My thesis was based on writing a virtual instruments package under win 3.x/95.
I could get the 55ms interupt operable, but anything faster than that is impossible under the normal PC architecture.
My thesis proved the reliability of sensing and control systems under windows, but the speed limit of 55ms was the absolute ceiling (but this is okay for control systems we used)

Does this help?
Des Bromilow
>>> Martin McCormick <martin@DC.CIS.OKSTATE.EDU> 11/2/99 2:57:18 am >>>
        I think one is going to have some trouble measuring real time
accurately for any period under a second in any sophisticated
operating system, be it any of the Windows flavors, DOS, or Linux.

        The tricky thing about exact timing on a modern computer is
that interrupts are constantly being serviced from many different
systems such that a finely-accurate timing routine may be put on hold
for a millisecond hear and another there every time the disk drive
needs servicing or the operating system must tend to another user.

        It would be like having a watch that stops cold at random
periods during the day without warning.  It will still have a dial or
display that gives some time value, but can we trust it?

        PIC's and other embedded systems are the best places to
deal with time-sensitive actions because one can write the software
with this in mind.  You can't hope to be able to do that nearly as
easily on a larger computer without running the risks of creating
unforeseen problems.

Martin McCormick