updated on Thu Nov 26 2013
maintained by Julien Langou, U. Colorado Denver and Julie Langou, U. Tennessee
RED means BUG WAS CONFIRMED but IT IS STILL HERE
ORANGE means BUG WAS NOT CONFIRMED
GREEN means BUG WAS CORRECTED :
-
correction will be included in next release
-
bug fix available in LAPACK SVN repository
bug :: Missing initialization of ICTXT in a few ScaLAPACK routines
-
CORRECTED
-
Present in ScaLAPACK
-
Bug reported by Dmitry Baksheev (Intel) on Nov 10th 2015
-
Link: http://icl.cs.utk.edu/lapack-forum/viewtopic.php?f=13&t=4838
-
committed by Julie on Nov 10 2015 (SVN: r202).
bug :: Incorrect call of CHK1MAT in pzheevd.f
-
CORRECTED
-
Present in ScaLAPACK
-
Bug reported by Dmitry Baksheev (Intel) on Nov 10th 2015
-
Link: http://icl.cs.utk.edu/lapack-forum/viewtopic.php?f=13&t=4837
-
committed by Julie on Nov 10 2015 (SVN: r201).
bug :: bug in dgamx2d (triggered in parpack)
-
NOT CONFIRMED
-
Present in ScaLAPACK
-
Bug reported by davydden on Jul 22nd
-
Link: http://icl.cs.utk.edu/lapack-forum/viewtopic.php?f=13&t=4676
-
Not Assigned
bug :: Wrong XERBLA call in pshseqr, pdhseqr, psgebal, pdgebal functions
-
CORRECTED
-
reported by Bjorn Adlerborn on Scalapack mailing list.
-
reported by eugene Chereshnev on LAPACK Forum
-
fixed from Rodney and Julie
-
committed by Rodney on Feb 5 2013 (SVN: r192).
-
committed by Julie on Oct 10 2014 and Apr 30 2015 (SVN: r199 and r200).
bug :: PDLAQR1 possible bug?
-
NOT CONFIRMED
-
reported on the LAPACK forum by Sieg Young
-
see Forum topic 4334
-
Not Assigned
bug :: Diagonal element of R not arranged correctly for complex pivoted QR factorization
-
CONFIRMED
-
reported on the scalapack mailing list
-
confirmed by Rodney, Sven and Jim on Thu Oct 20 2011
bug :: uninitialized variables, bug in p?trsm, and problem in xzsep testing (timeout)
-
CORRECTED
-
reported on the forum
-
fix provided by Joost VandeVondele
-
see forum topic 588
-
see forum topic 2625
-
confirmed by Julie Langou on Thu Aug 16 2011
-
committed by Julie on Thu Jul 07 2011 (SVN: r92).
bug :: ROFFZ and IZROW are not initialized in case WANTZ evaluates to .FALSE.
-
CORRECTED
-
confirmed by Julie Langou on Thu Jul 07 2011
-
fix from Julie
-
committed by Julie on Thu Jul 07 2011 (SVN: r92).
bug :: ScaLAPACK does not handle matrix larger than N > sqrt(2^31)
-
CORRECTED
-
Reported several times
-
The following fix works fine. The fix has been provided by John Moyart from CNES, France. It works great for all who have tried it.
-
Other fix: compile scalapack using 64-bit integers
-
committed by Julien on Sat Sep 12 2009 (SVN: r69).
bug :: workspace query not correct for IWORK in PDGECON when no local rows in process row
-
CORRECTED
-
reported by Jill Reese (MathWorks) on Fri Aug 28 2009
-
confirmed by Julien Langou on Fri Aug 28 2009
-
fix from Jill and Julien
-
committed by Julien on Sat Sep 12 2009 (SVN: r68).
BLACS
bug :: bug
-
NOT CONFIRMED
-
reported by Sergey Kuznetsov (Intel)
-
directly sent to Julien
bug :: bug in dlasd4/slasd4
-
CORRECTED
-
reported by Åke Sandgren (HPC2N, Umeå, Sweden) on Tue Mar 3 2009
-
see forum topic 917
bug :: false comments in igamx2d
-
CORRECTED
-
reported by Åke Sandgren (HPC2N, Umeå, Sweden) on Tue Mar 3 2009
-
see forum topic 917