Implications of setting SIGCHLD in relation to NIFs

Jesper Louis Andersen jesper.louis.andersen@REDACTED
Tue Nov 24 19:38:52 CET 2020


On Tue, Nov 24, 2020 at 6:40 PM Max Lapshin <max.lapshin@REDACTED> wrote:

>
> We analyse video streams with neural networks. It is almost impossible
> and useless to run these things in different processes.
>
>
Bandwidth usage is only part of the game. The other part is how large your
machine learning models can be. The vast majority of those are relatively
low bandwidth, i.e., there's not a whole lot of data, but heavy on compute.
Not saying there aren't considerations for your use case, but the solution
is definitely not common, especially with the deeper networks of today.
Clearly a shallow model in a high-bandwidth scenario will have trouble. But
in a low-bandwidth deep model scenario, or where latency isn't as
important, the idea of keeping the model outside of the VM is generally the
simplest one to pull off.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://erlang.org/pipermail/erlang-questions/attachments/20201124/46d0d3bf/attachment.htm>


More information about the erlang-questions mailing list