Mousius commented on code in PR #71: URL: https://github.com/apache/tvm-rfcs/pull/71#discussion_r895012147
########## rfcs/0071-target-json-parser.md: ########## @@ -0,0 +1,172 @@ +- Feature Name: target-json-preprocessor +- Start Date: 2022-04-04 +- RFC PR: [apache/tvm-rfcs#0071](https://github.com/apache/tvm-rfcs/pull/71) +- GitHub Issue: [apache/tvm#0000](https://github.com/apache/tvm/issues/0000) + +# Summary +[summary]: #summary +Extend the existing `TargetKind` `preprocessor` to allow preprocessing of the entire `Target` JSON representation rather than just `attrs`. + +# Motivation +[motivation]: #motivation + +Taking an example `Target` in JSON form: + +```js +{ + "id": "cuda", + "tag": "nvidia/tx2-cudnn", + "keys": ["cuda", "gpu"], + "libs": ["cudnn"], + "target_host": { + "id": "llvm", + "system_lib": True, + "mtriple": "aarch64-linux-gnu", + "mattr": "+neon" + } +} +``` + +We can see that there are additional fields which are of interest to TVM, note-ably `keys` and `libs` which we currently do not apply parsing to on `Target` instantiation. Extending the `TargetKind` `preprocessor` beyond `attrs` enables to customise parsing of the entire `Target`, enabling the values passed by the user to be used to infer other properties used during compilation. Review Comment: The current `preprocessor` only sees `attrs`, so if you want to pre-process any other field it's not possible, there are other fields which may be useful to pre-process (such as `keys` and `libs`). The main motivation I use here is with `keys`, as that enables different schedule selection based on the `Target` passed - not necessarily a smaller subset of the fields but generally having the capability to process the whole `Target`. Inference of features from the fields is kept separately in https://github.com/apache/tvm-rfcs/pull/78 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
