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
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
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
Behdad Esfahbod
Garret Rieger
jeremiazhao
Thomas Devoogdt