[GitHub] [tvm] mbs-octoml commented on issue #9022: [Bug] BuiltinLower does not use alloca for storage on kDLCPU target devices
mbs-octoml commented on issue #9022: URL: https://github.com/apache/tvm/issues/9022#issuecomment-921207626 + @csullivan who also needs finer grained scopes Can someone explain how the current Stage scope, which ends up in ProducerRealize nodes, would be coherent with the Allocate scope? @manupa-arm if you wanted to unblock EthosU today you could make the kMaxStackAlloca heuristic Target defined. That could buy us time to tackle scopes properly. -- 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: commits-unsubscr...@tvm.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
[GitHub] [tvm] mbs-octoml commented on issue #9022: [Bug] BuiltinLower does not use alloca for storage on kDLCPU target devices
mbs-octoml commented on issue #9022: URL: https://github.com/apache/tvm/issues/9022#issuecomment-920485102 Thank so much for for the context. I'll try to capture that in a comment. This is a 'bug' only in the sense that this heuristic is not working for the EthosU AOT codegen, I think because they are expecting to intercept the workpool ops downstream? But it does suggest a very simply way forward: make kMaxAlloca size a TargetKind attribute so they can force it to zero. @manupa-arm can you chime in here? -- 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: commits-unsubscr...@tvm.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org