[Snippets][CPU] Moved weight repacking of Brgemm to CreatePrimitive stage#29672
Merged
v-Golubev merged 8 commits intoopenvinotoolkit:masterfrom Mar 31, 2025
Merged
Conversation
a-sidorova
force-pushed
the
feature/snippets/weight_repacking
branch
5 times, most recently
from
e1f3f08 to
425110b
Compare
a-sidorova
force-pushed
the
feature/snippets/weight_repacking
branch
from
425110b to
82af9da
Compare
aobolensk
reviewed
Mar 25, 2025
src/plugins/intel_cpu/src/transformations/snippets/x64/pass/eliminate_brgemm_copy_b.cpp
Outdated
Show resolved
Hide resolved
...ns/intel_cpu/src/transformations/snippets/x64/pass/lowered/init_repacked_constant_inputs.cpp
Show resolved
Hide resolved
v-Golubev
reviewed
Mar 25, 2025
...ns/intel_cpu/src/transformations/snippets/x64/pass/lowered/init_repacked_constant_inputs.hpp
Outdated
Show resolved
Hide resolved
...gins/intel_cpu/src/transformations/snippets/x64/pass/lowered/external_repacking_adjuster.cpp
Show resolved
Hide resolved
...gins/intel_cpu/src/transformations/snippets/x64/pass/lowered/external_repacking_adjuster.cpp
Outdated
Show resolved
Hide resolved
...ns/intel_cpu/src/transformations/snippets/x64/pass/lowered/init_repacked_constant_inputs.cpp
Show resolved
Hide resolved
Comment on lines
23
to
-22
| auto m_rank_norm = ov::pass::pattern::optional<ov::snippets::op::RankNormalization>(m_param); | ||
| auto m_copy_b = ov::pass::pattern::wrap_type<BrgemmCopyB>({m_param}); |
Contributor
There was a problem hiding this comment.
Hm, it seems like there is some code style check issue: m_rank_norm was unused, but there were no indications
Anyway, thanks for the fix :)
src/plugins/intel_cpu/src/transformations/snippets/x64/pass/eliminate_brgemm_copy_b.cpp
Show resolved
Hide resolved
v-Golubev
reviewed
Mar 28, 2025
...ns/intel_cpu/src/transformations/snippets/x64/pass/lowered/init_repacked_constant_inputs.cpp
Outdated
Show resolved
Hide resolved
src/plugins/intel_cpu/src/transformations/snippets/x64/pass/eliminate_brgemm_copy_b.hpp
Outdated
Show resolved
Hide resolved
src/plugins/intel_cpu/src/transformations/snippets/x64/pass/eliminate_brgemm_copy_b.cpp
Outdated
Show resolved
Hide resolved
src/plugins/intel_cpu/src/transformations/snippets/x64/pass/eliminate_brgemm_copy_b.cpp
Show resolved
Hide resolved
src/plugins/intel_cpu/src/transformations/snippets/x64/pass/eliminate_brgemm_copy_b.cpp
Outdated
Show resolved
Hide resolved
aobolensk
reviewed
Mar 28, 2025
aobolensk
approved these changes
Mar 28, 2025
Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
sanleo-wq
pushed a commit
to sanleo-wq/openvino
that referenced
this pull request
Apr 1, 2025
…tage (openvinotoolkit#29672) ### Details: - *To reduce overheads in runtime, we moved repacking of second constant input of `Brgemm` from inference stage to model compilation stage.* - *Introduced helper `utils::get_planar_layout`* ### Tickets: - *CVS-164529* --------- Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
timxu826
pushed a commit
to timxu826/openvino
that referenced
this pull request
Apr 7, 2025
…tage (openvinotoolkit#29672) ### Details: - *To reduce overheads in runtime, we moved repacking of second constant input of `Brgemm` from inference stage to model compilation stage.* - *Introduced helper `utils::get_planar_layout`* ### Tickets: - *CVS-164529* --------- Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Details:
Brgemmfrom inference stage to model compilation stage.utils::get_planar_layoutTickets: