GPU-Based Autorouting for KiCad
Details
- External ID
- 45750356
- Source
- HN
- Company
- —
- Product
- GPU-Based Autorouting for KiCad
- Website domain
- github.com
- Launched
- Oct. 29, 2025
- Cohort
- —
- Upvotes
- 8
- Upvotes percentile
- 0.5094339622641509
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
This project began when I decided it would be easier to write an autorouter than route a 8000+ net backplane by hand.This is a KiCad plugin with a few different algorithms, the coolest of which is a 'Manhattan routing grid' autorouter that routes along orthogonal traces. The basic idea was to steal an algorithm from FPGA routing and apply it to PCBs. I'm using CuPy for speeding up the routing; CPU-bound is at least 10x slower than the GPU version.This is in a very pre-alpha state, but it does _technically_ work. It's not great by any measure but then again it is an autorouter.I have a writeup with the how and why it was made: https://bbenchoff.github.io/pages/OrthoRoute.htmlAnd a video showing it route a 512-net backplane in just over 2 minutes: https://www.youtube.com/watch?v=KXxxNQPTagAThis is very cool and one of the first good uses of the KiCad IPC API that was released a few months ago. If this sounds interesting and useful, PRs and issues welcome.
Enrichment
- Theme
- gpu compute and acceleration tools
- Vertical
- Manufacturing
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- gpu-accelerated circuit autorouting for kicad
- Manually corrected
- False
Could you build this?
No Developing high-performance GPU-accelerated autorouting algorithms for dense multi-layer PCB nets involves complex computational geometry and low-level parallel programming.
What it would actually take: Building this requires writing a C++/CUDA or WebGPU engine interfaced via KiCad's plugin architecture. It entails mapping PCB design rule checks (DRC), keepouts, and multi-layer trace geometries to a Manhattan grid or cellular automata, executing massively parallel pathfinding (like A* or Lee's maze router) on GPU hardware, and handling topological rip-up and reroute logic. This demands deep expertise in GPU compute optimization, EDA (Electronic Design Automation), and graph routing algorithms.
Discussion
6 comments analyzed.
Concerns raised: Doesn't handle impedance control, length matching, or differential pairs, Very expensive hobby project with limited practical applications, Only useful for very small subset of very complex boards
Feature requests: Add impedance control support, Add length matching support, Add differential pairs support
Competitors
Other products that read as similar to this one — 105 launches clear the similarity bar, closest 8 shown.
Attention rank: #63 of 106 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Looks like the first mover among its competitors.
- RunMat · hn · 2025-12-02 · 21 upvotes · similarity 0.52
- KiDoom · hn · 2025-11-25 · 362 upvotes · similarity 0.46
- Recursively apply patterns for pathfinding · hn · 2026-02-24 · 26 upvotes · similarity 0.44
- A physically-based GPU ray tracer written in Julia · hn · 2026-02-19 · 198 upvotes · similarity 0.42
- KiCad in the Browser · hn · 2026-07-05 · 111 upvotes · similarity 0.41
- PewCB · ph · 2026-09-22 · 67 upvotes · similarity 0.41
- taichi-path-tracer-from-buaa-cg2024 · github · 2026-09-13 · 25 upvotes · similarity 0.40
- macuda · github · 2026-09-16 · 30 upvotes · similarity 0.38
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.