[PROJ] Vector/SIMD acceleration

[Thomas Knudsen]

yes, but in my case, it calls 4 times the 4-double, the last time
recomputing the
5th and 6th-last coordinates once more (since I assume this is faster than
calling
the serial version twice), but ignores the repeated computations, using
only the
two first elements of the paralleldata structure in the last trip through
the loop...

Den fre. 17. apr. 2020 kl. 14.45 skrev Even Rouault <
even.rouault at spatialys.com>:

> > is this correctly understood?
>
>
>
> Yes, I think so. For example, if you have for a given function an
> implementation for 4-double and the default one for 1-double, if you
> process 14 points, PROJ would call 3 times the 4-double one and 2 times the
> 1-double one.
>
>
>
> --
>
> Spatialys - Geospatial professional services
>
> http://www.spatialys.com
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.osgeo.org/pipermail/proj/attachments/20200417/e2a1e86e/attachment.html>