Fixed double memory accesses of several pointwise operations. #5068
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
Because nvcc does not know that in/out pointers do not alias each other, if we assign a value to *out and then use *in again, the kernel has to emit a write to *out and then another read from *in. (Affected kernels become marginally faster after the fix.)
|
@pytorchbot retest this please |
soumith
approved these changes
Feb 6, 2018
|
Another possibility would be to use |
soumith
pushed a commit
that referenced
this pull request
Feb 7, 2018
Because nvcc does not know that in/out pointers do not alias each other, if we assign a value to *out and then use *in again, the kernel has to emit a write to *out and then another read from *in. (Affected kernels become marginally faster after the fix.)
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Outdated suggestions cannot be applied.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.
Because nvcc does not know that in/out pointers do not alias each other,
if we assign a value to *out and then use *in again, the kernel has to
emit a write to *out and then another read from *in.
(Affected kernels become marginally faster after the fix.)