Bug#1025480: another manifestation of the problem with AVX-512 kernel, workarond

[Sébastien Villemot]

Dear Enzo,

Le mardi 18 avril 2023 à 11:31 -0300, Enzo Alberto Dari a écrit :
> This bug was correctly retitled by the maintainer as related to the
> AVX-512 kernel.
> However, it is filed against the libopenblas0-pthread debian package
> while I have found another case that gives wrong results even using
> one thread.

Thanks for providing more information on this issue.

I am happy to let you know that, with upstream’s help, I have finally
been able to identify the cause of the problem and the relevant fix.

I am going to fix this issue in Debian “Bullseye” 11 (see bug #1039470
for the details).

I also confirm that Debian “Bookworm” 12 (which has recently been
released) is not affected by this bug.

Best wishes,

-- 
⢀⣴⠾⠻⢶⣦⠀  Sébastien Villemot
⣾⠁⢠⠒⠀⣿⡁  Debian Developer
⢿⡄⠘⠷⠚⠋⠀  https://sebastien.villemot.name
⠈⠳⣄  https://www.debian.org



signature.asc
Description: This is a digitally signed message part

Bug#1025480: another manifestation of the problem with AVX-512 kernel, workarond

[Enzo Alberto Dari]

This bug was correctly retitled by the maintainer as related to the AVX-512
kernel.
However, it is filed against the libopenblas0-pthread debian package while
I have found another case that gives wrong results even using one thread.
The script solves a linear elasticity problem using the finite element
method in octave, the files are shared here:
https://drive.google.com/file/d/1xkw-1YfX3W-mfqD92I1fNYnQM78yA9Sy/view?usp=sharing
After building the system of linear equations, it is solved using the
octave operator "\", and by "lu" factorization, the results are checked by
computing the residual vectors (should have a norm around the truncation
error).

These are the results of the tests:
-Using defaults:
$ octave fem_lame2d.m
Residualbackslash = 17.947
ResidualLUPQbackslash = 7.2444

-Forcing sequential mode (1 thread):
$ OMP_NUM_THREADS=1 octave fem_lame2d.m
Residualbackslash = 17.947
ResidualLUPQbackslash = 7.2444

-Avoiding the use of the openblas AVX-512 kernel (working workaround !!):
$ OPENBLAS_CORETYPE=Haswell octave fem_lame2d.m
Residualbackslash = 1.4547e-13
ResidualLUPQbackslash = 1.4879e-13

-- 
Enzo A. Dari
Profesor Titular
Instituto Balseiro