Yes two ops, even if they are independent, are run sequentially. This is the code that executes operators:
https://github.com/apache/incubator-tvm/blob/master/src/runtime/graph/graph_runtime.cc#L55-L57 If you have a custom HW and you are interested in inter-op parallelism, you should be looking at our external codegen mechanism aka Bring your own codegen, BYOC. See https://docs.tvm.ai/dev/relay_bring_your_own_codegen.html Basically, the main runtime is still TVM, but you can cut subgraphs and send them to your codegen/runtime. There you can execute them anyway you like. As long as you get the interface between TVM and your codegen/runtime right, TVM doesn't need to know how you execute subgraphs. --- [Visit Topic](https://discuss.tvm.ai/t/execution-order-of-operators-at-runtime-in-tvm/6572/13) 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/a4b83c59e064030146233c6f43c534b6ac6483fd55b65fffa4ee06b53b7abe96).
