AMD Slams SYSmark Benchmark - Calls it Biased and Unreliable
AMD Slams SYSmark Benchmark as Unreliable
Published: 15th January 2016 | Source: AMD |

AMD Slams SYSmark Benchmark - Calls it Biased and Unreliable
In a new video AMD has Slammed the SYSmark system Benchmark as unreliable and is only optimized for Intel, recommending Futuremark's the PCMARK benchmark as a reliable and accurate alternative when it comes to comparing performance.
In AMD's testing SYSmark AMD has found that SYSmark provides data that is not comparable to the difference in real world performance when it compared AMD and Intel CPUs, giving a performance delta of 50% for a comparable system when other benchmarks like PCMARK only give a delta of 7%.
The US' Federal Trade Commission, the FTC, now required Intel to post a disclaimer when using data from this benchmark, stating that SYSmark may only be optimized for Intel platforms.
AMD says that using SYSmark to judge PC performance and using it as a basis for judging PC performance will result in dramatic overspending, as this benchmark is only optimized for the Intel platform and only really judges CPU performance.
SYSmark is not a performance benchmark that we have ever used at OC3D, so we do not have any results comparing AMD and Intel platforms, but judging from the results of other websites and AMD's public damning of the benchmark it is certainly not a benchmark that we would consider using in the future.
You can join the discussion on AMD's public shaming of the popular SYSmark benchmark on the OC3D Forums.
AMD Slams SYSmark Benchmark - Calls it Biased, Unreliable and only optimized for Intel. https://t.co/054xOWSOlL pic.twitter.com/uIXcifdRVS
— OC3D (@OC3D) January 15, 2016Most Recent Comments
|
AMD discovers a synthetic benchmark isn't as realistic as a benchmark that uses real-life software shocker.
|
It seems AMD want to project an image of Open Standards and Fairness the public.
In the US this is a popular benchmark for advertising system performance, so AMD wants to discredit it because it is Intel friendly/pushed.Quote
|
That's a terrible plot twist considering they still lose in that benchmark...
|
|
It isn't the losing that was the problem. It was the inherent and systemic bias that is the problem.
|
AMD may well be touchy because they are readying to release Zen, though.
However any one with half an ounce of sense knows not to trust one benchmark and will use more than one before deciding if something is good or not.Quote
|
Right now as I type this it doesn't really matter if a benchmark is derped because AMD would not win any way.
AMD may well be touchy because they are readying to release Zen, though. However any one with half an ounce of sense knows not to trust one benchmark and will use more than one before deciding if something is good or not. |


http://www.overclock3d.net/gfx/artic...053620509l.jpg
Read more on AMD's public shaming of the SYSmark Benchmark.Quote