huangxiao2008 commented on pull request #10580: URL: https://github.com/apache/tvm/pull/10580#issuecomment-1066439483
> My Test is focused on TensorCore Convolution，which is implemented by Implicit GEMM. our schedule code is similar to batch matmul's ， performance get speed-up after fixing. Whatever, as shown in my screenshot，there do existing redundant computing in generated tir, and needs to be fixed. -- 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]
