zhiics commented on a change in pull request #5288: [BYOC] Refine DNNL Codegen URL: https://github.com/apache/incubator-tvm/pull/5288#discussion_r406524552
########## File path: src/relay/backend/vm/compiler.cc ########## @@ -924,19 +924,20 @@ IRModule VMCompiler::OptimizeModule(const IRModule& mod, const TargetsMap& targe pass_seqs.push_back(transform::LambdaLift()); pass_seqs.push_back(transform::InlinePrimitives()); + // Manifest the allocations. + pass_seqs.push_back(transform::ManifestAlloc(this->target_host_)); + // Compute away possibly introduced constant computation. + pass_seqs.push_back(transform::FoldConstant()); + // Fuse the shape functions. + pass_seqs.push_back(transform::FuseOps()); + Review comment: yeah, if batch_norm is encapsulated in an external function, it will be lifted out and therefore invisible by simplifyinference. Later on, if we inline it and run fusion, fusion pass will see this op and complain that on OpPattern is registered for this op... ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
