly the same as on Cypress.

    L2: 128KB per ROP block (so 512KB)
    L1: 8KB per SIMD
    LDS: 32KB per SIMD
    GDS: 64KB

    http://images.anandtech.com/doci/4061/MidLevelView...

    I don't have the register file size readily available.
  • DanNeely - Wednesday, December 15, 2010 - link

    How likely is the decrease from 2 to 1 operations per clock likely to affect real world applications?
  • yeraldin37 - Wednesday, December 15, 2010 - link

    My current cards are running at 870Mhz(GPU) and 1100Mhz(clock), faster than stock 5870, those benchmarks for new 6970 are really disappointing, I was seriously expecting to get a single 6970 for Christmas to replace my 5850OC CF cards and make room for additional cards or even have a free pcie to plug my gtx460 for physx capability. I was going to be happy to get at least 80% of my current 5850CF setup from new 6970. what a joke! I will not make any move and wait for upcoming next generation 28nm amd GPU's. We have to be fair and mention all great efforts from AMD team to bring new technology to newest radeon cards, however not enough performance for die hard gamers. If gtx 580 were 20% cheaper I might consider to buy one, I personally never ever pay more than $400 for one(1) video card.
  • Nfarce - Wednesday, December 15, 2010 - link

    Reading Tom's Hardware they essentially slam AMD's marketing these cards as a 570-580 beater. Guru3D is also less than friendly. Interstingly, *both* sites have benches showing the 570 an d580 beating the 6950 and 6970 commandingly. What's up with that exactly?
  • fausto412 - Wednesday, December 15, 2010 - link

    it's called AMD didn't deliver on the hype...they deserve to get slammed.
  • medi01 - Wednesday, December 15, 2010 - link

    AMD delivers cards with better performance/price ratio that also consume less power. How come there is a reason to "slam", eh?
  • zst3250 - Friday, December 31, 2010 - link

    Off yourself cretin, prefearbly by getting your cranium kicked in.
  • Mr Perfect - Thursday, December 16, 2010 - link

    Wait, is Tom's reputable again? Haven't read that site since the Athlon XP was new....
  • AnnonymousCoward - Wednesday, December 15, 2010 - link

    As a 30" owner and gamer, I would never run at 2560x1600 with AA enabled if that causes <60fps. I'd disable AA. Who wouldn't value framerate over AA? So when the fps is <60, please compare cards at 2560x1600 without AA, so that I'm able to apply the results to a purchase decision.
  • SimpJee - Wednesday, December 15, 2010 - link

    Greetings, also a 30'' gamer. If you see the FPS above 30 with AA enabled, you can assume it will be (much) higher without it enabled so what's the point in actually having the author bench it without AA? Plus, anything above 30 FPS is just icing on the cake as far as I'm concerned.

Log in

Don't have an account? Sign up now