@@ -177,4 +178,4 @@ The inference framework can be obtained under `-I x86_64`, `-I arm64` and `-I ar
...
@@ -177,4 +178,4 @@ The inference framework can be obtained under `-I x86_64`, `-I arm64` and `-I ar
> 1. `liboptimize.so` only exists in the output package of runtime-arm64 and is only used on ARMv8.2 and CPUs that support fp16.
> 1. `liboptimize.so` only exists in the output package of runtime-arm64 and is only used on ARMv8.2 and CPUs that support fp16.
> 2. Compile ARM64 to get the inference framework output of arm64-cpu by default, if you add `-e gpu`, you will get the inference framework output of arm64-gpu, and the package name is `mindspore-lite-{version}-runtime-arm64-gpu.tar.gz`, compiling ARM32 is in the same way.
> 2. Compile ARM64 to get the inference framework output of arm64-cpu by default, if you add `-e gpu`, you will get the inference framework output of arm64-gpu, and the package name is `mindspore-lite-{version}-runtime-arm64-gpu.tar.gz`, compiling ARM32 is in the same way.
> 3. Before running the tools in the converter, benchmark or time_profiler directory, you need to configure environment variables, and configure the path where the dynamic libraries of MindSpore Lite and Protobuf are located to the path where the system searches for dynamic libraries. Take the CPU compiled under version 0.7.0-beta as an example: configure converter: `export LD_LIBRARY_PATH=./output/mindspore-lite-0.7.0-converter-ubuntu/third_party/protobuf/lib:${LD_LIBRARY_PATH}`; configure benchmark and time_profiler: `export LD_LIBRARY_PATH= ./output/mindspore-lite-0.7.0-runtime-x86-cpu/lib:${LD_LIBRARY_PATH}`.
> 3. Before running the tools in the converter, benchmark or time_profiler directory, you need to configure environment variables, and configure the path where the dynamic libraries of MindSpore Lite and Protobuf are located to the path where the system searches for dynamic libraries. Take the compiled under version 0.7.0-beta as an example: configure converter: `export LD_LIBRARY_PATH=./output/mindspore-lite-0.7.0-converter-ubuntu/third_party/protobuf/lib:${LD_LIBRARY_PATH}`; configure benchmark and time_profiler: `export LD_LIBRARY_PATH= ./output/mindspore-lite-0.7.0-runtime-x86-cpu/lib:${LD_LIBRARY_PATH}`.
@@ -20,16 +20,16 @@ The TimeProfiler tool can be used to analyze the time consumption of forward inf
...
@@ -20,16 +20,16 @@ The TimeProfiler tool can be used to analyze the time consumption of forward inf
To use the TimeProfiler tool, you need to prepare the environment as follows:
To use the TimeProfiler tool, you need to prepare the environment as follows:
- Compilation: Install build dependencies and perform build. The code of the TimeProfiler tool is stored in the `mindspore/lite/tools/time_profiler` directory of the MindSpore source code. For details about the build operations, see the [Environment Requirements](https://www.mindspore.cn/lite/tutorial/en/r0.7/build.html#environment-requirements) and [Compilation Example](https://www.mindspore.cn/lite/tutorial/en/r0.7/build.html#compilation-example) in the build document.
- Compilation: Install build dependencies and perform build. The code of the TimeProfiler tool is stored in the `mindspore/lite/tools/time_profile` directory of the MindSpore source code. For details about the build operations, see the [Environment Requirements](https://www.mindspore.cn/lite/tutorial/en/r0.7/build.html#environment-requirements) and [Compilation Example](https://www.mindspore.cn/lite/tutorial/en/r0.7/build.html#compilation-example) in the build document.
- Run: Obtain the `time_profiler` tool and configure environment variables by referring to [Output Description](https://www.mindspore.cn/lite/tutorial/en/r0.7/build.html#output-description) in the build document.
- Run: Obtain the `timeprofile` tool and configure environment variables by referring to [Output Description](https://www.mindspore.cn/lite/tutorial/en/r0.7/build.html#output-description) in the build document.
## Parameter Description
## Parameter Description
The command used for analyzing the time consumption of forward inference at the network layer based on the compiled TimeProfiler tool is as follows:
The command used for analyzing the time consumption of forward inference at the network layer based on the compiled TimeProfiler tool is as follows:
@@ -49,7 +49,7 @@ The following describes the parameters in detail.
...
@@ -49,7 +49,7 @@ The following describes the parameters in detail.
Take the `test_timeprofiler.ms` model as an example and set the number of model inference cycles to 10. The command for using TimeProfiler to analyze the time consumption at the network layer is as follows:
Take the `test_timeprofiler.ms` model as an example and set the number of model inference cycles to 10. The command for using TimeProfiler to analyze the time consumption at the network layer is as follows:
After this command is executed, the TimeProfiler tool outputs the statistics on the running time of the model at the network layer. In this example, the command output is as follows: The statistics are displayed by`opName` and `optype`. `opName` indicates the operator name, `optype` indicates the operator type, and `avg` indicates the average running time of the operator per single run, `percent` indicates the ratio of the operator running time to the total operator running time, `calledTimess` indicates the number of times that the operator is run, and `opTotalTime` indicates the total time that the operator is run for a specified number of times. Finally, `total time` and `kernel cost` show the average time consumed by a single inference operation of the model and the sum of the average time consumed by all operators in the model inference, respectively.
After this command is executed, the TimeProfiler tool outputs the statistics on the running time of the model at the network layer. In this example, the command output is as follows: The statistics are displayed by`opName` and `optype`. `opName` indicates the operator name, `optype` indicates the operator type, and `avg` indicates the average running time of the operator per single run, `percent` indicates the ratio of the operator running time to the total operator running time, `calledTimess` indicates the number of times that the operator is run, and `opTotalTime` indicates the total time that the operator is run for a specified number of times. Finally, `total time` and `kernel cost` show the average time consumed by a single inference operation of the model and the sum of the average time consumed by all operators in the model inference, respectively.
