tkonolige commented on PR #11423: URL: https://github.com/apache/tvm/pull/11423#issuecomment-1137562962
Thanks for helping to clarify things @FranckQC! I think I'm a little confused still. Regarding 1), you are saying that right now `SyntacticToSemanticComputations` just happens to use `ExprDeepEqual`, but we intend to change it in the future? And so, right now (in main), `SyntacticToSemanticComputations` is essentially doing nothing? If so, could we just have `SyntacticToSemanticComputations` just be a no-op for now? Even if we switch `SyntacticToSemanticComputations` to a no-op, I worry that we are going to hit this O(N^2) problem in the future. Is there a way to get around the all-pairs comparison? Regarding 2), I didn't realize `ComputationTable` was already a `std::unordered_map<PrimExpr, size_t, StructuralHash, ExprDeepEqual>`. Whoops :). -- 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]
