SDK Tutorial: ETDump usage docs (#865)

Summary:
Pull Request resolved: #865

Docs for ETDump usage

Reviewed By: guangy10

Differential Revision: D50206992

fbshipit-source-id: 0dceb63713cba0382e439c4ab99c2086ed26b0da

Author: Varun Puri

examples/README.md

@@ -63,6 +63,11 @@ You will find demos of [ExecuTorch QNN Backend](./qualcomm) in the [`qualcomm/`]
 
 The [`xtensa/`](./xtensa) directory hosts a demo that showcases the process of exporting and executing a model on Xtensa Hifi4 DSP. You can utilize [this tutorial](../docs/source/build-run-xtensa.md) to guide you in configuring the demo and running it.
 
+
+## Demo of ExecuTorch SDK
+
+You will find demos of [ExecuTorch SDK](./sdk/) in the [`sdk/`](./sdk/) directory. The examples focuses on exporting and executing BundledProgram for ExecuTorch model verification and ETDump for collecting profiling and debug data.
+
 ## Dependencies
 
 Various models and workflows listed in this directory have dependencies on some other packages. You need to follow the setup guide in [Setting up ExecuTorch from GitHub](../docs/source/getting-started-setup.md) to have appropriate packages installed.

examples/sdk/README.md

@@ -37,25 +37,58 @@ buck2 run examples/sdk/sdk_example_runner:sdk_example_runner -- --bundled_progra
 ```
 
 
-## Generate ETDump
+## ETDump
 
-Next step is to generate an ``ETDump``. ``ETDump`` contains runtime results
-from executing the model. To generate, users have two options:
+### Getting Started
 
-**Option 1:**
+After exporting a `BundledProgram`, runtime profiling and debug data can be collected in an ``ETDump``. An ``ETDump`` is a buffer containing data generated by hooks within the ExecuTorch runtime.
+We offer an example runner that accepts a `BundledProgram` (`.bp`) and runs a single iteration over the first method defined.
+
+Running the program will generate an `ETDump` file (`.etdp`) at the location specified by `--etdump_path`. Make sure to build the program as specified below to enable the event tracer.
+
+**Buck**
 
-Use Buck::
 ```bash
    python3 -m examples.sdk.scripts.export_bundled_program -m mv2
-   buck2 run -c executorch.event_tracer_enabled=true examples/sdk/sdk_example_runner:sdk_example_runner -- --bundled_program_path mv2_bundled.bp
+   buck2 run -c executorch.event_tracer_enabled=true examples/sdk/sdk_example_runner:sdk_example_runner -- --bundled_program_path mv2_bundled.bp --etdump_path mv2_etdump.etdp
 ```
- **Option 2:**
+ **CMake**
 
- Use CMake::
 ```bash
    cd executorch
    rm -rf cmake-out && mkdir cmake-out && cd cmake-out && cmake -DBUCK2=buck2 -DEXECUTORCH_BUILD_SDK=1 -DEXECUTORCH_BUILD_EXTENSION_DATA_LOADER=1 ..
    cd ..
    cmake --build cmake-out -j8 -t sdk_example_runner
-   ./cmake-out/examples/sdk/sdk_example_runner --bundled_program_path mv2_bundled.bp
+   ./cmake-out/examples/sdk/sdk_example_runner --bundled_program_path mv2_bundled.bp --etdump_path mv2_etdump.etdp
+   ```
+
+### Parsing ETDump
+
+Once an `ETDump` has been generated, it can be viewed using the CLI inspector. This will print a tabular view of the data recorded in the ETDump.
+
+```bash
+   python3 -m sdk.inspector.inspector_cli --etdump_path mv2_etdump.etdp
+   ```
+### ETDump C++ API
+
+ETDump profiling can also be used in a custom C++ program. `ETDumpGen` is an implementation of the abstract `EventTracer` class.  Include the header file located at `sdk/etdump/etdump_flatcc.h`. To initialize the ETDump generator, construct it before loading the method from the program.
+
+```cpp
+   torch::executor::ETDumpGen etdump_gen = torch::executor::ETDumpGen();
+   Result<Method> method =
+      program->load_method(method_name, &memory_manager, &etdump_gen);
+   ```
+
+Since the `EventTracer` hooks are embedded within the runtime, profiling and debug data will be automatically recorded.
+
+Once execution has completed, finalize the ETDump buffer. This returns an `etdump_result`, a struct with the finalized buffer and its size.
+
+```cpp
+   etdump_result result = etdump_gen.get_etdump_data();
+   if (result.buf != nullptr && result.size > 0) {
+    FILE* f = fopen(FLAGS_etdump_path.c_str(), "w+");
+    fwrite((uint8_t*)result.buf, 1, result.size, f);
+    fclose(f);
+    free(result.buf);
+  }
    ```