8d0017b831
added a faster block splitter variant
...
that samples 1 in 5 positions.
This variant is fast enough for lazy2 and btlazy2,
but it's less good in combination with post-splitter at higher levels (>= btopt).
2024-10-21 14:56:43 -07:00
e468136677
minor split optimization
...
let's fill the initial stats directly into target fingerprint
2024-10-20 17:16:17 -07:00
e1c373fb8e
updated regression test results
2024-10-20 17:07:43 -07:00
dff9bb2ad2
fixed workspace alignment on non 64-bit systems
2024-10-18 16:47:41 -07:00
6be0ad2036
splitter workspace is now provided by ZSTD_CCtx*
2024-10-18 16:00:36 -07:00
ab44689a44
fix alignment test
...
for non 64-bit systems
2024-10-18 11:20:54 -07:00
85e98dfc05
fixed minor conversion warnings on Visual
2024-10-18 11:16:49 -07:00
56d0b4b3a6
ZSTD_splitBlock_4k() uses externally provided workspace
...
ideally, this workspace would be provided from the ZSTD_CCtx* state
2024-10-17 23:02:59 -07:00
30eb9d0f09
replaced uasan32 test by asan32 test
2024-10-17 17:05:17 -07:00
cf349ce7df
fixing minor formatting issue in 32-bit mode with logs enabled
2024-10-17 16:28:08 -07:00
31bfcce574
fixed VS2010 solution
2024-10-17 15:58:14 -07:00
2f9282b5d8
new Makefile target mesonbuild
...
for easier local testing
2024-10-17 15:42:02 -07:00
b8606b43f6
fixed meson build
2024-10-17 15:35:56 -07:00
db261901fe
fixed zstreamtest
2024-10-17 15:16:57 -07:00
017d4f38f2
fixed c90 comment style
2024-10-17 14:52:49 -07:00
a142f2ec8e
fix assert
2024-10-17 14:50:46 -07:00
99bfda84e6
only split full blocks
...
short term simplification
2024-10-17 14:46:47 -07:00
caf1afc64c
fixed single-library build
2024-10-17 14:41:26 -07:00
fa49eecf4a
fixed kernel build
2024-10-17 13:26:57 -07:00
befde12052
fixed RLE detection test
2024-10-17 13:21:55 -07:00
4786800c52
fix overlap write scenario in presence of incompressible data
2024-10-17 12:55:08 -07:00
9f692af18d
more ZSTD_memset() to apply
2024-10-17 11:40:13 -07:00
9e3d270f40
minor C++-ism
...
though I really wonder if this is a property worth maintaining.
2024-10-17 11:40:13 -07:00
be659c895e
use ZSTD_memset()
...
for better portability on Linux kernel
2024-10-17 11:40:13 -07:00
2d4332e557
do not use new as variable name
2024-10-17 11:40:13 -07:00
f714778f8e
fixed strict C90 semantic
2024-10-17 11:40:13 -07:00
52ed013b3f
XP: add a pre-splitter
...
instead of ingesting only full blocks, make an analysis of data, and infer where to split.
2024-10-17 11:40:13 -07:00
b880f20d52
Merge pull request #4171 from facebook/lvl3_ratio+
...
Improve compression ratio of levels 3 & 4
2024-10-17 11:39:41 -07:00
41d870fbbf
updated regression tests results
2024-10-17 11:06:26 -07:00
ff8e98bebe
enable regression tests at pull request time
...
was transferred from circleci,
but was only triggered on push into dev,
i.e. after pull request is merged.
2024-10-17 09:45:16 -07:00
47d4f5662d
rewrite code in the manner suggested by @terrelln
2024-10-17 09:37:23 -07:00
61d08b0e42
fix test
...
a margin of 4 is insufficient to guarantee compression success.
2024-10-17 09:37:23 -07:00
6326775166
slightly improved compression ratio at levels 3 & 4
...
The compression ratio benefits are small but consistent, i.e. always positive.
On `silesia.tar` corpus, this modification saves ~75 KB at level 3.
The measured speed cost is negligible, i.e. below noise level, between 0 and -1%.
2024-10-17 09:37:23 -07:00
18a42190c2
Merge pull request #4170 from facebook/dict_cSpeed
...
Improve dictionary compression speed
2024-10-16 17:36:49 -07:00
730d2dce41
fix test
2024-10-15 18:44:40 -07:00
c2abfc5ba4
minor improvement to level 3 dictionary compression ratio
2024-10-15 17:58:33 -07:00
e63896eb58
small dictionary compression speed improvement
...
not as good as small-blocks improvement,
but generally positive.
2024-10-15 17:48:35 -07:00
def3ee9548
Merge pull request #4167 from facebook/ci_m32test_faster
...
attempt to make 32-bit tests faster
2024-10-12 01:57:55 -07:00
e6740355e3
attempt parallel test running with -j
2024-10-11 18:01:28 -07:00
6f2e29a234
measure if -O2 makes the test complete faster
2024-10-11 17:30:55 -07:00
1024aa9252
attempt to make 32-bit tests faster
...
this is the longest CI test, reaching ~40mn on last PR
2024-10-11 16:24:25 -07:00
8c38bda935
Merge pull request #4165 from facebook/cspeed_cmov
...
Improve compression speed on small blocks
2024-10-11 16:20:19 -07:00
8e5823b65c
rename variable name
...
findMatch -> matchFound
since it's a test, as opposed to an active search operation.
suggested by @terrelln
2024-10-11 15:38:12 -07:00
83de00316c
fixed parameter ordering in dfast
...
noticed by @terrelln
2024-10-11 15:36:15 -07:00
7ba43091b8
Merge pull request #4164 from facebook/spec_043
...
spec update: huffman prefix code paragraph
2024-10-10 16:56:02 -07:00
fa1fcb08ab
minor: better variable naming
2024-10-10 16:07:20 -07:00
3e7c66acd1
added ascending order example
2024-10-09 01:06:24 -07:00
d45aee43f4
make __asm__ a __GNUC__ specific
2024-10-08 16:38:35 -07:00
741b860fc1
store dummy bytes within ZSTD_match4Found_cmov()
...
feels more logical, better contained
2024-10-08 16:34:40 -07:00
197c258a79
introduce memory barrier to force test order
...
suggested by @terrelln
2024-10-08 15:54:48 -07:00
