X1800/7800gt AA comparisons

Status
Not open for further replies.
geo said:
The fabled OGL rewrite snuck in and marketed as hardware improvements? :p

Okay, I've worked off my nasty suspicious side for the moment and will go back to just hoping this is as yummy as the original reports suggest until/unless further evidence goes another direction.
Click to expand...

Say, wasn't Humus hired to work on the OGL stuff at ATI? :devilish:

Dave Baumann said:
As far as I was aware it tweaks some registry parameters that alters the configuration of the memory controller.
Click to expand...

That's a pretty impressive improvement for a memory controller tweak... Just to eliminate the obvious, color compression is currently active on ATI cards in OpenGL right?

Nite_Hawk
 
Just a couple of comments from Raja:

I saw a few posts...Note that running the tool on R4xx might bring the performance down a bit - since this tool is blindly forcing the driver down the path that's optimal memory-wise for 5xx. The driver deals with it correctly

Also, note that this is still not yet the optimal path for 5xx. This just better than what we shipped with.


Btw - This should improve scores for all opengl AA games..Not just Doom3.

- Raja
Click to expand...
 
Quick Doom3 numbers from the XT only. Yay for coffee breaks.

bench-doom3.png
 
  • Like
Reactions: Geo
What about 4x AA and 16X AF?

And is that with HQ filtering? or performance filtering?

Is it reproducable in other OGL games? or Doom-III engine games?
 
Hellbinder said:
What about 4x AA and 16X AF?

And is that with HQ filtering? or performance filtering?

Is it reproducable in other OGL games? or Doom-III engine games?
Click to expand...

Default Quality filtering, 16xAF. 6xAA and 2xAA show the same thing in D3 and yes, it's the same kind of stuff in Riddick too.

No IQ differences that I can see (difference output from same spot screenies). Not got the time to do much else today other than post Riddick numbers and some GTX comparo numbers later on. Maybe someone else will pick up the tool and run with it more than I can.

Snowed under with motherboards right now, joy of joys.
 
Such updates and improvements definately make the X1K family more desirable. Great job ATI! We may be seeing justification for all the new work ATI put into the memory controller.
 
Rys said:
Maybe someone else will pick up the tool and run with it more than I can..
Click to expand...


Rys,
I will help you. Send me you 1800xt and I can do the rest of the data gathering... :) :) :)

Thanks for getting some numbers up for us!
 
ATI laying the smack down across the board in OGL would be one of those "Get the umbrellas out, boys, the frogs will be coming from the sky any moment" kind of transitions.

Edit: Given their well-known "D3D first" strategy, I wonder if we'd be justified in thinking that on the D3D side this is already there, in at least as robust a way as this add for OGL? (still leaving room for the "room to improve", of course).
 
Last edited by a moderator:
thatdude90210 said:
Try it on an X1800XL... just wondering if the performance increase come from optimizing the use of 512mb in the XT.
Click to expand...

Love to see it tested on XL, RV530, and RV515. On XL tho, the available bandwidth is a pretty big difference too, so I don't know you can come to definite conclusions about whether they might be doing some fun storage tricks with that extra 256mb on XT that somehow helps performance on AA beyond the shipping drivers (I'm not even sure what that would look like actually --what, they couldn't address the other 256mb in OGL? ;) ) that XT was originally reviewed with. Tho obviously if XL shows the same increases it would indicate they aren't.

I'm feeling more comfortable with the ATI email upstream, which was a pretty flat statement on the matter, but I'm sure we'll be dissecting this for awhile.
 
This change is for the X1K family. The X1Ks have a new programmable memory controller and gfx subsystem mapping. A simple set of new memory controller programs gave a huge boost to memory BW limited cases, such as AA (need to test AF). We measured 36% performance improvements on D3 @ 4xAA/high res. This has nothing to do with the rendering (which is identical to before). X800's also have partially programmable MC's, so we might be able to do better there too (basically, discovering such a large jump, we want to revisit our previous decisions).

But It's still not optimal. The work space we have to optimize memory settings and gfx mappings is immense. It will take us some time to really get the performance closer to maximum. But that's why we designed a new programmable MC. We are only at the beginning of the tuning for the X1K's.

As well, we are determined to focus a lot more energy into OGL tuning in the coming year; shame on us for not doing it earlier.
 
sireric said:
As well, we are determined to focus a lot more energy into OGL tuning in the coming year; shame on us for not doing it earlier.
Click to expand...

Well, hell of a nice way to announce the change in policy, at least! There are few more sincerely appreciated apologies than "here, have another 35%". :LOL:
 
Last edited by a moderator:
Does the boost in D3 relate to trade-offs in texturing memory accesses versus ROP/4xAA memory accesses? Or is the boost solely in terms of the effectiveness of ROP/4xAA accesses?

What about 6xAA?

Jawed
 
sireric said:
This change is for the X1K family. The X1Ks have a new programmable memory controller and gfx subsystem mapping. A simple set of new memory controller programs gave a huge boost to memory BW limited cases, such as AA (need to test AF). We measured 36% performance improvements on D3 @ 4xAA/high res. This has nothing to do with the rendering (which is identical to before). X800's also have partially programmable MC's, so we might be able to do better there too (basically, discovering such a large jump, we want to revisit our previous decisions).

But It's still not optimal. The work space we have to optimize memory settings and gfx mappings is immense. It will take us some time to really get the performance closer to maximum. But that's why we designed a new programmable MC. We are only at the beginning of the tuning for the X1K's.

As well, we are determined to focus a lot more energy into OGL tuning in the coming year; shame on us for not doing it earlier.
Click to expand...

That's great, but you should stop making me jealous, I got my 7800gtx for a good cause! :LOL:

In whatever capacity you can answer, how do your mappings differ compared to what you did previously? ~36% improvements are dramatic, and if you are expecting more improvements that is remarkable. I'm not a memory guy really, but are these mostly dealing with latency or throughput improvements? Better data packing? re-ordering? compression? Caching? Inquiring minds want to know! :)

Oh, any chance for improvments in D3d as well?

Nite_Hawk
 
Jawed said:
Does the boost in D3 relate to trade-offs in texturing memory accesses versus ROP/4xAA memory accesses? Or is the boost solely in terms of the effectiveness of ROP/4xAA accesses?

What about 6xAA?

Jawed
Click to expand...

It's a mixture of Z and Blend. Not sure which one gained more. I haven't seen 6xAA tested (or can't remember), but it's probably better too. I'm hoping that within a few weeks, we can tune most of this to get much better in all AA & AF modes. Can't promise any performance deltas, but I think it's fair to say that there's more in there. Given the immense space of possibilities, tuning of the X1k products will take some time. We are just at the beginning...
 
Status
Not open for further replies.

Similar threads

B
Kinect + wiimote... move... something?
Replies
2
Views
2K
orangpelupa
orangpelupa
R
S3 Chrome 20 AA Investigation - curiousity
2
Replies
24
Views
5K
Robbitop
R
P
Mind helping me interpret some #s?
Replies
18
Views
3K
Ailuros
Ailuros
K
Questions regarding target platform/development path of the PC game
Replies
5
Views
2K
Ken2012
K
S
X1800 XT makes the case...
2
Replies
30
Views
6K
rwolf
R
Back
Top