CUDA performance penalty when running in Windows

Question

I\'ve noticed a big performance hit when I run my CUDA application in Windows 7 (versus Linux). I think I may know where the slowdown occurs: For whatever reason, the Win

Answer 1

Even it's been almost 3 years since the issue has been active, I still consider it necesssary to provide my findings.

I've been in the same situation: the same cuda programme elapsed for 5ms in Ubuntu cuda 8.0 while over 30ms in Windows 10 cuda 10.1. Both with GTX 1080Ti. However, in Windows when I changed the compiler from VS Studio to cmd's nvcc compiler suddenly the programme was boosted to the same speed as the Linux one.

This suggests that maybe the problem comes from Visual Studio.