Open apowers313 opened 3 months ago
I'm currently working on WebGL support full time, primarily to support large networks. WebGL is much more broadly adopted and works on most mobile browsers.
My understanding is that it's two different purposes. WebGL is for graphics and will help visualization run faster, especially with large networks. WebGPU can also do graphics (I'm not advocating that) but it can also be used as thousands of tiny CPUs to parallelize graph algorithms and make them run faster. For example, calculating betweenness centrality on a graph with 3M nodes and 17M edges takes 513 seconds to run on a CPU and 16 seconds to run on a GPU.
@apowers313, does your team currently have capacity to contribute in this direction?
Waiting for this...
@maxkfranz I wish. Unfortunately this is a personal project, not Amazon related.
Please make this happen :) I really need this feature.
Description of new feature
networkx has an ability to use GPUs to accelerate algorithms resulting in orders of magnitude faster processing time for algorithms like centrality.
There is an emerging WebGPU browser standard with some desktop implementations that enables the use of the GPU in the browser for parallelizing algorithms.
Just throwing it out there that it might be interesting for cytoscape.js to either integrate GPU acceleration or expose a backend plugin API similar to networkx to enable others to do so.
For reviewers
Reviewers should ensure that the following tasks are carried out for incorporated issues:
unstable
branch via pull request. The corresponding pull request is cross-referenced.