CUDA - Oh there’s More

Oh I’m not done. Other than PhysX, NVIDIA is stressing CUDA as another huge feature that no other GPU maker on the world has.

For those who aren’t familiar, CUDA is a programming interface to NVIDIA hardware. Modern day GPUs are quite powerful, easily capable of churning out billions if not a trillion instructions per second when working on the right dataset. The problem is that harnessing such power is a bit difficult. NVIDIA put a lot of effort into developing an easy to use interface to the hardware and eventually it evolved into CUDA.

Now CUDA only works on certain NVIDIA GPUs and certainly won’t talk to Larrabee or anything in the ATI camp. Both Intel and ATI have their own alternatives, but let’s get back to CUDA for now.

The one area that GPU computing has had a tremendous impact already is the HPC market. The applications there lent themselves very well to GPU programming and thus we see incredible CUDA penetration there. What NVIDIA wants however is CUDA in the consumer market, and that’s a little more difficult.

The problem is that you need a compelling application and the first major one we looked at was Elemental’s Badaboom. The initial release of Badaboom fell short of the mark but over time it became a nice tool. While it’s not the encoder of choice for people looking to rip Blu-ray movies, it’s a good, fast way of getting your DVDs and other videos onto your iPod, iPhone or other portable media player. It only works on NVIDIA GPUs and is much faster than doing the same conversion on a CPU if you have a fast enough GPU.

The problem with Badaboom was that, like GPU accelerated PhysX, it only works on NVIDIA hardware and NVIDIA isn’t willing to give away NVIDIA GPUs to everyone in the world - thus we have another catch 22 scenario.

Badaboom is nice. If you have a NVIDIA GPU and you want to get DVD quality content onto your iPod, it works very well. But spending $200 - $300 on a GPU to run a single application just doesn’t seem like something most users would be willing to do. NVIDIA wants the equation to work like this:

Badaboom -> You buy a NVIDIA GPU

But the equation really works like this:

Games (or clever marketing) -> You buy a NVIDIA GPU -> You can also run Badaboom

Now if the majority of applications in the world required NVIDIA GPUs to run, then we’d be dealing in a very different environment, but that’s not reality in this dimension.

Mirror’s Edge: Do we have a winner? The Latest CUDA App: MotionDSP’s vReveal
Comments Locked

294 Comments

View All Comments

  • evilsopure - Thursday, April 2, 2009 - link

    Update: I guess Anand was making his updates while I was making my post, so the "marginal leader at this new price point of $250" line is gone and the Final Words actually now reflect my own personal conclusion above.
  • Anand Lal Shimpi - Thursday, April 2, 2009 - link

    I've updated the conclusion, we agree :)

    -A
  • SiliconDoc - Monday, April 6, 2009 - link

    You agree now that NVidia has moved their driver to the 2650 rez to win, since for months on end, you WHINED about NVidia not winning at the highest rez, even though it took everyting lower.
    So of COURSE, now is the time to claim 2650 doesn't matter much, and suddenly ROOT for RED at lower resolutions.
    It Nvidia screws you out of cards again, I certainly won't be surprised, because you definitely deserve it.
    Thanks anyway for changing Derek's 6 month plus long mindset where only the highest resolution mattered, as he had been ranting and red raving how wonderful they were.
    That is EXACTLY WHY his brain FARTED, and he declared NVidia the top dog - it's how he's been doing it for MONTHS.
    So good job there, you BONEHEAD - you finally caught the bias, just when the red rooster cards FAILED at that resolution.
    Look in the mirror - DUMMY - maybe you can figure it out.
  • 7Enigma - Thursday, April 2, 2009 - link

    Check the article again. Anand edited it and it is now very clear and concise.
  • 7Enigma - Thursday, April 2, 2009 - link

    Bah, internet lag. Ya got there first.... :)
  • sublifer - Thursday, April 2, 2009 - link

    As I predicted elsewhere, they probably should have named this new card the GTX 281. In almost every single benchmark and resolution it beats the 280. In one case it even beat the 285 somehow.
    /Gripe

    That said, Go AMD! I wanna check other sites and see if they benched with the card highly over-clocked. One site got 950 core and 1150 memory easily but they didn't include it on the graphs :(
  • Anand Lal Shimpi - Thursday, April 2, 2009 - link

    Hey guys, I just wanted to chime in with a few fixes:

    1) I believe Derek used the beta Catalyst driver that ATI gave us with the 4890, not the 8.12 hotfix. I updated the table to reflect this.

    2) Power consumption data is now in the article as well, 2nd to last page.

    3) I've also updated the conclusion to better reflect the data. What Derek was trying to say is that the GTX 275 vs. 4890 is more of a wash at 2560 x 1600, which it is. At lower than 2560 x 1600 resolutions, the 4890 is the clear winner, losing only a single test.

    Thank you for all the responses :)

    Take care,
    Anand
  • 7Enigma - Thursday, April 2, 2009 - link

    Thank you Anand for the update and the article changes. I think that will quell most of the comments so far (mine included).

    Could you possibly comment on the temps posted earlier in the comments section? My question is whether there are significant changes with the fan/heatsink between the stock 4870 and the 4890. The idle and load temps of the 4890 are much lower, especially when the higher frequency is taken into consideration.

    Also a request to describe the differences between the 4890 and the 4870 (several comments allude to a respin that would account for the higher clocks, lower temp, different die size).

    Thank you again for all of your hard work (both of you).
  • Warren21 - Thursday, April 2, 2009 - link

    Yeah, I would also second a closer comparison between RV790 and RV770, or at least mention it. It's got new power phases, different VRM (7-phase vs 5-phase respectively), slightly redesigned core (AT did mention this) and features a revised HS/F.
  • VooDooAddict - Thursday, April 2, 2009 - link

    I was very happy to see the PhysX details. I'd started worrying I might be missing out with my 4870. It's clear now that I'm not missing out on PhysX, but might be missing out on some great encoding performance wiht CUDA.

    I'll be looking forward to your SLI / Crossfire followup. Hoping to see some details about peformance with ultra high Anti-Aliasing that's only available with SLI/Crossfire. I used to run Two 4850s and enjoyed the high-end Edge Antialiasing. Unfortunetly the pair of 4850's were a too much heat in a tiny shuttle case so I had to switch out to a 4870.

    Your review reinforced something that I'd been feeling about the 4800s. There isn't much to complain about when running 1920x1200 or lower with modest AA. They seem well positioned for most gamers out there. For those out there with 30" screens (or lusting after them, like myself)... while the GTX280/285 has a solid edge, one really needs SLI/Crossfire to drive 30" well.


Log in

Don't have an account? Sign up now