| Re: [eigen] Parallel matrix multiplication causes heap allocation |
[ Thread Index |
Date Index
| More lists.tuxfamily.org/eigen Archives
]
Thanks for talking about libxsmm which I did not know about. It is strange that this library did not make its way to the MKL yet.
> On 22 Dec 2016, at 00:18, Benoit Steiner <benoit.steiner.goog@xxxxxxxxx> wrote:
>
> I've just started to merge some support for the libxsmm matrix multiplication kernels into Eigen. These kernels are extremely efficient and perform better than the Eigen ones on Haswell and above.
>
> Note that there is more work to be done, in particular wrt to multi-threading. This will be done over the next few months