adstraw opened a new pull request, #15616: URL: https://github.com/apache/tvm/pull/15616
Adds codegen support only for CUDA async copy with barrier synchronization. TVM currently uses group based synchronization for async copies through the InjectSoftwarePipeline pass but new "bulk" async copy instructions for Hopper require barrier synchronization. This PR adds codegen for barrier synchronization as a first step towards adding support for Hopper "bulk" async copy support. -- 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]
