ggml: Fix data race in ggml threadpool #11736
Merged
Conversation
This file contains 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
After the barrier in last iteration is executed, still the loop termination condition will be executed. However main thread can destroy the cgraph object and its nodes already, then another thread will access it, but the thing is already gone. Also trouble can happen when n_nodes == 0 or abort is called, but I'm not sure if the prior situation is possible. Last syncronization should be done after the loop to ensure the cgraph/cplan won't be accessed after the main thread exits from the function.
ggerganov
approved these changes
Feb 8, 2025
slaren
approved these changes
Feb 8, 2025
Animaxx
added a commit
to Animaxx/llama.cpp
that referenced
this pull request
Feb 12, 2025
tinglou
pushed a commit
to tinglou/llama.cpp
that referenced
this pull request
Feb 13, 2025
After the barrier in last iteration is executed, still the loop termination condition will be executed. However main thread can destroy the cgraph object and its nodes already, then another thread will access it, but the thing is already gone. Also trouble can happen when n_nodes == 0 or abort is called, but I'm not sure if the prior situation is possible. Last syncronization should be done after the loop to ensure the cgraph/cplan won't be accessed after the main thread exits from the function.
orca-zhang
pushed a commit
to orca-zhang/llama.cpp
that referenced
this pull request
Feb 26, 2025
After the barrier in last iteration is executed, still the loop termination condition will be executed. However main thread can destroy the cgraph object and its nodes already, then another thread will access it, but the thing is already gone. Also trouble can happen when n_nodes == 0 or abort is called, but I'm not sure if the prior situation is possible. Last syncronization should be done after the loop to ensure the cgraph/cplan won't be accessed after the main thread exits from the function.
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Feb 26, 2025
After the barrier in last iteration is executed, still the loop termination condition will be executed. However main thread can destroy the cgraph object and its nodes already, then another thread will access it, but the thing is already gone. Also trouble can happen when n_nodes == 0 or abort is called, but I'm not sure if the prior situation is possible. Last syncronization should be done after the loop to ensure the cgraph/cplan won't be accessed after the main thread exits from the function.
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.
After the barrier in last iteration is executed, still the loop termination condition will be executed. However main thread can destroy the cgraph object and its nodes already, then another thread will access it, but the thing is already gone. Also trouble can happen when
n_nodes == 0or abort is called, but I'm not sure if the prior situation is possible.Last syncronization should be done after the loop to ensure the cgraph/cplan won't be accessed after the main thread exits from the function.
Currently things are not breaking since in normal usage graph lives long and in tests disposable thread pools are used -> main thread will wait with exiting from
computefunction until the workers are finished.