-
Notifications
You must be signed in to change notification settings - Fork 2.4k
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
[Snippets] Moved infrastructure to Linear Intermediate Representation #16402
[Snippets] Moved infrastructure to Linear Intermediate Representation #16402
Conversation
c25c2e2
to
881d657
Compare
3604db5
to
af406c8
Compare
cd9bd24
to
61ef97a
Compare
c22b2f6
to
8f4cd19
Compare
9e45f70
to
d582f98
Compare
2486ac4
to
20f85d9
Compare
src/common/snippets/include/snippets/lowered/pass/fuse_loops.hpp
Outdated
Show resolved
Hide resolved
src/common/snippets/tests/src/pass/set_scalar_count_for_load_and_store.cpp
Outdated
Show resolved
Hide resolved
src/common/snippets/tests/src/pass/broadcast_to_movebroadcast.cpp
Outdated
Show resolved
Hide resolved
src/common/snippets/tests/include/pass/insert_movebroadcast.hpp
Outdated
Show resolved
Hide resolved
src/common/snippets/tests/include/pass/broadcast_to_movebroadcast.hpp
Outdated
Show resolved
Hide resolved
db63053
to
5297ddb
Compare
* [Snippets] Added support of Port Descriptor * review * Added Softmax support via common pipeline * Added Brgemm marking via general pipeline * TensorDescriptor -> ExpressionPort * Refactored expression factory * ExpressionPort - is interface * refactoring * fixed init loops * fixed brgemm ops * Moved PortDescriptor to lowered level * Removed PortDesc getters and setters from ExpressionPort and Tensor * Applied comments
ba99339
to
f71b552
Compare
a690418
to
14b8709
Compare
src/plugins/intel_cpu/src/emitters/x64/jit_snippets_emitters.cpp
Outdated
Show resolved
Hide resolved
src/common/snippets/include/snippets/lowered/port_descriptor.hpp
Outdated
Show resolved
Hide resolved
src/plugins/intel_cpu/src/emitters/x64/jit_snippets_emitters.cpp
Outdated
Show resolved
Hide resolved
static LinearIR::container deep_copy_range(LinearIR::container::const_iterator begin, LinearIR::container::const_iterator end); | ||
|
||
const container& get_ops() const {return m_lowered_ops; } | ||
const io_container& get_IO_ops() const {return m_io_lowered_ops; } |
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 looks like we are mixing lowered_ops
and expressions
naming. Does it make sense to align everywhere?
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.
Good point, renamed the class fields. Thanks
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.
Methods are still named as {smt}_ops. :)
Ok to postpone fix to seaprate PR.
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.
Oh, yeah, I see. My eyes are used to this naming and I didn't notice that. Thank you. I will fix it in separate PR
0ac8608
to
dbfe69a
Compare
Details:
Ticket:
Validation: