Fabian Hoppe

Hi Claudia, here are the versions I use: mpi4py 3.1.3 OpenMPI 4.0.3 heat 1.2.0-dev torch 1.11.0+cu102 Python 3.8.10 (default, Jun 22 2022, 20:18:18) [GCC 9.4.0] Everythin is run in a...

With the qr implementation from the features/436-SVD-block-diag branch I could not reproduce the error, so it looks like that this really fixed the isse 👍

Regarding the SVD i think the following test cases could be of interest: * matrices that are challenging for SVD-algorithms: I think the already implemented Parter matrix should belong to...

I have added the second bullet point from above (randomly generate low-rank matrices with known SVD) to the hSVD-branch #1041

It was a `.h5`-file

I have repeated the experiment on a CPU-cluster with a data set of roughly 180GB size; time is the average over 5 runs each.  I think it is quite...

@ClaudiaComito I have looked up, whether the data sets used for this experiments have been stored in chunked format in the h5-file via checking the `chunks`-attribute of the data sets:...

Stil relevant: #938 is a currently active PR that will resolve this issue. Reviewed within #1109.

see #890 for the particular case of `matmul` on higher dim arrays Reviewed within #1109 : still open and relevant

As far as I understand, computing percentiles in a distributed setting might really pose a problem in terms of quite heavy communication as re-ordering might be necessary. An option might...