Behdad Esfahbod
|
ad7f428be4
|
[set-digest] Comment
|
2 weeks ago |
|
Behdad Esfahbod
|
900db7b1bd
|
[bit-set] Add a couple of alias methods
|
2 weeks ago |
|
Behdad Esfahbod
|
942a30b7df
|
[aat] Remove now-unused code
|
2 weeks ago |
|
Behdad Esfahbod
|
44281b2856
|
[aat] Back to simplified heuristic
Performs overall better.
|
2 weeks ago |
|
Behdad Esfahbod
|
dc8da6129f
|
Merge pull request #5042 from harfbuzz/aat-regression
[aat] Fix performance regression
|
2 weeks ago |
|
Behdad Esfahbod
|
b857b21a45
|
[morx] Try using buffer-glyph-set adaptive to number of chains
|
2 weeks ago |
|
Behdad Esfahbod
|
491c8c4e10
|
Revert "[aat] Change threshold from 4 to 16"
This reverts commit 624d6edfe4.
Some other benchmarks see better results for 4. Let's leave at that.
|
2 weeks ago |
|
Behdad Esfahbod
|
624d6edfe4
|
[aat] Change threshold from 4 to 16
Still worth it it seems.
|
2 weeks ago |
|
Behdad Esfahbod
|
a26cf0f409
|
[aat] Fix regression in performance of shaping tiny strings
|
2 weeks ago |
|
Behdad Esfahbod
|
cec5c57130
|
[aat] Refactor a method
|
2 weeks ago |
|
Behdad Esfahbod
|
cd5dfc6dbe
|
[kerx] Use hb_bit_set_t instead of hb_set_t
|
2 weeks ago |
|
Behdad Esfahbod
|
d40c079fed
|
[morx] Use hb_bit_set_t instead of hb_set_t directly
|
2 weeks ago |
|
Behdad Esfahbod
|
7b9277486f
|
[bit-set] Rename a method
|
2 weeks ago |
|
Behdad Esfahbod
|
b44f6ff5fe
|
[perf/texts] Add a list of just 2letter strings
|
2 weeks ago |
|
Behdad Esfahbod
|
f738534042
|
Merge pull request #5041 from harfbuzz/aat-machine-initial
[morx] Only collect glyphs that can initiate action in the machine
|
2 weeks ago |
|
Behdad Esfahbod
|
fc825168d0
|
[aat] Remove idempotent check
Not necessary after the recent filtering.
Another 10% speedup with LucidaGrande.
|
2 weeks ago |
|
Behdad Esfahbod
|
849b17351e
|
[aat] Divide the logic of is_actionable() into two
The two different uses require different logic. I had combined
the two logic into one in 37bfdf79c6
|
2 weeks ago |
|
Behdad Esfahbod
|
b4787838e4
|
[aat] Speed up per-machine initial-glyph-set calculation
Use a bit-page instead of a full hb-set.
|
2 weeks ago |
|
Behdad Esfahbod
|
7d14eb5eb3
|
[aat] Minor rename
|
2 weeks ago |
|
Behdad Esfahbod
|
6215d68b69
|
[aat] Minor tweak to logic
DELETED_GLYPH can also initiate action.
|
2 weeks ago |
|
Behdad Esfahbod
|
dc4ff7012c
|
[bit-page] Add a couple of operators
|
2 weeks ago |
|
Behdad Esfahbod
|
37bfdf79c6
|
[morx] Only collect glyphs that can initiate action in the machine
And match them against the buffer glyph_set.
4% speedup in LucidaGrande.
|
2 weeks ago |
|
Behdad Esfahbod
|
d9e99baa9a
|
[aat] Move is_actionable outside of the driver_context
|
2 weeks ago |
|
Behdad Esfahbod
|
5ade5bab01
|
[aat] Move Flags out of driver_context_t
|
2 weeks ago |
|
Behdad Esfahbod
|
9f38690e8e
|
[aat] Remove another unused parameter
One logic change, but should be fine.
|
2 weeks ago |
|
Behdad Esfahbod
|
d9058c64e0
|
[aat] Remove an unused parameter
|
2 weeks ago |
|
Behdad Esfahbod
|
1a2780735c
|
[array] Micro-optimize
|
2 weeks ago |
|
Behdad Esfahbod
|
c87bfe410b
|
[morx] Reuse a variable
|
2 weeks ago |
|
Behdad Esfahbod
|
e99e6538d9
|
[aat-map] Micro-optimize a malloc
|
2 weeks ago |
|
Behdad Esfahbod
|
3e27038fca
|
[aat-map] Micro-optimize
|
2 weeks ago |
|
Behdad Esfahbod
|
7f5fac7c87
|
[test-buffer] Fix unintionally merged change
|
2 weeks ago |
|
Behdad Esfahbod
|
f0ead85283
|
[aat] Implement set filtering for Noncontextual chains as well
|
2 weeks ago |
|
Behdad Esfahbod
|
e5bdba0b3c
|
[aat] Rename a variable
|
2 weeks ago |
|
Behdad Esfahbod
|
cb09fe7995
|
[bit-set] Remove a likely()
|
2 weeks ago |
|
Behdad Esfahbod
|
749dc1eee0
|
[bit-set] Fix may_intersect() logic
|
2 weeks ago |
|
Behdad Esfahbod
|
b30c65e271
|
Merge pull request #5040 from harfbuzz/aat-set
[aat] Speed up subchain skipping using exact sets
|
2 weeks ago |
|
Behdad Esfahbod
|
22a21e81a0
|
[aat] Fix a crash
|
2 weeks ago |
|
Behdad Esfahbod
|
275fb565bb
|
[morx] Clean up memory
|
2 weeks ago |
|
Behdad Esfahbod
|
255dadc152
|
[set] Speed up may_intersect()
|
2 weeks ago |
|
Behdad Esfahbod
|
a617328005
|
[bit-set] Sprinkle a few .arrayZ around
All accesses are valid.
|
2 weeks ago |
|
Behdad Esfahbod
|
7862c7c5e1
|
Rename a method again
|
2 weeks ago |
|
Behdad Esfahbod
|
474bef1cfd
|
[aat] Use exact set for buffer intersection versus subchains
|
2 weeks ago |
|
Behdad Esfahbod
|
95eefa38f6
|
[set] Add a brute-force intersects(other_set)
|
2 weeks ago |
|
Behdad Esfahbod
|
80bbb0b2e9
|
[set-digest] Rename a method
|
2 weeks ago |
|
Behdad Esfahbod
|
7d17ea4996
|
Merge pull request #5037 from harfbuzz/face-blob
[face] Add fallback implementation to hb_face_reference_blob
|
2 weeks ago |
Khaled Hosny
|
a315d43b04
|
[doc] Update hb_face_reference_blob() and hb_reference_table_func_t
|
2 weeks ago |
|
Behdad Esfahbod
|
5b49ac21fe
|
Merge pull request #5039 from harfbuzz/lucida
[aat] Speed up Lucida Grande among others
|
2 weeks ago |
|
Behdad Esfahbod
|
722ab54868
|
[kerx] Don't compute buffer digest
We don't use it in kerx
|
2 weeks ago |
|
Behdad Esfahbod
|
449c7f2a0d
|
[aat] Add some tracing
|
2 weeks ago |
|
Behdad Esfahbod
|
3a1d7ee7e8
|
[aat] Remove the buffer-digest threshold
This can help us skip entire subchains, eg. when they are for
different scripts.
Speeds up LucidaGrande with ASCII text by 20%.
|
2 weeks ago |
