So I've did some playing around with bench marking and my 8 core fx/unraid setup on win10. With NPT disabled I am seeing what you described as progressively worse multi-threaded performance when adding additional cpus. It's downright horrible in some tests with all 8 cores. Single threaded performance, however, seems to be pretty consistent with ~12-15% performance drop across the board. 4 cpus looks like the sweet spot for overall system performance. It seems to be a mixed bag though. My cinebench tests did not show this behavior and performance seemed to scale up pretty well as I added additional cores. I'm also running a Linux Mint 18.1 vm and while I saw some noticeable degradation in win10 (login time, internet browsing, some desktop apps, etc), disabling NPT seemed to improve the overall desktop experience and I was not able reproduce the same weird multi-threaded issues.
So it looks like I'll be dealing with same issues with Ryzen... for a second I started to wander if I should hold off and wait a while longer to see if some of these things get ironed out before taking the dive. But then I realized that I've been with amd since the k5. What am going to do, go out and buy intel?