# Chisel4ml: Generating Fast Implementations of Deeply Quantized Neural Networks using Chisel Generators

- Institution: CERN
- Department: FPGA Developers' Forum (FDF)
- Speaker: Jure Vreča
- Year: 2025
- Language: English
- Source: [CERN](https://videos.cern.ch/record/3021065)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Teens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

Chisel4ml is a tool we developed for generating fast implementations of deeply quantized neural networks to FPGA devices. The tool is implemented in the Chisel Hardware Construction Language, and has a frontend in Python, to enable interfacing with neural network training libraries. We will present basics of the Chisel language and compare chisel4ml against hls4ml. In general, chisel4ml, is able to generate the hardware much faster then high-level synthesis solutions, because it uses structural descriptions of the circuits..

0:00:00 Slide 1

0:03:17 Slide 2

0:04:47 Slide 3

0:06:16 Slide 4

0:11:00 Slide 5

0:14:55 Slide 6

0:16:12 Slide 7

## Lectures

1. [Chisel4ml: Generating Fast Implementations of Deeply Quantized Neural Networks using Chisel Generators](https://invisiblenetwork.ai/learn/cern/3021065/874543be8535), 27 min (CERN's player)