AuroraMiddleware/zstd
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
6,948 Commits 1 Branch 0 Tags 27 MiB
2d5201b0ab
Commit Graph

491 Commits

Author SHA1 Message Date
Yann Collet
2d5201b0ab removed wildcopy8() 
which is no longer used,
noticed by @davidbolvansky
 2019-10-16 14:51:33 -07:00
Dávid Bolvanský
1ab1a40c9c Fixed one more place 2019-09-23 21:32:56 +02:00
Dávid Bolvanský
1f7228c040 Use clz ^ 31 instead of 31 - clz; better codegen for GCC 2019-09-23 21:23:09 +02:00
Nick Terrell
5cb7615f1f Add UNUSED_ATTR to ZSTD_storeSeq() 2019-09-20 21:37:13 -07:00
Nick Terrell
44c65da97e Remove literals overread in ZSTD_storeSeq() for ~neutral perf 2019-09-20 12:23:25 -07:00
Nick Terrell
cdad7fa512 Widen ZSTD_wildcopy to 32 bytes 2019-09-20 00:52:15 -07:00
Nick Terrell
efd37a64ea Optimize decompression and fix wildcopy overread 
* Bump `WILDCOPY_OVERLENGTH` to 16 to fix the wildcopy overread.
* Optimize `ZSTD_wildcopy()` by removing unnecessary branches and
  unrolling the loop.
* Extract `ZSTD_overlapCopy8()` into its own function.
* Add `ZSTD_safecopy()` for `ZSTD_execSequenceEnd()`. It is
  optimized for single long sequences, since that is the important
  case that can end up in `ZSTD_execSequenceEnd()`. Without this
  optimization, decompressing a block with 1 long match goes
  from 5.7 GB/s to 800 MB/s.
* Refactor `ZSTD_execSequenceEnd()`.
* Increase the literal copy shortcut to 16.
* Add a shortcut for offset >= 16.
* Simplify `ZSTD_execSequence()` by pushing more cases into
  `ZSTD_execSequenceEnd()`.
* Delete `ZSTD_execSequenceLong()` since it is exactly the
  same as `ZSTD_execSequence()`.

clang-8 seeds +17.5% on silesia and +21.8% on enwik8.
gcc-9 sees +12% on silesia and +15.5% on enwik8.

TODO: More detailed measurements, and on more datasets.

Crdit to OSS-Fuzz for finding the wildcopy overread.
 2019-09-19 21:07:14 -07:00
Yann Collet
3cac061db5
Merge pull request #1802 from bimbashrestha/rle_block_bound_fix_pt2 
Adding 4 blocks to FSE_BLOCKBOUND() in lib/common (different from las…
 2019-09-18 16:32:37 -07:00
Bimba Shrestha
6e9f6813bb adding bit container size 2019-09-18 13:49:45 -07:00
Bimba Shrestha
f9b6abb896 Adding 4 blocks to FSE_BLOCKBOUND() in lib/common (different from last week) 2019-09-18 13:29:05 -07:00
Yann Collet
bfff5b30a4
Merge pull request #1756 from mgrice/dev 
Improvements in zstd decode performance
 2019-09-18 11:35:50 -07:00
Felix Handte
2164a130f3
Merge pull request #1780 from felixhandte/workspace-efficiency-3 
Avoid Clearing Tables Even When Changing CParams
 2019-09-16 14:37:05 -04:00
W. Felix Handte
72ea79cacd Don't Include sanitizer/msan_interface.h, Since Not All Platforms Provide It 
Instead, explicitly declare the functions we use.
 2019-09-16 12:08:03 -04:00
Yann Collet
09b1844d9b
Merge pull request #1784 from bimbashrestha/fse_block_bound_err 
Rearranging assert and allowing 4 extra for FSE_BLOCKBOUND()
 2019-09-12 19:09:27 -07:00
Bimba Shrestha
fe9af338ed Added assert to BIT_flushBits() 2019-09-12 15:35:27 -07:00
Bimba Shrestha
43da5bf27e Rearranging assert and allowing 4 extra for FSE_BLOCKBOUND() 2019-09-12 14:43:50 -07:00
W. Felix Handte
a10c191613 __msan_poison() Workspace When Preparing for Re-Use 2019-09-11 17:14:45 -04:00
mgrice
5d89771529 fix warning: always_inline function might not be inlinable 2019-08-29 12:32:15 -07:00
mgrice
b830599582 Improvements in zstd decode performance 
Summary: The idea behind wildcopy is that it can be cheaper to copy more bytes (say 8) than it is to copy less (say, 3).  This change takes that further by exploiting some properties:
1. it's almost always OK to copy 16 bytes instead of 8, which means fewer copy instructions, and fewer branches
2. A 16 byte chunk size means that ~90% of wildcopy invocations will have a trip count of 1, so branch prediction will be improved.

Speedup on Xeon E5-2680v4 is in the range of 3-5%.

Measured wildcopy length distributions on silesia.tar:

level	<=8	<=16	<=24	>24
1	78.05%	11.49%	3.52%	6.94%
3	82.14%	8.99%	2.44%	6.43%
6	85.81%	6.51%	2.92%	4.76%
8	83.02%	7.31%	3.64%	6.03%
10	84.13%	6.67%	3.29%	5.91%
15	77.58%	7.55%	5.21%	9.66%
16	80.07%	7.20%	3.98%	8.75%

Test Plan: benchmark silesia, make check
 2019-08-29 12:25:56 -07:00
Carl Woffenden
901ea61f83 Tweaks to create a single-file decoder 
The CHECK_F macros differ slightly (but eventually do the same thing). Older GCC needs to fallback on the old-style pragma optimisation flags.
 2019-08-21 17:49:17 +02:00
Yann Collet
61936ba42a
Merge pull request #1705 from josepho0918/dev 
Add support for IAR C/C++ Compiler for Arm
 2019-08-05 15:57:28 +02:00
Yann Collet
0b0b83e8f3 fix test 122 
it's an unsupported scenario.
 2019-08-03 16:51:26 +02:00
Joseph Chen
3855bc4295 Add support for IAR C/C++ Compiler for Arm 2019-07-29 15:25:58 +08:00
mgrice
812e8f2a16 perf improvements for zstd decode (#1668) 
* perf improvements for zstd decode

tldr: 7.5% average decode speedup on silesia corpus at compression levels 1-3 (sandy bridge)

Background: while investigating zstd perf differences between clang and gcc I noticed that even though gcc is vectorizing the loop in in wildcopy, it was not being done as well as could be done by hand.  The sites where wildcopy is invoked have an interesting distribution of lengths to be copied.  The loop trip count is rarely above 1, yet long copies are common enough to make their performance important.The code in zstd_decompress.c to invoke wildcopy handles the latter well but the gcc autovectorizer introduces a needlessly expensive startup check for vectorization.

See how GCC autovectorizes the loop here:
https://godbolt.org/z/apr0x0

Here is the code after this diff has been applied: (left hand side is the good one, right is with vectorizer on)
After: https://godbolt.org/z/OwO4F8

Note that autovectorization still does not do a good job on the optimized version, so it's turned off\
 via attribute and flag.  I found that neither attribute nor command-line flag were entirely successful in turning off vectorization, which is why there were both.

    silesia benchmark data - second triad of each file is with the original code:

    file      orig        compressedratio     encode              decode           change
    1#dickens   10192446->   4268865(2.388),       198.9MB/s           709.6MB/s
    2#dickens   10192446->   3876126(2.630),       128.7MB/s           552.5MB/s
    3#dickens   10192446->   3682956(2.767),       104.6MB/s             537MB/s
    1#dickens   10192446->   4268865(2.388),       195.4MB/s           659.5MB/s     7.60%
    2#dickens   10192446->   3876126(2.630),         127MB/s           516.3MB/s     7.01%
    3#dickens   10192446->   3682956(2.767),         105MB/s           479.5MB/s    11.99%
    1#mozilla   51220480->  20117517(2.546),       285.4MB/s           734.9MB/s
    2#mozilla   51220480->  19067018(2.686),       220.8MB/s           686.3MB/s
    3#mozilla   51220480->  18508283(2.767),       152.2MB/s           669.4MB/s
    1#mozilla   51220480->  20117517(2.546),       283.4MB/s           697.9MB/s     5.30%
    2#mozilla   51220480->  19067018(2.686),       225.9MB/s             665MB/s     3.20%
    3#mozilla   51220480->  18508283(2.767),       154.5MB/s           640.6MB/s     4.50%
    1#mr         9970564->   3840242(2.596),       262.4MB/s           899.8MB/s
    2#mr         9970564->   3600976(2.769),       181.2MB/s           717.9MB/s
    3#mr         9970564->   3563987(2.798),       116.3MB/s             620MB/s
    1#mr         9970564->   3840242(2.596),       253.2MB/s           827.3MB/s     8.76%
    2#mr         9970564->   3600976(2.769),       177.4MB/s           655.4MB/s     9.54%
    3#mr         9970564->   3563987(2.798),       111.2MB/s           564.2MB/s     9.89%
    1#nci       33553445->   2849306(11.78),       575.2MB/s ,        1335.8MB/s
    2#nci       33553445->   2890166(11.61),       509.3MB/s ,        1238.1MB/s
    3#nci       33553445->   2857408(11.74),         431MB/s ,        1210.7MB/s
    1#nci       33553445->   2849306(11.78),       565.4MB/s ,        1220.2MB/s     9.47%
    2#nci       33553445->   2890166(11.61),       508.2MB/s ,        1128.4MB/s     9.72%
    3#nci       33553445->   2857408(11.74),       429.1MB/s ,        1097.7MB/s    10.29%
    1#ooffice    6152192->   3590954(1.713),       231.4MB/s ,         662.6MB/s
    2#ooffice    6152192->   3323931(1.851),       162.8MB/s ,         592.6MB/s
    3#ooffice    6152192->   3145625(1.956),        99.9MB/s ,         549.6MB/s
    1#ooffice    6152192->   3590954(1.713),       224.7MB/s ,         624.2MB/s     6.15%
    2#ooffice    6152192->   3323931 (1.851),        155MB/s ,         564.5MB/s     4.98%
    3#ooffice    6152192->   3145625(1.956),       101.1MB/s ,         521.2MB/s     5.45%
    1#osdb      10085684->   3739042(2.697),       271.9MB/s           876.4MB/s
    2#osdb      10085684->   3493875(2.887),       208.2MB/s             857MB/s
    3#osdb      10085684->   3515831(2.869),       135.3MB/s           805.4MB/s
    1#osdb      10085684->   3739042(2.697),       257.4MB/s           793.8MB/s    10.41%
    2#osdb      10085684->   3493875(2.887),       209.7MB/s           776.1MB/s    10.42%
    3#osdb      10085684->   3515831(2.869),       130.6MB/s           727.7MB/s    10.68%
    1#reymont    6627202->   2152771(3.078),       198.9MB/s           696.2MB/s
    2#reymont    6627202->   2071140(3.200),         170MB/s           595.2MB/s
    3#reymont    6627202->   1953597(3.392),       128.5MB/s           609.7MB/s
    1#reymont    6627202->   2152771(3.078),       199.6MB/s           655.2MB/s     6.26%
    2#reymont    6627202->   2071140(3.200),       168.2MB/s           554.4MB/s     7.36%
    3#reymont    6627202->   1953597(3.392),       128.7MB/s           557.4MB/s     9.38%
    1#samba     21606400->   5510994(3.921),       338.1MB/s            1066MB/s
    2#samba     21606400->   5240208(4.123),       258.7MB/s           992.3MB/s
    3#samba     21606400->   5003358(4.318),       200.2MB/s           991.1MB/s
    1#samba     21606400->   5510994(3.921),       330.8MB/s             974MB/s     9.45%
    2#samba     21606400->   5240208(4.123),       257.9MB/s           919.4MB/s     7.93%
    3#samba     21606400->   5003358(4.318),       198.5MB/s           908.9MB/s     9.04%
    1#sao        7251944->   6256401(1.159),       194.6MB/s           602.2MB/s
    2#sao        7251944->   5808761(1.248),       128.2MB/s           532.1MB/s
    3#sao        7251944->   5556318(1.305),          73MB/s           509.4MB/s
    1#sao        7251944->   6256401(1.159),       198.7MB/s           580.7MB/s     3.70%
    2#sao        7251944->   5808761(1.248),       129.1MB/s           502.7MB/s     5.85%
    3#sao        7251944->   5556318(1.305),        74.6MB/s           493.1MB/s     3.31%
    1#webster   41458703->  13692222(3.028),       222.3MB/s             752MB/s
    2#webster   41458703->  12842646(3.228),       157.6MB/s           532.2MB/s
    3#webster   41458703->  12191964(3.400),         124MB/s           468.5MB/s
    1#webster   41458703->  13692222(3.028),       219.7MB/s             697MB/s     7.89%
    2#webster   41458703->  12842646(3.228),       153.9MB/s           495.4MB/s     7.43%
    3#webster   41458703->  12191964(3.400),       124.8MB/s           444.8MB/s     5.33%
    1#xml        5345280->    696652(7.673),         485MB/s ,        1333.9MB/s
    2#xml        5345280->    681492(7.843),       405.2MB/s ,        1237.5MB/s
    3#xml        5345280->    639057(8.364),       328.5MB/s ,        1281.3MB/s
    1#xml        5345280->    696652(7.673),       473.1MB/s ,        1232.4MB/s     8.24%
    2#xml        5345280->    681492(7.843),       398.6MB/s ,        1145.9MB/s     7.99%
    3#xml        5345280->    639057(8.364),       327.1MB/s ,          1175MB/s     9.05%
    1#x-ray      8474240->   6772557(1.251),       521.3MB/s           762.6MB/s
    2#x-ray      8474240->   6684531(1.268),       230.5MB/s           688.5MB/s
    3#x-ray      8474240->   6166679(1.374),        68.7MB/s           478.8MB/s
    1#x-ray      8474240->   6772557(1.251),       502.8MB/s           736.7MB/s     3.52%
    2#x-ray      8474240->   6684531(1.268),       224.4MB/s             662MB/s     4.00%
    3#x-ray      8474240->   6166679(1.374),        67.3MB/s           437.8MB/s     9.37%

                                                                                     7.51%

* makefile changed to only pass -fno-tree-vectorize to gcc

* <Replace this line with a title. Use 1 line only, 67 chars or less>

Don't add "no-tree-vectorize" attribute on clang (which defines __GNUC__)

* fix for warning/error with subtraction of void* pointers

* fix c90 conformance issue - ISO C90 forbids mixed declarations and code

* Fix assert for negative diff, only when there is no overlap

* fix overflow revealed in fuzzing tests

* tweak for small speed increase
 2019-07-11 18:31:07 -04:00
Josh Soref
a880ca239b Spelling (#1582) 
* spelling: accidentally

* spelling: across

* spelling: additionally

* spelling: addresses

* spelling: appropriate

* spelling: assumed

* spelling: available

* spelling: builder

* spelling: capacity

* spelling: compiler

* spelling: compressibility

* spelling: compressor

* spelling: compression

* spelling: contract

* spelling: convenience

* spelling: decompress

* spelling: description

* spelling: deflate

* spelling: deterministically

* spelling: dictionary

* spelling: display

* spelling: eliminate

* spelling: preemptively

* spelling: exclude

* spelling: failure

* spelling: independence

* spelling: independent

* spelling: intentionally

* spelling: matching

* spelling: maximum

* spelling: meaning

* spelling: mishandled

* spelling: memory

* spelling: occasionally

* spelling: occurrence

* spelling: official

* spelling: offsets

* spelling: original

* spelling: output

* spelling: overflow

* spelling: overridden

* spelling: parameter

* spelling: performance

* spelling: probability

* spelling: receives

* spelling: redundant

* spelling: recompression

* spelling: resources

* spelling: sanity

* spelling: segment

* spelling: series

* spelling: specified

* spelling: specify

* spelling: subtracted

* spelling: successful

* spelling: return

* spelling: translation

* spelling: update

* spelling: unrelated

* spelling: useless

* spelling: variables

* spelling: variety

* spelling: verbatim

* spelling: verification

* spelling: visited

* spelling: warming

* spelling: workers

* spelling: with
 2019-04-12 11:18:11 -07:00
shakeelrao
0033bb4785 Update documentation for ZSTD_frameSizeInfo 2019-03-17 17:41:27 -07:00
shakeelrao
19b75b6ecb Test new ZSTD_findFrameCompressedSize and update documentation 2019-03-15 18:04:19 -07:00
W. Felix Handte
501eb25102 Rename FORWARD_ERROR -> FORWARD_IF_ERROR 2019-01-29 12:56:07 -05:00
W. Felix Handte
429987c9a6 Add Comment 2019-01-28 17:35:31 -05:00
W. Felix Handte
2179ce00e1 Remove CHECK_E Macro 2019-01-28 17:33:13 -05:00
W. Felix Handte
7ebd897157 Remove CHECK_F Macro 2019-01-28 17:16:32 -05:00
W. Felix Handte
324e9654d3 Add grep-able String to Error Macros 2019-01-28 12:50:36 -05:00
W. Felix Handte
a3538bbc6f Add RETURN_ERROR and FORWARD_ERROR Macros 2019-01-28 12:45:26 -05:00
W. Felix Handte
54fa31f03b Add RETURN_ERROR_IF Macro That Logs Debug Information When Check Fails 2019-01-28 11:43:33 -05:00
Yann Collet
ededcfca57 fix confusion between unsigned <-> U32 
as suggested in #1441.

generally U32 and unsigned are the same thing,
except when they are not ...

case : 32-bit compilation for MIPS (uint32_t == unsigned long)

A vast majority of transformation consists in transforming U32 into unsigned.
In rare cases, it's the other way around (typically for internal code, such as seeds).

Among a few issues this patches solves :
- some parameters were declared with type `unsigned` in *.h,
  but with type `U32` in their implementation *.c .
- some parameters have type unsigned*,
  but the caller user a pointer to U32 instead.

These fixes are useful.

However, the bulk of changes is about %u formating,
which requires unsigned type,
but generally receives U32 values instead,
often just for brevity (U32 is shorter than unsigned).
These changes are generally minor, or even annoying.

As a consequence, the amount of code changed is larger than I would expect for such a patch.

Testing is also a pain :
it requires manually modifying `mem.h`,
in order to lie about `U32`
and force it to be an `unsigned long` typically.
On a 64-bit system, this will break the equivalence unsigned == U32.
Unfortunately, it will also break a few static_assert(), controlling structure sizes.
So it also requires modifying `debug.h` to make `static_assert()` a noop.
And then reverting these changes.

So it's inconvenient, and as a consequence,
this property is currently not checked during CI tests.
Therefore, these problems can emerge again in the future.

I wonder if it is worth ensuring proper distinction of U32 != unsigned in CI tests.
It's another restriction for coding, adding more frustration during merge tests,
since most platforms don't need this distinction (hence contributor will not see it),
and while this can matter in theory, the number of platforms impacted seems minimal.

Thoughts ?
 2018-12-21 18:09:41 -08:00
Yann Collet
e4ae24c229
Merge pull request #1420 from felixhandte/zstd-decompress-minimal 
Various Macros to Allow Building Extremely Minimal Decoder Library
 2018-12-20 15:17:37 -08:00
W. Felix Handte
8e61ac8161 Use Unused Variable in ERR_getErrorString() 2018-12-19 12:36:10 -08:00
W. Felix Handte
c560e34c86 Add HUF_FORCE_DECOMPRESS_X2 2018-12-18 13:36:39 -08:00
W. Felix Handte
432314b58a Rename HUF_DECOMPRESS_MINIMAL -> HUF_FORCE_DECOMPRESS_X1 2018-12-18 13:36:39 -08:00
W. Felix Handte
605dd576ee Remove Error Strings with ZSTD_STRIP_ERROR_STRINGS 2018-12-18 13:36:39 -08:00
W. Felix Handte
9d5f3963ff Add Option to Not Request Inlining with ZSTD_NO_INLINE 2018-12-18 13:36:39 -08:00
W. Felix Handte
f45c9df42e Totally Hide/Disable X2 Variants when HUF_DECOMPRESS_MINIMAL is Defined 2018-12-18 13:36:39 -08:00
Yann Collet
373ff8b983 play around with rescale weights 2018-12-17 15:48:34 -08:00
Yann Collet
9c3265a53f
Merge pull request #1417 from facebook/advancedAPI 
Advanced API
 2018-12-10 18:48:15 -08:00
Ryan Schmidt
ef4df0df4a Fix i386 build failure "Junk character 13" 2018-11-16 02:16:21 -06:00
Yann Collet
d7e10a774a added constant ZSTD_WINDOWLOG_LIMIT_DEFAULT 
answering #1407.

Also : removed obsolete function ZSTD_setDStreamParameter()
which could only be used with one parameter (DStream_p_maxWindowSize).
Now replaced by ZSTD_DCtx_setWindowSize() (which exists since a few revisions)
 2018-11-13 18:12:34 -08:00
Yann Collet
626040ab53 changed PREFETCH() macro into PREFETCH_L2() 
which is more accurate
 2018-11-12 17:05:32 -08:00
Yann Collet
1b4a9c518b
Merge pull request #1410 from facebook/prefetch_dec 
improve long-range decoder speed
 2018-11-08 18:41:58 -08:00
Yann Collet
9126da5b5c improve long-range decoder speed 
on enwik9 at level 22 (which is almost a worst case scenario),
speed improves by +7% on my laptop (415 -> 445 MB/s)
 2018-11-08 12:47:46 -08:00
Nick Terrell
a8daa2d683 Signal before unlocking in pool.c 2018-11-08 10:45:53 -08:00