...
cgminer times how long it takes for the gpu code to "return" after it's been given work. Unfortunately with windows, the timer resolution is so shithouse at 15ms that I have to sample many many iterations of the GPU code and then average them to see how long it took.
...
cklovias, there are several ways to overcome this drawback of the simple windows time functions. Probably the two easiest ways are using the code from this explanation
http://msdn.microsoft.com/en-us/magazine/cc163996.aspx, or by using the .Net stopwatch class (for your code, you would have to call into a c++/cli dll wrapper around the class, then you have to deal with people needing the .Net framework installed too...maybe make it optional?)
I like using dynamic on my main windows computer, but I have been sticking with 2.7.5 because it has better dynamic behaviour for me. I have just been thinking, 'oh well, make it until the ASICs come out and that's good enough!'
Thanks for that but for such a convoluted process for the sake of one clock call when GPUs will be redundant in a couple of months seems a waste now - i.e. I'm not interested in developing in any significant fashion for GPUs any more. On the other hand, as you see from Kano's message, there are certainly other clock functions he implemented that suffer under windows that will be relevant to him.