A bit off topic: if one is not careful and mixes multithreaded Blas/Lapack + multithreading via TBB in deal.II, then calls to Lapack's invert() can take 1.371e+03s instead of 1.445e+00s ;-)
p.s. threading in Spack's Openblas and friends is being reworked here https://github.com/LLNL/spack/pull/5340 Regards, Denis. -- The deal.II project is located at http://www.dealii.org/ For mailing list/forum options, see https://groups.google.com/d/forum/dealii?hl=en --- You received this message because you are subscribed to the Google Groups "deal.II User Group" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/d/optout.
