FrozenGene commented on pull request #6042: URL: https://github.com/apache/incubator-tvm/pull/6042#issuecomment-657886398
I understand this pr ‘s purpose. I met 32 hangs for a bit long time on arm v7 cpu (Worse thing is single convolution op compile time is ok, but it is not well when to compile whole network). Previous fix is to limit the max_unroll to be 16. Everything works well. ---------------------------------------------------------------- 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]
