PurePC zrobiło testy z GTX1080

Według mnie sterowniki nVidii nie zostały (jeszcze?) zoptymalizowane pod Zeny

In addition to Lisa's comments, there are also some variables that could affect performance:
1) Early motherboard BIOSes were certainly troubled: disabling unrelated features would turn off cores. Setting memory overclocks on some motherboards would disable boost. Some BIOS revisions would plain produce universally suppressed performance.
2) Ryzen benefits from disabling High Precision Event Timers (HPET). The timer resolution of HPET can cause an observer effect that can subtract performance. This is a BIOS option, or a function that can be disabled from the Windows command shell.
3) Ryzen benefits from enabling the High Performance power profile. This overrides core parking. Eventually we will have a driver that allows people to stay on balanced and disable core parking anyways. Gamers have been doing this for a while, too. I misspoke, here. I want to clarify the benefit: High Performance mode allows the CPU to update its voltage/clockspeed in 1ms, vs. the 30ms that it takes balanced mode. This is what our driver will accomplish. Apologies for the confusion!
These are just some examples of the early growing pains that can be overcome with time.

1 We plan for AM4 to be around a long time. Future generations of processors will be delivered into the socket at many price points.
2 We are working with both the motherboard makers and game developers to address performance challenges. We want to ensure the best possible performance from Ryzen is delivered.
3 We definitely want to redefine the market by bringing Ryzen 7s multithread performance to the sub $500USD market. We see great results at higher resolutions for gaming, and as we work with developers on learning how to use Zen cores we expect to see an improved 1080p gaming experience as well.

Thanks for the question. In general, we've seen great performance from SMT in applications and benchmarks but there are some games that are using code optimized for our competitor... we are confident that we can work through these issues with the game developers who are actively engaging with our engineering teams.

Lisa had to take off to do some media interviews, but I can help!
Our next steps are to continue working with motherboard vendors to further refine their BIOSes. We're also working with game devs to address the cases where SMT is a performance reduction, or the game does not perform comparably to our competition. Based on IPC, clockspeeds, non-gaming performance that our performance should be more or less identical. In the cases where it's not, we'll get it addressed.

1) It's important to remember that Ryzen is a client consumer processor. For about 98% of the desktop market (a literal number), the workloads fit comfortably into 40 PCIe lanes and dual channel RAM. We need to focus on what's big before we can focus on what's small. You'll see that as a guiding hand in the platform decisions for Ryzen. Certainly Ryzen straddles the line between "workstation" and "desktop," which comes with pros and cons for each type of user. But overall I think a broadside against the high-performance market is what AMD needed.
2) Consider our 65W/8C16T Ryzen 7 1700.
3) We do not plan to move to quad channel on Ryzen. That sort of takes me back to answer #1. Memory controller is an area of improvement for us, but few consumer workloads are latency sensitive in the DRAM subsystem, and it was of greater significance to focus on cache, branch prediction, and engine throughput to lift our overall performance in Zen.