[runtime] reduce set_input and set_input_zero_copy overhead#3805
Merged
tqchen merged 1 commit intoapache:masterfrom Aug 29, 2019
Merged
[runtime] reduce set_input and set_input_zero_copy overhead#3805tqchen merged 1 commit intoapache:masterfrom
tqchen merged 1 commit intoapache:masterfrom
Conversation
hlu1
force-pushed
the
minimize_set_input_overhead
branch
from
2567891 to
e335da7
Compare
yinghai
approved these changes
Aug 20, 2019
| this->SetupOpExecs(); | ||
| for (size_t i = 0; i < input_nodes_.size(); i++) { | ||
| uint32_t nid = input_nodes_[i]; | ||
| std::string& name = nodes_[nid].name; |
There was a problem hiding this comment.
const or just inline this into next line.
hlu1
force-pushed
the
minimize_set_input_overhead
branch
from
e335da7 to
43693b7
Compare
Contributor
Author
|
@ZihengJiang, could you also take a look please? |
Member
wweic
pushed a commit
to wweic/tvm
that referenced
this pull request
Sep 16, 2019
wweic
pushed a commit
to wweic/tvm
that referenced
this pull request
Sep 16, 2019
wweic
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Sep 16, 2019
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Two optimizations:
std::unordered_mapto reduce lookup time, which could be significant where the number of inputs is largevectorto track the corresponding input arg dltensor* so we don't need to iterate through the inputs of all notes to look them up every single time. This is a followup to [Runtime] Enable set_input_zero_copy in GraphRuntime #3416@yinghai, @tqchen please review