This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
[MKLDNN] Remove overhead of sg_mkldnn_fullyconnected op #17707
Merged
Conversation
This file contains 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
pengzhao-intel
added this to In progress
in CPU Performance and Quantization
via automation
TaoLv
reviewed
Feb 29, 2020
| if (initialized_ && mkldnn_param.quantized) { | ||
| if (channel_wise) { | ||
| if (initialized_ && mkldnn_param.quantized && | ||
| dmlc::GetEnv("MXNET_MKLDNN_QFC_DYNAMIC_PARAMS", 0)) { |
There was a problem hiding this comment.
Yes, I think this env var could be removed in the future once the time consuming operation of weight_ver_ != weight.version() is resolved.
ciyongch
force-pushed
the
sg_mkldnnn_fc_opt
branch
from
376a198
to
5e41b60
Compare
|
@TaoLv @eric-haibin-lin please take a look. CI is not that stable... |
CPU Performance and Quantization
automation
moved this from In progress
to Reviewer approved
Mar 9, 2020
TaoLv
approved these changes
Mar 9, 2020
MoisesHer
pushed a commit
to MoisesHer/incubator-mxnet
that referenced
this pull request
Apr 10, 2020
ciyongch
added a commit
to ciyongch/incubator-mxnet
that referenced
this pull request
Apr 13, 2020
7 tasks
ciyongch
added a commit
to ciyongch/incubator-mxnet
that referenced
this pull request
Apr 16, 2020
pengzhao-intel
pushed a commit
that referenced
this pull request
Apr 17, 2020
anirudh2290
pushed a commit
to anirudh2290/mxnet
that referenced
this pull request
May 29, 2020
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Description
This PR is mainly focus on removing the overhead of sg_mkldnn_fullyconnected especially in the case of channel-wise quantization mode (no much change for FP32 or tensor-wise quantization mode) described in #17705, via removing extra condition check in the current logic (weights version and calibrated data value), but leaving an ENV of
MXNET_MKLDNN_QFC_DYNAMIC_PARAMSfor the scenario of changing those values on the fly (we don't meet such usage but in case there is).Checklist
Essentials
Please feel free to remove inapplicable items for your PR.
Changes
Comments
@TaoLv @eric-haibin-lin @pengzhao-intel