[ET-VK][12/n] aten.cat with more codegen #3388
Closed
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
1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/3388
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit f63bd46 with merge base e5471a5 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
yipjustin
added a commit
that referenced
this pull request
Apr 27, 2024
1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/) ghstack-source-id: 224195279 Pull Request resolved: #3388
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D56626865 |
1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D56626865 |
yipjustin
added a commit
that referenced
this pull request
Apr 27, 2024
Pull Request resolved: #3388 1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/) ghstack-source-id: 224195314
1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D56626865 |
copyrightly
approved these changes
Apr 27, 2024
1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D56626865 |
yipjustin
added a commit
that referenced
this pull request
Apr 27, 2024
Pull Request resolved: #3388 1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. ghstack-source-id: 224212207 Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/)
1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D56626865 |
yipjustin
added a commit
that referenced
this pull request
Apr 27, 2024
Pull Request resolved: #3388 1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. ghstack-source-id: 224214135 Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/)
1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/) [ghstack-poisoned]
yipjustin
added a commit
that referenced
this pull request
Apr 29, 2024
Pull Request resolved: #3388 1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. ghstack-source-id: 224249271 Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/)
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D56626865 |
1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D56626865 |
yipjustin
added a commit
that referenced
this pull request
Apr 29, 2024
Pull Request resolved: #3388 1. The `aten.cat` operation are very straightforward using the `copy_*_node`. 2. Complexity comes from the code-gen. We need to introduce a `AT_TENSOR_LIST` type, which contains a list of `AT_TENSOR` with `is_in=True`. The tensor list itself as a container is not an `IOValueRef`, but the element inside are. It leads to some ugly if-then-else in the codegen. ghstack-source-id: 224249802 Differential Revision: [D56626865](https://our.internmc.facebook.com/intern/diff/D56626865/)
Contributor
|
This pull request has been merged in fac1ae6. |
This was referenced Apr 29, 2024
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.
Stack from ghstack (oldest at bottom):
aten.catoperation are very straightforward using thecopy_*_node.AT_TENSOR_LISTtype, which contains a list ofAT_TENSORwithis_in=True. The tensor list itself as a container is not anIOValueRef, but the element inside are. It leads to some ugly if-then-else in the codegen.Differential Revision: D56626865