Intel® oneAPI Math Kernel Library
Ask questions and share information with other developers who use Intel® Math Kernel Library.
6652 Discussions

Potential bug in complex versions of mkl_?omatadd

AC_Simon
Beginner
756 Views

Hi all,

I think came upon a bug in the mkl_?omatadd routine, especially the complex versions. If both matrices A and B are conjugate transposed, the matrix A is only conjugated. I configured the zomatadd.c example file that intel provided in order to show that this is the case:

Screenshot 2020-10-20 at 13.26.30.png

Screenshot 2020-10-20 at 13.23.00.png

As you can see the results are the same, which is incorrect. The second computation gives the wrong answer.

There are actually two more cases I found, where the result is wrong:

  1. A transposed and B conjugated: This combination conjugate transposes A instead of just transposing it.
  2. A conjugated and B transposed: This combination conjugate transposes B instead of just transposing it.

The example file is also attached for you to test it.

 

Best regards,

Simon

0 Kudos
6 Replies
Gennady_F_Intel
Moderator
748 Views

what version of mkl do you use?


AC_Simon
Beginner
741 Views

I'm using the mkl that comes with 2020 update 2 parallel studio. I'm on MacOS. 

Gennady_F_Intel
Moderator
720 Views

Yes, you are right, that's the issue. You may escalate the case to Intel Online Service Center against Intel MKL.


AC_Simon
Beginner
711 Views

Thanks for confirming the issue. There was already a ticket created by Khoros, is that enough? 

Gennady_F_Intel
Moderator
540 Views

the fix of the issue has been released in the latest oneMKL 2021.2 which available for download.


Gennady_F_Intel
Moderator
540 Views

The issue is closing and we will no longer respond to this thread. If you require additional assistance from Intel, please start a new thread. Any further interaction in this thread will be considered community only.



Reply