nir/algebraic: Add missing 16-bit extract_[iu]8 patterns

No shader-db changes on any Intel platform.

v2: Use a loop to generate patterns.  Suggested by Jason.

Reviewed-by: Matt Turner <mattst88@gmail.com> [v1]
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
This commit is contained in:
Ian Romanick
2019-02-27 20:15:32 -08:00
parent 55c1ac4b75
commit 18e4bf65de
+3
View File
@@ -604,8 +604,10 @@ optimizations = [
('unpack_64_2x32_split_y', a)), a),
# Byte extraction
(('ushr', 'a@16', 8), ('extract_u8', a, 1), '!options->lower_extract_byte'),
(('ushr', 'a@32', 24), ('extract_u8', a, 3), '!options->lower_extract_byte'),
(('ushr', 'a@64', 56), ('extract_u8', a, 7), '!options->lower_extract_byte'),
(('ishr', 'a@16', 8), ('extract_i8', a, 1), '!options->lower_extract_byte'),
(('ishr', 'a@32', 24), ('extract_i8', a, 3), '!options->lower_extract_byte'),
(('ishr', 'a@64', 56), ('extract_i8', a, 7), '!options->lower_extract_byte'),
(('iand', 0xff, a), ('extract_u8', a, 0), '!options->lower_extract_byte')
@@ -623,6 +625,7 @@ optimizations.extend([(('extract_u8', ('extract_u16', a, 1), 0), ('extract_u8',
# After the ('extract_[iu]8', a, 3) patterns, above, trigger, there will be
# patterns like those below.
for op in ('extract_u8', 'extract_i8'):
optimizations.extend([((op, ('ishl', 'a@16', 8), 1), ('extract_u8', a, 0))])
optimizations.extend([((op, ('ishl', 'a@32', 24 - 8 * i), 3), ('extract_u8', a, i)) for i in range(2, -1, -1)])
optimizations.extend([((op, ('ishl', 'a@64', 56 - 8 * i), 7), ('extract_u8', a, i)) for i in range(6, -1, -1)])