terminal
protocol
sdk
rasterizer
compositing
performance
git license
mcu tests glitch
This is a run of bl_bench from Blend2D running on a single core of a i7-8650U at 2500Mhz. Numbers/bars are time elapsed for each test-case, smaller is better. The benchmark is run on a single core of a i7-8650U at 2500Mhz.
blend2d tested contains updated radial gradient code and feature selection for intel cpus over the last release, Skia is built with gcc, as the clang build crashed, the best of whether SkGraphics::Init() has been called or not has been used per case.
Qt6 and cairo are from debian bookworm, AGG is built with clang.
Last updated: 2024-04-17
The data for the RGBA8 time-trial benchmark is a blend2d-bench dataset - that also can be visualized in more detail Blend2D's performance comparison page by using the custom dataset functionality.
| 🥇 | 🥈 | 🥉 | ||||
| Blend2D | 184 | 14 | 5 | 1 | ctx | 15 | 166 | 19 | 4 | Qt6 | 3 | 11 | 51 | 32 | 53 | 54 | cairo | 2 | 3 | 35 | 49 | 55 | 26 | AGG | 9 | 35 | 26 | 21 | 11 | Skia | 1 | 59 | 92 | 41 | 11 |
The medal summary provides the overall data from this large dataset at a glance. In the following summary we group the tests by how ctx is performing.
This shows performance for doing color fills of circles without and with alpha==1.0. The native formats of ctx, BGRA8, GRAYA8 GRAYAF RGBAF and CMYKAF are performing well, for some others like RGB565 shortcuts have been added to increase performance.