Dear All,
I am new to TVM and having trouble understanding the way TVM selects and
executes operators.
Question: How TVM decides which operator (add1 and add2 are parellel) to
execute as follows? and where is this information (and how this information) is
being figured out by TVM?
```
x1 = relay.var('x1', shape=(10,2))
y1 = relay.var('y1', shape=(10,2))
add1 = relay.op.add(x1,y1)
x2 = relay.var('x2', shape=(10,2))
y2 = relay.var('y2', shape=(10,2))
add2 = relay.op.add(x2,y2)
z = add1*add2
```
2) Does the TVM Json file have any semantic information regarding the parallel
operators which can be executed by runtime? Looking at the JSON specification
from here (https://docs.tvm.ai/dev/nnvm_json_spec.html)
---
[Visit
Topic](https://discuss.tvm.ai/t/relationship-between-json-and-tvm-runtime-how-operators-are-selected-for-execution/6477/1)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/email/unsubscribe/2e20d590138074150c25a10f47108ac15c5373c20b53c4c24285a7b95524ca79).
