[BYOC] [DNNL] enable in-place post-op sum in dnnl json runtime #12371
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
|
@apeskov This is more like a work-around before the true solution based on memory planning is ready. |
masahi
approved these changes
Aug 12, 2022
xinetzone
pushed a commit
to daobook/tvm
that referenced
this pull request
Nov 25, 2022
…e#12371) * enable inplace post-op sum in dnnl byoc * add inplace post-op sum test
mikeseven
pushed a commit
to mikeseven/tvm
that referenced
this pull request
Sep 27, 2023
…e#12371) * enable inplace post-op sum in dnnl byoc * add inplace post-op sum test
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This PR enable in-place post-op sum in dnnl json runtime for performance concern. This feature only enabled if the
rhsofsumis notinputnoroutputof the current dnnl partition. Thus the workloads with large dnnl partition will benefit most.The correctness of this patch has been checked by the following 83 models from gluoncv:
['resnet18_v1', 'resnet34_v1', 'resnet50_v1', 'resnet101_v1', 'resnet152_v1', 'resnet18_v2', 'resnet34_v2', 'resnet50_v2', 'resnet101_v2', 'resnet152_v2', 'resnest14', 'resnest26', 'resnest50', 'resnest101', 'resnest200', 'resnest269', 'vgg11', 'vgg13', 'vgg16', 'vgg19', 'vgg11_bn', 'vgg13_bn', 'vgg16_bn', 'vgg19_bn', 'alexnet', 'densenet121', 'densenet161', 'densenet169', 'densenet201', 'squeezenet1.0', 'squeezenet1.1', 'googlenet', 'inceptionv3', 'xception', 'mobilenet1.0', 'mobilenet0.75', 'mobilenet0.5', 'mobilenet0.25', 'mobilenetv2_1.0', 'mobilenetv2_0.75', 'mobilenetv2_0.5', 'mobilenetv2_0.25', 'mobilenetv3_large', 'mobilenetv3_small', 'cifar_resnet20_v1', 'cifar_resnet56_v1', 'cifar_resnet110_v1', 'cifar_resnet20_v2', 'cifar_resnet56_v2', 'cifar_resnet110_v2', 'cifar_wideresnet16_10', 'cifar_wideresnet28_10', 'cifar_wideresnet40_8', 'cifar_resnext29_16x64d', 'resnet18_v1b', 'resnet34_v1b', 'resnet50_v1b', 'resnet101_v1b', 'resnet152_v1b', 'resnet50_v1c', 'resnet101_v1c', 'resnet152_v1c', 'resnet50_v1d', 'resnet101_v1d', 'resnet152_v1d', 'resnet50_v1s', 'resnet101_v1s', 'resnet152_v1s', 'resnext50_32x4d', 'resnext101_32x4d', 'resnext101_64x4d', 'se_resnext50_32x4d', 'se_resnext101_32x4d', 'se_resnext101_64x4d', 'senet_154', 'darknet53', 'resnet18_v1b_0.89', 'resnet50_v1d_0.86', 'resnet50_v1d_0.48', 'resnet50_v1d_0.37', 'resnet50_v1d_0.11', 'resnet101_v1d_0.76', 'resnet101_v1d_0.73']