1–5 Sept 2025
ETH Zurich
Europe/Zurich timezone

Chisel4ml: Direct Circuit Implementation of Deeply Quantized Neural Networks

Not scheduled
1h
HIT G floor (gallery)

HIT G floor (gallery)

Speaker

Jure Vreča

Description

Chisel4ml is a tool we developed for generating fast implementations of deeply quantized neural networks. The tool has a Python frontend and a Chisel backend. The Python frontend serves as an interface to the Python ecosystem for training neural networks. The Chisel backend consists of hardware generators written in the Chisel Hardware Construction Language. This is a language embedded in Scala that offers a wealth of powerful features, such as functional programming, object-oriented programming and static type safety. The tool is capable of processing QONNX-based, deeply quantized neural networks and generating a bit-exact circuit in the form of a Verilog file.

Author

Presentation materials

There are no materials yet.