Tony Tamasi Interview

[Ardrid]

Hey guys, TR's got an interview up with Tony Tamasi and it seems that the 6800 Ultra has gamma-corrected AA or at the very least "gamma adjusted"

http://www.techreport.com/etc/2004q2/tamasi/index.x?pg=1

 

[BRiT]

Interesting, if the 6800 truely has gamma-adjusted/corrected AA, the screenshots certainly don't show it.

 

[Geeforcer]

Interesting, thanks for the link.

BTW:

TR: Are the NV40 pixel shaders derived from NV30-series shaders, or are they a clean-sheet design?

Tamasi: It's a clean-sheet design. About the only thing they have in common is you could draw a block diagram and some of the blocks might look similar, but the code is all new.

This, if true, would yet again underscore what a colossal blunder NV3x PS design truly was.

 

[AlphaWolf]

Interesting, if the 6800 truely has gamma-adjusted/corrected AA, the screenshots certainly don't show it.

Obviously there is something not right either with what Tamasi is saying or with Nvidia's implementation of it.

I was also surprised to see that the non ultra is shipping with ddr1. Was he implying that it won't be available until July?

 

[DemoCoder]

http://www.beyond3d.com/forum/viewtopic.php?p=253502&highlight=#253502

It's not implemented yet, but it can be, quite easily actually on the NV40.

 

[Ardrid]

Yeah, that's what I was thinking. It's simply not enabled yet, just like the alternate 8X mode isn't enabled. As far as the July 4th date, I took it as meaning that their entire line up would be available by then. Not sure if that includes just the non-Ultra and Ultra or some extra stuff, like something to fill that $399 price point. Since he made a point of saying the "full line of the 6800 series", I'm thinking he means the 6800 and 6800U.

 

[AlphaWolf]

http://www.beyond3d.com/forum/viewtopic.php?p=253502&highlight=#253502

It's not implemented yet, but it can be, quite easily actually on the NV40.

What ATI does is do a gamma adjustment to gamma 2.2, which can be correct depending on your display, and that's essentially what we do, as well. Gamma correction would typically would mean you could do an adjustment to any gamma, and that would require a shader pass.

Odd he didnt mention that? It sounds like he is saying its being done now to me.

 

[noko]

Yes very interesting, especially that the NV40 is a complete new design! Didn't take Nvidia too long to make a good card, ATI really woke up a napping giant is the feeling I got. Now is Nvidia going to up the frequency some on the 6800U, if so I think they will win this round if not then their extra features will get trouched upon by sheer performance from the ATI camp.

 

[Geeforcer]

TR: Inside of the pixel pipeline, you've got two of the FP32 pixel shaders in each pixel pipe. Can both of them do parallel vector operations per clock?

Tamasi: Yep. The way to think about it is that you can dual (or more) issue instructions per shader unit, and then you can co-issue between them as well, so, in fact, you can have four, or in some cases more than four, instructions being issued on a single pixel pipeline—two in shader unit one and two in shader unit two—two independent instructions in shader unit one and another two independent instructions in shader unit two. We also have mini-ALUs in each of those shader units, as well, which also can have instructions issued to them. We gave a shader example that actually had up to seven instructions being executed in parallel in one pass.

So, he saying that each NV4x pipeline can work on 4 vector ops per clock, and each of the 2 PS Units has a mini-ALU. Which brings the question, since 12 pipeline R420 can outperform NV40 by up to 100% in shader-intensive cases, would that indicate that each R420 pipeline has 3 PS Units?

 

[radar1200gs]

Interesting, if the 6800 truely has gamma-adjusted/corrected AA, the screenshots certainly don't show it.

Early drivers.

 

[Ardrid]

Which brings the question, since 12 pipeline R420 can outperform NV40 by up to 100% in shader-intensive cases, would that indicate that each R420 pipeline has 3 PS Units?

Since when?

 

[KimB]

Hey guys, TR's got an interview up with Tony Tamasi and it seems that the 6800 Ultra has gamma-corrected AA or at the very least "gamma adjusted"

http://www.techreport.com/etc/2004q2/tamasi/index.x?pg=1

Notice that it did state that a shader pass would be required. Therefore don't expect the ability to force gamma correction in the driver, and if it is forceable, expect some performance hit.

At least it would be configurable, though.

 

[FUDie]

http://www.beyond3d.com/forum/viewtopic.php?p=253502&highlight=#253502
It's not implemented yet, but it can be, quite easily actually on the NV40.

NVIDIA also claimed gamma corrected AA for the NV30 and we all know how that worked out...

-FUDie

 

[Althornin]

Interesting, if the 6800 truely has gamma-adjusted/corrected AA, the screenshots certainly don't show it.

Early drivers.

huh.
you crucify ATI for problems in early drivers, where are your harsh words for nVidia?

 

[Geeforcer]

Since when?

MuFu[/url]]
Still much faster than nV when running full precision shaders in the vast majority of cases; sometimes by ~100% in synthetic benchmarks (and that's just the X800 Pro, heh). How's that?

Notice that it did state that a shader pass would be required. Therefore don't expect the ability to force gamma correction in the driver, and if it is forceable, expect some performance hit.

At least it would be configurable, though.

That's not the way I am reading this at all:

Tamasi: It does, and I want to be really specific about this, because there's a lot of confusion about it. There's a great deal of difference between gamma correction and gamma adjustment. What ATI does is do a gamma adjustment to gamma 2.2, which can be correct depending on your display, and that's essentially what we do, as well. Gamma correction would typically would mean you could do an adjustment to any gamma, and that would require a shader pass.

To me, he is saying that :
A) What ATi does should be called Gamma Adjustment, not Gamma Correction because it adjusts to a pre-set user-unchagable value.
B) NV40 can do it as well.
C) "Gamma Correction" would allow adjustmant to *any* value (not just the pre-set 2.2) but would requite a shager pass.

 

[Geeforcer]

Interesting, if the 6800 truely has gamma-adjusted/corrected AA, the screenshots certainly don't show it.

Early drivers.

huh.
you crucify ATI for problems in early drivers, where are your harsh words for nVidia?

Why would there be any harsh worlds regarding such problems in NV40 drivers when neither the drivers nor the hardware is actually available? I don't think anyone is bothered by any flaws in the early drivers for the card they don't have. If the drivers included with shipping cards have said problems, that the parallel would actually hold water.

 

[DemoCoder]

Hey guys, TR's got an interview up with Tony Tamasi and it seems that the 6800 Ultra has gamma-corrected AA or at the very least "gamma adjusted"

http://www.techreport.com/etc/2004q2/tamasi/index.x?pg=1

Notice that it did state that a shader pass would be required. Therefore don't expect the ability to force gamma correction in the driver, and if it is forceable, expect some performance hit.

At least it would be configurable, though.

That's a pass on a screensized quad, and the performance hit should be negligable (back in the old days, chips would do another pass in order to do the final downsample. Minor fillrate usage, mostly a bandwidth saver) I'm not sure the NV40 requires an extra pass tho.

 

[radar1200gs]

Interesting, if the 6800 truely has gamma-adjusted/corrected AA, the screenshots certainly don't show it.

Early drivers.

huh.
you crucify ATI for problems in early drivers, where are your harsh words for nVidia?

We will have to see what the drivers supplied to consumers with the card are capable of. I'm already concerned about the lack of an anisotropic quality selection mechanism in the current drivers (and have stated my concerns twice in this forum previously if you care to open your bigotted eyes and actually look), that is something that being worked on also. Hopefully it will be an item of its own (like the trilinear option), not just part of the quality slider.

EDIT: The lack of gamma correction in nVidia's early drivers won't cause any program to fail to run, which is more than can be said of R300 and NOLF2.

 

[Ailuros]

The lack of gamma correction in nVidia's early drivers won't cause any program to fail to run, which is more than can be said of R300 and NOLF2.

I can live w/o gamma correction for the record and haven't seen anything that I can't so far excuse in previews when it comes to NV40. The results were fine for me in such an early stage it was tested.

However that last part of the sentence was entirely unnecessary too; if you really want me to start splitting hair, there's no perfection either in NV40's premature drivers. Understandably so, but do I really need to start listing things that do not work yet as they should?

 

[volt]

http://www.beyond3d.com/forum/viewtopic.php?p=253502&highlight=#253502
It's not implemented yet, but it can be, quite easily actually on the NV40.

NVIDIA also claimed gamma corrected AA for the NV30 and we all know how that worked out...

-FUDie

They did?

In any event, one might think NV40 is "broken" (wasn't this the term used when NV3x was launched? ) or not fully capable. However, I'd rather not see a ~10% performance hit once gamma-correction is "enabled" -- would make the [p]reviews useless.