DickJC123 commented on pull request #19426: URL: https://github.com/apache/incubator-mxnet/pull/19426#issuecomment-827286131
Nice work! This will be an important and complementary addition to the work you already PR'd in #18622. Some high-level questions: Do you have any data on the overheads involved in RTC launch vs. compiled kernel launch, e.g. on the first iteration and thereafter (perhaps for both hybridized and unhybridized models)? I'm sorry to see all those floating point constants in the MXNet RTC code. Are there no compiler-defined constants that can be used, or is there a motivation for avoiding them? Having worked on these reduce functions quite a bit, you probably have a good sense of the level of testing. Do you feel it's adequate? Can RTC-based reduction invoke any new regions of the operator parameter space? -- 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]
