adae2f2272
[subset-perf] Cache a glyph map for gsub.
...
This allows us in some cases to avoid using glyph_set_gsub as a filter.
2022-05-18 18:25:36 -06:00
202e6c4699
[subset] Remove unnecessary test
2022-05-18 17:12:43 -06:00
cedf739646
Add some commented-out code
2022-05-18 16:53:26 -06:00
6b62c10f02
[priority-queue] Remove old init/fini
2022-05-18 16:27:54 -06:00
bff8248a9d
[repacker] Pre-alloc vertices
2022-05-18 16:25:03 -06:00
39a424caf0
[priority-queue] Optimize heap access
2022-05-18 16:19:44 -06:00
9308659fd7
[priority-queue] Optimize swap()
2022-05-18 16:14:25 -06:00
c7317ef761
[repacker] Avoid destroying and recreating objects
2022-05-18 16:03:41 -06:00
864e09a0c4
[repacker] Reuse allocated vector
2022-05-18 15:59:29 -06:00
ca77f16470
[repacker] Remove unnecessary vector .fini() calls
2022-05-18 15:55:49 -06:00
4cfc2d668e
[subset] Use a std::move on set_t when feasible
2022-05-18 15:32:19 -06:00
1f578b5a32
[set] Add pre-allocation internal API
2022-05-18 15:25:00 -06:00
48dfbd54a3
[subset] minor cleanup.
2022-05-18 15:24:54 -06:00
482c6e5dc4
[subset-perf] Speed up Coverage::serialize by caching iterator.
2022-05-18 15:24:54 -06:00
14b18725f0
In Coverage::iter_t, assume iterators are from same Coverage object
...
No need to support otherwise.
2022-05-18 15:14:32 -06:00
27141735c3
[subset] Add Coverage::__end__ implementation
2022-05-18 15:12:49 -06:00
c476f58adb
[subset] Write CoverageFormat2::intersects_coverage() as bsearch()
2022-05-18 14:20:23 -06:00
63c6695108
[ot-layout] Cosmetic
...
The implementation of HBUINT16 operator == is slower than just
comparing to ints.
2022-05-18 13:53:52 -06:00
777debd748
[subset] Rewrite CoverageFormat2::intersects as dagger
2022-05-18 13:46:06 -06:00
cf5001fac7
[subset] Optimize CoverageFormat2::intersected_coverage_glyphs
2022-05-18 13:38:29 -06:00
6f37c20798
[subset] Minor rewrite in CoverageFormat2::serialize()
2022-05-18 13:25:42 -06:00
e91863b717
[subset-cff] Pre-size map in subr_remap_t::create()
2022-05-18 12:39:55 -06:00
ce60462173
[subset-plan] Pre-size maps in _create_old_gid_to_new_gid_map()
2022-05-18 12:34:27 -06:00
f82ee17a75
[map] Pre-size map in constructor if we can
2022-05-18 12:19:49 -06:00
b5aa8a27ea
[subset-cff] Cosmetic
2022-05-18 11:58:58 -06:00
0b201623f5
[subset-cff] Fix previous commit
...
Oops!
2022-05-18 11:58:22 -06:00
4792309265
[subset-cff] Access vector directly
2022-05-18 11:54:08 -06:00
7c86f2e763
[subset-cff] Pre-alloc out buffer
2022-05-18 11:45:27 -06:00
0761e7cdfd
[subset-cff] Avoid resetting buffer as encoder does
2022-05-18 11:38:25 -06:00
71aa10a394
[subset-cff] Manually grow vector to avoid memset overhead
2022-05-18 11:37:24 -06:00
f455cc53fd
[subset-cff] Reuse buffer allocation
2022-05-18 11:31:55 -06:00
e24797aeac
[ot-tags] Follow-up to previous commit
...
Part of https://github.com/harfbuzz/harfbuzz/issues/3591
2022-05-18 11:10:10 -06:00
f5d619be79
[ot-tags] Further gate the slow complex case, and add more tests
...
Part of https://github.com/harfbuzz/harfbuzz/issues/3591
Still 'zh-trad' is the slowest case.
--------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
--------------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON zh_trad 136 ns 136 ns 5107838
BM_hb_ot_tags_from_script_and_language/COMMON ab_abcd 115 ns 115 ns 6103104
BM_hb_ot_tags_from_script_and_language/COMMON ab_abc 25.4 ns 25.3 ns 27674482
BM_hb_ot_tags_from_script_and_language/COMMON abcdef_XY 20.2 ns 20.1 ns 34795719
BM_hb_ot_tags_from_script_and_language/COMMON abcd_XY 19.4 ns 19.3 ns 36390401
BM_hb_ot_tags_from_script_and_language/COMMON cxy_CN 33.5 ns 33.4 ns 20998939
BM_hb_ot_tags_from_script_and_language/COMMON exy_CN 25.1 ns 25.0 ns 27705832
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 34.2 ns 34.1 ns 20564356
BM_hb_ot_tags_from_script_and_language/COMMON en_US 15.5 ns 15.5 ns 45032204
BM_hb_ot_tags_from_script_and_language/LATIN en_US 15.9 ns 15.8 ns 44412379
BM_hb_ot_tags_from_script_and_language/COMMON none 4.72 ns 4.71 ns 149101665
BM_hb_ot_tags_from_script_and_language/LATIN none 4.72 ns 4.70 ns 149254498
2022-05-18 11:04:52 -06:00
9c64bda21d
[ot-tag] Whitespace
2022-05-17 17:31:18 -06:00
3df8017e9b
[ot-tag] Optimize subtag_matches() more
2022-05-17 17:29:39 -06:00
7f6e8c5536
[ot-tags] Optimize subtag_matches() further
...
Part of https://github.com/harfbuzz/harfbuzz/issues/3591
Comparing before to after
Benchmark Time CPU Time Old Time New CPU Old CPU New
----------------------------------------------------------------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON abcd_XY -0.3371 -0.3371 71 47 71 47
2022-05-17 16:58:35 -06:00
27c11405a2
[ot-tag] Optimize subtag_matches
...
Part of https://github.com/harfbuzz/harfbuzz/issues/3591
2022-05-17 16:51:51 -06:00
a07d818597
[ot-tag] Add a likely() to the cache hit case
2022-05-17 16:46:10 -06:00
dfca47f419
[ot-tag] Cache last bsearch result
...
Part of https://github.com/harfbuzz/harfbuzz/issues/3591
Humm. Looks like not all of the fat is bsearch overhead now. I cached
the last bsearch result, but most of the time is still there. I'm
baffled.
Before:
------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON abcd_XY 8.08 ns 8.05 ns 84500482
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 42.2 ns 42.1 ns 16722006
BM_hb_ot_tags_from_script_and_language/COMMON en_US 16.1 ns 16.0 ns 43461527
BM_hb_ot_tags_from_script_and_language/LATIN en_US 16.5 ns 16.5 ns 42448505
BM_hb_ot_tags_from_script_and_language/COMMON none 4.34 ns 4.33 ns 161290530
BM_hb_ot_tags_from_script_and_language/LATIN none 4.34 ns 4.33 ns 162339799
After:
------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON abcd_XY 8.13 ns 8.11 ns 80438134
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 40.0 ns 39.9 ns 17487939
BM_hb_ot_tags_from_script_and_language/COMMON en_US 12.7 ns 12.7 ns 55124394
BM_hb_ot_tags_from_script_and_language/LATIN en_US 13.1 ns 13.0 ns 53660125
BM_hb_ot_tags_from_script_and_language/COMMON none 4.61 ns 4.60 ns 151394104
BM_hb_ot_tags_from_script_and_language/LATIN none 4.70 ns 4.68 ns 150402847
2022-05-17 16:21:02 -06:00
909f00ac6e
[ot-tags] Further speed up language bsearch()
...
Using an integer tag to bsearch, instead of string.
Part of: https://github.com/harfbuzz/harfbuzz/issues/3591
Before:
------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON abcd_XY 8.11 ns 8.08 ns 87067795
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 53.6 ns 53.5 ns 13042418
BM_hb_ot_tags_from_script_and_language/COMMON en_US 24.2 ns 24.1 ns 29052731
BM_hb_ot_tags_from_script_and_language/LATIN en_US 24.4 ns 24.3 ns 28736769
BM_hb_ot_tags_from_script_and_language/COMMON none 4.43 ns 4.41 ns 160370413
BM_hb_ot_tags_from_script_and_language/LATIN none 4.35 ns 4.34 ns 160578191
After:
------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON abcd_XY 7.97 ns 7.95 ns 85208363
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 41.7 ns 41.6 ns 16945817
BM_hb_ot_tags_from_script_and_language/COMMON en_US 16.1 ns 16.0 ns 43613523
BM_hb_ot_tags_from_script_and_language/LATIN en_US 16.5 ns 16.4 ns 42568107
BM_hb_ot_tags_from_script_and_language/COMMON none 4.30 ns 4.29 ns 164055469
BM_hb_ot_tags_from_script_and_language/LATIN none 4.29 ns 4.27 ns 163793591
2022-05-17 15:51:41 -06:00
c460cf74ce
[ot-tags] Cosmetic
2022-05-17 15:30:11 -06:00
1c8226ed14
Fix compiler warning
...
On Mac compiler:
FAILED: src/libharfbuzz.0.dylib.p/hb-ot-tag.cc.o
c++ -Isrc/libharfbuzz.0.dylib.p -Isrc -I../src -I. -I.. -I/usr/local/opt/freetype/include/freetype2 -I/usr/local/Cellar/graphite2/1.3.14/include -I/usr/local/Cellar/glib/2.72.1/include/glib-2.0 -I/usr/local/Cellar/glib/2.72.1/lib/glib-2.0/include -I/usr/local/opt/gettext/include -I/usr/local/Cellar/pcre/8.45/include -Xclang -fcolor-diagnostics --coverage -pipe -Wall -Winvalid-pch -Wnon-virtual-dtor -std=c++11 -fno-rtti -O2 -g -fno-exceptions -fno-rtti -fno-threadsafe-statics -fvisibility-inlines-hidden -DHAVE_CONFIG_H -Wno-non-virtual-dtor -MD -MQ src/libharfbuzz.0.dylib.p/hb-ot-tag.cc.o -MF src/libharfbuzz.0.dylib.p/hb-ot-tag.cc.o.d -o src/libharfbuzz.0.dylib.p/hb-ot-tag.cc.o -c ../src/hb-ot-tag.cc
In file included from ../src/hb-ot-tag.cc:29:
In file included from ../src/hb.hh:481:
../src/hb-array.hh:359:14: error: missing default argument on parameter 'ds'
Ts... ds) const
^
../src/hb-ot-tag.cc:292:58: note: in instantiation of function template specialization 'hb_sorted_array_t<const LangTag>::bfind<const char *, unsigned int>' requested here
if (hb_sorted_array (ot_languages, ot_languages_len).bfind (lang_str, &tag_idx,
^
1 error generated.
2022-05-17 15:28:50 -06:00
c1f4b57c06
[ot-tags] Optimize language comparison
...
Now that we know both strings are of equal len of 2 or 3, optimize.
Part of https://github.com/harfbuzz/harfbuzz/issues/3591
Before:
------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON abcd_XY 8.50 ns 8.47 ns 81221549
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 79.6 ns 79.3 ns 8785804
BM_hb_ot_tags_from_script_and_language/COMMON en_US 40.0 ns 39.9 ns 17462768
BM_hb_ot_tags_from_script_and_language/LATIN en_US 39.2 ns 39.1 ns 17886793
BM_hb_ot_tags_from_script_and_language/COMMON none 4.31 ns 4.30 ns 162805417
BM_hb_ot_tags_from_script_and_language/LATIN none 4.32 ns 4.31 ns 162656688
After:
------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON abcd_XY 8.27 ns 8.24 ns 81868701
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 56.1 ns 56.0 ns 12353284
BM_hb_ot_tags_from_script_and_language/COMMON en_US 24.3 ns 24.2 ns 28955030
BM_hb_ot_tags_from_script_and_language/LATIN en_US 24.5 ns 24.4 ns 28664868
BM_hb_ot_tags_from_script_and_language/COMMON none 4.35 ns 4.34 ns 161190014
BM_hb_ot_tags_from_script_and_language/LATIN none 4.36 ns 4.34 ns 161319000
2022-05-17 15:19:40 -06:00
dde48d78c1
Fix compiler warning
2022-05-17 15:07:49 -06:00
15be0deda0
[ot-tags] Optimize lang_matches()
...
Part of https://github.com/harfbuzz/harfbuzz/issues/3591
Before:
------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON abcd_XY 8.67 ns 8.64 ns 80324382
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 91.2 ns 90.9 ns 7674131
BM_hb_ot_tags_from_script_and_language/COMMON en_US 41.1 ns 41.0 ns 17174093
BM_hb_ot_tags_from_script_and_language/LATIN en_US 41.3 ns 41.2 ns 17000876
BM_hb_ot_tags_from_script_and_language/COMMON none 4.56 ns 4.55 ns 153914130
BM_hb_ot_tags_from_script_and_language/LATIN none 4.53 ns 4.52 ns 153830303
After:
------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
------------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON abcd_XY 8.24 ns 8.21 ns 84078465
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 77.5 ns 77.2 ns 9059230
BM_hb_ot_tags_from_script_and_language/COMMON en_US 38.8 ns 38.7 ns 17790692
BM_hb_ot_tags_from_script_and_language/LATIN en_US 37.6 ns 37.5 ns 18648293
BM_hb_ot_tags_from_script_and_language/COMMON none 4.50 ns 4.49 ns 155573267
BM_hb_ot_tags_from_script_and_language/LATIN none 4.49 ns 4.47 ns 156456653
2022-05-17 14:57:08 -06:00
dd3c858f84
[ot-tags] Speed up hb_ot_tags_from_language()
...
Part of https://github.com/harfbuzz/harfbuzz/issues/3591
"After that, bulk of the time I suppose is spent in binary-searching the
language table. I suggest we split the language table in 2-letter and
3-letter tags, to speed-up the vast majority of cases that are
2-letter."
benchmark-ot, before:
----------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
----------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 112 ns 111 ns 6286271
BM_hb_ot_tags_from_script_and_language/COMMON en_US 60.6 ns 60.4 ns 11671176
BM_hb_ot_tags_from_script_and_language/LATIN en_US 61.3 ns 61.1 ns 11442645
BM_hb_ot_tags_from_script_and_language/COMMON none 4.75 ns 4.74 ns 146997235
BM_hb_ot_tags_from_script_and_language/LATIN none 4.65 ns 4.64 ns 150938747
After:
----------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
----------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 89.5 ns 89.2 ns 7747649
BM_hb_ot_tags_from_script_and_language/COMMON en_US 38.5 ns 38.4 ns 18199432
BM_hb_ot_tags_from_script_and_language/LATIN en_US 39.0 ns 38.9 ns 18049238
BM_hb_ot_tags_from_script_and_language/COMMON none 4.53 ns 4.52 ns 154895110
BM_hb_ot_tags_from_script_and_language/LATIN none 4.54 ns 4.52 ns 154762105
2022-05-17 14:28:28 -06:00
9baccb9860
[ot-tags] Speed up hb_ot_tags_from_complex_language()
...
Part of https://github.com/harfbuzz/harfbuzz/issues/3591
2. All the subtag_matches outside the switch match long strings (>= 6 or so).
As such, check the tag for such length before going into any of them.
benchmark-ot, before:
----------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
----------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 172 ns 171 ns 4083155
BM_hb_ot_tags_from_script_and_language/COMMON en_US 120 ns 119 ns 5849947
BM_hb_ot_tags_from_script_and_language/LATIN en_US 113 ns 112 ns 5840326
BM_hb_ot_tags_from_script_and_language/COMMON none 4.66 ns 4.64 ns 151396224
BM_hb_ot_tags_from_script_and_language/LATIN none 4.66 ns 4.64 ns 149019593
After:
----------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations
----------------------------------------------------------------------------------------------
BM_hb_ot_tags_from_script_and_language/COMMON zh_CN 112 ns 112 ns 6357763
BM_hb_ot_tags_from_script_and_language/COMMON en_US 60.5 ns 60.3 ns 11475091
BM_hb_ot_tags_from_script_and_language/LATIN en_US 54.9 ns 54.8 ns 12575690
BM_hb_ot_tags_from_script_and_language/COMMON none 4.61 ns 4.59 ns 152388450
BM_hb_ot_tags_from_script_and_language/LATIN none 4.66 ns 4.64 ns 151497600
2022-05-17 13:34:34 -06:00
fb413f5202
[subset/cff] Don't use bitfields for hot bools
...
The struct has room because of alignment, and these bools are hot.
2022-05-16 17:38:18 -06:00
a4d98b63ea
[subset/cff1] Collect glyph-to-sid map to avoid an O(n^2) algorithm
...
Saves 13 for largest benchmark:
BM_subset/subset_glyphs/SourceHanSans-Regular_subset.otf/10000 -0.1313 -0.1308 75 65 75 65
BM_subset/subset_codepoints/SourceHanSans-Regular_subset.otf/4096 -0.1009 -0.1004 54 48 54 48
BM_subset/subset_codepoints/SourceHanSans-Regular_subset.otf/10000 -0.1067 -0.1066 70 62 69 62
2022-05-16 17:38:18 -06:00
b87f48e948
[cff1] get_sid() move bounds check into each implementation
2022-05-16 17:38:18 -06:00
e1e359b4da
[cff1] Tighten up range_list_t a bit
2022-05-16 16:36:28 -06:00
3fbac0942d
[cff1] Lazy-load & sort glyph names
...
Improves subset benchmarks by up to 70% for small CFF1 subset of
non-CID fonts!
BM_subset/subset_glyphs/SourceSansPro-Regular.otf/10 -0.7067 -0.7071 1 0 1 0
BM_subset/subset_glyphs/SourceSansPro-Regular.otf/64 -0.4817 -0.4824 1 0 1 0
BM_subset/subset_glyphs/SourceSansPro-Regular.otf/512 -0.1948 -0.1956 2 2 2 2
BM_subset/subset_glyphs/SourceSansPro-Regular.otf/2000 -0.0767 -0.0761 6 6 6 6
2022-05-16 16:36:28 -06:00
b58bfd9818
[font] Minor move of code to silence gcc-12 warning
...
See mailing list discussion.
2022-05-16 11:21:45 -06:00
602e0ca79d
[cff] Minor restructure of struct
...
Surprisingly this shows tiny benchmark improvement consistently.
2022-05-16 10:14:34 -06:00
acdab17ed3
[cff] Cosmetic in parsed_values_t
2022-05-13 14:14:36 -06:00
b46c7faa9c
[cff] Check buf_len, not buf
...
Ouch!
2022-05-13 14:02:54 -06:00
19a8db8545
[subset] fix potential integer overflow in gname_t::cmp.
2022-05-13 13:55:39 -06:00
2d2f66e1a3
[cff-common] In INDEX, return empty bytes if length is zero
...
Before it was possible to return non-null arrayZ.
2022-05-13 13:53:17 -06:00
a2f132f1fc
[cff] Check glyph-name's length, not arrayZ
...
As the latter can be non-null while still zero-length.
2022-05-13 13:49:39 -06:00
c657c4e1f8
[meta] fix type traits on gcc 4.9 #3526
...
Signed-off-by: Thomas Devoogdt <thomas.devoogdt@barco.com>
2022-05-13 11:26:12 -06:00
e61234c5f7
[vector] Add tests for move constructor/assignment
2022-05-12 13:20:10 -06:00
7fa580bc4f
[map] Fix map copy/move constructors to actually work
...
Ouch!
2022-05-12 13:05:32 -06:00
a09dd87ca3
[set] Fix set copy/move constructors to actually work
...
Ouch!
2022-05-12 12:58:07 -06:00
76fc27713f
[vector] Remove explicit std::move
...
Was confusing compilers. Let them figure it out themselves.
Makes NotoNastaliqu subsetting/1000 benchmark more than twice faster:
Benchmark Time CPU Time Old Time New CPU Old CPU New
------------------------------------------------------------------------------------------------------------------------------------------------------------
BM_subset/subset_glyphs/NotoNastaliqUrdu-Regular.ttf/1000 -0.5064 -0.5065 111 55 110 55
BM_subset/subset_codepoints/NotoNastaliqUrdu-Regular.ttf/1000 -0.5494 -0.5493 132 59 131 59
2022-05-12 12:14:07 -06:00
c81198b5bc
[set] Tweak move operators a bit
...
Should be equivalent.
2022-05-12 12:14:02 -06:00
175319cd89
[gsubgpos] Clean up OT::ClassDefFormat2::intersected_class_glyphs 0 case
2022-05-11 13:47:17 -06:00
137af3612b
[gsubgpos] Simplify OT::ClassDefFormat2::intersected_class_glyphs()
2022-05-11 13:39:30 -06:00
3261e05bdb
[subset] Optimize ClassDef1::intersected_class_glyphs() for class0
2022-05-11 13:16:31 -06:00
c78d8ba60b
[subset] Allocate same size as source table for GSUB/GPOS/name
2022-05-11 13:05:41 -06:00
2e7f1ae48f
[subset] Use vector.allocated size instead of tracking buf_size
2022-05-11 12:52:27 -06:00
f08537963b
[cff-subset] Pre-alloc vector for operator decoding
2022-05-11 12:14:49 -06:00
aeb50b8942
[subset] Retain buffer across table subset operations
2022-05-11 12:14:49 -06:00
bff78e6515
[cff] Convert interpretation environment to use constructor
2022-05-10 16:50:38 -06:00
de053e2efb
[cff] Convert subr_subset_param_t to use constructor
2022-05-10 16:17:20 -06:00
96140db485
[cff] Convert cff2_extents_param_t to use constructor
2022-05-10 16:17:20 -06:00
54544f2a57
[cff] Convert cff1_extents_param_t to use constructor
2022-05-10 16:17:20 -06:00
377befd0c7
[cff] Convert get_seac_param_t to use constructor
2022-05-10 16:17:20 -06:00
8fd70362fa
[cff] Use hb_ubytes_t() instead of Null(hb_ubytes_t)
2022-05-10 16:17:20 -06:00
9033c7f99d
[cff-common] Optimize INDEX::operator[]
...
Previous try showed slowdown in benchmarks, suprisingly.
Rewrite it keeping the function, hopefully allowing better optimization.
2022-05-10 14:58:53 -06:00
3aace2431b
Revert "[cff-common] Optimize INDEX::operator[]"
...
This reverts commit 9edb03ac7a
2022-05-10 14:54:04 -06:00
b31ef081db
Revert "[cff] Add an unlikely()"
...
This reverts commit 9ba9adb7ed
2022-05-10 14:52:40 -06:00
9ba9adb7ed
[cff] Add an unlikely()
2022-05-10 14:43:00 -06:00
9edb03ac7a
[cff-common] Optimize INDEX::operator[]
2022-05-10 14:43:00 -06:00
0a42410dc8
[cff2] Change extents/shape stack to be just a number
...
Do the blending immediately.
Fixes https://github.com/harfbuzz/harfbuzz/issues/3559
Benchmark on AdobeVFPrototype shows 35% speedup. Now we're faster
than FreeType:
Benchmark Time CPU Time Old Time New CPU Old CPU New
------------------------------------------------------------------------------------------------------------------------------------------------
BM_Font/glyph_extents/AdobeVFPrototype.otf/hb -0.3792 -0.3792 1584 983 1581 982
BM_Font/glyph_extents/AdobeVFPrototype.otf/ft +0.0228 +0.0224 1220 1248 1218 1245
BM_Font/glyph_extents/AdobeVFPrototype.otf/var/hb -0.3513 -0.3518 1616 1048 1613 1046
BM_Font/glyph_extents/AdobeVFPrototype.otf/var/ft +0.0172 +0.0169 1232 1254 1230 1251
2022-05-10 13:41:12 -06:00
8f9f0c494b
[subset] Enforce cmap12 group ordering constraints in collect_mapping.
...
Fixes fuzzer issue: https://oss-fuzz.com/testcase-detail/6365271012540416
2022-05-10 12:15:09 -06:00
1b14d2ff13
[cff] Fix arg-stack peek() impl
2022-05-09 18:15:31 -06:00
6106ef8c0f
[cff] Tighten up arg-stack access
2022-05-09 18:15:11 -06:00
8c616a6efe
[cff] Allocate stack inline instead of using hb_vector_t
...
Speeds up glyph_extents and glyph_shape benchmarks for CFF by 10
to 16 percent!
2022-05-09 17:50:59 -06:00
c941ece60f
[cff] Use using instead of typedef
2022-05-09 17:34:58 -06:00
64d63cebe2
[cff-common] Use existing types for str_buff_vec_t
2022-05-09 17:34:58 -06:00
e1838ec1f8
[cff-common] Remove unused method
2022-05-09 17:34:58 -06:00
8aa54aaca2
[cff] Replace byte_str_t with hb_bytes_t use
2022-05-09 17:34:58 -06:00
fe1d85a55a
[cff] Remove custom byte_str_t impl
2022-05-09 17:34:58 -06:00
c8a5f1e3c0
[cff-common] Indent
2022-05-09 17:34:58 -06:00
be7b2905cb
[cff-common] Remove unused INDEX::serialize() method
2022-05-09 17:34:58 -06:00
60390169b6
[cff-common] Write str_buf_t::total_size() as dagger
2022-05-09 17:34:58 -06:00
258afb45b7
[cff-common] Use range-based loop in str_buff_vec_t
2022-05-09 17:34:58 -06:00
8bb1a3ce9a
[cff-common] Write INDEX offset-size calc using hb_bit_storage()
2022-05-09 17:34:58 -06:00
2ccfe84eff
[cff-common] Add assert to INDEX::set_offset_at()
2022-05-09 17:34:58 -06:00
4bcab9e99a
[cff-common] Use byte_str_t() instead of Null(byte_str_t)
2022-05-09 17:34:58 -06:00
94f7a26322
[cff-common] Fix get_size() for Null object
...
The special-casing didn't make sense.
2022-05-09 17:34:58 -06:00
c9cc7d5d21
[cff-common] Inline once-used method in INDEX
2022-05-09 17:34:58 -06:00
11482a3a39
[cff-common] Remove unused method from INDEX
2022-05-09 17:34:58 -06:00
d1bb3b08f6
[cff-common] Hide more INDEX internals
2022-05-09 17:34:58 -06:00
d3b21387fd
[cff-common] Remove redundant operator implementation
2022-05-09 17:34:58 -06:00
a96b408d80
[cff-common] Hide INDEX internals
2022-05-09 17:34:58 -06:00
335b1d83cf
[cff-common] No need to check max-offset in INDEX
...
The length_at() function makes sure out-of-range offsets
are discarded. We just need to check the last offset.
2022-05-09 17:34:58 -06:00
b051f3fa83
[subset] Fix cpal subsetting when there are partial palette overlaps.
...
The existing code doesn't correctly handle the case where palettes partially overlap in the color record array. This changes the subsetting to only share entries in the color record array when palettes have the same first color index. Partially overlapping palettes will be converted to disjoint segments in the color record array.
Updates one of the color tests to use multiple palettes.
Also fixes fuzzer: https://oss-fuzz.com/testcase-detail/5568200165687296 .
2022-05-09 12:25:05 -06:00
2884eb97bf
[cff-common] Remove special-casing of count=0 in INDEX serialize
...
The generic code-path now can handle count=0.
2022-05-06 13:33:13 -06:00
fc7f51aece
[cff-common] Reduce iterator calls
2022-05-06 13:33:13 -06:00
c857b8e3c6
[cff-common] Set INDEX min_size to 2
...
That is what it is, for an empty INDEX.
2022-05-06 13:33:13 -06:00
dd71d2c1c3
[gvar] Protect against offset underflow
2022-05-06 13:02:26 -06:00
9a6dabd61a
[gvar] Remove sanitize check for data array
...
We are not checking in sanitize that offset array is ascending,
so this check was bogus.
2022-05-06 12:43:45 -06:00
38478d1061
[gvar] DEFINE_SIZE_ARRAY instead of DEFINE_SIZE_MIN
2022-05-06 12:43:45 -06:00
90d278c92e
[gvar] Remove requirement that num_glyphs matches the font's
2022-05-06 12:43:45 -06:00
ca8a0f3ea3
[gvar] Protect against out-of-range access
...
Fixes https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=47281
Fixes https://oss-fuzz.com/testcase-detail/5508865908670464
2022-05-06 11:54:38 -06:00
f10ddb8dd8
[cmap] Use -1 as Unicode sentinel, not U+FFFF in Format12 serialize
2022-05-05 11:21:24 -06:00
8a19968c8b
[cmap] Use iterator bool operator
2022-05-05 11:17:23 -06:00
8bfeea4828
[subset] Compute set max using previous()
2022-05-05 11:13:57 -06:00
00cb8c629d
[subset] Don't go into glyf table if it's empty
2022-05-05 11:13:57 -06:00
4fe69bc413
[subset] Use del_range in _remove_invalid_gids
2022-05-05 11:13:57 -06:00
2a42edccbe
[subset] Cosmetic; use set bulk array population instead of for loop
2022-05-05 10:35:54 -06:00
43938ecdc2
[subset] Remove outdated comment
...
I tried something like that. It was slower because of the allocations.
2022-05-04 16:59:28 -06:00
50db78ba83
[subset] In cmap planning, remove a qsort()
2022-05-04 16:18:27 -06:00
052812b6ba
Merge pull request #3561 from googlefonts/cmap_opt
...
[subset] Further cmap subsetting speed optimizations
2022-05-04 15:38:30 -06:00
7cb36e4222
[subset] Re-introduce size threshold in choosing unicode collection method.
...
Threshold is needed since the unicodes set might be an inverted set.
2022-05-04 21:22:26 +00:00
42c54eba83
[subset] Presize unicode to gid list to unicodes + glyphs size.
2022-05-04 20:21:43 +00:00
7c7c01d28c
[subset] Remove switch to alternate unicode collection at large subset sizes.
...
Benchmarks show that the first path is always faster even at large subset sizes:
BM_subset_codepoints/subset_roboto/10_median +0.0324 +0.0325 0 0 0 0
BM_subset_codepoints/subset_roboto/64_median +0.0253 +0.0255 0 1 0 1
BM_subset_codepoints/subset_roboto/512_median +0.0126 +0.0128 1 1 1 1
BM_subset_codepoints/subset_roboto/4000_median +0.0500 +0.0491 6 7 6 7
BM_subset_codepoints/subset_amiri/10_median +0.0338 +0.0332 1 1 1 1
BM_subset_codepoints/subset_amiri/64_median +0.0238 +0.0234 1 1 1 1
BM_subset_codepoints/subset_amiri/512_median +0.0066 +0.0063 8 8 8 8
BM_subset_codepoints/subset_amiri/4000_median -0.0011 -0.0012 13 13 13 13
BM_subset_codepoints/subset_noto_nastaliq_urdu/10_median +0.0226 +0.0226 0 0 0 0
BM_subset_codepoints/subset_noto_nastaliq_urdu/64_median +0.0047 +0.0044 20 20 20 20
BM_subset_codepoints/subset_noto_nastaliq_urdu/512_median +0.0022 +0.0021 165 166 165 166
BM_subset_codepoints/subset_noto_nastaliq_urdu/1000_median -0.0021 -0.0023 166 166 166 165
BM_subset_codepoints/subset_noto_devangari/10_median +0.0054 +0.0054 0 0 0 0
BM_subset_codepoints/subset_noto_devangari/64_median +0.0024 +0.0019 0 0 0 0
BM_subset_codepoints/subset_noto_devangari/512_median +0.0089 +0.0090 5 5 5 5
BM_subset_codepoints/subset_noto_devangari/1000_median -0.0028 -0.0019 5 5 5 5
BM_subset_codepoints/subset_mplus1p/10_median +0.0001 +0.0002 0 0 0 0
BM_subset_codepoints/subset_mplus1p/64_median +0.0073 +0.0075 1 1 1 1
BM_subset_codepoints/subset_mplus1p/512_median +0.0034 +0.0034 1 1 1 1
BM_subset_codepoints/subset_mplus1p/4096_median -0.1248 -0.1248 7 6 7 6
BM_subset_codepoints/subset_mplus1p/10000_median -0.0885 -0.0885 13 12 13 12
BM_subset_codepoints/subset_notocjk/10_median +0.0031 +0.0032 2 2 2 2
BM_subset_codepoints/subset_notocjk/64_median -0.0010 -0.0010 2 2 2 2
BM_subset_codepoints/subset_notocjk/512_median -0.0023 -0.0023 9 9 9 9
BM_subset_codepoints/subset_notocjk/4096_median -0.1725 -0.1726 28 23 28 23
BM_subset_codepoints/subset_notocjk/32768_median -0.0277 -0.0287 140 137 140 136
BM_subset_codepoints/subset_notocjk/100000_median -0.0929 -0.0926 162 147 162 147
2022-05-03 22:45:39 +00:00
f0c04114bc
[subset] Embed unicode to gid list vector in subset plan.
2022-05-03 22:02:59 +00:00
15fa8afb21
Add fast-path for big-endian 32-bit byteswap
...
Speeds up cmap format-12 decoding by some 40% as measured by
the newly added test in perf/benchmark-font!
2022-05-02 16:46:41 -06:00
3fff2e9182
[perf/benchmark-font] Cosmetic
2022-05-02 16:42:10 -06:00
307d2d8bb6
[cmap] Sprinkle some 'unlikely's
2022-05-02 16:30:22 -06:00
85ec5cbcef
[subset] In _populate_unicodes_to_retain populate unicodes in order.
...
Allows the set insert to take advantage of page lookup cache.
2022-05-02 22:29:43 +00:00
088133d939
[subset] cache cp to new gid list in subset plan.
...
This avoids having to recompute the ordered list multiple times during cmap generation.
2022-05-02 21:29:16 +00:00
6922a2561f
[subset] Change serialize_rangeoffset_glyid back to using iterator.
2022-04-29 23:30:32 +00:00
c66fd50c26
[subset] in cmap4 serialization save cp to gid iter to memory.
...
Iterator accesses are slow and it's iterated multiple times.
2022-04-29 23:18:53 +00:00
17b98563dc
[subset] In cmap4 serialization reduce unnessecary calls into the iterator.
...
Gives ~20% speedup for large subsets.
2022-04-29 22:49:02 +00:00
5e241094bf
[subset] In unicodes cache cleanup if set insert fails.
2022-04-29 22:45:16 +00:00
a424a92ce5
[subset] s/void */intptr_t.
2022-04-29 22:14:03 +00:00
aad67f5629
[subset] cache results of collect_unicodes.
2022-04-29 22:05:34 +00:00
b4236b7de6
[subset] Optimize Cmap4 collect_unicodes.
...
Use set add_range() instead of individual add() calls.
2022-04-29 19:22:00 +00:00
067225a86d
[set] Optimize const page_for() using last_page_lookup caching
...
Similar to previous commit.
This speeds up SetLookup benchmark by 50%, but that's because that
lookup always hits the same page...
2022-04-29 13:04:36 -06:00
c283e41ce3
[set] Optimize non-const page_for() using last_page_lookup caching
...
This speeds up SetOrderedInsert tests by 15 to 40 percent, and the
subset_mplus1p benchmarks by 9 to 27 percent.
2022-04-29 12:45:48 -06:00
d8292b8446
[CFF] Fix parsing of empty Index
...
https://github.com/harfbuzz/harfbuzz/issues/3545#issuecomment-1111047941
2022-04-27 12:38:35 -06:00
6454cec085
[USE] Classify U+10A38 as CONS_MOD_BELOW
2022-04-24 11:41:32 -06:00
f7aee78e90
4.2.1
2022-04-24 05:47:57 +02:00
6695bf0560
[gsubgpos] Remove wrong condition in Context application
...
Fixes https://github.com/harfbuzz/harfbuzz/issues/3545
2022-04-22 13:48:41 -06:00
8575a8f50c
Add _hb_codepoint_is_regional_indicator()
2022-04-21 11:15:34 -06:00
c1ee7d28f3
Typo
...
Co-authored-by: Khaled Hosny <khaled@aliftype.com>
2022-04-21 11:15:34 -06:00
4d48fae4f2
Enforce Regional_Indicators native direction to LTR
...
And undo the morx direction reversal change introduced in
https://github.com/harfbuzz/harfbuzz/pull/3315
23159084b4https://github.com/harfbuzz/harfbuzz/issues/3314
And the reversion in morx code fixes regressions:
https://github.com/harfbuzz/harfbuzz/issues/3528
https://github.com/harfbuzz/harfbuzz/issues/3535
Supersedes:
https://github.com/harfbuzz/harfbuzz/pull/3529
2022-04-21 11:15:34 -06:00
Garret Rieger
Behdad Esfahbod
Thomas Devoogdt
David Corbett
Khaled Hosny