Optimze copy tensor with padding #32461
Open
+76
−8
Conversation
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
susbhere
force-pushed
the
optimize_padded_copy
branch
2 times, most recently
from
820f1d4 to
31ed86d
Compare
|
build_jenkins |
susbhere
force-pushed
the
optimize_padded_copy
branch
5 times, most recently
from
c2698b0 to
98db555
Compare
Tensor layout related properties are calculated once and used those cached values during per element offset calculation. This brings ~200x improvement in wait time between two queries for PhiSlica model. That means a user has to wait only for 0.36 sec (instead of 74 sec !!!) between two queries. These numbers are from LNL. JIRA: https://jira.devtools.intel.com/browse/CVS-174810
susbhere
force-pushed
the
optimize_padded_copy
branch
from
98db555 to
f3da61f
Compare
yeonbok
reviewed
Oct 17, 2025
| for (size_t i = 0; i < p_sizes.size(); i++) { | ||
| padded_sizes[i] = p_sizes[i]; | ||
| } | ||
| } |
There was a problem hiding this comment.
BTW, do we need this function inside the layout.cpp?
Seems that we can calculate jut in the target copy function.
There was a problem hiding this comment.
It is using memeber variables of layout class. For example, data_padding. Even get_tensor() call has dependency to the layout object.
yeonbok
reviewed
Oct 17, 2025
| } | ||
|
|
||
| private: | ||
| static void get_axes_map(cldnn::format& fmt, int64_t* axes_map, size_t& map_size); |
There was a problem hiding this comment.
#32371 (comment)
Also, as I mentioned in the previous comment, please move this function to format.hpp
There was a problem hiding this comment.
We can move get_linear_offset_params() to layout.hpp. May I know the reason or advantage you see to keep in hpp?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Tensor layout related properties are calculated once and used those
cached values during per element offset calculation. This brings ~200x improvement in wait time between two queries for PhiSlica model. That means a user has to wait only for 0.36 sec (instead of 74 sec !!!) between two queries. These numbers are from LNL.
JIRA: https://jira.devtools.intel.com/browse/CVS-174810