Hellbinder says full trilinear would cost 50% preformance?

[Tim Murray]

Re: Hellbinder says full trilinear would cost 50% preformanc

Hellbinder is the one in the know for ATI he always has the scoop

Haha. Hahaha. HAHAHAHAHAHA!

Hellbinder knows very little. His "technical details" are often nothing more than FUD. If HB says something, believe the opposite.

 

[SiliconAbyss]

Hellbinder knows very little. His "technical details" are often nothing more than FUD. If HB says something, believe the opposite.

Then educate us if Hellbinder knows so little.

How much of a performance hit will ATi take with adaptive AF disabled. Inform us all with your superior knowledge.

 

[jimmyjames123]

How much of a performance hit will ATi take with adaptive AF disabled. Inform us all with your superior knowledge.

I don't think there is any proper way to nail down a number, it will depend totally on the situation and what game is tested.

 

[Pete]

How much of a performance hit will ATi take with adaptive AF disabled. Inform us all with your superior knowledge.

The issue at hand is adaptive trilinear. Dave quoted as little as a 2% hit, whereas computerbase showed a larger hit with--but with coloredmips, which may make for an invalid comparison (though the 9800XT score didn't change, whereas the X800P score dropped).

 

[CarstenS]

Might have missed it, but did Dave mention where and how his 2% were obtained?

 

[Drak]

How much of a performance hit will ATi take with adaptive AF disabled. Inform us all with your superior knowledge.

The issue at hand is adaptive trilinear. Dave quoted as little as a 2% hit, whereas computerbase showed a larger hit with--but with coloredmips, which may make for an invalid comparison (though the 9800XT score didn't change, whereas the X800P score dropped).

Which game did computerbase use?

 

[rwolf]

Re: Hellbinder says full trilinear would cost 50% preformanc

Hellbinder is the one in the know for ATI he always has the scoop

Haha. Hahaha. HAHAHAHAHAHA!

Hellbinder knows very little. His "technical details" are often nothing more than FUD. If HB says something, believe the opposite.

I think hellbinder was right on the money with the X800 Pro. It was MUFU and others that where out to lunch.

 

[KimB]

Then educate us if Hellbinder knows so little.

How much of a performance hit will ATi take with adaptive AF disabled. Inform us all with your superior knowledge.

First of all, all anisotropic is adaptive.

Anyway, it really depends on the scenario, but all you have to do is look at benchmarks. The performance hit typically seems to be ~20% for disabling the "trilinear optimizations."

 

[CarstenS]

Which game did computerbase use?

We used UT2003 as an illustration, because it is widely used as a benchmark. We did, of course, confirm a perfomance drop in similar orders of magnitude on other games as well (Delta Force BHD, Call of Duty etc.).

 

[Nick Spolec]

Mayeb HB meant there is a 50% hit when doing full trilinear at 16x AF?

 

[MuFu]

Re: Hellbinder says full trilinear would cost 50% preformanc

Hellbinder is the one in the know for ATI he always has the scoop

Haha. Hahaha. HAHAHAHAHAHA!

Hellbinder knows very little. His "technical details" are often nothing more than FUD. If HB says something, believe the opposite.

I think hellbinder was right on the money with the X800 Pro. It was MUFU and others that where out to lunch.

Yeah but sometimes I say stuff that's deliberately wrong to keep everybody (Edit - especially nVidia) on their toes and I never let out the whole truth until after the release. You see... the R420; sometimes it's 8 thingies, sometimes 12 thingies, sometimes 16 thingies; it depends which level of forum mentality you subscribe to and what you think a "thingy" is. Me? I don't really know... but I have to say something instead of "I don't know", don't I? That'd be insane.

L.M.A.O.

 

[PaulS]

 

[ChrisRay]

Re: Hellbinder says full trilinear would cost 50% preformanc

Yeah but sometimes I say stuff that's deliberately wrong to keep everybody (Edit - especially nVidia) on their toes and I never let out the whole truth until after the release. You see... the R420; sometimes it's 8 thingies, sometimes 12 thingies, sometimes 16 thingies; it depends which level of forum mentality you subscribe to and what you think a "thingy" is. Me? I don't really know... but I have to say something instead of "I don't know", don't I? That'd be insane.

L.M.A.O.

So in other words, We cant take you seriously all the time either. :?

 

[MrBond]

Re: Hellbinder says full trilinear would cost 50% preformanc

Hellbinder is the one in the know for ATI he always has the scoop and here is what he had to say.

Originally posted by Hellbinder
Scene Complexity per Frame is growing at an astronomical rate,, especially in the comming year. Cards Simply will not have the ability to do Full Trillinear on an entire Frame without at least a 50% hit in performance. Thats just the bottom line.

To play devil's advocate, it sounds like he's talking about games in the future (at least, that's what the first sentence of that paragraph suggests). Doesn't mean he can't be offbase about the future games either though 50% is a rather large number...

 

[KimB]

Re: Hellbinder says full trilinear would cost 50% preformanc

To play devil's advocate, it sounds like he's talking about games in the future (at least, that's what the first sentence of that paragraph suggests). Doesn't mean he can't be offbase about the future games either though 50% is a rather large number...

Perhaps, but he just has no idea what causes the performance hit of trilinear filtering. In the future, as games start to have more pixel shader instructions per texture call, hardware should have an easier time increasing trilinear performance without resorting to questionable optimizations.

I don't believe there is much of any correlation between complex scenes and high degrees of anisotropy, either. I would tend to think that simpler games would be more likely to use higher levels of anisotropy (i.e. flat floor/walls stretching far into the distance, as seen in Serious Sam).

 

[bloodbob]

Re: Hellbinder says full trilinear would cost 50% preformanc

Well I guess this is probably why ATI won't give us a full trilinear option in the control panel.

Figures I'm getting are more in the region of 2%! (although I suspect that not wholly accurate). However, the higer the level of AF applied, the more you are using samples from just the first mip level in the first place, so the comparative reduction in performance is reduced with AF.

That just prove Hellbinder wrong.

I'm sorry to say it this whole thread was to prove hellbinder wrong he is currently running all over R3d spread this sort of disinformation and such other things as "Trilinear isn't defined anywhere like bilinear" which is complete fud. Now if this fud stayed on R3D I wouldn't mind but I have to keep repeating myself over and over that trilinear is well defined. So new people please take everything anyone says with a grain of salt including what I say.

The preformance of Trilinear over bilinear can cause a 50% preformance hit if and only if the framebuffer << textures but frame buffers are from neglible.

That means that the Primary Texture is pushed so far back into the scene before the first mip-map is even generated that you almost dont need to use it. 16x AF is a whole different ball game.

Yeah thats so wrong just open up a AF tester folks and see if he is correct.

And thats enough childish behavior from myself lets find something interesting to talk about see in another thread.

 

[Tim Murray]

I'm sorry, when someone mentions Hellbinder, I think back to when he mentioned that "R360 has the best feature ever OMGLOLZ!!!1111one" (referring to Overdrive, if you couldn't figure it out). I can't take him seriously.

 

[bloodbob]

I'm sorry, when someone mentions Hellbinder, I think back to when he mentioned that "R360 has the best feature ever OMGLOLZ!!!1111one" (referring to Overdrive, if you couldn't figure it out). I can't take him seriously.

In the end we all found out the R360 chip didn't even have the feature it was an external sensor.

 

[Tim Murray]

And hence, Hellbinder is a rabid fanboy who hears a few very vague rumors, spices them up with his own insane ideas without mentioning that, and then capitalizes random words.

 

[Hellbinder]

No,,, I dont think so,,,

I Think if you look back at hardware that did Actualy Full trilinear with no performance hacks at all it was nearly a 50% hit. Furthermore as i mentioned as scene complexity increases Full trilinear will get more and more expensive.

So laugh if you want. I dont mind. 8)