Skip to content

Latest commit

 

History

History
9 lines (6 loc) · 284 Bytes

README.md

File metadata and controls

9 lines (6 loc) · 284 Bytes

v831-npu

Reverse engineering the V831 Neural Network Accelerator (NNA)

Hardware is primarily based off NVIDIA Deep Learning Accelerator(NVDLA) architecture see http://nvdla.org

Differences fromn nvdla implementation:

  1. Verified no FP16 support only int8/16
  2. Verified no Rubik