X800 PRO launch on 4th of May + specs

Page 2 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Davegod

Platinum Member
Nov 26, 2001
2,874
0
76
Not sure how much "schooling" will be getting done, since the 12x pipeline part is ATI's version of the 6800 while they also have the 16 in their 6800Ultra. I think everyone should know by now to ignore mhz accross platforms Wont be surprised if ati's cards are actually generally available before nvidia's, for what thats worth.

I'll wait for x800 & x800XT vs. 6800/6800ultra roundups before making assumptions, I'd expect nvidia's fastest to be the fastest, though ati might have done something else unexpected and expensive with their x800xt. Hopefully it's reasonably close, regardless of the "winner".

Really I'm most interested in what these guys will have in a year, since thats when I'll next be buying

ps. I've heard some incredible pish from developers, including a straight from the mouth of a lead programmer who was convinced all AMD cpu are substandard bargain bin parts, all flaky and unstable. This was late 2003.
 

XBoxLPU

Diamond Member
Aug 21, 2001
4,249
1
0
Originally posted by: AIWGuru
Originally posted by: UlricT
AIWGuru... 1.x shaders are from DirectX 8!
I think the argument here is DX9b vs. DX9c!!!

Yes, but what we're talking about is PS 3.0 being able to do the same ammount of work in 1/10th the ammount of time as PS 2.0.
Saying PS 2.0 = PS 3.0 just because it's capable of producing the same visuals EVENTUALLY (with much more work) is stupid.
It can't be PRACTICALLY done because it's MUCH MUCH slower.
That's like saying that a pentium 1 and a pentium 4 are the same since given the same SETI unit, they'll both come up with the same result even though one takes longer.

Obviously, PS 3.0 DOES allow for more advanced visual effects because the horsepower is not present to perform them under 2.0, not because it's not technically possible.

But how do you know that the R420 cant produce the same things that can be done with PS3.0, with PS2.0 in the same amount of time done with PS3.0 if they had it ???
 
Apr 16, 2004
27
0
0
AIWGuru,
do you have any idea what the hell you're talking about?
the first screenshot may as well be a DX7 shot, they've taken out bump maps, reduced textures, etc, that is NOT an indication that P.S 3 isn't being used, you've got to be feckkin naive as shite to believe that (nvidia obviously hopes people like you will buy into it). Let me restate: P.S.3 takes off some programmability limits, but there is NOT a difference like you've implied in those screens. Doom3 hardly uses the type of programmability in P.S.2, let alone 3.
 

AIWGuru

Banned
Nov 19, 2003
1,497
0
0
Originally posted by: XBoxLPU
Originally posted by: AIWGuru
Originally posted by: UlricT
AIWGuru... 1.x shaders are from DirectX 8!
I think the argument here is DX9b vs. DX9c!!!

Yes, but what we're talking about is PS 3.0 being able to do the same ammount of work in 1/10th the ammount of time as PS 2.0.
Saying PS 2.0 = PS 3.0 just because it's capable of producing the same visuals EVENTUALLY (with much more work) is stupid.
It can't be PRACTICALLY done because it's MUCH MUCH slower.
That's like saying that a pentium 1 and a pentium 4 are the same since given the same SETI unit, they'll both come up with the same result even though one takes longer.

Obviously, PS 3.0 DOES allow for more advanced visual effects because the horsepower is not present to perform them under 2.0, not because it's not technically possible.

But how do you know that the R420 cant produce the same things that can be done with PS3.0, with PS2.0 in the same amount of time done if PS3.0 if they had it ???

PS 3.0 is inherently a better "instruction set."
It's able to do more work with less horsepower.
The best analogy of this is a 486 without a math co-processor.
It can't crunch floating point (remainders) in hardware and so must do extra work to get those results.
When the Pentium was released with an integrated floating point unit, it was able to crunch FP equations at the same speed as a 486 despite a large clock speed disadvantage. A P90 was much faster in FP than a 133 486 (yes, they did reach 133)

Because the GeForce 6 series has such improved PS 2.0 performance (raw horsepower) and can support the inherently more efficient (supports unlimited loops, longer strings etc) PS 3.0 it's hard to imagine R420 producing visual effects with PS 2.0 as NV40 can produce with PS 3.0. Exactly how fast is ATI's 486 running at anyway?

I predict that it will be a close race in PS 2.0 performance but that ATI will not be able to stand up to PS 3.0 performance.
 

Alkali

Senior member
Aug 14, 2002
483
0
0
Thats my point too Xbox man...

Remember that ATi presentation that got leaked from the ATi site, the notes of that guy said that PS3.0 will be slow this generation - obviously he's talking about the extra features in PS3.0 that arent in PS2.0. Its starting to make sense to me why Ati are just missing it out until R5XX - because if they can produce same performance using PS2.0 instead, who cares seen as the visuals are exactly the same...
 

Alkali

Senior member
Aug 14, 2002
483
0
0
Originally posted by: AIWGuru

I predict that it will be a close race in PS 2.0 performance but that ATI will not be able to stand up to PS 3.0 performance.

Ok, look, if ATi don't support PS3.0 at all in the X800 - then there arent going to be any comparisons like this anyway seen as the graphics are the same with either pixel shader set... it will just be down to FPS. See? Get the point yet?
 

AIWGuru

Banned
Nov 19, 2003
1,497
0
0
Jesus...
"Pixel Shader 3.0 (PS3.0) allows shader programs of over 65,000 lines and includes dynamic flow control (branching). This revision also requires that compliant hardware offer 4 Multiple Render Targets (MRT's allow shaders to draw to more than one location in memory at a time), full 32-bit floating point precision, shader antialiasing, and a total of ten texture coordinate inputs per pixel.

The main advantage here is the ability for developers to write longer, more complex, shader programs that run more efficiently. The flow control will give developers the freedom to write more intuitive code without sacrificing efficiency. Branching allows a shader program the expanded ability to make decisions based on its current state and inputs. Rather than having to run multiple shaders that do different things on different groups of pixels, developers can have a single shader handle an entire object and take care of all its shading needs. Our example of choice will be shading a tree: one shader can handle rendering the dynamics of each leaf, smooth new branches near the top, rugged old bark on the trunk, and dirty roots protruding from the soil.

Vertex Shader 3.0 extends its flow control ability by adding if/then/else statements and including the ability to call subroutines in shader programs. The instruction limit on VS3.0 is also extended to over 65000. Vertex textures are also supported, allowing more dynamic manipulation of vertices. This will get even more exciting when we make our way into the next DirectX revision which will allow for dynamic creation of vertices (think very cool particle systems and hardware morphing of geometry).

One of the coolest things that VS3.0 offers is something called instancing. This functionality can remove a lot of the overhead created by including multiple objects based on the same 3d model (these objects are called instances). Currently, the geometry for every model in the scene needs to be setup and sent to the GPU for rendering, but in the future developers can create as many instances of one model as they want from one vertex stream. These instances can be translated and manipulated by the vertex shader in order to add "individuality" to each instance of the model. To continue with our previous example, a developer can create a whole forest of trees from the vertex stream of one model. This takes pressure off of the CPU and the bus (less data is processed and sent to the GPU).
"
 
Apr 16, 2004
27
0
0
R500 won't even be PS3, it'll be directly running PS4 code from DX10. That's why I think it's so irrelevent touting PS3, the next gen of games aren't going to look much different with 6800 running a few extensions to DX9, but they'll look a hell of a lot of different on DX10/R500. PS3 at the moment's just a moot point for most, in the same way Geforce3 was when Doom 3 was shown..
 
Apr 16, 2004
27
0
0
AIW,
my main point is that there is nothing immediate *visually* to distinguish PS3. Of course it adds more programmability features, I didn't deny that.
 
Apr 16, 2004
27
0
0
Taking your last post to its logical conclusion - a faster newer CPU gives you the second screenshot you posted, and a slower CPU gives you the blurry top one. (no).
 

AIWGuru

Banned
Nov 19, 2003
1,497
0
0
If you follow my analogy of the FP performance of the 486 to the pentium, which seem to apply well...

You'll see that you need a 486 running at a much higher speed to perform FP equally well as the pentium at a much lower speed.

This applies well to these complex shaders, yes?

Do you really believe that R420 has THAT much more horsepower than NV40?

From journalist reports from the backroom demos of both companies, nv420 was not performing as well as NV40 let alone better.

Yes, you can say that a 486 at 133mhz can do FP as fast as a Pentium at 90mhz. But what we're talking about here is more like a 486 at 100mhz to a p90.

Aside from the raw horsepower aspect,
the full programability that PS 3.0 allows (i.e. if, then statements, more branching) allows the GPU to acts in ways it isn't able to with PS 2.0.
If programmed for correctly, it can be used as a second general purpose CPU ot handle things like AI, collision detection, etc etc which will increase game performance further beyond what shader efficiency would suggest.

PS 3.0 also has amazing implications to applications such as (we know NV40 supports) video encoding and possibly any number of non-gaming tasks which might benefit from a dedicated SIMD co-processor.
 

AIWGuru

Banned
Nov 19, 2003
1,497
0
0
Originally posted by: gauravsharma311
Taking your last post to its logical conclusion - a faster newer CPU gives you the second screenshot you posted, and a slower CPU gives you the blurry top one. (no).

You obviously don't understand wtf I"m talking about.
Those two CPUs in that post would generate the same image. The point is that one requires more clock speed to do it as it doesn't have an integrated FPU.
 

AIWGuru

Banned
Nov 19, 2003
1,497
0
0
Originally posted by: shady06
Originally posted by: gauravsharma311
ill also restate the visual differences between PS2 and PS3 are neglibible.

negligable? really?

take a look at this

lol, dude, that's what we've been DISCUSSING for the last few pagedowns.
People amaze me sometimes...
thanks for the support...but...
 

AIWGuru

Banned
Nov 19, 2003
1,497
0
0
Originally posted by: PorBleemo
I wonder if the lower end NV40 cards will have the encoder also. It's starting to look to me that nVidia might win this round.

-Por

The video encoder is not a fixed function unit. It's just drivers taking advantage of fully programmable PS 3.0 shaders. As long as the lower end NV4x cards support PS 3.0, there's no technical limitation why they shouldn't support video encoding.
 
Apr 16, 2004
27
0
0
as someoneone pointed out, that's not PS2 vs PS3 (read the actual page).
and anyway, they're extreme cases - PS1 *can* do bump mapping and water effects, and they *can* be made to look comparable, but in those screenshots they've just turned EVERYTHING down, even textures, and then said "uh yeah PS1 can only do this", that's just plain misleading.
 

NFS4

No Lifer
Oct 9, 1999
72,647
27
91
Originally posted by: shady06
Originally posted by: gauravsharma311
ill also restate the visual differences between PS2 and PS3 are neglibible.

negligable? really?

take a look at this

Dude, those screenshots are comparing PS 1.1 to PS 3.0. Not PS 2.0 to PS 3.0
Update2: While we still try to get ahold of this mod, below is the official statement from NVIDIA on these screenshots. The first screenshots are NOT using PS2.0, but PS1.x instead.
You guys really need to READ before you start beatin' your chests.
 

Alkali

Senior member
Aug 14, 2002
483
0
0
Originally posted by: shady06
Originally posted by: gauravsharma311
ill also restate the visual differences between PS2 and PS3 are neglibible.

negligable? really?

take a look at this

Shady, please re-read this thread (and/or 217 others on the net) concerning the incorrect assumption that the 'before' screenshots are with anything other than ps1.x
 

AIWGuru

Banned
Nov 19, 2003
1,497
0
0
Originally posted by: gauravsharma311
and yes, I mean the above at similar rendering speeds.

I've long since stopped addressing those two screenshots.
Care to address any of the points I've made in my last few posts?
Can you?
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |