# Multithreading by MUMPS or SUPERLU

**URL:** <https://fenicsproject.discourse.group/t/multithreading-by-mumps-or-superlu/1989>\
**Category:** Linear Algebra\
**Created:** [November 26, 2019, 1:59pm UTC](https://fenicsproject.discourse.group/t/multithreading-by-mumps-or-superlu/1989 "2019-11-26T13:59:55Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![RossMech](https://yyz2.discourse-cdn.com/free1/user_avatar/fenicsproject.discourse.group/rossmech/32/390_2.png) [@RossMech](https://fenicsproject.discourse.group/u/RossMech)\
**Post date:** [November 26, 2019, 1:59pm UTC](https://fenicsproject.discourse.group/t/multithreading-by-mumps-or-superlu/1989/1 "2019-11-26T13:59:55Z")

</div>

Can anyone say how multithreading approach is working in fenics by usage of, f.e. MUMPS or SUPERLU solver and how it is possible to make to make it parallel via shared memory parallel approach?

---

<div class="post-metadata">

**Author:** ![dparsons](https://avatars.discourse-cdn.com/v4/letter/d/5e9695/32.png) [@dparsons](https://fenicsproject.discourse.group/u/dparsons)\
**Post date:** [November 21, 2021, 7:42pm UTC](https://fenicsproject.discourse.group/t/multithreading-by-mumps-or-superlu/1989/2 "2021-11-21T19:42:48Z")

</div>

Probably you want an optimized BLAS implementation such as OpenBLAS, configured with pthreads or openmp.

cf. [SLEPC solver running in Parallel - #2 by dparsons](https://fenicsproject.discourse.group/t/slepc-solver-running-in-parallel/6514/2)