OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

nir: handle negatives in ffma reassociation optimisation

Browse Source 
shader-db results Iris (BDW):

total instructions in shared programs: 16632076 -> 16631057 (<.01%)
instructions in affected programs: 48010 -> 46991 (-2.12%)
helped: 47
HURT: 6

total cycles in shared programs: 915266726 -> 915263622 (<.01%)
cycles in affected programs: 1182283 -> 1179179 (-0.26%)
helped: 18
HURT: 27

total loops in shared programs: 4929 -> 4929 (0.00%)
loops in affected programs: 0 -> 0
helped: 0
HURT: 0

total spills in shared programs: 18834 -> 18801 (-0.18%)
spills in affected programs: 525 -> 492 (-6.29%)
helped: 3
HURT: 0

total fills in shared programs: 23008 -> 22981 (-0.12%)
fills in affected programs: 435 -> 408 (-6.21%)
helped: 3
HURT: 0

Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8608>
This commit is contained in:
Timothy Arceri
2021-01-21 15:38:45 +11:00
committed by Marge Bot
parent b4f7535ba2
commit 9f474bd4b4
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -2302,6 +2302,8 @@ late_optimizations = [
('ffma', a, b, ('ffma', c, d, ('ffma', e, 'f', 'g'))), '(info->stage != MESA_SHADER_VERTEX && info->stage != MESA_SHADER_GEOMETRY) && !options->intel_vec4'),
(('~fadd', ('ffma(is_used_once)', a, b, ('fmul', 'c(is_not_const_and_not_fsign)', 'd(is_not_const_and_not_fsign)') ), 'e(is_not_const)'),
('ffma', a, b, ('ffma', c, d, e)), '(info->stage != MESA_SHADER_VERTEX && info->stage != MESA_SHADER_GEOMETRY) && !options->intel_vec4'),
(('~fadd', ('fneg', ('ffma(is_used_once)', a, b, ('ffma', c, d, ('fmul', 'e(is_not_const_and_not_fsign)', 'f(is_not_const_and_not_fsign)')))), 'g(is_not_const)'),
('ffma', ('fneg', a), b, ('ffma', ('fneg', c), d, ('ffma', ('fneg', e), 'f', 'g'))), '(info->stage != MESA_SHADER_VERTEX && info->stage != MESA_SHADER_GEOMETRY) && !options->intel_vec4'),
# Section 8.8 (Integer Functions) of the GLSL 4.60 spec says:
#