Reverend
13-Jun-2003, 17:07
http://www.yetistudios.co.uk/
Yeti Studios are proud to announce the release of the Gun Metal Benchmark. We hope that you find this tool useful to assess the speed and performance of your hardware.
The Benchmark intentionally incorporates features and functions that are designed to really push the latest DirectX 9 compatible 3D accelerators to the limit and therefore the speed of the benchmark should not be taken as representative of the speed of the game. We would always expect the game to run at a higher frame-rate than the Benchmark on the same hardware configuration.
I haven't downloaded it (50MB) so I can't give any comments.
[edit]Here's the short FAQ :
Q: What API is supported?
Microsoft DirectX 9.0
Q: What data does it report?
Frames per second are reported to an HTML file at the end of the benchmark. The final numbers are not a score; it reports an average FPS, minimum FPS, and maximum FPS at a set resolution.
Q: What Vertex Shader version does the benchmark use?
Vertex Shader 2.0
Q: What Pixel Shader version does it use?
Pixel Shader 1.1
Q: Can you turn off AA and AF?
The benchmark uses Anisotropic filtering & antialiasing by default, as these are must have features in modern gaming and that is level of image quality we are seeking from Gun Metal. Anisotropic filtering cannot be turned off.
Q: How many codepaths are there?
All GPU's take the same DX9 codepath. If not, the benchmark will report the results as invalid (or simply just fail). It is a deterministic benchmark, so every frame will be rendered the same on each piece of hardware.
Q: Is it a good GPU benchmark?
Yes, it is GPU-limited and uses complex DX9 features.
Q: Is it a good CPU benchmark?
It is neither a good nor bad CPU benchmark, as the application is GPU limited.
Yeti Studios are proud to announce the release of the Gun Metal Benchmark. We hope that you find this tool useful to assess the speed and performance of your hardware.
The Benchmark intentionally incorporates features and functions that are designed to really push the latest DirectX 9 compatible 3D accelerators to the limit and therefore the speed of the benchmark should not be taken as representative of the speed of the game. We would always expect the game to run at a higher frame-rate than the Benchmark on the same hardware configuration.
I haven't downloaded it (50MB) so I can't give any comments.
[edit]Here's the short FAQ :
Q: What API is supported?
Microsoft DirectX 9.0
Q: What data does it report?
Frames per second are reported to an HTML file at the end of the benchmark. The final numbers are not a score; it reports an average FPS, minimum FPS, and maximum FPS at a set resolution.
Q: What Vertex Shader version does the benchmark use?
Vertex Shader 2.0
Q: What Pixel Shader version does it use?
Pixel Shader 1.1
Q: Can you turn off AA and AF?
The benchmark uses Anisotropic filtering & antialiasing by default, as these are must have features in modern gaming and that is level of image quality we are seeking from Gun Metal. Anisotropic filtering cannot be turned off.
Q: How many codepaths are there?
All GPU's take the same DX9 codepath. If not, the benchmark will report the results as invalid (or simply just fail). It is a deterministic benchmark, so every frame will be rendered the same on each piece of hardware.
Q: Is it a good GPU benchmark?
Yes, it is GPU-limited and uses complex DX9 features.
Q: Is it a good CPU benchmark?
It is neither a good nor bad CPU benchmark, as the application is GPU limited.