[Unity][Transform] Memory plan across the IRModule#14220
Merged
tqchen merged 1 commit intoapache:unityfrom Mar 7, 2023
Merged
Conversation
Previously the static memory planning pass only works at single function level - each function inside the an IRModule will be independently planned. This is not perfect for the VM to reuse allocated memory across different functions. Therefore, this PR turns the static memory planning pass into a module pass. Now the plan is done across the IRModule, so that memory alloation in different functions can share the same storage token when planning. With this PR, it is hopeful that the VM will find more opportunities of memory reuse.
Collaborator
|
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment.
Generated by tvm-bot |
1 similar comment
Collaborator
|
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment.
Generated by tvm-bot |
Hzfengsy
approved these changes
Mar 7, 2023
tqchen
pushed a commit
that referenced
this pull request
Mar 13, 2023
Previously the static memory planning pass only works at single function level - each function inside the an IRModule will be independently planned. This is not perfect for the VM to reuse allocated memory across different functions. Therefore, this PR turns the static memory planning pass into a module pass. Now the plan is done across the IRModule, so that memory alloation in different functions can share the same storage token when planning. With this PR, it is hopeful that the VM will find more opportunities of memory reuse.
tqchen
pushed a commit
that referenced
this pull request
Mar 13, 2023
Previously the static memory planning pass only works at single function level - each function inside the an IRModule will be independently planned. This is not perfect for the VM to reuse allocated memory across different functions. Therefore, this PR turns the static memory planning pass into a module pass. Now the plan is done across the IRModule, so that memory alloation in different functions can share the same storage token when planning. With this PR, it is hopeful that the VM will find more opportunities of memory reuse.
tqchen
pushed a commit
that referenced
this pull request
Mar 13, 2023
Previously the static memory planning pass only works at single function level - each function inside the an IRModule will be independently planned. This is not perfect for the VM to reuse allocated memory across different functions. Therefore, this PR turns the static memory planning pass into a module pass. Now the plan is done across the IRModule, so that memory alloation in different functions can share the same storage token when planning. With this PR, it is hopeful that the VM will find more opportunities of memory reuse.
tqchen
pushed a commit
that referenced
this pull request
Mar 13, 2023
Previously the static memory planning pass only works at single function level - each function inside the an IRModule will be independently planned. This is not perfect for the VM to reuse allocated memory across different functions. Therefore, this PR turns the static memory planning pass into a module pass. Now the plan is done across the IRModule, so that memory alloation in different functions can share the same storage token when planning. With this PR, it is hopeful that the VM will find more opportunities of memory reuse.
tqchen
pushed a commit
that referenced
this pull request
Mar 20, 2023
Previously the static memory planning pass only works at single function level - each function inside the an IRModule will be independently planned. This is not perfect for the VM to reuse allocated memory across different functions. Therefore, this PR turns the static memory planning pass into a module pass. Now the plan is done across the IRModule, so that memory alloation in different functions can share the same storage token when planning. With this PR, it is hopeful that the VM will find more opportunities of memory reuse.
tqchen
pushed a commit
that referenced
this pull request
Apr 1, 2023
Previously the static memory planning pass only works at single function level - each function inside the an IRModule will be independently planned. This is not perfect for the VM to reuse allocated memory across different functions. Therefore, this PR turns the static memory planning pass into a module pass. Now the plan is done across the IRModule, so that memory alloation in different functions can share the same storage token when planning. With this PR, it is hopeful that the VM will find more opportunities of memory reuse.
tqchen
pushed a commit
that referenced
this pull request
Apr 1, 2023
Previously the static memory planning pass only works at single function level - each function inside the an IRModule will be independently planned. This is not perfect for the VM to reuse allocated memory across different functions. Therefore, this PR turns the static memory planning pass into a module pass. Now the plan is done across the IRModule, so that memory alloation in different functions can share the same storage token when planning. With this PR, it is hopeful that the VM will find more opportunities of memory reuse.
tqchen
pushed a commit
that referenced
this pull request
Apr 1, 2023
Previously the static memory planning pass only works at single function level - each function inside the an IRModule will be independently planned. This is not perfect for the VM to reuse allocated memory across different functions. Therefore, this PR turns the static memory planning pass into a module pass. Now the plan is done across the IRModule, so that memory alloation in different functions can share the same storage token when planning. With this PR, it is hopeful that the VM will find more opportunities of memory reuse.
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
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.
Previously the static memory planning pass only works at single function level - each function inside the an IRModule will be independently planned. This is not perfect for the VM to reuse allocated memory across different functions.
Therefore, this PR turns the static memory planning pass into a module pass. Now the plan is done across the IRModule, so that memory alloation in different functions can share the same storage token when planning. With this PR, it is hopeful that the VM will find more opportunities of memory reuse.