Rewrite lerp operator to use TensorIterator and support compile-time vectorization. #22038
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
pytorchbot
added
module: cpu
cpuhrsch
reviewed
Jun 20, 2019
cpuhrsch
reviewed
Jun 20, 2019
Contributor
|
@pytorchbot retest this please |
Contributor
facebook-github-bot
left a comment
facebook-github-bot
left a comment
There was a problem hiding this comment.
@VitalyFedyunin has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
cpuhrsch
approved these changes
Jun 21, 2019
Contributor
|
@VitalyFedyunin merged this pull request in fe580e8. |
iotamudelta
pushed a commit
to ROCm/pytorch
that referenced
this pull request
Jun 21, 2019
…vectorization. (pytorch#22038) Summary: Get benefit from the compile time vectorization and multi-threading. Before: ```python In [1]: import torch In [2]: x = torch.randn(1000000) In [3]: y = torch.randn(1000000) In [4]: w = 0.7 In [5]: timeit torch.lerp(x, y, w) 2.29 ms ± 23.9 µs per loop (mean ± std. dev. of 7 runs, 100 loops each) ``` After: ```python In [1]: import torch In [2]: x = torch.randn(1000000) In [3]: y = torch.randn(1000000) In [4]: w = 0.7 In [5]: timeit torch.lerp(x, y, w) 452 µs ± 1.81 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each) ``` After with multi-processing: ```python In [1]: import torch In [2]: x = torch.randn(1000000) In [3]: y = torch.randn(1000000) In [4]: w = 0.7 In [5]: timeit torch.lerp(x, y, w) 167 µs ± 48.8 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each) ``` Pull Request resolved: pytorch#22038 Differential Revision: D15941468 Pulled By: VitalyFedyunin fbshipit-source-id: fa8a5126187df4e6c849452e035b00b22be25739
zdevito
pushed a commit
to zdevito/ATen
that referenced
this pull request
Jun 21, 2019
…vectorization. (#22038) Summary: Get benefit from the compile time vectorization and multi-threading. Before: ```python In [1]: import torch In [2]: x = torch.randn(1000000) In [3]: y = torch.randn(1000000) In [4]: w = 0.7 In [5]: timeit torch.lerp(x, y, w) 2.29 ms ± 23.9 µs per loop (mean ± std. dev. of 7 runs, 100 loops each) ``` After: ```python In [1]: import torch In [2]: x = torch.randn(1000000) In [3]: y = torch.randn(1000000) In [4]: w = 0.7 In [5]: timeit torch.lerp(x, y, w) 452 µs ± 1.81 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each) ``` After with multi-processing: ```python In [1]: import torch In [2]: x = torch.randn(1000000) In [3]: y = torch.randn(1000000) In [4]: w = 0.7 In [5]: timeit torch.lerp(x, y, w) 167 µs ± 48.8 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each) ``` Pull Request resolved: pytorch/pytorch#22038 Differential Revision: D15941468 Pulled By: VitalyFedyunin fbshipit-source-id: fa8a5126187df4e6c849452e035b00b22be25739
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 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.
Get benefit from the compile time vectorization and multi-threading.
Before:
After:
After with multi-processing: