-
Notifications
You must be signed in to change notification settings - Fork 6.7k
[FEATURE] add oneDNN support for numpy transpose #20419
Conversation
|
Hey @RafLit , Thanks for submitting the PR
CI supported jobs: [centos-cpu, edge, centos-gpu, windows-gpu, unix-cpu, miscellaneous, unix-gpu, windows-cpu, sanity, website, clang] Note: |
|
@RafLit For non-square matrices, the algorithm is more complicated (in-place). Could you tell me whether you have any results for a non-square matrix? |
@anko-intel I updated the table and added some data for non-square matrices |
|
@mxnet-bot run ci [centos-cpu, windows-cpu] |
|
@mxnet-bot run ci [unix-gpu] |
|
Jenkins CI successfully triggered : [unix-gpu] |
|
@mxnet-bot run ci [centos-cpu, unix-cpu, unix-gpu, windows-gpu] |
|
Jenkins CI successfully triggered : [unix-cpu, unix-gpu, centos-cpu, windows-gpu] |
|
@mxnet-bot run ci [centos-cpu, unix-cpu] |
|
Jenkins CI successfully triggered : [centos-cpu, unix-cpu] |
|
@mxnet-bot run ci [unix-cpu] |
|
Jenkins CI successfully triggered : [unix-cpu] |
bgawrych
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
|
@szha Could you please review the changes and merge if it's ok? |
|
@bgawrych should be able to help with the merge. |
Description
Transpose operator benchmark results with onednn
Checklist
Essentials