AMDResearch/intelliperf

Automated bottleneck detection and solution orchestration

44
/ 100
Emerging

This tool helps performance engineers and GPU developers automatically find and fix bottlenecks in their GPU applications. By taking your application's source code and profiling data, it identifies specific code lines causing performance issues like bank conflicts or memory access problems. It then uses AI to suggest and apply optimized code changes, validating them for correctness and speed. This allows you to quickly improve your application's performance.

Use this if you are developing high-performance GPU applications, especially on AMD MI300X GPUs, and need to automatically identify and resolve complex performance bottlenecks.

Not ideal if you are working with non-GPU applications or are looking for a general-purpose code optimization tool not focused on specific GPU performance issues.

GPU-programming performance-tuning code-optimization HPC-engineering kernel-profiling
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

19

Forks

3

Language

Python

License

MIT

Last pushed

Feb 24, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/AMDResearch/intelliperf"

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