saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-29 20:14:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update perf tool documentation to reflect the new graph optimization enums. Relax constraint for enable_all. (#1650)

Browse source
This commit is contained in:
Pranav Sharma 2019-08-19 14:27:33 -07:00 committed by Changming Sun
parent 413730365f
commit 6f3a835d38
2 changed files with 9 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/ONNX_Runtime_Perf_Tuning.md
View file

@ -72,7 +72,7 @@ sess_options.set_graph_optimization_level(2)
```
* sess_options.session_thread_pool_size=2 controls how many thread do you want to use to run your model
* sess_options.enable_sequential_execution=True controls whether you want to run operators in your graph sequentially or in parallel. Usually when your model has many branches, set this option to false will give you better performance.
* sess_options.set_graph_optimization_level(2). There are three levels, 0 means disable optimization, 1 means enable optimizations before graph partition, 2 means enable all optimization.
* sess_options.set_graph_optimization_level(2). Please see onnxruntime_c_api.h (enum GraphOptimizationLevel) for the full list of all optimization levels.
### MKL_DNN/nGraph/MKL_ML Execution Provider
MKL_DNN, MKL_ML and nGraph all depends on openmp for parallization. For those execution providers, we need to use openmp enviroment variable to tune the performance.

11
onnxruntime/test/perftest/command_args_parser.cc
View file

@ -42,7 +42,7 @@ namespace perftest {
"\t-v: Show verbose information.\n"
"\t-x [thread_size]: Session thread pool size.\n"
"\t-P: Use parallel executor instead of sequential executor.\n"
"\t-o [optimization level]: 0: disable optimization, 1: basic optimization, 2: extended optimization, 3: extended+layout optimization. \n"
"\t-o [optimization level]: Please see onnxruntime_c_api.h (enum GraphOptimizationLevel) for the full list of all optimization levels. \n"
"\t-h: help\n");
}
@ -143,8 +143,13 @@ namespace perftest {
case ORT_ENABLE_ALL:
test_config.run_config.optimization_level = ORT_ENABLE_ALL;
break;
default:
return false;
default: {
if (tmp > ORT_ENABLE_ALL) { // relax constraint
test_config.run_config.optimization_level = ORT_ENABLE_ALL;
} else {
return false;
}
}
}
break;
}