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

nir/algebraic: optimize iand/ior of (n)eq zero when umax/umin not available

Browse Source 
Before 8e1b75b330 ("nir/algebraic: optimize iand/ior of (n)eq zero") this
optimization didn't need the use of umax/umin. VC4 HW supports only signed
integer max/min operations.

lower_umin and lower_umax are added to allow enabling previous optimizations
behaviour for this cases.

Fixes: 8e1b75b330 ("nir/algebraic: optimize iand/ior of (n)eq zero")
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7083>
This commit is contained in:
Jose Maria Casanova Crespo
2020-10-09 18:33:26 +02:00
parent 210db65b1a
commit e7127b3468
2 changed files with 12 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/compiler/nir/nir.h
View File

@@ -3160,6 +3160,12 @@ typedef struct nir_shader_compiler_options {
/** enables rules to lower iabs to ineg+imax */
bool lower_iabs;
/** enable rules that avoid generating umax from signed integer ops */
bool lower_umax;
/** enable rules that avoid generating umin from signed integer ops */
bool lower_umin;
/* lower fdph to fdot4 */
bool lower_fdph;

10
src/compiler/nir/nir_opt_algebraic.py
View File

@@ -738,10 +738,12 @@ optimizations.extend([
# Integer sizes
for s in [8, 16, 32, 64]:
optimizations.extend([
(('iand', ('ieq', 'a@{}'.format(s), 0), ('ieq', 'b@{}'.format(s), 0)), ('ieq', ('umax', a, b), 0)),
(('ior', ('ieq', 'a@{}'.format(s), 0), ('ieq', 'b@{}'.format(s), 0)), ('ieq', ('umin', a, b), 0)),
(('iand', ('ine', 'a@{}'.format(s), 0), ('ine', 'b@{}'.format(s), 0)), ('ine', ('umin', a, b), 0)),
(('ior', ('ine', 'a@{}'.format(s), 0), ('ine', 'b@{}'.format(s), 0)), ('ine', ('umax', a, b), 0)),
(('iand', ('ieq', 'a@{}'.format(s), 0), ('ieq', 'b@{}'.format(s), 0)), ('ieq', ('ior', a, b), 0), 'options->lower_umax'),
(('ior', ('ine', 'a@{}'.format(s), 0), ('ine', 'b@{}'.format(s), 0)), ('ine', ('ior', a, b), 0), 'options->lower_umin'),
(('iand', ('ieq', 'a@{}'.format(s), 0), ('ieq', 'b@{}'.format(s), 0)), ('ieq', ('umax', a, b), 0), '!options->lower_umax'),
(('ior', ('ieq', 'a@{}'.format(s), 0), ('ieq', 'b@{}'.format(s), 0)), ('ieq', ('umin', a, b), 0), '!options->lower_umin'),
(('iand', ('ine', 'a@{}'.format(s), 0), ('ine', 'b@{}'.format(s), 0)), ('ine', ('umin', a, b), 0), '!options->lower_umin'),
(('ior', ('ine', 'a@{}'.format(s), 0), ('ine', 'b@{}'.format(s), 0)), ('ine', ('umax', a, b), 0), '!options->lower_umax'),
# True/False are ~0 and 0 in NIR. b2i of True is 1, and -1 is ~0 (True).
(('ineg', ('b2i{}'.format(s), 'a@{}'.format(s))), a),