frozenleaves/pytorch
1
0
Fork 0
mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Pytorch Edge] Enable kineto profiler on mobile via EdgeKinetoProfiler (#62419)

Browse Source 
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/62419

This diff adds support for cpu only kineto profiler on mobile. Thus
enabling chrome trace generation on mobile. This bring cpp API for
mobile profiling on part with Torchscript.
This is done via:
1. Utilizating debug handle annotations in KinetoEvent.
2. Adding post processing capability, via callbacks, to
KinetoThreadLocalState
3. Creating new RAII stype profiler, KinetoEdgeCPUProfiler, which can be
used in surrounding scope of model execution. This will write chrome
trace to the location specified in profiler constructor.

Test Plan:
MobileProfiler.ModuleHierarchy

Imported from OSS

Reviewed By: raziel

Differential Revision: D29993660

fbshipit-source-id: 0b44f52f9e9c5f5aff81ebbd9273c254c3c03299
This commit is contained in:
Kimish Patel
2021-08-13 21:37:57 -07:00
committed by Facebook GitHub Bot
parent 77a6436cac
commit 38c185189c
24 changed files with 406 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
android/pytorch_android/build.gradle
View File

@ -18,9 +18,9 @@ android {
externalNativeBuild {
cmake {
if(System.env.BUILD_LITE_INTERPRETER == '0') {
arguments "-DANDROID_STL=c++_shared", "-DBUILD_LITE_INTERPRETER=OFF"
arguments "-DANDROID_STL=c++_shared", "-DBUILD_LITE_INTERPRETER=OFF", "-DUSE_LITE_INTERPRETER_PROFILER=OFF"
} else {
arguments "-DANDROID_STL=c++_shared"
arguments "-DANDROID_STL=c++_shared", "-DUSE_LITE_INTERPRETER_PROFILER=OFF"
}
}
}