[Runtime] Special Memory Scope Support #7488
Merged
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
tqchen
reviewed
Feb 23, 2021
tqchen
requested changes
Feb 23, 2021
tqchen
requested changes
Feb 23, 2021
tqchen
requested changes
Feb 23, 2021
tqchen
requested changes
Feb 23, 2021
tqchen
reviewed
Feb 23, 2021
tqchen
reviewed
Feb 23, 2021
tqchen
reviewed
Feb 24, 2021
Member
|
cc @junrushao1994 @csullivan would be great if you can help review as well |
tqchen
requested changes
Feb 25, 2021
[RUNTIME] AllocDataSpace API. [RUNTIME] Update RPC CopyToRemote. [RUNTIME] Update RPC APIs. [RUNTIME] Reuse RPCReference. [RUNTIME] Update doc. [RUNTIME] Update RPC APIs. [RUNTIME] Clang format. [RUNTIME] TvmJS Support. [RUNTIME] Address comment. [RUNTIME] Update CRT. [RUNTIME] Fix.
csullivan
reviewed
Feb 25, 2021
Member
|
Thanks @csullivan , please take another look and https://tvm.apache.org/docs/contribute/code_review.html?highlight=approve%20changes#approve-and-request-changes-explicitly |
csullivan
approved these changes
Feb 26, 2021
Contributor
csullivan
left a comment
csullivan
left a comment
There was a problem hiding this comment.
LGTM 
, thanks @ZihengJiang @tqchen!
junrushao
approved these changes
Feb 27, 2021
Member
junrushao
left a comment
junrushao
left a comment
There was a problem hiding this comment.
It looks good to me! I didn't have any extra comments other than nitpicks. Thanks Ziheng for the contribution!
tqchen
reviewed
Feb 27, 2021
tqchen
reviewed
Feb 27, 2021
tqchen
reviewed
Feb 27, 2021
tqchen
approved these changes
Feb 28, 2021
Member
|
Thanks @ZihengJiang @junrushao1994 @csullivan ! |
Lokiiiiii
pushed a commit
to Lokiiiiii/tvm
that referenced
this pull request
Mar 2, 2021
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Mar 2, 2021
This was referenced Mar 18, 2021
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.
In current TVM system, we categorize the machine's memory into serval types:
global,shared, etc. Based on this, we implicitly allocate and use those memory with the scheduling primitivescache_read/cache_write. However, caching still requires explicit movement during launch of every kernel, it can be beneficial to allocate these special memory explicitly during runtime so they can be reused across operators. Apart from this, TVM assumes that all the memory objects can be manipulated with a plain pointer (void*). The main limitations of the current runtime are:This PR bings changes in the TVM runtime to support special memory. See RFC here: https://discuss.tvm.apache.org/t/runtime-support-for-special-memory-scope/9187