There is a lot to read every time MATLAB releases a new version. Here is a summary of what has changed in 2016a from the eyes of someone doing HPC/Scientific Computing/Numerical Analysis. This means I will leave off a lot, and you should check it out yourself but if you’re using MATLAB for science then this may cover most of the things you care about.

1. Support for sparse matrices on the GPU. A nice addition is sprand and pcg (Preconditioned Conjugate Gradient solvers) for sprase GPU matrices.
2. One other big change in the parallel computing toolbox is you can now set nonlinear solvers to estimate gradients and Jacobians in parallel. This should be a nice boost to the MATLAB optimization toolbox.
3. In the statistics and machine learning toolbox, they added some algorithms for high dimensional data and now let you run kmeans on a GPU.
4. If you are using Distributed Computing Servers, then you’ll be glad to hear that linear solvers (backslash,cgs,pcg) now work on distributed arrays.
5. Bioinformatics toolbox is virtually unchanged.
6. The PDE solver is pretty much the same, but can handle eigenvalue problems.
7. MATLAB finally has a unit testing framework.

To me, this seems like a pretty quiet release. The new editor in the style of IPython/IJulia/Mathematica has never been that useful for me making larger numerical packages, though for some it could help writing scientific journals. It seems a lot has been put into more Simulink functionality this release which I never use. All in all, after some strong updates to the parallel computing toolbox (massive upgrades in GPU computing the last few times) and a JIT compiler, it seems the focus on performance has slowed a bit.

Honestly, I think what they really need to tackle next is multiple GPU linear algebra. With the availability of CuBLASxt as a way to perform such calculations, and with the leading GPU (the Tesla K80) being a dual GPU, it seems like a step that shouldn’t be too hard but could benefit a lot of people.