-
-
Notifications
You must be signed in to change notification settings - Fork 9.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
ENH: improve the speed of array conversions using AVX2 if available #21123
Open
zephyr111
wants to merge
2
commits into
numpy:main
Choose a base branch
from
zephyr111:faster-casts
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,7 @@ | ||
Faster casting on modern x86-64 processors | ||
------------------------------------------ | ||
Implicit/explicit casting is now significantly faster on contiguous arrays on | ||
processors supporting AVX-2. This speeds many functions up like `numpy.sum`, | ||
`numpy.prod`, `np.cumsum`, `np.cumprod`, `np.all` and `np.any`. | ||
Functions like `np.mean` or basic binary operation with a constant of a | ||
different type requiring the array to be casted are a bit faster. |
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
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Meant to do a review, but then posted instead:
IIRC this branch is never used (
NPY_USE_UNALIGNED_ACCESS
is always 0 here) and I don't think vectorization is OK if it was used. So I would either not do this, or just delete the whole# if
block: It doesn't really add a whole lot.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I am unsure of the meaning of NPY_USE_UNALIGNED_ACCESS, but if we can remove it here since it is always set to 0, why not removing it from the whole file and possibly the whole code ? It would make the code a bit more clean/readable.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Based on the comment of this macro, vectorization should be disabled at a build level. AFAIK, telling the compiler that AVX can be used does not change anything. Using O3 causes GCC to auto-vectorize the code as opposed to O2 so far but the new versions of GCC (starting from GCC 12) should now enable the auto-vectorization even in O2 which is the default optimization level for Numpy so far. Thus, this change should not cause more harm than currently (but I think the code path enabled by
NPY_USE_UNALIGNED_ACCESS
is certainly arlready harmful). What do you think about that?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I have to look closer, but I think we should just delete this code (if you agree with that).