FrozenGene commented on pull request #6711: URL: https://github.com/apache/incubator-tvm/pull/6711#issuecomment-716340083
I like this change. May I ask two questions? 1. could we make `smlal` / `smlal2` work on convolution too? 2. If we don't use tensorize, do we have method to handle this? For example, add optimization of custom LLVM pass or low detail analyze on tir or llvm ir? ---------------------------------------------------------------- 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: [email protected]
