KULeuven-MICAS/zigzag
HW Architecture-Mapping Design Space Exploration Framework for Deep Learning Accelerators
This framework helps hardware architects and designers evaluate the performance and cost of different deep learning accelerator designs. You provide an ONNX deep learning model and specifications for a custom hardware architecture, and it outputs detailed energy and latency estimates. This is ideal for researchers and engineers developing specialized hardware for AI workloads.
186 stars.
Use this if you need to quickly and accurately estimate the hardware cost and performance of various deep learning accelerator designs before physical implementation.
Not ideal if you are looking for a tool to train deep learning models or optimize software-only performance.
Stars
186
Forks
56
Language
C++
License
MIT
Category
Last pushed
Jan 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KULeuven-MICAS/zigzag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
fastmachinelearning/hls4ml
Machine learning on FPGAs using HLS
alibaba/TinyNeuralNetwork
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
fastmachinelearning/hls4ml-tutorial
Tutorial notebooks for hls4ml
doonny/PipeCNN
An OpenCL-based FPGA Accelerator for Convolutional Neural Networks
es-ude/elastic-ai.creator
Design, train and generate neural networks optimized specifically for FPGAs.