Ok
  The current kernels count time spent in the FPE as interrupt time.
So if you are seeing a lot of interrupt time then this is indicating
that the kernel is spending a lot of time in the FPE.

With the most recent kernel interrupt time is also properly
accumulated so the interrupt time may appear slightly higher.

Accumulating interrupt time instead of system time during the FPE
is purley temporary so that folks can see just how much time is being spent
in the FPE and it shows that software floating point seriously hits
performance. Those of you lucky enough to have an ARM700+FPA will notice
a significant reduction in interrupt time.

If people want kernels that dont measure FPE time as interrupt time
have a look in arm32/include/cpu.h at the definition of CLKF_INTR
and rebuild a kernel with a suitable change.

Cheers,
				Mark
Mark Brinicombe				amb@physig.ph.kcl.ac.uk
Research Associate			http://www.ph.kcl.ac.uk/~amb/
Department of Physics			tel: 0171 873 2894
King's College London			fax: 0171 873 2716