[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: ATLAS version 3.2 available


>Greetings!  I have a little script which plays back the output of
>'make install arch=foo' on an arbitrary box of the same major
>architecture, skipping all timings.  Clint, would it be possible for
>you to make available the output of the installs on the alphas and
>sparcs at your disposal, so I can configure the Debian package

Sure.  What, exactly, do you need?  Will the contents of
give you everything?  Also, do you just want linux versions, or tru64 and
solaris installs as well (I have no access to linux+sparcs, for instance)?

Also, I've had reports from a couple of people who've installed ATLAS 3.2
under Windows.  The good news is that, using cygnus, the Level 3 SSE stuff
rocks.  The bad news is that none of your level 2 routines are used, 'cause
they all cause erorrs of the form:

>/atlas/bin/ntp3/ATLrun.sh /atlas/tune/blas/gemv/ntp3 xcmv -C 6 -l 0.750000 -A N
>                  -m 1000 -n 1000 -f 16 -o res/cgemvN_6_75
>      0 [main] xcmv 1360 handle_exceptions: Exception: STATUS_ACCESS_VIOLATION
>   2217 [main] xcmv 1360 stackdump: Dumping stack trace to xcmv.exe.stackdump
>Signal 11

This means none of your level 2 routines are used in windows, and it may mean
you are reading/writing outside the memory bound on these routines (you
corrected some errors like this before release as well).  As soon as I can
get around to it, I hope to use something like checker to verify whether there
are problems in these routines or not (what I wouldn't give for purify under
linux) . . .

Anyway, I thought it possible you might want to eyeball these routines and see
if you are reading/writing out of bounds (for instance, the classic error
of not ending the prefetch loop an iteration ahead so you don't read off the
end of the array);  if the routines have such errors, it'll need to be
errataed ASAP . . .