echuraev opened a new pull request #8210: URL: https://github.com/apache/tvm/pull/8210
I wasn't able to run inception-v2 model on iPad Air. Model was successfully compiled but when I run the model, I got the following error: `Compute function exceeds available temporary registers` The problem occurs due to the generated kernel for one convolution was more than 4000 lines long. It happened due to unrolling. As a solution, decrease value of `auto_unroll_max_step`. Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from [Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers) by @ them in the pull request thread. -- 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]
