After the surprisingly hard critics from Valve's Gabe Newell on NVIDIA yesterday, the press today got the chance to get our own performance numbers in Halflife 2. Within the scope of ATI's Shader Day event we were allowed to test on four machines that were provided by ATI. In the meantime, we also received an official statement from NVIDIA on the situation.
The benchmark results were ran on machines with Intel Pentium 4 2.8 GHz processors (FSB800), equipped with 1Gb of RAM and actual released driver from ATI and NVIDIA:
- NVIDIA: Detonator v45.23
- ATI: Catalyst v3.7
Valve did not allow us to also run test with a new Beta version of the upcoming NVIDIA Detonator 50 driver. Valve explained that they only want to see scores of already released drivers. We're still waiting for a more detailed explanation from Valve what exactly they don't like on that Beta driver. NVIDIA asked us to test with that driver because it would contain a lot new (and legal) optimizations for DX9 games - including Halflife 2- and we were very curious to see its results. On the other hand, the test conditions as they were complied exactly with the conditions of the Doom III tests earlier this year, where ATI did not have the chance to provide a better driver for the tests.
What we did not like was the very limited time of only 90 minutes for the test runs. Some cards needed more than 20 minutes for a single configuration. This means there was no time for verification of the scores. In comparison, we had more than a whole day from 8:00 AM until midnight for the Doom III tests at NVIDIA early this year.