32 Commits

Author SHA1 Message Date
G.E
7fd45f864c next batch for cppeheck, addressing syntaxError and
constParameterPointer
2024-04-24 17:32:09 +03:00
Konstantinos Margaritis
d3ff893871 prefetch works best when addresses are 64-byte aligned 2021-10-12 11:50:32 +03:00
Konstantinos Margaritis
521f233cfd Revert "replace long macro and switch statement with function pointer array and branchless execution"
This reverts commit cc9dfed2494d709aac79051c29adb0a563903ba9.
2021-10-12 11:50:32 +03:00
Konstantinos Margaritis
92916e311f replace long macro and switch statement with function pointer array and branchless execution 2021-10-12 11:50:32 +03:00
Konstantinos Margaritis
87413fbff0 optimize get_conf_stride_1() 2021-01-25 12:13:35 +02:00
Konstantinos Margaritis
4686ac47b6 replace andn() by explicit bitops and group loads/stores, gives ~1% gain 2021-01-25 12:13:35 +02:00
Konstantinos Margaritis
b62247a36e borrow cache prefetching tricks from the Marvell port, seem to improve performance by 5-28% 2021-01-25 12:13:35 +02:00
Konstantinos Margaritis
39945b7775 clear zones array 2020-12-03 19:30:50 +02:00
Konstantinos Margaritis
9f3ad89ed6 move andn helper function to bitutils.h 2020-09-22 12:17:27 +03:00
Chang, Harry
2b1d3383aa replace "_avx2" with "_fat". 2017-08-21 11:14:59 +10:00
Wang, Xiang W
86c5f7feb1 FDR: Squash buckets of included literals in FDR confirm
- Change the compile of literal matchers to two passes.
 - Reverse the bucket assignment in FDR, bucket with longer literals has
   smaller bucket id.
 - Squash the buckets of included literals and jump to the the program of
   included literals directly from parent literal program without going
   through FDR confirm for included iterals.
2017-08-21 11:12:36 +10:00
Wang, Xiang W
67a8f43355 literal matchers: change context passed to callback to scratch 2017-08-21 11:12:36 +10:00
Justin Viiret
b126cbf556 fdr/teddy: simplify computing of confirm base 2017-08-21 10:39:00 +10:00
Justin Viiret
9bdd370163 fdr: align major structures to cachelines 2017-08-21 10:38:59 +10:00
Matthew Barr
cd418ea6a8 Wrapper for system intrin header 2017-04-26 15:18:26 +10:00
Matthew Barr
8201183138 Check compiler architecture flags in one place 2017-04-26 15:18:26 +10:00
Wang, Xiang W
448ce8a496 UE-3098: add unaligned load for andn without BMI 2017-04-26 15:17:03 +10:00
Wang, Xiang W
ffab97ca8c FDR: delete dead confirm code 2017-04-26 15:16:27 +10:00
Wang, Xiang W
90216921b0 FDR: front end loop improvement 2017-04-26 15:11:10 +10:00
Alex Coyte
8af4850d85 remove 'fast teddy' models 2017-04-26 14:43:43 +10:00
Wang, Xiang W
df7bc22ae0 fdr: remove confirm split and pull-back 2017-04-26 14:43:09 +10:00
Justin Viiret
68bf473e2e fdr: move long literal handling into Rose
Move the hash table used for long literal support in streaming mode from
FDR to Rose, and introduce new instructions CHECK_LONG_LIT and
CHECK_LONG_LIT_NOCASE for doing literal confirm for long literals.

This simplifies FDR confirm, and guarantees that HWLM matchers will only
be used for literals < 256 bytes long.
2016-10-28 14:52:26 +11:00
Justin Viiret
9346a9090e fdr: remove groups from struct FDR_Runtime_Args 2016-08-10 14:55:52 +10:00
Justin Viiret
85f049edb2 fdr: remove extra control ptr 2016-08-10 14:55:51 +10:00
Matthew Barr
e3d416a6ea Apply some consistency to the names we give shifts 2016-07-08 11:07:50 +10:00
Matthew Barr
4d6934fc77 Move limex specific shuffle utils and ssse3 funcs 2016-07-08 11:07:50 +10:00
Justin Viiret
95f35aad0e fdr: ensure 16 bytes of pre-history in block mode 2016-05-18 16:28:27 +10:00
Mohammad Abdul Awal
ed772380c0 teddy: remove python codegen, refactor code
Major cleanup of the Teddy runtime code. Removes python code generation,
splits AVX2 models into their own file, improves readability.
2016-05-18 16:28:11 +10:00
Justin Viiret
1a373d0619 fdr: confVal load can be unaligned 2016-05-18 16:25:35 +10:00
Mohammad Abdul Awal
598f0565cf fdr: Remove python codegen, add safezones 2016-05-18 16:22:52 +10:00
Mohammad Abdul Awal
313822c157 FDR runtime simplification
Removed static specialisation of domains.
2015-11-20 14:44:43 +11:00
Matthew Barr
904e436f11 Initial commit of Hyperscan 2015-10-20 09:13:35 +11:00