FX and PS 1.4, DX9 tests?

[Typedef Enum]

Am I the only guy that's sitting here, beside myself, over the fact that nVidia's latest/greatest "well beyond DX9 spec" card does NOT support DX9 in the drivers yet?

Holy crap...What the hell is going on over there?

 

[tb]

Someone needs to write or find hw independant shader code and let gffx run it. Existing benchmarks like 3dmark, nature, etc. might be bias towards one ihv. Basically, provide an open source shader code.

ShaderMarks shader code is included, simple text files, so everyone can look at it and maybe change/optimize it (the shaders are compiles from these *.sha files at runtime). There are no secrets in it.

Thomas

 

[LeStoffer]

PS2.0 aren't working in 42.63 Dets. And VS2.0 is buggy. But all DX8.1 functionality (including PS1.4) is there.

Thanks, that answer my question about the lackluster launch of the CineFX part of the GeForce FX.

 

[Ante P]

Someone needs to write or find hw independant shader code and let gffx run it. Existing benchmarks like 3dmark, nature, etc. might be bias towards one ihv. Basically, provide an open source shader code.

ShaderMarks shader code is included, simple text files, so everyone can look at it and maybe change/optimize it (the shaders are compiles from these *.sha files at runtime). There are no secrets in it.

Thomas

hey thomas there you are
the problem with sahder mark is that if you run autobench it will begin benching the moment you press A
thus lights will be at different points in the picture

just a suggestion here:
increase the time of each test just a little bit to gain more reliable results and make sure when pressing A that also restarts the test so that all light soucres and models begin at the same point every time you benchmark

I've behcnmarked the last test three times in a row and this is what I got
98 fps
132 fps
102 fps

but after I carefully timed the pressing of B while looking at the light soucres making sure I began testing at the same time every time I got these results after benching three times
100
100
102

well if you have the time it would be übernice since I intend to use it for my FX review (whenever the sample arrives.......)

 

[DegustatoR]

does it support that functionality in Open GL then?

Yeap. Elf girl and such are running fine on these drivers, AFAIK.

As for 42.70 - they are the same as 42.63 in not supporting DX9 on NV30.

 

[Ante P]

does it support that functionality in Open GL then?

Yeap. Elf girl and such are running fine on these drivers, AFAIK.

As for 42.70 - they are the same as 42.63 in not supporting DX9 on NV30.

I hope nVidias has prepared some new drivers by the time I get my sample (whenever that is) or at least that soem new driver has leaked.

Do you know if 42.70 fixes some of the rendering errors as seen in [H]s review?

 

[Brent]

does it support that functionality in Open GL then?

Yeap. Elf girl and such are running fine on these drivers, AFAIK.

As for 42.70 - they are the same as 42.63 in not supporting DX9 on NV30.

I hope nVidias has prepared some new drivers by the time I get my sample (whenever that is) or at least that soem new driver has leaked.

Do you know if 42.70 fixes some of the rendering errors as seen in [H]s review?

I'll try it out today with the 42.70 drivers in those apps again....

 

[Ante P]

I'll try it out today with the 42.70 drivers in those apps again....

Great.
If you also had those problems with 2x FSAA that Anand had in UT2003 perhaps you could also see if 42.70 fixes it (or the fog for that matter).

Does anyone know what the latest interim build is?

 

[tb]

Someone needs to write or find hw independant shader code and let gffx run it. Existing benchmarks like 3dmark, nature, etc. might be bias towards one ihv. Basically, provide an open source shader code.

ShaderMarks shader code is included, simple text files, so everyone can look at it and maybe change/optimize it (the shaders are compiles from these *.sha files at runtime). There are no secrets in it.

Thomas

hey thomas there you are
the problem with sahder mark is that if you run autobench it will begin benching the moment you press A
thus lights will be at different points in the picture

just a suggestion here:
increase the time of each test just a little bit to gain more reliable results and make sure when pressing A that also restarts the test so that all light soucres and models begin at the same point every time you benchmark

I've behcnmarked the last test three times in a row and this is what I got
98 fps
132 fps
102 fps

but after I carefully timed the pressing of B while looking at the light soucres making sure I began testing at the same time every time I got these results after benching three times
100
100
102

well if you have the time it would be übernice since I intend to use it for my FX review (whenever the sample arrives.......)

I'll fix this in the next release (1-2 weeks)

Thomas

 

[Brent]

I editted my post on the first page of this thread, check it out, my initial impressions of DX9 support were wrong

the 42.63 drivers do support DX9 features

 

[LeStoffer]

I editted my post on the first page of this thread, check it out, my initial impressions of DX9 support were wrong

the 42.63 drivers do support DX9 features

The caps might say yes, but does it work at all?

 

[Joe DeFuria]

Brent,

There are DX9 Demos on ATI's web site:

http://mirror.ati.com/developer/demos/r9700.html

give them a whirl on the FX!

 

[Ante P]

Brent,

There are DX9 Demos on ATI's web site:

http://mirror.ati.com/developer/demos/r9700.html

give them a whirl on the FX!

or tb's shadermark for that matter
it would be cool if you could just post the "shadermark_results.txt" file here

 

[Luminescent]

Wonder if Humus' demos will run correctly on the hardware? Hopefully we can get results up ASAP.

 

[SvP]

Well?

 

[Luminescent]

Nice sig Joe .

 

[DegustatoR]

Ante P

does it support that functionality in Open GL then?

Yeap. Elf girl and such are running fine on these drivers, AFAIK.

As for 42.70 - they are the same as 42.63 in not supporting DX9 on NV30.

I hope nVidias has prepared some new drivers by the time I get my sample (whenever that is) or at least that soem new driver has leaked.

Let me correct myself - DX9 support IS in these dets, but it's buggy as hell. Let's wait for Brent results w/ATI demos...

Do you know if 42.70 fixes some of the rendering errors as seen in [H]s review?

No idea.

 

[tb]

Brent,

There are DX9 Demos on ATI's web site:

http://mirror.ati.com/developer/demos/r9700.html

give them a whirl on the FX!

or tb's shadermark for that matter
it would be cool if you could just post the "shadermark_results.txt" file here

If released ShaderMark v1.6 with a more accurate timing routine and fixed light positions.

Thomas

 

[Brent]

Ok, I ran ShaderMark version 1.6 with the 42.63 drivers on the GFFX with NoAA and NoAF at 1024x768x32, here are the results:

ShaderMark v1.6 - DX9 2.0 Pixel Shader Benchmark - ToMMTi-Systems (http://www.tommti-systems.com)

video mode / device info
(1024x768), X8R8G8B8 (D24X8)
HAL (pure hw vp): NVIDIA GeForce FX 5800 Ultra
benchmark info
DX9 mip filter reflections: on
mip filter reflections: on

shaders:
Fixed Function - Gouraud Shading
Fixed Function - Gouraud Shading
582.84 fps

shaders:
Fixed Function - Diffuse Texture Mapping
Fixed Function - Diffuse Texture Mapping
572.49 fps

shaders:
Fixed Function - Diffuse Bump Mapping
Fixed Function - Diffuse Bump Mapping
282.81 fps

shaders:
PS 2.0 - Diffuse Bump Mapping
PS 2.0 - Diffuse Bump Mapping
85.65 fps

shaders:
PS 2.0 - Diffuse Bump Mapping
PS 2.0 - Bumped Diffuse Lighting with per pixel intensity falloff
63.06 fps

shaders:
PS 2.0 - Bumped Diffuse + Specular
PS 2.0 - Diffuse Bump Mapping
85.30 fps

shaders:
PS 2.0 - Bumped Diffuse + Specular
PS 2.0 - Bumped Diffuse Lighting with per pixel intensity falloff
68.67 fps

shaders:
PS 2.0 - Bumped Diffuse and Specular Lighting with per pixel Specular Exponent
PS 2.0 - Diffuse Bump Mapping
87.93 fps

shaders:
PS 2.0 - Bumped Diffuse and Specular Lighting with per pixel Specular Exponent
PS 2.0 - Bumped Diffuse Lighting with per pixel intensity falloff
70.37 fps

shaders:
PS 2.0 - Per Pixel Anisotropic Lighting
PS 2.0 - Diffuse Bump Mapping
94.75 fps

shaders:
PS 2.0 - Per Pixel Anisotropic Lighting
PS 2.0 - Bumped Diffuse Lighting with per pixel intensity falloff
74.59 fps

shaders:
PS 2.0 - Per Pixel Bumped Anisotropic Lighting plus Diffuse
PS 2.0 - Diffuse Bump Mapping
79.36 fps

shaders:
PS 2.0 - Per Pixel Bumped Anisotropic Lighting plus Diffuse
PS 2.0 - Bumped Diffuse Lighting with per pixel intensity falloff
64.62 fps

shaders:
PS 2.0 - Cubic Environment Bumped Reflections
PS 2.0 - Diffuse Bump Mapping
83.26 fps

shaders:
PS 2.0 - Cubic Environment Bumped Reflections
PS 2.0 - Bumped Diffuse Lighting with per pixel intensity falloff
67.44 fps

shaders:
PS 2.0 - Cubic Environment Bumped Diffuse and Independently Colored Reflections
PS 2.0 - Diffuse Bump Mapping
70.74 fps

shaders:
PS 2.0 - Cubic Environment Bumped Diffuse and Independently Colored Reflections
PS 2.0 - Bumped Diffuse Lighting with per pixel intensity falloff
58.72 fps

shaders:
PS 2.0 - Ghost Shader
PS 2.0 - Diffuse Bump Mapping
59.77 fps

shaders:
PS 2.0 - Ghost Shader
PS 2.0 - Bumped Diffuse Lighting with per pixel intensity falloff
49.34 fps

shaders:
PS 2.0 - Cubic Environment Bumped Diffuse and Tinted Reflections with per pixel Fresnel Term
PS 2.0 - Diffuse Bump Mapping
70.73 fps

shaders:
PS 2.0 - Cubic Environment Bumped Diffuse and Tinted Reflections with per pixel Fresnel Term
PS 2.0 - Bumped Diffuse Lighting with per pixel intensity falloff
59.08 fps

shaders:
PS 2.0 - Cubic Environment Bumped Diffuse and Independently Colored Reflections
PS 2.0 - Diffuse Bump Mapping
71.81 fps

shaders:
PS 2.0 - Cubic Environment Bumped Diffuse and Independently Colored Reflections
PS 2.0 - Bumped Diffuse Lighting with per pixel intensity falloff
59.59 fps

shaders:
PS 2.0 - 4 Lights/Pass Diffuse Bump Mapping
PS 2.0 - 4 Lights/Pass Diffuse Bump Mapping
33.54 fps

shaders:
PS 2.0 - 2 Spot Lights
PS 2.0 - 2 Spot Lights
28.07 fps

shaders:
PS 2.0 - Cubic Environment Bumped Diffuse and Independently Colored Reflections
PS 2.0 - 4 Lights/Pass Diffuse Bump Mapping
33.57 fps

shaders:
PS 2.0 - Cubic Environment Diffuse Light and Tinted Refractions
PS 2.0 - 4 Lights/Pass Diffuse Bump Mapping
35.50 fps

 

[Doomtrooper]

We need someone with a 9700 now to compare (mine is not here yet)..and possibly if Brent could run a FSAA mode 4X