# distributed-memory QR / TSQR / linear algebra

**URL:** <https://discourse.julialang.org/t/distributed-memory-qr-tsqr-linear-algebra/9849>\
**Category:** Numerics\
**Created:** [March 20, 2018, 11:11pm UTC](https://discourse.julialang.org/t/distributed-memory-qr-tsqr-linear-algebra/9849 "2018-03-20T23:11:48Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![nychiang](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/nychiang/32/3848_2.png) [@nychiang](https://discourse.julialang.org/u/nychiang)\
**Post date:** [March 20, 2018, 11:11pm UTC](https://discourse.julialang.org/t/distributed-memory-qr-tsqr-linear-algebra/9849/1 "2018-03-20T23:11:48Z")

</div>

I’m looking for a distributed-memory parallel TSQR (tall and skinny QR) factorization package in Julia.  
However, it seems that there is no such implementation inside Julia, and what I can do is the following:  
— use MPI and Scalapack to do parallel QR via PDGEQRF @andreasnoack  
( Note that PDGEQRF is not implemented from TSQR algorithm, see lapack working note [www.netlib.org/lapack/lawnspdf/lawn224.pdf](http://www.netlib.org/lapack/lawnspdf/lawn224.pdf) )

Hope someone here can show me that I am wrong, and there is other approaches/packages to use parallel TSQR inside Julia.

Additionally, I wonder if there is any distributed-memory linear algebra package in Julia?

Cheers,

---

<div class="post-metadata">

**Author:** ![simonbyrne](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/simonbyrne/32/19_2.png) [@simonbyrne](https://discourse.julialang.org/u/simonbyrne)\
**Post date:** [March 20, 2018, 11:39pm UTC](https://discourse.julialang.org/t/distributed-memory-qr-tsqr-linear-algebra/9849/2 "2018-03-20T23:39:40Z")

</div>

You could try [Elemental.jl](https://github.com/JuliaParallel/Elemental.jl): it plays nicely with [DistributedArrays.jl](https://github.com/JuliaParallel/DistributedArrays.jl).

It seems like the QR isn’t currently available in the Julia package, but it is in [the underlying library](http://libelemental.org/documentation/0.85/lapack_like/factor/QR.html), so it it should be a matter of adding the necessary wrappers.