Since the first benchmark of a new game, Ashes of the Singularity from Oxide Games, based on Microsoft’s new API, DirectX 12, there are a lot of controversies starting developing. The main reason appears to be the surprising result which we have seen after the benchmarks.
NVIDIA Was Putting Pressure On Us To Disable Certain Settings In The Benchmark
As per the result of benchmark tool, NVIDIA’s latest beast GeForce GTX 980 Ti was noticed struggling against AMD’s old R9 290x. Yes, that’s correct. The old R9 290x outperformed newly launched GTX 980 Ti in the DX 12. NVIDIA’s issued statement by saying that the real performance between two cards on DX 12 could not be judged by the Ashes of the Singularity and also it was reported that the NVIDIA claimed that the benchmarking tool was not accurate.
“There is no war of words between us and Nvidia. Nvidia made some incorrect statements, and at this point they will not dispute our position if you ask their PR. That is, they are not disputing anything in our blog. I believe the initial confusion was because Nvidia PR was putting pressure on us to disable certain settings in the benchmark, when we refused, I think they took it a little too personally.”
Recently, a representative of Oxide Games have claimed that NVIDIA’s Maxwell based graphics cards do not support the DirectX 12 Asynchronous Compute. He also said that AMD is more focused on Asynchronous Compute and more friendly with Paralellism since the launch of GCN architecture. According to him, NVIDIA was more concerned about the software support of DirectX 11 while AMD was more focused towards the support with DirectX 12, and that’s why we have seen such benchmark results.
“Personally, I think one could just as easily make the claim that we were biased toward Nvidia as the only ‘vendor’ specific code is for Nvidia where we had to shutdown async compute. By vendor specific, I mean a case where we look at the Vendor ID and make changes to our rendering path. Curiously, their driver reported this feature was functional but attempting to use it was an unmitigated disaster in terms of performance and conformance so we shut it down on their hardware. As far as I know, Maxwell doesn’t really have Async Compute so I don’t know why their driver was trying to expose that. The only other thing that is different between them is that Nvidia does fall into Tier 2 class binding hardware instead of Tier 3 like AMD which requires a little bit more CPU overhead in D3D12, but I don’t think it ended up being very significant. This isn’t a vendor specific path, as it’s responding to capabilities the driver reports.”