diff options
author | Jason Ekstrand <jason.ekstrand@intel.com> | 2018-08-14 14:37:39 -0500 |
---|---|---|
committer | Jason Ekstrand <jason.ekstrand@intel.com> | 2018-08-29 14:04:02 -0500 |
commit | 4dd5263663585b55119e49c8dfade015c86aff1a (patch) | |
tree | 9b88bd636f74f3fe7c536dbed1248ec7d1d604f5 | |
parent | 116b47fe3c0395e95b67c6bd3506ab7d6a83393e (diff) |
nir/algebraic: Add more extract_[iu](8|16) optimizations
This adds the "(a << N) >> M" family of mask or sign-extensions. Not a
huge win right now but this pattern will soon be generated by NIR format
lowering code.
Shader-db results on Kaby Lake:
total instructions in shared programs: 15166918 -> 15166916 (<.01%)
instructions in affected programs: 36 -> 34 (-5.56%)
helped: 2
HURT: 0
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
-rw-r--r-- | src/compiler/nir/nir_opt_algebraic.py | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py index 9c890c0eb24..8a0ddf1c325 100644 --- a/src/compiler/nir/nir_opt_algebraic.py +++ b/src/compiler/nir/nir_opt_algebraic.py @@ -543,13 +543,23 @@ optimizations = [ ('unpack_64_2x32_split_y', a)), a), # Byte extraction + (('ushr', ('ishl', 'a@32', 24), 24), ('extract_u8', a, 0), '!options->lower_extract_byte'), + (('ushr', ('ishl', 'a@32', 16), 24), ('extract_u8', a, 1), '!options->lower_extract_byte'), + (('ushr', ('ishl', 'a@32', 8), 24), ('extract_u8', a, 2), '!options->lower_extract_byte'), (('ushr', 'a@32', 24), ('extract_u8', a, 3), '!options->lower_extract_byte'), + (('ishr', ('ishl', 'a@32', 24), 24), ('extract_i8', a, 0), '!options->lower_extract_byte'), + (('ishr', ('ishl', 'a@32', 16), 24), ('extract_i8', a, 1), '!options->lower_extract_byte'), + (('ishr', ('ishl', 'a@32', 8), 24), ('extract_i8', a, 2), '!options->lower_extract_byte'), + (('ishr', 'a@32', 24), ('extract_i8', a, 3), '!options->lower_extract_byte'), (('iand', 0xff, ('ushr', a, 16)), ('extract_u8', a, 2), '!options->lower_extract_byte'), (('iand', 0xff, ('ushr', a, 8)), ('extract_u8', a, 1), '!options->lower_extract_byte'), (('iand', 0xff, a), ('extract_u8', a, 0), '!options->lower_extract_byte'), # Word extraction + (('ushr', ('ishl', 'a@32', 16), 16), ('extract_u16', a, 0), '!options->lower_extract_word'), (('ushr', 'a@32', 16), ('extract_u16', a, 1), '!options->lower_extract_word'), + (('ishr', ('ishl', 'a@32', 16), 16), ('extract_i16', a, 0), '!options->lower_extract_word'), + (('ishr', 'a@32', 16), ('extract_i16', a, 1), '!options->lower_extract_word'), (('iand', 0xffff, a), ('extract_u16', a, 0), '!options->lower_extract_word'), # Subtracts |