in-place ops to alias tensor args of function#877
Merged
Conversation
crcrpar
commented
Jul 30, 2024
github-actions
bot
added
the
documentation
crcrpar
force-pushed
the
crpa/alias-inplace-poc
branch
from
250ccc3 to
8d9939f
Compare
crcrpar
force-pushed
the
crpa/alias-inplace-poc
branch
from
8d9939f to
5524f1f
Compare
crcrpar
force-pushed
the
crpa/alias-inplace-poc
branch
from
5524f1f to
768ce1d
Compare
crcrpar
changed the title
elements Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
commit 394d418 Author: Masaki Kozuki <mkozuki@nvidia.com> Date: Fri Jul 26 12:16:26 2024 +0900 header to inform which base/views are replaced by which Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com> commit 0b9405d Author: Masaki Kozuki <mkozuki@nvidia.com> Date: Fri Jul 26 11:50:03 2024 +0900 track base and views for better in-place modification propagation Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com> Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
…_canonicalized_trace` Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
…sting in-place logic Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
Signed-off-by: Masaki Kozuki <mkozuki@nvidia.com>
crcrpar
force-pushed
the
crpa/alias-inplace-poc
branch
from
af6176a to
100fef3
Compare
jjsjann123
reviewed
Nov 16, 2024
| t = bsym.flat_proxy_args[1] | ||
| index = arg_to_idx[t] | ||
| numel = t.numel | ||
| tensor_args_consumed_by_inplace_grouped_by_numel[numel].append(index) |
Collaborator
There was a problem hiding this comment.
question here: what's the reason that we are grouping them by numel?
jjsjann123
reviewed
Nov 16, 2024
| numel = t.numel | ||
| tensor_args_consumed_by_inplace_grouped_by_numel[numel].append(index) | ||
| tensor_indices.append(index) | ||
| if len(tensor_args_consumed_by_inplace_grouped_by_numel) > 1: |
Collaborator
There was a problem hiding this comment.
follow up question, what's the implication of the bucket size > 1?
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
What does this PR do?
This is based on #798 and #869 and is trying to manage to support #738.
cc @Borda @apaz-cli