FareedKhan-dev/small-gpu

Building a Tiny GPU to understand AI hardware engineering

46
/ 100
Emerging

Implements a fully functional GPU in SystemVerilog with 12 core components (ALU, memory controller, scheduler, dispatcher, etc.), simulated entirely on your laptop rather than requiring fabrication labs. Uses INT8 quantized arithmetic and strips away caches and branch prediction to create a clear, educational model of parallel thread execution and warp scheduling. Includes practical testing modules and architectural comparisons to NVIDIA H100 to bridge the gap between PyTorch-level AI engineering and silicon-level hardware fundamentals.

No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 11 / 25
Community 17 / 25

How are scores calculated?

Stars

46

Forks

9

Language

SystemVerilog

License

MIT

Last pushed

Jan 22, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/FareedKhan-dev/small-gpu"

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