In message <Pine.ULT.4.05.10012141405150.28309-100000@lightning.msu.montana.edu
>, "Michael L. Hitch" writes:
>just before the for (;;) loop.  This should result in a non-zero return
>when only the S_INTR_LATCH bit is set.

I'm willing to try possible strategies.  I have a reasonably stable source
tree, a couple of cards, and a test case that seems to semi-reliably trigger
the failure.

I'm currently trying to figure out why my fairly respectable Intel card can't
produce more than 5MB/sec on this box.

-s