hughperkins/VeriGPU

OpenSource GPU, in Verilog, loosely based on RISC-V ISA

46
/ 100
Emerging

This project helps hardware architects and designers create custom GPU designs specifically optimized for machine learning tasks. It takes Verilog descriptions of GPU components and simulates their behavior, allowing you to evaluate performance and area metrics. The target end-user is a hardware engineer or architect focused on ASIC design for AI acceleration.

1,280 stars. No commits in the last 6 months.

Use this if you are designing a custom GPU for machine learning and need to simulate and verify its architecture before costly physical fabrication.

Not ideal if you are looking for a pre-built GPU to use immediately or want to develop software on existing hardware platforms.

ASIC design GPU architecture Machine learning hardware Hardware verification VLSI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

1,280

Forks

140

Language

SystemVerilog

License

MIT

Last pushed

Nov 22, 2024

Commits (30d)

0

Get this data via API

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

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