Our great sponsors
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
It's possible you ran into problems with large pathtags, fixed by [235], but that hasn't been merged yet. With that and some other tweaks (we still have to manually adjust buffer sizes, but that will soon be dynamic again as well), we are able to render the paris-30k test file, which has ~50k paths and almost a million path segments.
We will also soon be special-casing rectangles. Might be worth rerunning your experiment in a few weeks when all this has landed.
In any case, glad for your interest!
[235]: https://github.com/linebender/vello/pull/235
In the ML section you mentioned Kompute and MediaPipe. Have you seen IREE? It has a Vulkan-like compute-only HAL. https://github.com/iree-org/iree
Think of Vulkan, Metal, DirectX 12 (DX12) as different database engines. They run compute/render shaders which are incompatible dialects of each other (like Oracle SQL != Postgres SQL != MySQL). WGPU tries to be the ANSI SQL.
This an oversimplification ofc. Today most shaders compile to an intermediate form Spir-V which then targets different backends and can lead to some funny translation.
See https://github.com/gpuweb/gpuweb/issues/566