[ETHOSN] Fix output tensor ordering#12317
Merged
lhutton1 merged 1 commit intoapache:mainfrom Aug 8, 2022
Merged
Conversation
During compilation of an NPU subgraph, the input and output tensor ordering is determined by creating a mapping of Support Library buffers to TVM buffers. The runtime had been using this mapping incorrectly by instead interpreting it as a mapping of TVM buffers to support library buffers. This can result in undefined behaviour. The runtime now interprets the mapping as Support Library buffers to TVM buffers. A test has been added to check the correct ordering of outputs is provided correctly in the runtime. Change-Id: Ifaaf18478958607224f69f4459809112c25cee4c
Contributor
Author
|
@tvm-bot merge |
Contributor
Author
|
Thanks @leandron! |
xinetzone
pushed a commit
to daobook/tvm
that referenced
this pull request
Nov 25, 2022
During compilation of an NPU subgraph, the input and output tensor ordering is determined by creating a mapping of Support Library buffers to TVM buffers. The runtime had been using this mapping incorrectly by instead interpreting it as a mapping of TVM buffers to support library buffers. This can result in undefined behaviour. The runtime now interprets the mapping as Support Library buffers to TVM buffers. A test has been added to check the correct ordering of outputs is provided correctly in the runtime.
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
During compilation of an NPU subgraph, the input and output tensor ordering is determined by creating a mapping of Support Library buffers to TVM buffers. The runtime had been using this mapping incorrectly by instead interpreting it as a mapping of TVM buffers to support library buffers. This can result in undefined behavior. The runtime now interprets the mapping as Support Library buffers to TVM buffers.
A test has been added to check the correct ordering of outputs is provided correctly in the runtime.
cc @leandron @manupa-arm @Leo-arm