Many supported cores use the AUTOPREFETCHER_WEAK setting which tries to order...

Many supported cores use the AUTOPREFETCHER_WEAK setting which tries
to order loads and stores to improve streaming performance.  Since significant
gains were reported in http://patchwork.ozlabs.org/patch/534469/ it seems
like a good idea to enable this setting too for -mcpu=generic.  Since the
weak model only keeps the order if it doesn't make the schedule worse, it
should not impact performance adversely on cores that don't show a gain.

    gcc/
        * config/aarch64/aarch64.c (generic_tunings): Update prefetch model.

From-SVN: r247610
This commit is contained in:
Wilco Dijkstra 2017-05-04 17:52:03 +00:00 committed by Wilco Dijkstra
parent 9779b2e87c
commit 3b4c0f7e1e
2 changed files with 5 additions and 1 deletions

View File

@ -1,3 +1,7 @@
2017-05-04 Wilco Dijkstra <wdijkstr@arm.com>
* config/aarch64/aarch64.c (generic_tunings): Update prefetch model.
2017-05-04 Wilco Dijkstra <wdijkstr@arm.com>
* config/aarch64/aarch64.c (cortexa35_tunings): Set jump alignment to 4.

View File

@ -547,7 +547,7 @@ static const struct tune_params generic_tunings =
2, /* min_div_recip_mul_df. */
0, /* max_case_values. */
0, /* cache_line_size. */
tune_params::AUTOPREFETCHER_OFF, /* autoprefetcher_model. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE) /* tune_flags. */
};