Enable GPU memory trace dump#276
Merged
Merged
Conversation
Adds `webnn_enable_resource_dump = true` to create a trace dump. Then open the dump in chrome://tracing to analyze GPU memory usage.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
How to collect:
webnn_enable_resource_dump = truetoargs.gn.gpgmm_event_trace.jsoninchrome://tracing.How to analyze:
You basically want
GPU allocation utilizationto be always 100% andGPU memory utilizationto be always under 100%. The former means NO allocation is being wasted and the latter means NO memory is being paged-out to the OS.GPU memory freereports waste due to fragmentation, this should be small.How does it work:
GPGMM tracks how much actual resource memory was used. For example, if you create 1GB heap, that contains a 1 byte resource, this will correctly reported as 1B used. OS tools like WPA just report 1GB being used, not very helpful.
@fujunwei @mingmingtasd