Half-Life 2 Performance Benchmark Preview
by Anand Lal Shimpi on September 12, 2003 12:34 AM EST- Posted in
- GPUs
More on Mixed-Mode for NV3x
We briefly mentioned the Mixed Mode of operation for NV3x GPUs that Valve implemented in Half-Life 2, but there is much more to it than just a special NV3x code path. In fact, the mixed mode NV3x code path was really only intended for the GeForce FX 5900 Ultra (NV35). The mainstream FX chips (5200/5600) require a slightly different code path.
Here you can see the 40% performance boost NVIDIA gets from the special NV3x
code path.
The GeForce FX 5600 (NV31) uses a code path that is internally referred to as dx82; this path is a combination of DX9 (pixel shader 2.0) and DX8.1 (pixel shader 1.4) code, and thus, doesn't look as good as what you'll see on the 5900 Ultra.
Although the 5900 Ultra performs reasonably well with the special NV3x mixed mode path, the 5600 and 5200 cards do not perform well at all. Valve's recommendation to owners of 5600/5200 cards is to run the DX8 (pixel shader 1.4) code path in order to receive playable performance under Half-Life 2. The performance improvement gained by dropping to the DX8 code path is seen most on the GeForce FX 5200; although, there is a slight improvement on the 5600 as you can see below:
The sacrifices that you encounter by running either the mixed mode path or the DX8 path are obviously visual. The 5900 Ultra, running in mixed mode, will exhibit some banding effects as a result of a loss in precision (FP16 vs. FP32), but still looks good - just not as good as the full DX9 code path. There is a noticeable difference between this mixed mode and the dx82 mode, as well as the straight DX8 path. For example, you'll notice that shader effects on the water aren't as impressive as they are in the native DX9 path.
Are the visual tradeoffs perceptive? Yes. The native DX9 path clearly looks better than anything else, especially the DX8.0/8.1 modes.
111 Comments
View All Comments
Anonymous User - Friday, September 12, 2003 - link
another thing i just noticed looking at the doom 3 and hl2 benchies.take a look at the performance of 9800pro and 9600pro...
in hl2, the 9800pro is about 27% ahead of the 9600pro, in doom 3 the 9800pro is near 50% faster than the 9600pro. the whole thing just feels weird.
enigma
Anonymous User - Friday, September 12, 2003 - link
I'm surprised that Anand mentioned nothing about the comparisons between 4x2 and 8x1 pipelines? Does he even know that MS is working to included paired textures with simutainious wait states for the nV arcitexture? You see the DX9 SDK was developed thinking only one path and since each texture has a defined FIFO during the pass the second pipe in the nV is dormant until the first pipe FIFO operation is complete, with paired textures in the pipe using syncronus wait states this 'problem' will be greatly relieved.Anonymous User - Friday, September 12, 2003 - link
its fake.... HL2 test are not ready today , great fake Anandtech :)rogerw99 - Friday, September 12, 2003 - link
#28Ooo Ooo Ooo... I know the answer to that one.
It was Mrs. White, but it wasn't with the gun, it was the lead pipe.
Anonymous User - Friday, September 12, 2003 - link
ATI The Way It Should Be PlayedAnonymous User - Friday, September 12, 2003 - link
Quote: 'So why is it that in the age of incredibly fast, absurdly powerful DirectX 9 hardware do we find it necessary to bicker about everything but the hardware? Because, for the most part, we've had absolutely nothing better to do with this hardware.'Don't we? Wrong!
http://www.cs.virginia.edu/~gfx/pubs/multigridGPU/
;)
Anonymous User - Friday, September 12, 2003 - link
one thing that i think is kinda interesting. check out this benchmark hardocp did - fx5900 ultra vs. radeon 9800 pro in doom 3 (with help from id software).http://www.hardocp.com/article.html?art=NDc0LDE=
after reading this, read carmack's Jan 03 .plan, where he states that under the default openGL codepath, the fx architecture is about half as fast as the r300 - something that is pretty much resembled in the hl2 benchmarks. furthermore he states that using the default path the r300 is clearly superior (+100%), but when converting to vendor-specific codepaths, the fx series is the clear winner.
conclusions? none, but some possibilities
.) ati is better in directx, nvidia in opengl
.) id can actually code, valve cannot
.) and your usual conspiracy theories, feel free to use one you specifically like
bottom line. neither ati nor nvidia cards are the "right ones" at the moment, wait for the next generation of video cards and upgrade THEN.
enigma
Anonymous User - Friday, September 12, 2003 - link
I'm so glad i converted to Ati, i have never regret it & now it feels even better. Ati rulesnotoriousformula - Friday, September 12, 2003 - link
i'm sure Nvidia will strike back.. prolly with DOOM III..well till then i'll enjoy my little army of ATI cards: ATI 9800NP>PRO, ATI 9700, ATI 9600PRO :P..long live ATI!!! :DAnonymous User - Friday, September 12, 2003 - link
Anand should have benchmarked on a more widely used computer like a 2400 or 2500+ AMD. Who here has the money to buy a p4 3Gb 8000mhz FSB cpu?