|
c41b0d7b
|
2023-07-10T17:23:58
|
|
[sanitize/PairValueRecord] Add a max_size for faster sanitize
|
|
|
d84c5f29
|
2023-07-08T15:22:51
|
|
Revert "[gsubgpos] Make (Chain)Context funcs templatized"
This reverts commit 03ac08d267eb7ad2f1ac039115fc0030ea475fae.
|
|
|
e73223b9
|
2023-07-08T15:22:18
|
|
[gsubgpos] Make (Chain)Context funcs templatized
Unfortunately they still won't be inlined because the matcher_t
needs function pointers. So, no speed up. Going to revert.
|
|
|
0b879afb
|
2023-07-07T22:35:43
|
|
[sanitize] Inline Coverage::sanitize
|
|
|
2006d321
|
2023-07-07T17:07:11
|
|
[sanitize] Add "fastpath" for ArrayOfOffset16To<> objects with max size
Unfortunately this doesn't speed up NotoNastaliq or Gulzar as I was
hoping for. Their GSUB tables are not large enough for this to kick
in...
|
|
|
7a85663c
|
2023-07-07T19:21:18
|
|
Revert "[sanitize] Add "fastpath" for ArrayOfOffset16To<> objects with max size"
This reverts commit 10f8556c73f3cf231c6b5a900a6a1903f9516f90.
This was, unfortunately, wrong :(.
|
|
|
10f8556c
|
2023-07-07T17:07:11
|
|
[sanitize] Add "fastpath" for ArrayOfOffset16To<> objects with max size
|
|
|
68b78914
|
2023-07-07T17:07:11
|
|
[sanitize] Add "fastpath" for ArrayOfOffset16To<> objects with max size
Unfortunately this doesn't speed up NotoNastaliq or Gulzar as I was
hoping for. Their GSUB tables are not large enough for this to kick
in...
|
|
|
90752cd5
|
2023-07-07T15:47:28
|
|
[type] Add HeadlessArray16Of
|
|
|
25297408
|
2023-07-03T10:34:26
|
|
[COLR] Fix PaintComposite sanitize timeout
Was timing out after recent sanitize() change.
Fixes https://oss-fuzz.com/testcase-detail/5692635449524224
|
|
|
eae82788
|
2023-07-02T13:07:26
|
|
[GPOS] Micro-optimize lazy_some_gpos check
Speeds up 11% in:
BM_Font/load_face_and_shape/Roboto-Regular.ttf/hb
|
|
|
46e54a23
|
2023-07-02T13:03:16
|
|
[GPOS] Remove extra check
|
|
|
7f5380fe
|
2023-07-02T12:19:22
|
|
[Composite] Don't apply transformation if phantom_only
|
|
|
0cf759b0
|
2023-07-02T12:15:43
|
|
[Glyph] Don't shift anchored Composite if phantom_only
Fixes https://oss-fuzz.com/testcase-detail/5114131137822720
|
|
|
645bde47
|
2023-07-02T12:07:22
|
|
[Glyph] Pass phantom-only to gvar only for SIMPLE glyphs
For Composites we need to get the translation offset deltas.
|
|
|
2d6091fc
|
2023-06-30T11:48:56
|
|
[GPOS] Make AnchorMatrix sanitize lazy again
Was reverted in the previous commit, because it was incomplete.
|
|
|
0887382c
|
2023-06-30T11:39:46
|
|
[GPOS] Fix sanitize
|
|
|
690af7aa
|
2023-06-30T10:36:01
|
|
[GPOS] Sanitize Device tables lazily
This speeds up face loading for variable fonts by 80%!
Comparing before to after
Benchmark Time CPU Time Old Time New CPU Old CPU New
---------------------------------------------------------------------------------------------------------------------------------------------------------------
BM_Font/load_face_and_shape/Roboto-Regular.ttf/hb -0.0368 -0.0366 20 20 20 19
BM_Font/load_face_and_shape/RobotoFlex-Variable.ttf/hb -0.7149 -0.7162 77 22 77 22
BM_Font/load_face_and_shape/RobotoFlex-Variable.ttf/var/hb -0.7241 -0.7255 80 22 79 22
BM_Font/load_face_and_shape/SourceSansPro-Regular.otf/hb -0.1441 -0.1445 28 24 28 24
BM_Font/load_face_and_shape/AdobeVFPrototype.otf/hb -0.7893 -0.7910 66 14 66 14
BM_Font/load_face_and_shape/AdobeVFPrototype.otf/var/hb -0.7865 -0.7882 67 14 66 14
BM_Font/load_face_and_shape/SourceSerifVariable-Roman.ttf/hb -0.8895 -0.8900 227 25 226 25
BM_Font/load_face_and_shape/SourceSerifVariable-Roman.ttf/var/hb -0.8895 -0.8900 226 25 225 25
BM_Font/load_face_and_shape/Comfortaa-Regular-new.ttf/hb -0.5512 -0.5531 42 19 42 19
BM_Font/load_face_and_shape/NotoNastaliqUrdu-Regular.ttf/hb -0.1511 -0.1510 227 192 225 191
BM_Font/load_face_and_shape/NotoSerifMyanmar-Regular.otf/hb -0.1494 -0.1498 41 35 40 34
OVERALL_GEOMEAN -0.6443 -0.6456 0 0 0 0
|
|
|
d338506c
|
2023-06-30T10:13:05
|
|
[GPOS] Reuse sanitize_values_stride_unsafe in another function
|
|
|
794fac32
|
2023-06-29T20:55:52
|
|
[glyf] Minor another range for loop
|
|
|
0ae16766
|
2023-06-29T20:38:42
|
|
[CompositeGlyph] Minor use a range for loop
|
|
|
05c01ad5
|
2023-06-29T16:49:20
|
|
[SimpleGlyph] Minor use a range for loop
|
|
|
4123e0c7
|
2023-06-29T16:27:35
|
|
[path-builder] Speed up mid-point calculation
|
|
|
ca44c38c
|
2023-06-29T14:41:21
|
|
Add HB_ALWAYS_INLINE
With MSVC implementation as well.
|
|
|
c49ca371
|
2023-06-29T12:38:45
|
|
[Glyph] Minor micro-optimize away a function call
For when coords are not set.
|
|
|
5fb7b02a
|
2023-06-29T12:28:43
|
|
[CompositeGlyph] Minor use range loop
|
|
|
20b32b04
|
2023-06-29T12:08:11
|
|
[SimpleGlyph] Micro-optimize phantom_only
|
|
|
04809ede
|
2023-06-29T11:58:53
|
|
[CompositeGlyph] Micro-optimize translate()
|
|
|
229db973
|
2023-06-29T11:54:10
|
|
[CompositeGlyph] Minor use vector::push()
|
|
|
75101802
|
2023-06-29T10:54:49
|
|
[CompositeGlyph] Micro-optimize
|
|
|
e9d74d6b
|
2023-06-29T10:53:52
|
|
[SimpleGlyph] Minor add an unlikely to error condition
|
|
|
6abca413
|
2023-06-29T10:39:49
|
|
[path-builder] Micro-optimize
No need to initialize these when has_data=false.
|
|
|
5703c1c4
|
2023-06-29T10:35:23
|
|
[path-builder] Add a couple of unlikely's
|
|
|
f5eead04
|
2023-06-28T15:07:15
|
|
[glyf/gvar] Optimize getting variable phantom points
Used when there's no HVAR table and get_h_advance().
I see some 10% speedup with a SourceSerifVariable-Roman with
the HVAR table removed.
|
|
|
e42d6df5
|
2023-06-28T14:25:11
|
|
[glyf] Minor refactor a couple of lines and micro-optimize
|
|
|
c31471d1
|
2023-06-28T13:51:54
|
|
[glyf] Micro-optimize
|
|
|
83d75d5e
|
2023-06-28T13:35:24
|
|
[glyf] always_inline consume_point
7% speedup in:
BM_Font/draw_glyph/Roboto-Regular.ttf/hb
|
|
|
8795cced
|
2023-06-28T13:29:29
|
|
Revert "[SimpleGlyph] Avoid branches in read_points"
This reverts commit ba062c713e469f91f57f3c85990f721789ec7c2a.
|
|
|
ba062c71
|
2023-06-28T13:24:37
|
|
[SimpleGlyph] Avoid branches in read_points
Calculate total bytes in read_flags and bounds-check once.
This slows things down apparently, so going to revert.
|
|
10b9ca54
|
2023-06-28T07:46:33
|
|
Fix typo: subtitution -> substitution
|
|
|
452557cd
|
2023-06-26T18:40:54
|
|
Replace a free with hb_free
Ouch.
|
|
|
1fc128f6
|
2023-06-26T18:34:27
|
|
Replace a few memset/memcpy's with hb_ equivalents
|
|
|
67b16247
|
2023-06-07T16:15:48
|
|
[set] Simplify a few set iterations as range loop
|
|
|
dcecb4d1
|
2023-06-05T16:03:36
|
|
[subset/ValueFormat] Micro-optimize
|
|
|
469e82a2
|
2023-06-05T15:23:22
|
|
[subset/PairPos] Micro-optimize
|
|
|
6593d2aa
|
2023-06-05T15:11:43
|
|
[subset/PairPos] Speed up
|
|
|
15048e50
|
2023-06-04T10:07:04
|
|
[serialize] Add more function attributes
|
|
|
4e076da9
|
2023-06-04T09:48:42
|
|
Another try at fixing build
|
|
|
b08866af
|
2023-06-04T09:44:37
|
|
Fix build
|
|
|
82741304
|
2023-06-04T09:41:41
|
|
[subset] start_embed never returns nullptr
Remove checks.
|
|
|
af3fdf1f
|
2023-06-04T09:22:42
|
|
[subset/glyf] Simplify error handling
|
|
|
3dd1de46
|
2023-06-04T09:15:14
|
|
[subset/glyf] Fix a few return_trace's
|
|
|
73f2f935
|
2023-06-04T09:12:18
|
|
[subset/glyf] Fix another leak
|
|
|
3d08a2f1
|
2023-06-03T23:38:38
|
|
[subset/glyf] Fix leak
|
|
|
fc33200d
|
2023-06-03T23:29:39
|
|
[subset/glyf] Avoid a vector copy
Oops!
|
|
|
3bfcbd61
|
2023-06-03T23:17:56
|
|
[subset/glyf] Minor use range lopp
|
|
|
917c8d0a
|
2023-06-03T23:15:56
|
|
[subset/glyf] Minor change of value
|
|
|
b5792f11
|
2023-06-03T22:24:06
|
|
[subset] Reuse num_glyphs in various places
|
|
|
87cf09bd
|
2023-06-03T21:00:56
|
|
[subset/loca] Fix up for retaingid null glyphs at the end
We currently don't have those, but in case we add.
|
|
|
38fa0323
|
2023-06-03T18:51:09
|
|
Revert "[subset/loca] Build in the serializer memory"
This reverts commit 546b51818666ca1ddb01824f752eccbd6a751b4b.
|
|
|
546b5181
|
2023-06-03T18:50:35
|
|
[subset/loca] Build in the serializer memory
Because it's hot. Doesn't seem to speed up though. Slight
slowdown. Going to revert.
|
|
|
3cb2b49e
|
2023-06-03T18:44:56
|
|
[subset/loca] Shuffle code around
|
|
|
b0d0babb
|
2023-06-03T17:14:55
|
|
[subset/loca] Rewrite loop faster
|
|
|
ca27925d
|
2023-06-03T16:18:15
|
|
Use hb_codepoint_pair_t in more places
|
|
|
c7493efe
|
2023-06-03T15:39:27
|
|
[subset/loca] Micro-optimize
|
|
|
efefec13
|
2023-06-02T20:33:52
|
|
[subset/glyf] Remove unneeded codepath
|
|
|
ac1f5ca0
|
2023-06-02T17:07:44
|
|
[subset/loca] Micro-optimize
|
|
|
6eae9325
|
2023-06-02T17:05:27
|
|
[subset/loca] Reduce a vector allocation
|
|
|
ec8965e4
|
2023-06-02T16:10:25
|
|
[subset/glyf] Don't clear loca allocation
|
|
|
b67e464b
|
2023-06-02T15:11:06
|
|
[subset/retaingid] Regain perf lost
In 0f12fd5a66a5dd1c3c9ac5ea8a52341bafcfe567
|
|
|
0f12fd5a
|
2023-06-02T13:58:55
|
|
[subset/glyf] Fix for non-monotonic glyphmap
Slows things down again, but is correct. Still a good win
combined with the previous changes.
|
|
|
66ce902c
|
2023-06-02T13:53:21
|
|
[glyf] Reduce allocation again
|
|
|
0e0110e7
|
2023-06-02T13:34:58
|
|
[glyf] Avoid a SubsetGlyph copy
Unfortunately hb_second() always does a copy...
|
|
|
33ea8b5e
|
2023-06-02T13:10:52
|
|
[subset/glyf] Don't allocate empty SubsetGlyf's
Shows 33% speedup on Mplus/retaingid/10 benchmark:
Comparing before to after
Benchmark Time CPU Time Old Time New CPU Old CPU New
--------------------------------------------------------------------------------------------------------------------------------------------------------
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/retaingids/10 -0.3296 -0.3294 0 0 0 0
|
|
|
b04ca1c1
|
2023-06-01T20:43:07
|
|
Revert "[subset/glyf] Exact allocation"
This reverts commit a830f085c849846f8441f5d92d4db36130ef71f8.
Weirdly enough in a benchmark I'm running I see this show
some slowdown. Makes zero sense.
|
|
|
a830f085
|
2023-06-01T20:37:29
|
|
[subset/glyf] Exact allocation
|
|
|
ff0b85cf
|
2023-06-01T20:30:56
|
|
[subset/glyf] Empty .notdef only if old-gid was also 0
Otherwise it wasn't a .notdef, even if new-gid is 0.
|
|
|
65a7d8c6
|
2023-06-01T20:20:00
|
|
[glyf] Empty glyphs need no padding
|
|
|
73c18d1d
|
2023-06-01T20:06:42
|
|
[glyf] Micro-optimize padded_offsets
|
|
|
4d853b8b
|
2023-06-01T18:47:58
|
|
[subset/regaingid/glyf] Add a fastpath for empty glyphs
Mplus benchmark:
Comparing before to after
Benchmark Time CPU Time Old Time New CPU Old CPU New
-----------------------------------------------------------------------------------------------------------------------------------------------------------
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/retaingids/10 -0.1764 -0.1771 0 0 0 0
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/retaingids/64 -0.1394 -0.1394 0 0 0 0
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/retaingids/512 -0.0644 -0.0645 0 0 0 0
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/retaingids/4096 +0.0132 +0.0131 1 1 1 1
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/retaingids/10000 -0.0029 -0.0034 3 3 3 3
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/10 +0.0364 +0.0362 0 0 0 0
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/64 +0.0346 +0.0343 0 0 0 0
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/512 +0.0271 +0.0268 0 0 0 0
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/4096 +0.0193 +0.0193 1 1 1 1
BM_subset/subset_glyphs/Mplus1p-Regular.ttf/10000 -0.0240 -0.0243 2 2 2 2
OVERALL_GEOMEAN -0.0305 -0.0307 0 0 0 0
|
|
|
6ec7629f
|
2023-06-01T18:18:30
|
|
[subset/glyf] Add a const
|
|
|
208c9490
|
2023-05-26T12:02:03
|
|
[VarComposite] Limit number of axes that are copied
Bandaid for https://oss-fuzz.com/testcase-detail/4591122882887680
|
|
|
5872bdf6
|
2023-05-26T11:41:54
|
|
[vector] Add copy-constructor for array_t's
|
|
|
5543d058
|
2023-05-17T17:29:44
|
|
[subset] Use vector instead of map for glyph bounds (#4232)
* [subset] Use vector instead of map for glyph bounds
Is faster.
Part of https://github.com/harfbuzz/harfbuzz/issues/4231
* [subset] initialize bounds_vec value to 0xFFFFFFFF
Some non-EMPTY glyph might have 0 bounds width/height
---------
Co-authored-by: Qunxin Liu <qxliu@google.com>
|
|
bf298e50
|
2023-05-01T13:40:19
|
|
[instancer ]update OS_2/post/glyf tables to accept Triple for axes positions
|
|
|
33ef96b6
|
2023-05-09T11:13:51
|
|
[glyf] Micro-optimize a few hash operations
|
|
|
2f05c32c
|
2023-05-08T14:29:07
|
|
[Coverage] Minor access arrayZ directly in a couple places
|
|
|
4ad443d5
|
2023-05-08T10:14:43
|
|
[Coverage/ClassDef] Don't call qsort if sorted already
|
|
|
8df5cdbc
|
2023-05-07T15:49:50
|
|
[Coverage/ClassDef] Handle glyphID overflow in serialize
|
|
|
71910fdf
|
2023-05-05T15:37:07
|
|
[Coverage] Remove unnecessary check
|
|
|
ee9b631d
|
2023-05-05T10:26:57
|
|
[SingleSubst] Fix condition to upgrade to beyond-64k
|
|
|
0e9ebf10
|
2023-05-05T06:57:51
|
|
[config] Add HB_OPTIMIZE_SIZE_MORE and enable in HB_TINY
Part of https://github.com/harfbuzz/harfbuzz/issues/4220
|
|
|
31949636
|
2023-05-04T16:29:48
|
|
Revert "[layout] Cache subtable coverages in hb_map_t"
This reverts commit 7a715d74e06720c17d28ba7b4c3da0b583f8d1d3.
|
|
|
7a715d74
|
2023-05-04T16:28:11
|
|
[layout] Cache subtable coverages in hb_map_t
Proof-of-concept. Going to revert. Memory consumption is more
than I like. It does speed up Roboto shaping another 15% though.
Perhaps if we could add logic to choose which subtables to
cache, this might be a useful approach.
|
|
|
1be39729
|
2023-05-04T13:18:34
|
|
[subset] Support unordered glyphlist in Coverage/ClassDef serialize
|
|
|
a10fad7c
|
2023-05-04T11:32:07
|
|
[config] Add HB_NO_GDEF_CACHE
|
|
|
319a488b
|
2023-05-04T10:36:48
|
|
[GDEF] Fix null check
Fixes https://oss-fuzz.com/testcase-detail/5920994267889664
|
|
|
fb795dc3
|
2023-05-03T15:17:20
|
|
[GPOS] Optimize iterator reset
Speeds up Gulzar shaping 5%.
|
|
|
8a8fc37c
|
2023-05-03T14:57:00
|
|
[GDEF] Use a cache for glyph classes
Shows 5% speedup for Roboto shaping.
|
|
|
323a1fe4
|
2023-05-03T13:52:43
|
|
[PairPos] Fix what I broke
|