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 2021/12/01 01:36:13 UTC

[GitHub] [tvm] apeskov opened a new pull request #9618: [DNNL] Add support of QNN primitives for DNNL runtime

apeskov opened a new pull request #9618:
URL: https://github.com/apache/tvm/pull/9618


   The main value of that change is enable qnn.conv2d and qnn.dense primitive for DNNL base json runtime.
   Some of these changes is useful for all type of workloads, not only int8 specific. 
   
   Together with that there was performed some refactoring of internal infrastructure of DNNL plugin. The main int8 unrelated  changes are:
    * Improved thread safety. Now DNNL runtime can be used in multi instance mode.
    * Zero copy input/output handling
    * Scratchpad specification
    * Use DNNL query api to define proper layouts (additional data copy is possible)
    * Indirect addressing of memory objects. Internal tensor registry allow to clone temp/const tensor depending particular thread id.  
    * Relative positioning of input arguments. Index of each optional arguments specified via attributes
    * Introduced ability of calculating constant subgraphs in DNNL code generator stage
   


-- 
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-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] apeskov commented on pull request #9618: [DNNL] Add support of QNN primitives for DNNL runtime

Posted by GitBox <gi...@apache.org>.
apeskov commented on pull request #9618:
URL: https://github.com/apache/tvm/pull/9618#issuecomment-1012964021


   @masahi PR is updated. You may continue review.


-- 
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-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] apeskov commented on pull request #9618: [DNNL] Add support of QNN primitives for DNNL runtime

Posted by GitBox <gi...@apache.org>.
apeskov commented on pull request #9618:
URL: https://github.com/apache/tvm/pull/9618#issuecomment-1013156518


   @tmoreau89 @gfursin Just FYI.


-- 
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-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] masahi commented on pull request #9618: [DNNL] Add support of QNN primitives for DNNL runtime

Posted by GitBox <gi...@apache.org>.
masahi commented on pull request #9618:
URL: https://github.com/apache/tvm/pull/9618#issuecomment-1008443655


   Please update this 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.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] masahi edited a comment on pull request #9618: [DNNL] Add support of QNN primitives for DNNL runtime

Posted by GitBox <gi...@apache.org>.
masahi edited a comment on pull request #9618:
URL: https://github.com/apache/tvm/pull/9618#issuecomment-1015835747


   > Together with that there was performed some refactoring of internal infrastructure of DNNL plugin
   
   If that's the case, I want this PR to be split into smaller ones. It's hard to review 3K PR with lots of moving pieces. Indeed 3K is too big for just introducing int8 support.


-- 
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-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] masahi commented on pull request #9618: [DNNL] Add support of QNN primitives for DNNL runtime

Posted by GitBox <gi...@apache.org>.
masahi commented on pull request #9618:
URL: https://github.com/apache/tvm/pull/9618#issuecomment-1015835747


   > Together with that there was performed some refactoring of internal infrastructure of DNNL plugin
   
   If that's the case, I want this PR to be split into smaller ones. It's hard to review 3K PR with lots of moving pieces.


-- 
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-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] tmoreau89 commented on pull request #9618: [DNNL] Add support of QNN primitives for DNNL runtime

Posted by GitBox <gi...@apache.org>.
tmoreau89 commented on pull request #9618:
URL: https://github.com/apache/tvm/pull/9618#issuecomment-1015604008


   Thanks @apeskov - I'm also looping in @mbs-octoml on the review of this 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.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org