Cleanup and optimize SSE/AVX code
authormstembera <MissingEmail@email>
Sun, 9 Aug 2020 23:23:33 +0000 (16:23 -0700)
committerJoost VandeVondele <Joost.VandeVondele@gmail.com>
Mon, 10 Aug 2020 12:38:17 +0000 (14:38 +0200)
commitf948cd008d3a289ebbadc463271f84888e8069ba
tree64922e8090d6b807b2dc47f13ac3e673a53ffa22
parentcb0504028e8830dbc71be53cbd701d78c3d562a1
Cleanup and optimize SSE/AVX code

AVX512 +4% faster
AVX2 +1% faster
SSSE3 +5% faster

passed non-regression STC:
STC https://tests.stockfishchess.org/tests/view/5f31249f90816720665374f6
LLR: 2.96 (-2.94,2.94) {-1.50,0.50}
Total: 17576 W: 2344 L: 2245 D: 12987
Ptnml(0-2): 127, 1570, 5292, 1675, 124

closes https://github.com/official-stockfish/Stockfish/pull/2962

No functional change
src/nnue/layers/affine_transform.h
src/nnue/nnue_accumulator.h
src/nnue/nnue_common.h
src/nnue/nnue_feature_transformer.h