[Prototype] [PyTorch Edge] Speed up model loading by 12% by directly calling the C file API from FileAdapter #61997
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
…calling the C file API from FileAdapter After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/) [ghstack-poisoned]
🔗 Helpful links
💊 CI failures summary and remediationsAs of commit 19c3dfc (more details on the Dr. CI page): 💚 💚 Looks good so far! There are no failures yet. 💚 💚 This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.Please report bugs/suggestions to the (internal) Dr. CI Users group. |
…y directly calling the C file API from FileAdapter" After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/) [ghstack-poisoned]
…y directly calling the C file API from FileAdapter" After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/) [ghstack-poisoned]
…y directly calling the C file API from FileAdapter" After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/) [ghstack-poisoned]
dhruvbird
added a commit
that referenced
this pull request
Jul 23, 2021
…calling the C file API from FileAdapter Pull Request resolved: #61997 After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. ghstack-source-id: 134206924 Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/)
…y directly calling the C file API from FileAdapter" After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/) [ghstack-poisoned]
dhruvbird
added a commit
that referenced
this pull request
Jul 23, 2021
…calling the C file API from FileAdapter Pull Request resolved: #61997 After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. ghstack-source-id: 134223858 Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/)
QYP-842653
pushed a commit
to QYP-842653/Pytorch
that referenced
this pull request
Jul 27, 2021
…calling the C file API from FileAdapter Pull Request resolved: pytorch/pytorch#61997 After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. ghstack-source-id: 134042630 Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/)
…y directly calling the C file API from FileAdapter" After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/) [ghstack-poisoned]
This was referenced Jul 28, 2021
dhruvbird
added a commit
that referenced
this pull request
Jul 28, 2021
…calling the C file API from FileAdapter Pull Request resolved: #61997 After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. ghstack-source-id: 134489363 Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/)
…y directly calling the C file API from FileAdapter" After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/) [ghstack-poisoned]
dhruvbird
added a commit
that referenced
this pull request
Jul 28, 2021
…calling the C file API from FileAdapter Pull Request resolved: #61997 After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. ghstack-source-id: 134529654 Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/)
…y directly calling the C file API from FileAdapter" After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/) [ghstack-poisoned]
dhruvbird
added a commit
that referenced
this pull request
Jul 29, 2021
…calling the C file API from FileAdapter Pull Request resolved: #61997 After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses `std::istream` under the hood, which is not that efficient. This change reduces the model loading time from [~293ms](https://www.internalfb.com/intern/aibench/details/600870874797229) to [~254ms](https://www.internalfb.com/intern/aibench/details/163731416457694), which is a reduction of ~12%. ghstack-source-id: 134634610 Differential Revision: [D29812191](https://our.internmc.facebook.com/intern/diff/D29812191/)
|
This pull request has been merged in 725d98b. |
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.
Stack from ghstack:
After profiling the model loading latency on AI Bench (Android Galaxy S8 US), it seems like a significant amount of time was spent reading data using FileAdapter, which internally calls IStreamAdapter. However, IStreamAdapter uses
std::istreamunder the hood, which is not that efficient. This change reduces the model loading time from ~293ms to ~254ms, which is a reduction of ~12%.Differential Revision: D29812191