CMU-SAFARI/Athena

A reinforcement learning based policy to dynamically coordinate off-chip predictor with multiple data prefetchers, as described in the HPCA2026 paper by Bera and Lang et al.: https://arxiv.org/abs/2601.17615

34
/ 100
Emerging

Athena is a tool for computer architects and system designers to optimize the performance of high-performance processors. It takes in workload execution traces and configuration details of various cache prefetchers and off-chip predictors. The output helps analyze and improve processor execution cycles and memory access efficiency, specifically by coordinating how data is fetched and predicted.

Use this if you are designing or evaluating high-performance processor architectures and need to optimize the interaction between data prefetchers and off-chip predictors to reduce memory latency.

Not ideal if you are working on software-level performance optimization or general application profiling, as this tool is focused on hardware-level architectural simulations.

computer-architecture processor-design memory-hierarchy performance-optimization hardware-simulation
No License No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 5 / 25
Community 15 / 25

How are scores calculated?

Stars

8

Forks

4

Language

C++

License

Last pushed

Jan 27, 2026

Commits (30d)

0

Get this data via API

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

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