2 layers
Small-2
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
240 parts56Apache-2.0
2 layers
Small-9
NVlabs/Cypress56Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
- Copper layers
- 2
- Thickness
- 1.6 mm
- Parts
- 476
- Nets
- 1,512
- Pads
- 2,212
- Tracks, vias
- 2,606, 237
- Routed
- Yes
- KiCad
- KiCad 8.0 (file 20240108)
- Created
- 11 Oct 2024
- Updated
- 3 Mar 2026
Overview
Small-9 is an open-source printed circuit board by NVlabs, from the NVlabs/Cypress repository on GitHub, published under the Apache-2.0 licence. It is a 2-layer board with 476 parts on 1,512 nets, routed with 2,606 tracks and 237 vias.
README
README.mdCypress: VLSI-Inspired Scalable GPU-Accelerated PCB Placement
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
How to Build
You can build in two ways:
- Build without Docker by following the instructions of the DREAMPlace build at README_DREAMPlace.md.
- Use the provided Dockerfile to build an image with the required library dependencies.
Run PCB Placement
cd /Cypress
python dreamplace/Placer.py path/to/your/config.jsonRun Hyperparameter search
./tuner/run_tuner.sh 1 1 test/tune/pcb-configspace.json /path/to/aux_file test/tuner/tuner-ppa.json "" 100 4 0 0 10 ./tuner ./results/result_pathAcknowledgement
Cypress builds upon and extends the following open-source projects:
-
DREAMPlace: A deep learning toolkit-enabled VLSI placement framework that provides the foundation for our GPU-accelerated placement engine.
-
AutoDMP: An automated design methodology platform that inspired aspects of our hyperparameter tuning approach.
We thank the authors and contributors of these projects for their valuable work that made Cypress possible.
Citation
If you find this work useful, please cite the following paper:
@inproceedings{zhang2025cypress,
title={Cypress: VLSI-Inspired PCB Placement with GPU Acceleration},
author={Zhang, Niansong and Agnesina, Anthony and Shbat, Noor and Leader, Yuval and Zhang, Zhiru and Ren, Haoxing},
booktitle={Proceedings of the 2025 International Symposium on Physical Design},
pages={xx--xx},
year={2025}
}Parts
476| Qty | Value | Footprint | References |
|---|---|---|---|
| 1 | C106 | C106 | C106 |
| 1 | C107 | C107 | C107 |
| 1 | C108 | C108 | C108 |
| 1 | C109 | C109 | C109 |
| 1 | C110 | C110 | C110 |
| 1 | C111 | C111 | C111 |
| 1 | C112 | C112 | C112 |
| 1 | C113 | C113 | C113 |
| 1 | C120 | C120 | C120 |
| 1 | C121 | C121 | C121 |
| 1 | C122 | C122 | C122 |
| 1 | C129 | C129 | C129 |
| 1 | C131 | C131 | C131 |
| 1 | C133 | C133 | C133 |
| 1 | C135 | C135 | C135 |
| 1 | C136 | C136 | C136 |
| 1 | C140 | C140 | C140 |
| 1 | C141 | C141 | C141 |
| 1 | C142 | C142 | C142 |
| 1 | C144 | C144 | C144 |
| 1 | C146 | C146 | C146 |
| 1 | C148 | C148 | C148 |
| 1 | C150 | C150 | C150 |
| 1 | C151 | C151 | C151 |
| 1 | C153 | C153 | C153 |
| 1 | C155 | C155 | C155 |
| 1 | C177 | C177 | C177 |
| 1 | C178 | C178 | C178 |
| 1 | C179 | C179 | C179 |
| 1 | C196 | C196 | C196 |
| 1 | C197 | C197 | C197 |
| 1 | C198 | C198 | C198 |
| 1 | C199 | C199 | C199 |
| 1 | C200 | C200 | C200 |
| 1 | C201 | C201 | C201 |
| 1 | C202 | C202 | C202 |
| 1 | C203 | C203 | C203 |
| 1 | C204 | C204 | C204 |
| 1 | C205 | C205 | C205 |
| 1 | C206 | C206 | C206 |
| 1 | C222 | C222 | C222 |
| 1 | C223 | C223 | C223 |
| 1 | C224 | C224 | C224 |
| 1 | C225 | C225 | C225 |
| 1 | C228 | C228 | C228 |
| 1 | C331 | C331 | C331 |
| 1 | C332 | C332 | C332 |
| 1 | C333 | C333 | C333 |
| 1 | C334 | C334 | C334 |
| 1 | C335 | C335 | C335 |
| 1 | C336 | C336 | C336 |
| 1 | C337 | C337 | C337 |
| 1 | C338 | C338 | C338 |
| 1 | C339 | C339 | C339 |
| 1 | C340 | C340 | C340 |
| 1 | C341 | C341 | C341 |
| 1 | C342 | C342 | C342 |
| 1 | C343 | C343 | C343 |
| 1 | C344 | C344 | C344 |
| 1 | C345 | C345 | C345 |
| 1 | C346 | C346 | C346 |
| 1 | C347 | C347 | C347 |
| 1 | C348 | C348 | C348 |
| 1 | C349 | C349 | C349 |
| 1 | C350 | C350 | C350 |
| 1 | C351 | C351 | C351 |
| 1 | C352 | C352 | C352 |
| 1 | C353 | C353 | C353 |
| 1 | C354 | C354 | C354 |
| 1 | C355 | C355 | C355 |
| 1 | C356 | C356 | C356 |
| 1 | C357 | C357 | C357 |
| 1 | C358 | C358 | C358 |
| 1 | C359 | C359 | C359 |
| 1 | C360 | C360 | C360 |
| 1 | C361 | C361 | C361 |
| 1 | C362 | C362 | C362 |
| 1 | C363 | C363 | C363 |
| 1 | C364 | C364 | C364 |
| 1 | C365 | C365 | C365 |
The 80 most common of 476 parts.
More from NVlabs/Cypress
11- 2 layers
Small-10
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
136 parts56Apache-2.0 - 2 layers
Small-8
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
115 parts56Apache-2.0 - 2 layers
Small-3
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
63 parts56Apache-2.0 - 2 layers
Small-1
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
57 parts56Apache-2.0 - 2 layers31.2 × 21 mm
Small-7 legacy
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
52 parts56Apache-2.0 - 2 layers
Small-7
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
52 parts56Apache-2.0 - 2 layers31.3 × 21 mm
S7-cypress
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
50 parts56Apache-2.0 - 2 layers
Small-6
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
46 parts56Apache-2.0 - 2 layers31.3 × 21 mm
Small-4
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
43 parts56Apache-2.0 - 2 layers31.3 × 21 mm
Small-5
NVlabs/Cypress
Cypress is a scalable, GPU-accelerated PCB placement method inspired by VLSI. It incorporates tailored cost functions, constraint handling, and optimized techniques adapted for PCB layouts.
41 parts56Apache-2.0
Similar boards
- 2 layers203.2 × 114.6 mm
- 2 layers50 × 93 mm
Led bar Panelize
JamesBond6873/Airborne_Rescue_Line_2025
Airborne's full RoboCup Rescue Line 2025 code and documentation
476 parts3MIT - 2 layers112.8 × 114.8 mm
- 2 layers285.8 × 285.8 mm
Donutcables scrabblepad kicad files scrabblepad 6mil traces
oomlout/oomlout_oomp_project_bot_v_2
475 parts - 2 layers410.2 × 272.4 mm
- 2 layers332.1 × 248.3 mm
Apple color monitor iie a2m2056
fredsa/apple-color-monitor-iie-a2m2056
Apple ColorMonitor IIe (A2M2056) KiCad schematic
478 parts3Apache-2.0 - 2 layers93 × 173 mm
Batch 1
CDFER/Business-Cards
Showcasing a collection of functional PCB business cards, each demonstrating a unique embedded electronics project.
479 parts9 - 2 layers66 × 61 mm
Bingo card-1a
strickyak/copico-bonobo
KICAD: Simple and cheap PI PICO cartridge for Coco; can spoonfeed to boot, and has Control & Data ports decoded.
479 parts6MIT
Questions
What parts does the Small-9 use?
476 parts. The full list of its parts is on this page, with links to each part's symbol and footprint where PCBKit's library has them.
Where can I download the Small-9 KiCad files?
From the NVlabs/Cypress repository on GitHub, at the commit this page was made from: the board is artifacts/kicad/small-9.kicad_pcb. PCBKit opens the board in the browser, with nothing to install.
Can I use the Small-9 design in my own project?
Its repository publishes it under the Apache-2.0 licence: you may reuse it on that licence's terms (keep the author's notice, and for a copyleft licence share your changes alike).