Benchmarks Of AMD's Newest Gallium3D Driver

[pingufunkybeat]

Now this got me interested.

You really don't expect significant performance increase for the Gallium-based Radeon drivers?

Or do you think that this kind of benchmarking is not good for measuring the increase?

[elanthis]

show me every single paper you read about that tropic it can not be so much papers

That's an easy game to play. I doubt you can actually even comprehend any papers given the general gibberish you write. Do you have even a single reference that shows that anyone is seriously implementing or proposing a broken ray tracer that generates noise and erroneous images as the future of graphics? I don't need to see "every single paper," you just need to show a single solitary one from a reputable source. I'd really like to see it, and I'd really like to show it to the few dozen top-tier graphics experts I work with. I bet they'd like to know that their jobs just got a lot easier because the future means they can write broken lazy graphics engines that generate incomplete and noisy images. Save them a lot of time if they can just half-ass everything from now on.

Just to humor you though, here's the just first three meaningful articles/papers that come up in a Google search, all of which quite explicitly mention complete frames, frame rates, and explicit desire to match the visual quality of contemporary ray tracers (that is, no noise or garbage):

http://gpurt.sourceforge.net/DA07_0405_Ray_Tracing_on_GPU-1.0.5.pdf

http://www.keldysh.ru/pages/cgraph/articles/dep20/publ2010/GPU-RayTracing.pdf

http://blogs.intel.com/research/2007/10/real_time_raytracing_the_end_o.php

Funnily enough, searching for realtime ray tracing without frames turns up this thread on Phoronix before it turns up a single paper. And still doesn't show any papers three pages into the results. Conspiracy? Government suppression of information? Alien abduction of ray tracing engineers? Stupid forum posters making shit up? You decide.

If you don't have a single link or reference, I'm done -- beaten my head into a wall enough with this "conversation." I think I've at least managed to make sure nobody else chancing into this thread will inadvertently believe anything coming out of you and start parroting it, so at least your nonsense won't spread.

[d2kx]

elanthis,

seriously you should know better for someone who joined Phoronix in 2007. Never. Discuss. Anything. With Qaridarium, unless you are ill and feel bored.

[elanthis]

elanthis,

seriously you should know better for someone who joined Phoronix in 2007. Never. Discuss. Anything. With Qaridarium, unless you are ill and feel bored.

I know. Trust me, I know. I think I might actually be mentally ill, because I logically know better than to argue _anything_ on the Internet for any reason but yet I keep doing it. I should maybe find a 12-step program or something.

[glisse]

Now this got me interested.

You really don't expect significant performance increase for the Gallium-based Radeon drivers?

Or do you think that this kind of benchmarking is not good for measuring the increase?

Just that with current design for r600g i don't think we can't match 50% of fglrx speed on things like nexuiz or newer game/engine. So you won't see any major boost until a complete rewrite (shader compiler excluded). That's my current feeling, i could be wrong.

[pingufunkybeat]

Is the r600g design considerably different from r300g (of course, the hardware architectures are very different)?

I believe that r300g passed the 50% mark.

Also, do you think that a complete rewrite is feasible/planned? Being stuck at <50% of the maximum forever would be a bit disappointing.

[HokTar]

Just that with current design for r600g i don't think we can't match 50% of fglrx speed on things like nexuiz or newer game/engine. So you won't see any major boost until a complete rewrite (shader compiler excluded). That's my current feeling, i could be wrong.

It's not even finished yet and it requires a rewrite already?
That is more than disappointing...

[BlackStar]

It's not even finished yet and it requires a rewrite already?
That is more than disappointing...

That's not disappointing, that's expected and encouraging. There's only one kind of software that doesn't get constantly rewritten: dead software.

As the drivers gain more features (and hence more real-world testing), bottlenecks will appear and/or shift around. And as the developers gain more experience, existing architectural deficiencies will be discovered and dealt with.

(Note that a rewrite doesn't mean "throw away everything and start from scratch". It means things like, "hey, if we move state validation from part X to part Y, we can avoid re-validations under circumstances Z and W and increase batch submission performance by up to 15%.")

[HokTar]

That's not disappointing, that's expected and encouraging. There's only one kind of software that doesn't get constantly rewritten: dead software.

As the drivers gain more features (and hence more real-world testing), bottlenecks will appear and/or shift around. And as the developers gain more experience, existing architectural deficiencies will be discovered and dealt with.

(Note that a rewrite doesn't mean "throw away everything and start from scratch". It means things like, "hey, if we move state validation from part X to part Y, we can avoid re-validations under circumstances Z and W and increase batch submission performance by up to 15%.")

Well, glisse wrote: "until a complete rewrite (shader compiler excluded)".
That pretty much sounds like we have to restart from (almost) scratch. Obviously, I hope what you said is correct but it does not seem so.

[bridgman]

I suspect glisse is talking about more than just the actual r600g driver... usually you find bottlenecks scattered all through the stack.

I don't think he is saying "just rewrite the r600g part and everything will be fine"... remember that the r600g code is only 1-2% of the 3D driver stack, and AFAIK this is the first time the open source stack has really been put to work on high performance graphics hardware.

Things that were "nicely tuned" in the r200 days can easily become major bottlenecks on newer graphics hardware simply because the newer GPUs are so much faster.