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

  • 7Enigma - Thursday, April 2, 2009 - link

    Deja vu again, and again, and again. I've posted in no less than 3 other articles how bad some of the conclusions have been. There is NO possible way you could conclude the 275 is the better card at anything other than the 30" display resolution. Not only that, but it appears with the latest Nvidia drivers they are making things worse.

    Honestly, does anyone else see the parallel between the original OCZ SSD firmware and these new Nvidia drivers? Seems like they were willing to sacrifice 99% of their customers for the 1% that have 30" displays (which probably wouldn't even be looking at the $250 price point). Nvidia, take a note from OCZ's situation; lower performance at 30" to give better performance at 22-24" resolutions would do you much better in the $250 price segment. You shot yourselves in the foot on this one...
  • Gary Key - Thursday, April 2, 2009 - link

    The conclusion has been clarified to reflect the resolution results. It falls right into line with your thoughts and others as well as our original thoughts that did not make it through the edits correctly.
  • 7Enigma - Thursday, April 2, 2009 - link

    Yup, I responded to Anand's post with a thank you. We readers just like to argue, and when something doesn't make sense, we're quick to go on the attack. But also quick to understand and appreciate a correction.
  • duploxxx - Thursday, April 2, 2009 - link

    Just some thoughts:

    There is only 1 single benchmark out of 7 where the 275 has better frame rates for 1680 and 1920 resolution against the 4890 and yet your final words are that you favor the 275???? Only in 2560 the 275 is clearly the better choice. Are you already in the year 2012 where 2560 might be the standard resolution of the sales, it is only very recent that the 1680 became standard and even then this resolution is high for global OEM market sales. Your 2560 is not even few % of the market.

    I think you have to clarify your final words a bit more with your choice.... Perhaps if we see power consumption, fan noice etc that would be added value to the choice, but for now, TWIMTBP is really not enough push to prefer the card, I am sure the red team will improve there drivers as usual also.

    anything else i missed in your review that could counter my thoughts?
  • SiliconDoc - Monday, April 6, 2009 - link

    Derek has been caught in the 2560 wins it all no matter what with the months on end of ati taking that cake since the 4870 releasse. No lower resolutions mattered for squat since the ati lost there - so you'll have to excuse his months long brainwashing.
    Thankfully anand checked in and smacked it out of his review just in time for the red fanboy to start enjoying lower resolution wins while nvidia takes the high resolution crown, which is- well.. not a win here anymore.
    Congratulations, red roosters.
  • duploxxx - Thursday, April 2, 2009 - link

    just as addon, I also checked some other reviews (yes i always read anandtech first as main source of info) and i saw that it is cooler then a 4870 and actually consumes 10% less then a 4870 so this can't be the reason either while the 275 stays at the same 280 power consumption. Also OC parts are already shown GPU above 1000....
  • cyriene - Thursday, April 2, 2009 - link

    I would have liked to see some information on heat output and the temperatures of the cards while gaming.
    Otherwise, nice article.
  • 7Enigma - Thursday, April 2, 2009 - link

    This is an extreme omission. The fact that the 4890 is essentially an overclocked 4870 means with virtually nothing changed you HAVE to show the temps. I still stick by my earlier comment that the Vapo-chill model of the Sapphire 4870 is possibly a better card since it's temps are significantly lower than the stock 4870, while already being overclocked. I could easily imagine that for $50-60 less you could have the performance of the 4890 at cooler temps (by OC'ing the vapochill further).

    Comon guys, you have to give thought to this!
  • SiliconDoc - Monday, April 6, 2009 - link

    Umm, they - you know the AT bosses, don't like the implications of that. So many months, even years, spent on screeching like women about nvidia rebranding has them in a very difficult position.
    Besides, they have to keep the illusion of superior red power useage, so only after demand will they put up the power chart.
    They tried to get away with not, but they couldn't do it.
  • initialised - Thursday, April 2, 2009 - link

    GPU-z lists the R790 as having a surface area of 282mm2 while the R770 has 256mm2 but both are listed as having the same transistor count.

Log in

Don't have an account? Sign up now