NEW 100036
REGRESSION(r116210 - r131528): Hindi line-breaking on TOT is 5% slower than Safari 6.0.1 
https://bugs.webkit.org/show_bug.cgi?id=100036
Summary REGRESSION(r116210 - r131528): Hindi line-breaking on TOT is 5% slower than S...
Eric Seidel (no email)
Reported 2012-10-22 14:53:28 PDT
REGRESSION(r116210 - r131528): Hindi line-breaking on TOT is 5% slower than Safari 6.0.1 Obviously the real regression range is much smaller. r116210 is when safari-536-branch (Safari 6) was made from trunk. The microbenchmark in question is attached to bug 100024. I wrote the microbenchmark to make sure that the 8-bit TextRun optimization (bug 99393) wouldn't be a slowdown for complex text for the harfbuzz ports. It's also possible that the microbenchmark a. doesn't test what I want it to. or b. isn't interesting and that this isn't a regression we care about.
Attachments
Add attachment proposed patch, testcase, etc.
Eric Seidel (no email)
Comment 1 2012-10-22 14:57:44 PDT
On my rMBP: r131528: avg 95.18194456386033 runs/s median 95.1814733027575 runs/s stdev 0.22485624887911804 runs/s min 94.7867298578199 runs/s max 95.4653937947494 runs/s Safari 6.0.1 (8536.26.14): avg 104.41866244835714 runs/s median 104.43864229765013 runs/s stdev 0.22674389758002172 runs/s min 104.03120936280884 runs/s max 104.84927916120577 runs/s
Alexey Proskuryakov
Comment 2 2012-10-22 15:10:22 PDT
<rdar://problem/12551884>
Ahmad Saleem
Comment 3 2024-06-22 03:17:12 PDT
*** Safari 18 Beta **** Runs -> [1111.111111111111, 1106.9182389937107, 1090.4584882280044, 1086.4197530864203, 1095.890410958904, 1066.6666666666667, 1055.4089709762534, 1065.2463382157123, 1085.0801479654747, 1093.167701863354, 1093.1677018633566, 1090.4584882280049, 1079.7546012269938, 1089.1089108910867, 1079.7546012269963, 1061.0079575596842, 1071.863580998782, 1074.481074481072, 1073.1707317073146, 1075.794621026895] runs/s mean: 1082.24650486379 runs/s median: 1082.4173745962355 runs/s stdev: 14.656705850006862 runs/s min: 1055.4089709762534 runs/s max: 1111.111111111111 runs/s *** Chrome Canary 128 *** :Runs -> [2174.987642112666, 2172.303135030386, 2281.5659839297377, 2208.004014548626, 2071.733782211984, 2222.222222222222, 2104.4324608686466, 2437.7856780102948, 2310.0144375891055, 2210.7775405110206, 2135.404028150438, 2515.0641865326998, 1888.2769472865243, 2499.349127833718, 1932.1338002665375, 2291.506004188286, 1983.1432821003004, 2245.1843347355066, 2346.6666666666665, 2322.512536286975] runs/s mean: 2217.6533905541173 runs/s median: 2216.4998813666216 runs/s stdev: 170.54885316645746 runs/s min: 1888.2769472865243 runs/s max: 2515.0641865326998 runs/s *** Firefox Nightly 129 *** :Runs -> [2656.4495530012773, 2673.5218508997427, 2687.33850129199, 2704.81144343303, 2704.81144343303, 2715.404699738903, 2708.3333333333335, 2718.954248366013, 2726.08125819135, 2704.81144343303, 2708.3333333333335, 2708.3333333333335, 2704.81144343303, 2694.300518134715, 2711.864406779661, 2708.3333333333335, 2704.81144343303, 2701.2987012987014, 2690.8150064683055, 2708.3333333333335] runs/s mean: 2702.0876314001234 runs/s median: 2704.81144343303 runs/s stdev: 15.677598390574223 runs/s min: 2656.4495530012773 runs/s max: 2726.08125819135 runs/s ___ Microbenchmark - https://jsfiddle.net/et7fwkvg/
zalan
Comment 4 2024-06-22 05:42:18 PDT
We spend enormous amount of time in fallback font handling.
Note You need to log in before you can comment on or make changes to this bug.