tqchen opened a new pull request #6586: URL: https://github.com/apache/incubator-tvm/pull/6586
The previous behavior of non-sync can be unsafe for GPU devices. In particular, the need for an explicit synchronization could leads to confusion behavior e.g. asnumpy does not immediately return the right content for vulkan. Also brings the requirement of array being contiguous. Right now we encourage compact array since they are easier for optimization. We can consider bring support later by introducing a compactify PackedFunc(which might need be jitted). 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]
