Meteorix opened a new pull request #7147: URL: https://github.com/apache/tvm/pull/7147
Add legalize pass: padding dense/conv2d/batch_matmul ops to legal shapes for using tensorcore on cuda target. To limit the overhead introduced by padding, we count the `extra_flops` and set the threshold to 2x, which is conservative compared to the speedup of tensorcore. This pr is dependent on https://github.com/apache/tvm/pull/7146 . @jcf94 @merrymercy could you also help review this pr? ---------------------------------------------------------------- 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]
