andy-yang-1 commented on PR #14329: URL: https://github.com/apache/tvm/pull/14329#issuecomment-1475209243
@LeiWang1999 Yeah, you are right. The ptx_ldg32 pass only supports ldg32 instruction for loading 4 bytes from global memory. I will also add support for them in the future :wink: I confused this with the automatic async work done by Tian. This work does not need to consider the architecture issue. Thank you very much for your feedback! -- 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]
