Danila Kutenin 49eb18ee4f Optimize vectorscan for aarch64 by using shrn instruction ...

This optimization is based on the thread
https://twitter.com/Danlark1/status/1539344279268691970 and uses
shift right and narrow by 4 instruction https://developer.arm.com/documentation/ddi0596/2020-12/SIMD-FP-Instructions/SHRN--SHRN2--Shift-Right-Narrow--immediate--

To achieve that, I needed to redesign a little movemask into comparemask
and have an additional step towards mask iteration. Our benchmarks
showed 10-15% improvement on average for long matches.

2022-06-26 22:55:45 +00:00

..

bitfield.cpp

util: switch from Boost to std::unordered set/map

2017-08-21 11:14:55 +10:00

bitutils.cpp

bugfix compress128/expand128, add unit tests

2021-02-08 19:20:37 +02:00

charreach.cpp

Initial commit of Hyperscan

2015-10-20 09:13:35 +11:00

compare.cpp

Initial commit of Hyperscan

2015-10-20 09:13:35 +11:00

database.cpp

avx512: CPU detection and platform hints

2017-05-30 13:59:23 +10:00

depth.cpp

util: switch from Boost to std::unordered set/map

2017-08-21 11:14:55 +10:00

fdr_flood.cpp

FDR: Squash buckets of included literals in FDR confirm

2017-08-21 11:12:36 +10:00

fdr_loadval.cpp

unit: use bytecode_ptr instead of aligned_unique_ptr

2017-04-26 15:19:36 +10:00

fdr.cpp

FDR: Squash buckets of included literals in FDR confirm

2017-08-21 11:12:36 +10:00

flat_map.cpp

util: switch from Boost to std::unordered set/map

2017-08-21 11:14:55 +10:00

flat_set.cpp

util: switch from Boost to std::unordered set/map

2017-08-21 11:14:55 +10:00

graph_undirected.cpp

gcc-10: fix hyperscan compile issue

2020-05-25 13:47:53 +00:00

graph.cpp

update copyright year

2017-01-17 11:38:09 +11:00

insertion_ordered.cpp

insertion_ordered_{map,set}: add new containers

2017-08-21 11:25:21 +10:00

lbr.cpp

remove !LBR constraints from merge passes

2017-09-18 13:22:56 +10:00

limex_nfa.cpp

limex: add fast NFA check

2021-01-25 14:13:13 +02:00

main.cpp

msvc: use the vectorcall calling convention

2017-06-09 10:12:02 +10:00

masked_move.cpp

use correct include

2021-02-15 13:54:19 +02:00

multi_bit_compress.cpp

use STL make_unique, remove wrapper header, breaks C++17 compilation

2021-10-12 11:51:34 +03:00

multi_bit.cpp

use STL make_unique, remove wrapper header, breaks C++17 compilation

2021-10-12 11:51:34 +03:00

nfagraph_common.h

ng: split NGWrapper into NGHolder, ExpressionInfo

2017-04-26 15:18:09 +10:00

nfagraph_comp.cpp

ng_calc_components: add Grey box control

2017-04-26 15:18:13 +10:00

nfagraph_equivalence.cpp

ng: split NGWrapper into NGHolder, ExpressionInfo

2017-04-26 15:18:09 +10:00

nfagraph_find_matches.cpp

Add support for Hamming distance approx matching

2018-01-19 06:11:43 -05:00

nfagraph_literal_analysis.cpp

Initial commit of Hyperscan

2015-10-20 09:13:35 +11:00

nfagraph_redundancy.cpp

ng: split NGWrapper into NGHolder, ExpressionInfo

2017-04-26 15:18:09 +10:00

nfagraph_repeat.cpp

depth: make constructor explicit

2017-04-26 15:19:19 +10:00

nfagraph_util.cpp

util: switch from Boost to std::unordered set/map

2017-08-21 11:14:55 +10:00

nfagraph_width.cpp

depth: make constructor explicit

2017-04-26 15:19:19 +10:00

noodle.cpp

align array

2021-02-15 13:54:19 +02:00

pack_bits.cpp

use STL make_unique, remove wrapper header, breaks C++17 compilation

2021-10-12 11:51:34 +03:00

parser.cpp

Initial commit of Hyperscan

2015-10-20 09:13:35 +11:00

partial.cpp

Initial commit of Hyperscan

2015-10-20 09:13:35 +11:00

pqueue.cpp

Initial commit of Hyperscan

2015-10-20 09:13:35 +11:00

repeat.cpp

use STL make_unique, remove wrapper header, breaks C++17 compilation

2021-10-12 11:51:34 +03:00

rose_build_merge.cpp

use STL make_unique, remove wrapper header, breaks C++17 compilation

2021-10-12 11:51:34 +03:00

rose_mask_32.cpp

rose: add new instruction CHECK_MASK_32

2016-10-28 14:43:33 +11:00

rose_mask.cpp

rose: add CHECK_BYTE/CHECK_MASK instructions

2016-08-10 14:57:48 +10:00

rvermicelli.cpp

remove vermicelli.h and replace it with vermicelli.hpp

2021-11-02 22:30:53 +02:00

shuffle.cpp

Fix all ASAN issues in vectorscan

2022-02-18 17:14:51 +00:00

shufti.cpp

no need to convert to size_t

2021-10-12 11:51:35 +03:00

simd_utils.cpp

Fix all ASAN issues in vectorscan

2022-02-18 17:14:51 +00:00

state_compress.cpp

add some debug and minor optimizations in unit test

2020-11-05 19:21:16 +02:00

supervector.cpp

Optimize vectorscan for aarch64 by using shrn instruction

2022-06-26 22:55:45 +00:00

truffle.cpp

shufti/truffle tests: silence ubsan warning

2017-08-21 11:12:16 +10:00

unaligned.cpp

Initial commit of Hyperscan

2015-10-20 09:13:35 +11:00

unicode_set.cpp

Initial commit of Hyperscan

2015-10-20 09:13:35 +11:00

uniform_ops.cpp

unit: avoid UB by making integer literal explicitally unsigned

2019-08-13 14:49:37 +08:00

utf8_validate.cpp

hscollider: fix input length for UTF8 check

2018-06-27 14:04:53 +08:00

util_string.cpp

unit: add PrintTo for ue2_literal

2017-09-18 13:26:18 +10:00

vermicelli.cpp

remove vermicelli.h and replace it with vermicelli.hpp

2021-11-02 22:30:53 +02:00