-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Sns transpose support #56
Sns transpose support #56
Conversation
a153865
to
95739fc
Compare
communication approach
95739fc
to
83c027d
Compare
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.
First part
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.
rest
src/inference/dev_api/cpp_interfaces/interface/ie_internal_plugin_config.hpp
Show resolved
Hide resolved
src/plugins/intel_cpu/tests/functional/shared_tests_instances/snippets/add.cpp
Show resolved
Hide resolved
src/tests/ngraph_helpers/snippets_ngraph_functions/src/subgraph_permute.cpp
Show resolved
Hide resolved
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.
As agreed all the comments will be resolved in separate PR
const auto transpose = ov::as_type_ptr<ngraph::opset1::Transpose>( | ||
pattern_to_output.at(match_transpose).get_node_shared_ptr()); | ||
|
||
const auto order = ov::as_type_ptr<ov::op::v0::Constant>(pattern_to_output.at(match_order).get_node_shared_ptr()); |
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.
To avoid some potential warnings from static analyzers I would recommend to check transpose
and order
on nullptr
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.
It's an interesting question. Do we have a common practice on this point?
Because I intentionally skipped the checks to avoid extra penalty in runtime? since the matcher guarantees that they are not nullptr. Let's discuss this on the sync.
Details: