[Apache TVM Discuss] [Development/pre-RFC] [Discussion/Alignment] Memory Planning

2021-06-02 Thread aca88 via Apache TVM Discuss
Hi, Very interesting work. I was wondering about the need to [get all topological sorts](https://github.com/tum-ei-eda/tvm/blob/tumeda_memplan/python/tvm/relay/memopt/simnet.py#L196). How robust is this method given that there are many many topological sorts to general DAGs? I guess most man

[Apache TVM Discuss] [Development/pre-RFC] [Discussion/Alignment] Memory Planning

2021-06-02 Thread Rafael Stahl via Apache TVM Discuss
Hi @aca88 thanks for your interest! For the evaluated models, we just used a single schedule as given by TVM: https://github.com/tum-ei-eda/tvm/blob/tumeda_memplan/python/tvm/relay/memplan.py#L187 You are right that for more complex graphs, we would have to evaluate more schedules to find t