Yoan Picchi 7054378c93 Speed up truffle with 256b TBL instructions ...

256b wide SVE vectors allow some simplification of truffle.
Up to 40% speedup on graviton3. Going from 12500 MB/s to 17000 MB/s
onhe microbenchmark.
SVE2 also offer this capability for 128b vector with a speedup around
25% compared to normal SVE

Add unit tests and benchmark for this wide variant

Signed-off-by: Yoan Picchi <yoan.picchi@arm.com>

2024-05-22 16:13:53 +00:00

..

compiler

Merge branch 'develop' into wip-cppcheck271-part2

2024-05-17 11:08:09 +03:00

fdr

Merge pull request #287 from gtsoul-tech/bugFix/cppcheck-cStylecasts-Part4

2024-05-21 15:59:51 +03:00

hwlm

Speed up truffle with 256b TBL instructions

2024-05-22 16:13:53 +00:00

nfa

Speed up truffle with 256b TBL instructions

2024-05-22 16:13:53 +00:00

nfagraph

Merge pull request #283 from isildur-g/wip-cppcheck271-part2

2024-05-21 15:52:15 +03:00

parser

Merge pull request #283 from isildur-g/wip-cppcheck271-part2

2024-05-21 15:52:15 +03:00

rose

Speed up truffle with 256b TBL instructions

2024-05-22 16:13:53 +00:00

smallwrite

Merge pull request #287 from gtsoul-tech/bugFix/cppcheck-cStylecasts-Part4

2024-05-21 15:59:51 +03:00

som

constVariablePointer

2024-05-02 14:30:18 +03:00

util

Speed up truffle with 256b TBL instructions

2024-05-22 16:13:53 +00:00

alloc.c

msvc: use the vectorcall calling convention

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

allocator.h

Initial commit of Hyperscan

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

crc32.c

variableScopeFix

2024-04-29 13:28:16 +03:00

crc32.h

Initial commit of Hyperscan

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

database.c

remove Windows/ICC support

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

database.h

cstylecasts suppress,fixes

2024-05-20 17:09:30 +03:00

dispatcher.c

static dispatch for fat runtimes. eliminates the need for ifunc.

2024-04-19 12:32:00 +03:00

grey.cpp

tools: add catches for C++ exceptions

2019-01-21 09:59:37 +08:00

grey.h

DFA state compression: 16-bit wide and sherman co-exist

2019-01-21 09:56:37 +08:00

hs_common.h

remove Windows/ICC support

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

hs_compile.h

Logical Combination: bypass combination flag in hs_expression_info.

2022-08-29 15:03:14 +03:00

hs_internal.h

Logical Combination: bypass combination flag in hs_expression_info.

2022-08-29 15:03:14 +03:00

hs_runtime.h

Windows porting: port hyperscan and chimera tools to windows.

2018-07-09 11:40:43 -04:00

hs_valid_platform.c

False positive knownConditionTrueFalse

2024-05-15 17:01:02 +03:00

hs_version.c

msvc: use the vectorcall calling convention

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

hs_version.h.in

Fix version getting out of sync #175

2023-10-03 09:57:10 +03:00

hs.cpp

Fix C-style casts

2024-05-16 12:03:42 +03:00

hs.h

Fix version getting out of sync #175

2023-10-03 09:57:10 +03:00

report.h

Logical combination: support EOD match from purely negative case.

2019-08-13 14:50:07 +08:00

runtime.c

Fix remaining marked as done const* cppcheck warnings

2024-05-15 10:52:31 +03:00

scratch_dump.cpp

multibit, fatbit: make _size build-time only

2016-12-14 15:28:54 +11:00

scratch_dump.h

Initial commit of Hyperscan

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

scratch.c

Fix false positive duplicateAssignExpression warnings

2024-05-11 23:13:45 +03:00

scratch.h

next batch for cppeheck, addressing syntaxError and

2024-04-24 17:32:09 +03:00

state.h

scratch: remove quick validity check

2023-09-05 13:58:17 +03:00

stream_compress_impl.h

Fix unreadVariable warning

2024-05-15 17:05:50 +03:00

stream_compress.c

multibit compression support

2017-08-21 11:19:11 +10:00

stream_compress.h

support dynamic stream compression

2017-08-21 11:18:54 +10:00

ue2common.h

adding ifndef around HS_PUBLIC_API definition so that vectorscan can be statically linked into another shared library without exporting symbols

2023-08-23 11:07:56 -05:00