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.

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]

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index 42cf76730710efb30132f9f70a5f33d00d9e179a..bdf70787937c19cb75cc90ed3e737e5ea0e9af87 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -611,8 +611,10 @@ 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')
@@ -630,6 +632,7 @@ 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), (op, a, 0))])
    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)])