ATI Radeon HD 4890 vs. NVIDIA GeForce GTX 275
by Anand Lal Shimpi & Derek Wilson on April 2, 2009 12:00 AM EST- Posted in
- GPUs
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.
Facebook
Twitter
RSS
294 Comments
View All Comments
piesquared - Thursday, April 2, 2009 - link
Must be tough trying to write a balanced review when you clearly favour one side of the equation. Seriously, you tow NV's line without hesitation, including soon to be extinct physx, a reviewer relieased card, and unreleased drivers at the time of your review. And here's the kicker; you ignore the OC potential of AMD's new card, which as you know, is one of it's major selling points.Could you possibly bend over any further for NV? Obviously you are perfectly willing to do so. F'n frauds
Chlorus - Friday, April 3, 2009 - link
What?! Did you even read the article? They specifically say they cannot really endorse PhysX or CUDA and note the lack of support in any games. I think you're the one towing a line here.SiliconDoc - Monday, April 6, 2009 - link
The red fanboys have to chime in with insanities so the reviewers can claim they're fair because "both sides complain".Yes, red rooster whiner never read the article, because if he had he would remember the line that neither overclocked well, and that overclocking would come in a future review ( in other words, they were rushed again, or got a chum card and knew it - whatever ).
So, they didn't ignore it , they failed on execution - and delayed it for later, so they say.
Yeah, red rooster boy didn't read.
tamalero - Thursday, April 9, 2009 - link
jesus dude, you have a strong persecution complex right?its like "ohh noes, they're going against my beloved nvidia, I MUST STOP THEM AT ALL COSTS".
I wonder how much nvidia pays you? ( if not, you're sad.. )
SiliconDoc - Thursday, April 23, 2009 - link
That's interesting, not a single counterpoint, just two whining personal attacks.Better luck next time - keep flapping those red rooster wings.
(You don't have any decent couinterpoints to the truth, do you flapper ? )
Sometimes things are so out of hand someone has to say it - I'm still waiting for the logical rebuttals - but you don't have any, neither does anyone else.
aguilpa1 - Thursday, April 2, 2009 - link
All these guys talking about how irrelevant physx and how not so many games use it don't get it. The power of physx is bringing the full strength of those GPU's to bear on everyday apps like CS4 or Badaboom video encoding. I used to think it was kind of gimmicky myself until I bought the "very" inexpensive badaboom encoder and wow, how awesome was that! I forgot all about the games.Rhino2 - Monday, April 13, 2009 - link
You forgot all about gaming because you can encode video faster? I guess we are just 2 different people. I don't think I've ever needed to encode a video for my ipod in 60 seconds or less, but I do play a lot of games.z3R0C00L - Thursday, April 2, 2009 - link
You're talking about CUDA not Physx.Physx is useless as HavokFX will replace it as a standard through OpenCL.
sbuckler - Thursday, April 2, 2009 - link
No physx has the market, HavokFX is currently demoing what physx did 2 years ago.What will happen is the moment HavokFX becomes anything approaching a threat nvidia will port Physx to OpenCL and kill it.
As far as ATI users are concerned the end result is the same - you'll be able to use physics acceleration on your card.
z3R0C00L - Thursday, April 2, 2009 - link
You do realize that Havok Physics are used in more games than Physx right (including all the source engine based games)?And that Diablo 3 makes use of Havok Physics right? Just thought I'd mention that to give you time to change your conclusion.