freetype-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: ftbench update: make integrated


From: Ahmet Göksu
Subject: Re: ftbench update: make integrated
Date: Thu, 20 Jul 2023 15:00:07 +0300

Thank you Hin-Tak. 
I have checked the makefile of demos and used libs and the includes as there. (it was overriding the ccraw to cc)

about percentages, i runned the bench with -c 200 to have instant results for development process. here in the benchmark file attached, it made more acceptable result when increased the -c flag to 2000.

I changed compiling and the linking process as the demo programs. i would like to continue to another build system if it seem ok.

Best,
Goksu
goksu.in
On 16 Jul 2023 10:44 +0300, Werner LEMBERG <wl@gnu.org>, wrote:

* i modified benchmark program not to report 'time per op’ but
rather 'cumulative time per N iterations'
* changed the table design
* sentence 'smaller values are better’ is present
* embed a small CSS fragment at the top of the page
* linked to the original baseline and benchmark `.txt`
* everything is being created in the build directory

Nice, thanks! Now the next problem: For the same commit IDs, I see
differences in percentage up to 47% in your HTML file! This
essentially means that the delivered numbers are still completely
meaningless – the differences must be at most a few percent or even
smaller, given that the tests are run on exactly the same machine.

Please investigate how to improve that, probably by modifying the
benchmark test options, or probably even by implementing per-test
options so that the single tests can be fine-tuned. Perhaps you
should do some internet research to find how other, similar benchmark
tests are constructed to get meaningful numbers.


Werner

Benchmark Results

Warning: Baseline and Benchmark have the same commit ID

Info

InfoBaselineBenchmark
Parameters-c 2000-c 2000
Commit IDe9362ecce9362ecc
Commit Date2023-07-14 16:18:00 +03002023-07-14 16:18:00 +0300
BranchGSoC-2023-AhmetGSoC-2023-Ahmet

*Smaller values mean faster operation

Results for Roboto_subset.ttf

Test N Baseline (ms) Benchmark (ms) Difference (%)
Load 240000 1218.299 1146.114 5.9
Load_Advances (Normal) 240000 1253.112 1146.197 8.5
Load_Advances (Fast) 240000 6.242 6.113 2.1
Load_Advances (Unscaled) 240000 5.707 5.780 -1.3
Render 207120 / 197280 785.332 779.617 0.7
Get_Glyph 240000 355.068 347.508 2.1
Get_Char_Index 188000 5.013 4.963 1.0
Iterate CMap 2000 3.994 4.032 -1.0
New_Face 2000 85.614 86.143 -0.6
Embolden 240000 473.296 463.575 2.1
Stroke 55800 / 55200 1595.643 1599.108 -0.2
Get_BBox 240000 237.693 232.396 2.2
Get_CBox 240000 180.251 176.402 2.1
New_Face & load glyph(s) 240000 219.056 213.172 2.7

Results for Arial_subset.ttf

Test N Baseline (ms) Benchmark (ms) Difference (%)
Load 190000 1584.787 1450.270 8.5
Load_Advances (Normal) 190000 1418.097 1396.258 1.5
Load_Advances (Fast) 190000 4.993 5.029 -0.7
Load_Advances (Unscaled) 190000 4.693 4.711 -0.4
Render 160930 / 159980 605.964 613.998 -1.3
Get_Glyph 190000 311.771 313.342 -0.5
Get_Char_Index 188000 4.883 4.939 -1.1
Iterate CMap 2000 4.004 4.007 -0.1
New_Face 2000 102.681 102.656 0.0
Embolden 190000 419.544 416.402 0.7
Stroke 53200 / 53295 1485.566 1485.318 0.0
Get_BBox 190000 198.476 198.821 -0.2
Get_CBox 190000 143.832 146.177 -1.6
New_Face & load glyph(s) 190000 220.099 218.949 0.5

Results for TimesNewRoman_subset.ttf

Test N Baseline (ms) Benchmark (ms) Difference (%)
Load 190000 1772.051 1703.292 3.9
Load_Advances (Normal) 190000 1665.753 1689.698 -1.4
Load_Advances (Fast) 190000 5.021 5.053 -0.6
Load_Advances (Unscaled) 190000 4.639 4.657 -0.4
Render 139270 / 135185 585.516 581.286 0.7
Get_Glyph 165015 / 174325 285.711 288.795 -1.1
Get_Char_Index 188000 4.915 4.865 1.0
Iterate CMap 2000 4.008 3.990 0.4
New_Face 2000 106.830 107.081 -0.2
Embolden 150955 / 153995 448.020 461.508 -3.0
Stroke 39710 / 39330 1537.242 1539.127 -0.1
Get_BBox 172710 / 169290 214.260 221.825 -3.5
Get_CBox 165110 / 161310 134.227 137.620 -2.5
New_Face & load glyph(s) 190000 280.419 287.387 -2.5

Results for Tahoma_subset.ttf

Test N Baseline (ms) Benchmark (ms) Difference (%)
Load 190000 951.933 954.087 -0.2
Load_Advances (Normal) 190000 976.267 977.870 -0.2
Load_Advances (Fast) 190000 5.032 5.043 -0.2
Load_Advances (Unscaled) 190000 4.638 4.688 -1.1
Render 190000 666.053 677.000 -1.6
Get_Glyph 190000 298.770 314.108 -5.1
Get_Char_Index 188000 4.877 4.910 -0.7
Iterate CMap 2000 3.994 3.997 -0.1
New_Face 2000 95.020 98.911 -4.1
Embolden 190000 441.194 439.829 0.3
Stroke 59090 1563.986 1550.612 0.9
Get_BBox 190000 185.814 188.716 -1.6
Get_CBox 190000 137.206 140.941 -2.7
New_Face & load glyph(s) 190000 206.031 210.472 -2.2

Results for Verdana_subset.ttf

Test N Baseline (ms) Benchmark (ms) Difference (%)
Load 190000 921.440 861.377 6.5
Load_Advances (Normal) 190000 934.869 920.798 1.5
Load_Advances (Fast) 190000 5.066 5.069 -0.1
Load_Advances (Unscaled) 190000 4.670 4.758 -1.9
Render 190000 671.072 679.944 -1.3
Get_Glyph 190000 296.105 305.615 -3.2
Get_Char_Index 188000 4.872 4.895 -0.5
Iterate CMap 2000 3.997 3.998 -0.0
New_Face 2000 95.302 94.055 1.3
Embolden 190000 412.991 415.975 -0.7
Stroke 62035 / 61275 1571.461 1578.974 -0.5
Get_BBox 190000 186.651 190.252 -1.9
Get_CBox 190000 140.051 143.831 -2.7
New_Face & load glyph(s) 190000 202.830 225.799 -11.3

Freetype Benchmark

reply via email to

[Prev in Thread] Current Thread [Next in Thread]