This is the mail archive of the
mailing list for the GCC project.
Re: Autovectorized HIRLAM - latest results.
On Oct 29, 2007 10:49 AM, Dorit Nuzman <DORIT@il.ibm.com> wrote:
> I wonder if it's versioning-for-aliasing (run-time dependence testing) that
> was responsible for a lot of the new vectorizable loops
It is then possible that the code size noticeably increased. Toon
could you provide more data on the size of the executables with and
without vectorization, and also:
$ grep 'versioning for alias checks' HL_Prepare_00.html | wc -l
AMD - GNU Tools