yonseicasl/NPUsim

NPUsim: Full-Model, Cycle-Level, and Value-Aware Simulator for DNN Accelerators

39
/ 100
Emerging

This framework helps hardware architects and researchers design and analyze specialized hardware for deep neural networks (DNNs). It takes your proposed DNN accelerator specifications, DNN network configurations, and a scheduling table as input. It then outputs detailed, cycle-level simulation results, showing how your accelerator performs before you build physical hardware. Hardware architects, computer architects, and system designers would use this.

No commits in the last 6 months.

Use this if you are designing or evaluating a new deep neural network accelerator and need to understand its performance and efficiency at a cycle-level, pre-silicon.

Not ideal if you are a software developer looking to train or deploy DNNs, or if you need to simulate general-purpose CPUs or GPUs.

hardware-design DNN-accelerators computer-architecture pre-silicon-validation system-design
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

50

Forks

8

Language

C++

License

Last pushed

Jan 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yonseicasl/NPUsim"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.