| commit | f26bb6c74a973fde3d2783ac35324d5ce8def814 | [log] [tgz] |
|---|---|---|
| author | Artem Serov <artem.serov@linaro.org> | Fri Sep 01 10:59:03 2017 +0100 |
| committer | Artem Serov <artem.serov@linaro.org> | Thu Sep 07 21:29:41 2017 +0100 |
| tree | 70149908a20503dfaf1276d04d561024f3441c6f | |
| parent | 66e3af9ce5b3aaa43e5ce3bce8233235af139072 [diff] |
ARM64: Tune SIMD loop unrolling factor heuristic.
Improve SIMD loop unrolling factor heuristic for ARM64 by
accounting for max desired loop size, trip_count, etc. The
following example shows 21% perf increase:
for (int i = 0; i < LENGTH; i++) {
bc[i] = ba[i]; // Byte arrays
}
Test: test-art-host, test-art-target.
Change-Id: Ic587759c51aa4354df621ffb1c7ce4ebd798dfc1