You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2020/06/26 11:33:04 UTC

[GitHub] [incubator-tvm] kazum opened a new pull request #5934: [CODEGEN][CONTRIB] Various update for CoreML codegen

kazum opened a new pull request #5934:
URL: https://github.com/apache/incubator-tvm/pull/5934


   - Update relay.ext.coremlcompiler based on the change in #5770.
   - Support int32 for Core ML input and output
   - Handle "run" in CoreMLRuntime::GetFunction to measure time with Module.time_evaluator.
   - Return PackedFunc() when CoreMLRuntime::GetFunction handles nothing.
   - Add test for each operator supported by CoreML codegen.
   - Support relay.expand_dims and relay.nn.relu.


----------------------------------------------------------------
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:
users@infra.apache.org

[GitHub] [incubator-tvm] zhiics merged pull request #5934: [CODEGEN][CONTRIB] Various update for CoreML codegen

Posted by GitBox <gi...@apache.org>.
zhiics merged pull request #5934:
URL: https://github.com/apache/incubator-tvm/pull/5934


   


----------------------------------------------------------------
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:
users@infra.apache.org

[GitHub] [incubator-tvm] zhiics edited a comment on pull request #5934: [CODEGEN][CONTRIB] Various update for CoreML codegen

Posted by GitBox <gi...@apache.org>.
zhiics edited a comment on pull request #5934:
URL: https://github.com/apache/incubator-tvm/pull/5934#issuecomment-650246386


   aah, I haven't noticed that CoreML codegen was also using BYOC infra. Thanks for updating it. I have a question which is not relevant to this change. I see `SetInput` needs to allocate memory and copy from DLTensor to the local memory every time. Is it possible to pre-allocate memory or directly do zero-copy by sharing the passed tensor?


----------------------------------------------------------------
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:
users@infra.apache.org

[GitHub] [incubator-tvm] zhiics commented on pull request #5934: [CODEGEN][CONTRIB] Various update for CoreML codegen

Posted by GitBox <gi...@apache.org>.
zhiics commented on pull request #5934:
URL: https://github.com/apache/incubator-tvm/pull/5934#issuecomment-650305829


   Thanks @kazum 


----------------------------------------------------------------
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:
users@infra.apache.org

[GitHub] [incubator-tvm] zhiics commented on pull request #5934: [CODEGEN][CONTRIB] Various update for CoreML codegen

Posted by GitBox <gi...@apache.org>.
zhiics commented on pull request #5934:
URL: https://github.com/apache/incubator-tvm/pull/5934#issuecomment-650246386


   aah, I haven't noticed that CoreML codegen was also using BYOC infra. Thanks for the updating it. I have a question which is not relevant to this change. I see `SetInput` needs to allocate memory and copy from DLTensor to the local memory every time. Is it possible to pre-allocate memory or directly do zero-copy by sharing the passed tensor?


----------------------------------------------------------------
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:
users@infra.apache.org

[GitHub] [incubator-tvm] kazum commented on pull request #5934: [CODEGEN][CONTRIB] Various update for CoreML codegen

Posted by GitBox <gi...@apache.org>.
kazum commented on pull request #5934:
URL: https://github.com/apache/incubator-tvm/pull/5934#issuecomment-650301527


   @zhiics Relevant changes to #5770 are:
   https://github.com/apache/incubator-tvm/pull/5934/files#diff-639424334c798703f0e62ec8a5eaf779R30
   https://github.com/apache/incubator-tvm/pull/5934/files#diff-271e7167e72d0f1de3aee097fa5cb5d2R232-R245
   
   >  Is it possible to pre-allocate memory or directly do zero-copy by sharing the passed tensor?
   
   We can at least pre-allocate memory.  I think of doing more optimization for input tensor management in another PR :)


----------------------------------------------------------------
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:
users@infra.apache.org

[GitHub] [incubator-tvm] zhiics commented on pull request #5934: [CODEGEN][CONTRIB] Various update for CoreML codegen

Posted by GitBox <gi...@apache.org>.
zhiics commented on pull request #5934:
URL: https://github.com/apache/incubator-tvm/pull/5934#issuecomment-650303757


   @kazum no problem. We shouldn't do that in this PR. I was just curious if you have a plan to do that.


----------------------------------------------------------------
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:
users@infra.apache.org