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

Re: ATLAS version 3.2 available



Camm,

>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
>accordingly? 

Sure.  What, exactly, do you need?  Will the contents of
   ATLAS/bin/<arch>/INSTALL_LOG
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 . . .

Thanks,
Clint