diff options
author | Siddhesh Poyarekar <siddhesh@sourceware.org> | 2018-08-03 01:51:42 +0000 |
---|---|---|
committer | Siddhesh Poyarekar <siddhesh@gcc.gnu.org> | 2018-08-03 01:51:42 +0000 |
commit | 561d011953965a425463900548c29187c2898179 (patch) | |
tree | c12a319bd1393dcd45fb07c736b6ba9f1da656ea /gcc/ada/xnmake.adb | |
parent | 90d981fb124adf29d3e0da41ea7954058c0c8601 (diff) | |
download | gcc-561d011953965a425463900548c29187c2898179.zip gcc-561d011953965a425463900548c29187c2898179.tar.gz gcc-561d011953965a425463900548c29187c2898179.tar.bz2 |
[aarch64] Fix falkor pipeline description for dup<q>
There was a typo in the pipeline description where DUP was assigned to
the vector pipes for quad mode ops when it really only uses the VTOG
pipes. Fixing this does not show any noticeable difference in
performance (there's a very small bump of 1.7% in x264 but that's
about it) in my tests but is the more precise description of operations
for falkor.
* config/aarch64/falkor.md (falkor_am_1_vxvy_vxvy): Move
neon_dup_q to...
(falkor_am_1_gtov_gtov): ... a new insn reservation.
From-SVN: r263285
Diffstat (limited to 'gcc/ada/xnmake.adb')
0 files changed, 0 insertions, 0 deletions