mirrors/mesa
0
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2024-12-02 22:54:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

nir/algebraic: Optimize some ifind_msb to ufind_msb

Browse Source 
On Intel platforms, the uclz lowering if ufind_msb is either one
instruction better (Gfx7 and newer) or two instructions better (all
older platforms) than the ifind_msb implementations.

On platforms that use lower_find_msb_to_reverse, there should be no
difference.

All Haswell and newer Intel platforms had similar results. (Ice Lake shown)
total instructions in shared programs: 19938662 -> 19938634 (<.01%)
instructions in affected programs: 850 -> 822 (-3.29%)
helped: 2 / HURT: 0

total cycles in shared programs: 858467067 -> 858465538 (<.01%)
cycles in affected programs: 10080 -> 8551 (-15.17%)
helped: 2 / HURT: 0

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19042>
This commit is contained in:
Ian Romanick 2022-10-10 13:42:56 -07:00 committed by Marge Bot
parent db6d1edc1b
commit 831f9d3f61
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/compiler/nir/nir_opt_algebraic.py
View File

@ -1814,6 +1814,8 @@ optimizations.extend([
(('find_lsb', ('bitfield_reverse', a)), ('ufind_msb_rev', a), 'options->has_find_msb_rev'),
(('ufind_msb_rev', ('bitfield_reverse', a)), ('find_lsb', a), '!options->lower_find_lsb'),
(('ifind_msb', ('f2i32(is_used_once)', a)), ('ufind_msb', ('f2i32', ('fabs', a)))),
(('~fmul', ('bcsel(is_used_once)', c, -1.0, 1.0), b), ('bcsel', c, ('fneg', b), b)),
(('~fmul', ('bcsel(is_used_once)', c, 1.0, -1.0), b), ('bcsel', c, b, ('fneg', b))),
(('~fmulz', ('bcsel(is_used_once)', c, -1.0, 1.0), b), ('bcsel', c, ('fneg', b), b)),