diff options
| author | Wilco Dijkstra <wdijkstr@arm.com> | 2017-05-05 09:40:01 +0000 |
|---|---|---|
| committer | Wilco Dijkstra <wilco@gcc.gnu.org> | 2017-05-05 09:40:01 +0000 |
| commit | 9d29ae83ed27a06cdd729cd7f0cceb12c28b91dc (patch) | |
| tree | 8e1a45a11552c8773d1770494a16e028b354522b /gcc/tree-vrp.c | |
| parent | dfae9048a0ce06a8f240dd17c282cb1e1eaf2097 (diff) | |
| download | gcc-9d29ae83ed27a06cdd729cd7f0cceb12c28b91dc.zip gcc-9d29ae83ed27a06cdd729cd7f0cceb12c28b91dc.tar.gz gcc-9d29ae83ed27a06cdd729cd7f0cceb12c28b91dc.tar.bz2 | |
Code scheduling for Cortex-A53 isn't as good as it could be.
Code scheduling for Cortex-A53 isn't as good as it could be. It turns out
code runs faster overall if we place loads and stores with a dependency
closer together. To achieve this effect, this patch adds a bypass between
cortex_a53_load1 and cortex_a53_load*/cortex_a53_store* if the result of an
earlier load is used in an address calculation. This significantly improved
benchmark scores in a proprietary benchmark suite.
gcc/
* config/arm/aarch-common.c (arm_early_load_addr_dep_ptr):
New function.
(arm_early_store_addr_dep_ptr): Likewise.
* config/arm/aarch-common-protos.h
(arm_early_load_addr_dep_ptr): Add prototype.
(arm_early_store_addr_dep_ptr): Likewise.
* config/arm/cortex-a53.md: Add new bypasses.
From-SVN: r247631
Diffstat (limited to 'gcc/tree-vrp.c')
0 files changed, 0 insertions, 0 deletions