tqchen commented on issue #9022: URL: https://github.com/apache/tvm/issues/9022#issuecomment-921220669
Thanks @manupa-arm . I understand that proposal R4 can also work by having a pass to convert "global" to something more specialize as a pass (essentially R1 and R4 are not that different except for different choices of scope names). The main question is what is the semantics around the scope "global". Each memory scope represent a "constraint" of what kind of memory it is. Right now, when the device type is CPU, "global" means any memory that can be accessed by the host cpu. This would include TVMBAW, memory from stack, or memory allocated by other means. While a memory allocated by TVMBAW can have other benefit(e.g. accessible by other devices because it is pinned), it is not the constraint specified by the "global" scope. We can of course further constraint the setting, to be say "global.workspace", that reduces the possible ways to allocate the memory, but still not preclude from choosing between multiple buffers. So from semantics point of view. The pass can choose to return "global" or rewrite to "global.stack", but if the scope is "global", we should not preclude the possibility for downstream from allocating from stack. So as we can see that this is another kind of flexibility we want to enable here -- flexibility of picking possible backend allocation implementations. -- 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]
