NVDLA
productionNVIDIA's open Deep Learning Accelerator, in RTL.
Indexed from a public source and curated by LibFPGA. Own this project? Claim it by adding a manifest file to your repo.
Source on GitHub → Docs / homepage
Verification
We have not run this core through the LibFPGA toolchain yet, so it carries no earned badges. Many of these projects have strong verification of their own. Claim the listing to run our checks.
- 2,111 GitHub stars
About
The NVIDIA Deep Learning Accelerator: a full, configurable inference engine for convolutional neural networks, released as synthesizable RTL with a C model and testbench. NVDLA is the reference architecture for open deep-learning hardware, scalable from tiny edge configurations to datacenter-class. Released under NVIDIA's Open NVDLA License, check the terms before use.