CMU-SAFARI/Pythia

A customizable hardware prefetching framework using online reinforcement learning as described in the MICRO 2021 paper by Bera et al. (https://arxiv.org/pdf/2109.12021.pdf).

58
/ 100
Established

This project offers a customizable framework for enhancing computer hardware's data prefetching capabilities. It uses reinforcement learning to intelligently anticipate and fetch data before it's explicitly requested, improving processor efficiency. By feeding it program context information, the system learns to make better prefetch decisions, resulting in faster and more efficient program execution. Hardware architects, computer engineers, and researchers working on processor and memory system design would find this valuable.

158 stars.

Use this if you are a hardware designer or researcher looking to evaluate and implement advanced, learning-based data prefetching strategies in processor architectures to improve system performance.

Not ideal if you are a software developer or end-user simply looking to improve application performance without engaging in detailed hardware simulation and design.

hardware-design processor-architecture memory-systems computer-engineering performance-optimization
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

158

Forks

48

Language

C++

License

MIT

Last pushed

Feb 21, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CMU-SAFARI/Pythia"

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