nir/algebraic: Add missing 64-bit extract_[iu]8 patterns

No shader-db changes on any Intel platform.

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

v3: Fix a copy-and-paste bug in the extract_[ui] of ishl loop that would
replace an extract_i8 with and extract_u8.  This broke ~180 tests.  This
bug was introduced in v2.

Reviewed-by: Matt Turner <mattst88@gmail.com> [v1]
Reviewed-by: Dylan Baker <dylan@pnwbakers.com> [v2]
Acked-by: Jason Ekstrand <jason@jlekstrand.net> [v2]
This commit is contained in:
Ian Romanick
2019-02-27 20:12:46 -08:00
parent bc17f5a2a3
commit cbad201c2b

View File

@@ -612,7 +612,9 @@ optimizations = [
# Byte extraction
(('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@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')
]
@@ -629,6 +631,7 @@ optimizations.extend([(('extract_u8', ('extract_u16', a, 1), 0), ('extract_u8',
# patterns like those below.
for op in ('extract_u8', 'extract_i8'):
optimizations.extend([((op, ('ishl', 'a@32', 24 - 8 * i), 3), (op, a, i)) for i in range(2, -1, -1)])
optimizations.extend([((op, ('ishl', 'a@64', 56 - 8 * i), 7), (op, a, i)) for i in range(6, -1, -1)])
optimizations.extend([
# Word extraction