Allow using MKLML header/libs when use_mklml is specified#178
Merged
Conversation
jywu-msft
previously approved these changes
Dec 14, 2018
souptc
pushed a commit
that referenced
this pull request
Dec 17, 2018
Add support for getting model metadata. Will add test cases once the initial review looks good. Note that this is slightly different from the LotusRT versions of GetInputs/GetOutputs in that the NodeArg is not directly exposed to the clients of the session class. Also, notice the return by pair<>. Did this to achieve 2 things: (1) ensure that an appropriate error code is returned if the client didn't load the model to begin with (2) avoid copying of the metadata. The LotusRT version didn't check if the model was loaded or not when these functions were called. Related work items: #178
ke1337
force-pushed
the
gt/kedeng/mkl
branch
3 times, most recently
from
ad492a8 to
82a74d1
Compare
ke1337
changed the title
ke1337
force-pushed
the
gt/kedeng/mkl
branch
from
ee82292 to
a27a9ab
Compare
ke1337
changed the title
baowenlei
approved these changes
Dec 17, 2018
liwchang
approved these changes
Dec 17, 2018
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
As mkldnn_sgemm is slower than cblas_sgemm in MKLML. This also allows providers to use MKL integer BLAS directly.