How to integrate TVM and NVDLA?

[chayi]

Hi, I am the beginner of TVM, I find some clues about integrating NVDLA with TVM, such as:

How to extend NNVM/TVM as a static compiler for HW accelerator like NVDLA?

I have an interest in using NNVM/TVM as a static compiler to generate a runtime image for HW accelerator like that of NVDLA. NVDLA accelerates at a much higher level of abstraction than CPU and GPU, e.g. conv2d, batchborm, etc. Graph level optimisation like ops fusion by NNVM will be very useful. Can you advise how best I should approach, e.g. relevant topics in the documentation/tutorial etc. Thanks. –kahho

Integrating NVDLA to VTA (Diary)

Here is my branch

 but not easy to get a real simple example to teach me how to do step by step.     
 Is it possible to integrate NVDLA to VTA? Or it is better to use original NVDLA Compiler and 
 just use TVM to generate NVDLA Canonical Graph? I mean use TVM BYOC to generate NVDLA JSON file for NVDLA Compiler, ... NVDLA Runtime...

 Any suggestion is appreciated,

Thank you, –chayi

[sun-lingyu]

Same question, any help is appreciated, plz!

[kfeng123]

This project may help:

GitHub - LCAI-TIHU/SW: LCAI-TIHU SW is a software stack of the AI inference...