Codegen: Add TVMCG_DEBUG_ALLOCATIONS and handle error code properly

tum-ei-eda / utvm_staticrt_codegen

This project contains a code generator that produces static C NN inference deployment code targeting tiny micro-controllers (TinyML) as replacement for other µTVM runtimes. This tools generates a runtime, which statically executes the compiled model. This reduces the overhead in terms of code size and execution time compared to having a dynamic on-device runtime.

Apache License 2.0

27 stars 9 forks source link

Codegen: Add TVMCG_DEBUG_ALLOCATIONS and handle error code properly #10

Closed PhilippvK closed 3 years ago

PhilippvK commented 3 years ago

Waiting to CI to complete before merging...

PhilippvK commented 3 years ago

okay, i will update the tvm patches later to fix this...

PhilippvK commented 3 years ago

I have added some linter checks to the CI config to ensure that the formatting of c++ is fine. (Copied most parts over from another project, so it was not too much effort) There are still some issues with a few targets I will fix later…

PhilippvK commented 3 years ago

Will close this and open another PR when I have more time.