NVDLA

The NVIDIA Deep Learning Accelerator (NVDLA) is a free and open architecture that promotes a standard way to design deep learning inference accelerators. With its modular architecture, NVDLA is scalable, highly configurable, and designed to simplify integration and portability. The hardware supports a wide range of IoT devices. Delivered as an open source project under the NVIDIA Open NVDLA License, all of the software, hardware, and documentation will be available on GitHub. Contributions are welcome.

  • Open Source: Developed on GitHub in an open directed community where contributions are encouraged.
  • Complete Solution: Comes complete with a Verilog and C-model, compiler, Linux drivers, test benches and test suites, kernel- and user-mode software, and software development tools. Easily portable to other operating systems.
  • Scalable: Well-suited to scale across a wide range of IoT devices.
  • Proven Hardware Architecture: Based on Xavier — the world's first autonomous processor that NVIDIA designed for automotive products and more — and backed by a full verification suite.
  • Deep Learning Savvy: Smart, efficient, and ready to work with the wide range of NVIDIA supported solutions.

Learn About NVDLA

Gain a full understanding of NVDLA in our conceptual overview.

Learn More >

What's Next

Preview the NVDLA roadmap.

Learn More >

Dive Deep

Ready to dive into NVDLA? Check out the documentation.

Learn More >

Get the Code

Go straight to the source and get the NVDLA code from our repository on GitHub.

Learn More >

Have questions that we haven't answered? Feel free to contact the NVDLA team by e-mail.