Commit Graph

14463 Commits

Author SHA1 Message Date
Behdad Esfahbod 03e6bde790 [glyf] Minor adjustment to lastflag handling
No logic change.
2022-11-22 14:40:50 -07:00
Behdad Esfahbod 0ca9fda889 [glyf] Remove misplaced comment 2022-11-22 14:39:10 -07:00
Behdad Esfahbod 44be8ef4ce [gvar] Skip degenerate all-untouched delta-sets 2022-11-22 14:21:25 -07:00
Behdad Esfahbod 656bb223f1 [gvar] Micro-optimize unpack_points 2022-11-22 14:16:40 -07:00
Behdad Esfahbod a383027262 [gvar] Cosmetic 2022-11-22 14:15:17 -07:00
Behdad Esfahbod be89919a70 [gvar] is_valid() remove a check
I don't know why this check was there, but it doesn't make sense
because that function never returns 0 / false.
2022-11-22 13:56:20 -07:00
Behdad Esfahbod e8ddf107d0 [gvar] Optimize a loop 2022-11-22 13:29:32 -07:00
Behdad Esfahbod dd6fcec92c [gvar] Remove a conditional 2022-11-22 13:27:40 -07:00
Behdad Esfahbod a02317238a [gvar] Refactor deltas array access 2022-11-22 13:24:39 -07:00
Behdad Esfahbod c34c77698c [gvar] Don't try IUP if all points are specified 2022-11-22 13:21:01 -07:00
Behdad Esfahbod 27c4037e59 [gvar] Micro-optimize boundary-checking 2022-11-22 13:12:22 -07:00
Behdad Esfahbod ab8346fb6f [gvar] Add an unlikely 2022-11-22 13:07:39 -07:00
Behdad Esfahbod 1e8a342ea2 [gvar] Micro-optimize int types 2022-11-22 13:04:32 -07:00
Behdad Esfahbod 4afcdf675b More hb_memcpy 2022-11-22 12:56:48 -07:00
Behdad Esfahbod 58a696d80e More hb_memset 2022-11-22 12:56:05 -07:00
Behdad Esfahbod 59c45f6deb Use hb_memcpy instead of memcpy consistently 2022-11-22 12:54:50 -07:00
Behdad Esfahbod ac0efaf818 Use hb_memset instead of memset consistently 2022-11-22 12:50:36 -07:00
Behdad Esfahbod 44a892a233 [shape] Use hb_memcmp instead of memcmp 2022-11-22 12:48:52 -07:00
Behdad Esfahbod c53c648127 [subset-cff] Another handrolled memcpy 2022-11-22 12:46:25 -07:00
Behdad Esfahbod ae578705c2 [array] Write hash as range for loop again
Now that our range loop is faster than our own iter.
2022-11-22 12:23:17 -07:00
Behdad Esfahbod 13e1ca9eb5 [cff] Micro-optimize memcpy 2022-11-22 12:19:28 -07:00
Behdad Esfahbod 2968dd7844 [gvar] Optimize as_array() access 2022-11-22 11:57:29 -07:00
Behdad Esfahbod bb3bb76450 [gvar] Optimize scalar = 1.0 case 2022-11-22 11:53:35 -07:00
Behdad Esfahbod 2d098d5d7f [gvar] Use memset 2022-11-22 11:51:04 -07:00
Behdad Esfahbod e630a65e60 [gvar] Micro-optize vector extend 2022-11-22 11:29:13 -07:00
Behdad Esfahbod 49d4f62135 [gvar] Micro-optimize 2022-11-22 11:14:56 -07:00
Behdad Esfahbod 1758ee6646 [glyf] Minor write loop more idiomatically 2022-11-22 10:55:16 -07:00
Behdad Esfahbod 16ec9dcc1b [gvar] Whitespace 2022-11-22 10:55:16 -07:00
Behdad Esfahbod b567ce51d3 [subset] Don't trim glyf's again if preprocessed
Speeds up M1/10000 benchmark by 30%!
2022-11-22 10:55:08 -07:00
Behdad Esfahbod 72059a4789 [gvar] Optimize IUP alg 2022-11-22 10:41:37 -07:00
Behdad Esfahbod ee9873b5ed [gvar] Disable initializing vectors when not necessary 2022-11-22 10:23:17 -07:00
Behdad Esfahbod b0d2641186 [vector] Add "initialize" argument to resize() 2022-11-22 10:20:11 -07:00
Behdad Esfahbod a2059f8f55 [gvar] Optimize unpack_points 2022-11-22 10:16:21 -07:00
Behdad Esfahbod 6d7206b68b [gvar] Optimize unpack_deltas 2022-11-22 10:13:14 -07:00
Behdad Esfahbod bca569ae53 [array] Speed up hash() for byte arrays 2022-11-21 23:19:42 -07:00
Behdad Esfahbod d7b492e3f5 Revert "[array] Remove hash specializations for bytes"
This reverts commit 213117317c.
2022-11-21 23:08:51 -07:00
Behdad Esfahbod 1572ba281a [subset-cff] Return in subr closure if already seen subr
Not sure why this was not done before.
2022-11-21 22:26:44 -07:00
Behdad Esfahbod a29ca6efbc [subset-cff] Comment 2022-11-21 22:02:17 -07:00
Behdad Esfahbod 28e767ddea [subset-cff] Really optimize op_str_t / parsed_cs_op_t layout
Now parsed_cs_op_t and op_str_t are both 16 bytes.

Saves another 7% in SourceHanSans/10000 benchmark.
2022-11-21 21:59:51 -07:00
Behdad Esfahbod 2d5ee23731 [subset-cff] Readjust parsed_cs_op_t
Now it doesn't matter anymore since op_str_t is adjusted and
is 16 bytes with 8byte alignment.
2022-11-21 21:55:21 -07:00
Behdad Esfahbod 4f056b923a [subset-cff] Optimize op_str_t layout 2022-11-21 21:37:57 -07:00
Behdad Esfahbod a750cb0128 Simplify rvalue creation 2022-11-21 21:03:32 -07:00
Behdad Esfahbod 86a763c651 [map] Make keys moveable 2022-11-21 20:53:44 -07:00
Behdad Esfahbod cf20d2ec5d [map] Take const key 2022-11-21 20:47:17 -07:00
Behdad Esfahbod 3d1c76f713 [serializer] Don't hash objects twice 2022-11-21 19:40:32 -07:00
Behdad Esfahbod 35878df215 [algs] Implement swap() for pair_t
Helps priority_queue::pop_minimum and friends, which help subsetter
repacker. Shows a few percentage improvement on NotoNastaliq benchmark.
2022-11-21 19:14:03 -07:00
Behdad Esfahbod a2984a2932 [cff] Remove unnecessary namespacing 2022-11-21 18:40:52 -07:00
Behdad Esfahbod dc3bb5e0ed [subset-cff] Pre-allocate values array for subroutines as well 2022-11-21 18:18:48 -07:00
Behdad Esfahbod c6279224db [cff] Adjust pre-allocation
This better matches actual usage, given that ops are one or two
bytes, and vector also allocates 50% extra.
2022-11-21 18:01:50 -07:00
Behdad Esfahbod bab8ec58b0 [subset-cff] Disable sharing when packing charstring INDEXes
Saves another 8%ish.
2022-11-21 17:46:32 -07:00