fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-25 21:40:08 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

nir/opt_algebraic: alternative 8bit pack_[us]norm_4x8 lowering

Browse source 
Foz-DB Navi21:
Totals from 42 (0.05% of 79395) affected shaders:
Instrs: 2709529 -> 2705848 (-0.14%)
CodeSize: 14720732 -> 14711384 (-0.06%); split: -0.06%, +0.00%
VGPRs: 4096 -> 4104 (+0.20%)
Latency: 17907612 -> 17904468 (-0.02%); split: -0.02%, +0.00%
InvThroughput: 4723551 -> 4722649 (-0.02%); split: -0.02%, +0.00%
Copies: 223516 -> 219819 (-1.65%)
Branches: 109578 -> 109594 (+0.01%); split: -0.00%, +0.02%
VALU: 1730848 -> 1727151 (-0.21%)

Tested-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Jason Ekstrand <jason.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28882>
This commit is contained in:
Georg Lehmann 2024-04-24 08:51:14 +02:00 • committed by Marge Bot
parent f66883a875
commit 75b1fa9263
1 changed files with 12 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
src/compiler/nir/nir_opt_algebraic.py
View file

@ -2240,7 +2240,12 @@ optimizations.extend([
(('pack_unorm_4x8', 'v'),
('pack_uvec4_to_uint',
('f2u32', ('fround_even', ('fmul', ('fsat', 'v'), 255.0)))),
'options->lower_pack_unorm_4x8'),
'options->lower_pack_unorm_4x8 && !options->has_pack_32_4x8'),
(('pack_unorm_4x8', 'v'),
('pack_32_4x8',
('f2u8', ('fround_even', ('fmul', ('fsat', 'v'), 255.0)))),
'options->lower_pack_unorm_4x8 && options->has_pack_32_4x8'),
(('pack_snorm_2x16', 'v'),
('pack_uvec2_to_uint',
@ -2250,7 +2255,12 @@ optimizations.extend([
(('pack_snorm_4x8', 'v'),
('pack_uvec4_to_uint',
('f2i32', ('fround_even', ('fmul', ('fmin', 1.0, ('fmax', -1.0, 'v')), 127.0)))),
'options->lower_pack_snorm_4x8'),
'options->lower_pack_snorm_4x8 && !options->has_pack_32_4x8'),
(('pack_snorm_4x8', 'v'),
('pack_32_4x8',
('f2i8', ('fround_even', ('fmul', ('fmin', 1.0, ('fmax', -1.0, 'v')), 127.0)))),
'options->lower_pack_snorm_4x8 && options->has_pack_32_4x8'),
(('unpack_unorm_2x16', 'v'),
('fdiv', ('u2f32', ('vec2', ('extract_u16', 'v', 0),