Qualcomm AI Engine Direct - QAIRT Visualizer Engagement

Summary:
- Add QAIRT Visualizer e2e example script.
- Add README for QAIRT Visualizer.
- Integrate QAIRT Visualizer into CI.
- Remove redundant context size log in QnnDlcManager to avoid duplicate log message.
- Remove DLC test case from context extraction, as it has already been covered in the generate optrace test case.

Author: DannyYuyang-quic

backends/qualcomm/debugger/README.md

@@ -0,0 +1,93 @@
+# QAIRT Visualizer
+
+[QAIRT Visualizer](https://pypi.org/project/qairt-visualizer/) is a Python package designed to help you visualize and analyze data from Qualcomm AI Engine Direct (QNN) models. It provides tools to generate and interpret op traces (`optrace`) and QNN HTP Analysis Summary (`QHAS`), enabling detailed insights into your model's performance and behavior.
+
+## Installation
+
+You can install the QAIRT Visualizer package directly from [QAIRT Visualizer](https://pypi.org/project/qairt-visualizer/):
+
+```bash
+pip install qairt-visualizer
+```
+
+## Quick start
+This command launches an interactive GUI interface to visualize the `optrace` and `QHAS` results.
+```
+python -m examples.qualcomm.util_scripts.qairt_visualizer_demo -H ${host} -s {device} -b build-android -a ${path_to_output_folder} --online_prepare
+```
+- If online prepare mode is `enabled`, the following artifacts will be generated:
+    - `model`.dlc
+    - `optrace`.json
+    - `QHAS`
+- If online prepare mode is `disabled`, the following artifacts will be generated:
+    - `model`.bin
+    - `optrace`.json
+    - `QHAS`.json
+
+Note: Model visualization is supported only in online prepare mode.
+The `.bin` format is not compatible with the QAIRT visualizer.
+To enable model visualization, please add the `--online_prepare` flag.
+
+## Details
+### 1. Lower to QNN backend
+Generate an ExecuTorch binary for Qualcomm platforms.
+```python
+build_executorch_binary(
+    model,
+    example_input,
+    args.model,
+    f"{args.artifact}/{pte_filename}",
+    [example_input],
+    quant_dtype=QuantDtype.use_8a8w,
+    online_prepare=args.online_prepare,
+    optrace=True,
+)
+```
+### 2. Generate optrace and QHAS
+Generate optrace and QHAS files using QNN tools under $QNN_SDK_ROOT. After finishing, you will get a `binaries_trace` dictionary.
+``` python
+adb = SimpleADB(
+    qnn_sdk=os.getenv("QNN_SDK_ROOT"),
+    build_path=f"{args.build_folder}",
+    pte_path=f"{args.artifact}/{pte_filename}.pte",
+    workspace=f"/data/local/tmp/executorch/{pte_filename}",
+    device_id=args.device,
+    host_id=args.host,
+    soc_model=args.model,
+)
+binaries_trace = generate_optrace(
+    args, adb, f"{args.artifact}/{pte_filename}.pte", example_input
+)
+```
+- **`binaries_trace`**: A dictionary where keys are the dumped file paths and values are tuples containing the paths to the generated optrace and QHAS JSON files.
+
+- Example 1: {"forward_0.dlc": (optrace.json, optrace_qnn_htp_analysis_summary.json)}
+- Example 2: {"forward_0.bin": (optrace.json, optrace_qnn_htp_analysis_summary.json)}
+
+### 3. Visualizing and Analyzing optrace and QHAS
+
+Once you have the optrace and QHAS files, you can leverage the QAIRT Visualizer to visualize the model graph, optrace and QHAS data. Here's how you can do it:
+
+```python
+import qairt_visualizer
+qairt_visualizer.view(f"{args.artifact}/forward_0.dlc", reports=[optrace, qhas])
+```
+or
+```python
+import qairt_visualizer
+qairt_visualizer.view(reports=[optrace, qhas])
+```
+
+- `model`: Path to your QNN model file (e.g., `path_to_your_model.dlc`).
+- **`reports`**: List of report file paths, including the optrace (`optrace.json`) and QHAS (`optrace_qnn_htp_analysis_summary.json`).
+
+Note: Files ending with `.bin ` do not support graph visualization in qairt_visualizer.
+
+## Demo
+
+<figure>
+    <img src="assets/qairt_visualizer_demo.png" alt="QAIRT visualizer demo"> <figcaption>
+    </figcaption>
+</figure>
+
+For more details, visit the [QAIRT Visualizer](https://pypi.org/project/qairt-visualizer/).

backends/qualcomm/debugger/assets/qairt_visualizer_demo.png

@@ -1,9 +1,18 @@
+import json
 import os
+import re
 import shutil
+import subprocess
 import tempfile
+from pathlib import Path
+from typing import Tuple
 
 import executorch.backends.qualcomm.python.PyQnnWrapperAdaptor as PyQnnWrapper
 import pandas as pd
+import torch
+from executorch.backends.qualcomm.serialization.qc_schema import QcomChipset
+from executorch.backends.qualcomm.utils.utils import dump_context_from_pte
+
 from graphviz import Digraph
 
 
@@ -180,3 +189,255 @@ def draw(self):
                 dot_file = os.path.join(temp_directory, f"{self.filename}")
                 dot_dest_file = os.path.join(".", f"{self.filename}.dot")
                 shutil.move(dot_file, dot_dest_file)
+
+
+class QnnTool:
+    def __init__(
+        self,
+        tmp_dir,
+        sample_input,
+        soc_id,
+        adb,
+        build_folder,
+        workspace="/data/local/tmp/qnn_executorch_test",
+    ):
+        self.qnn_sdk = os.environ.get("QNN_SDK_ROOT", None)
+        self.ndk = os.environ.get("ANDROID_NDK_ROOT", None)
+        assert self.qnn_sdk, "QNN_SDK_ROOT was not found in environment variable"
+        assert self.ndk, "ANDROID_NDK_ROOT was not found in environment variable"
+
+        self.tmp_dir = tmp_dir
+        self.workspace = workspace
+        self.adb = adb
+        self.sample_input = sample_input
+        self.build_folder = build_folder
+        self.root = str(Path(__file__).resolve().parents[3])
+        self.config = {
+            "backend_extension_config": {
+                "backend_extensions": {
+                    "config_file_path": "config.json",
+                },
+                "features": {
+                    "qhas_json": True,
+                },
+            },
+            "config": {
+                "devices": [
+                    {
+                        "profiling_level": "linting",
+                        "cores": [
+                            {"perf_profile": "burst", "rpc_control_latency": 100}
+                        ],
+                        "soc_id": int(soc_id),
+                    }
+                ]
+            },
+        }
+
+    def qnn_context_binary_generator(
+        self,
+        qnn_binary_file="forward_0.dlc",
+        binary_name="forward.serialized",
+    ):
+        for file_name, data in self.config.items():
+            with open(f"{self.tmp_dir}/{file_name}.json", "w") as json_file:
+                json.dump(data, json_file, indent=4)
+
+        target = "x86_64-linux-clang"
+        cmds = [
+            f"{self.qnn_sdk}/bin/{target}/qnn-context-binary-generator",
+            "--backend",
+            f"{self.qnn_sdk}/lib/{target}/libQnnHtp.so",
+            "--model",
+            f"{self.qnn_sdk}/lib/{target}/libQnnModelDlc.so",
+            "--dlc_path",
+            f"{self.tmp_dir}/{qnn_binary_file}",
+            f"--config_file {self.tmp_dir}/backend_extension_config.json",
+            f"--binary_file {binary_name}",
+            f"--output_dir {self.tmp_dir}",
+            "--profiling_level detailed",
+            "--profiling_option optrace",
+        ]
+        result = subprocess.run(
+            " ".join(cmds),
+            shell=True,
+            executable="/bin/bash",
+            capture_output=True,
+        )
+        assert os.path.isfile(f"{self.tmp_dir}/{binary_name}.bin"), result.stderr
+
+    def qnn_net_run(self, graph_name="forward.serialized"):
+        input_list = ""
+        for idx, _ in enumerate(self.sample_input):
+            input_name = f"input_{idx}_0.raw"
+            input_list += input_name + " "
+        input_list = input_list.strip() + "\n"
+
+        self.config["backend_extension_config"]["backend_extensions"][
+            "shared_library_path"
+        ] = "./libQnnHtpNetRunExtensions.so"
+        for file_name, data in self.config.items():
+            with open(f"{self.tmp_dir}/{file_name}.json", "w") as json_file:
+                json.dump(data, json_file, indent=4)
+
+        target = "aarch64-android"
+        files = [
+            f"{self.qnn_sdk}/lib/{target}/libQnnHtpNetRunExtensions.so",
+            f"{self.tmp_dir}/backend_extension_config.json",
+            f"{self.tmp_dir}/config.json",
+            f"{self.tmp_dir}/{graph_name}.bin",
+            f"{self.qnn_sdk}/bin/{target}/qnn-net-run",
+        ]
+        cmds = [
+            f"export LD_LIBRARY_PATH={self.workspace} &&",
+            f"export ADSP_LIBRARY_PATH={self.workspace} &&",
+            f"cd {self.workspace} &&",
+            "./qnn-net-run",
+            "--backend libQnnHtp.so",
+            "--input_list input_list.txt",
+            f"--retrieve_context {graph_name}.bin",
+            "--use_native_input_files",
+            "--use_native_output_files",
+            "--config_file backend_extension_config.json",
+            "--profiling_level detailed",
+            "--profiling_option optrace",
+        ]
+        self.adb.push(
+            inputs=self.sample_input,
+            input_list=input_list,
+            files=files,
+        )
+        self.adb.execute(custom_runner_cmd=" ".join(cmds))
+        self.adb._adb(
+            [
+                "pull",
+                "-a",
+                f"{self.workspace}/output/qnn-profiling-data_0.log",
+                self.tmp_dir,
+            ]
+        )
+
+        assert os.path.isfile(
+            f"{self.tmp_dir}/qnn-profiling-data_0.log"
+        ), f"Error: qnn-profiling-data_0.log not found in {self.tmp_dir}"
+
+    def qnn_profile_viewer(self, graph_name="forward_schematic", graph_idx=0):
+        self.config["backend_extension_config"]["backend_extensions"][
+            "shared_library_path"
+        ] = "./libQnnHtpNetRunExtensions.so"
+        self.config["backend_extension_config"] = {"features": {"qhas_json": True}}
+        for file_name, data in self.config.items():
+            with open(f"{self.tmp_dir}/{file_name}.json", "w") as json_file:
+                json.dump(data, json_file, indent=4)
+
+        target = "x86_64-linux-clang"
+        cmds = [
+            f"{self.qnn_sdk}/bin/{target}/qnn-profile-viewer",
+            f"--config {self.tmp_dir}/backend_extension_config.json",
+            f"--schematic {self.root}/{graph_name}.bin",
+            f"--reader {self.qnn_sdk}/lib/{target}/libQnnHtpOptraceProfilingReader.so",
+            f"--input_log {self.tmp_dir}/qnn-profiling-data_0.log",
+            f"--output {self.tmp_dir}/optrace_{graph_idx}.json",
+        ]
+        result = subprocess.run(
+            " ".join(cmds),
+            shell=True,
+            executable="/bin/bash",
+            capture_output=True,
+        )
+        assert (
+            result.returncode == 0
+        ), f"Process failed with error: {result.stderr.decode('utf-8')}"
+
+    def generate_optrace(
+        self,
+        qnn_binary_file="forward_0.dlc",
+    ):
+        """
+        Generate Qnn HTP Optrace Profiling https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/htp_backend.html#qnn-htp-optrace-profiling
+        and QNN HTP Analysis Summary (QHAS) https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/htp_backend.html#qnn-htp-analysis-summary-qhas
+        . You can utilize the QAIRT Visualizer (https://pypi.org/project/qairt-visualizer/) to visualize the results from the files above.
+        """
+        graph_name, file_extension = os.path.splitext(qnn_binary_file)
+        assert file_extension in [
+            ".dlc",
+            ".bin",
+        ], f"Invalid file extension '{file_extension}'. Supported extensions are 'dlc' and 'bin'."
+
+        # Attempt to extract a numeric index from the end of the graph name (e.g., "forward_123")
+        match = re.match(r"^(.*)_(\d+)$", graph_name)
+        graph_base_name = graph_name
+        graph_idx = 0
+
+        if match:
+            graph_base_name = match.group(1)
+            graph_idx = int(match.group(2))
+
+        # Handle .dlc file extension by generating a serialized version of the graph
+        if file_extension == ".dlc":
+            self.qnn_context_binary_generator(
+                qnn_binary_file, f"{graph_base_name}.serialized"
+            )
+            graph_name = f"{graph_base_name}.serialized"
+
+        # Run the QNN graph and generate the schematic
+        self.qnn_net_run(graph_name=graph_name)
+        self.qnn_profile_viewer(
+            graph_name=f"{graph_base_name}_schematic", graph_idx=graph_idx
+        )
+
+        # Clean up the schematic binary file if it exists
+        schematic_bin_path = os.path.join(self.root, f"{graph_base_name}_schematic.bin")
+        if os.path.isfile(schematic_bin_path):
+            os.remove(schematic_bin_path)
+
+        optrace_path = os.path.join(self.tmp_dir, f"optrace_{graph_idx}.json")
+        qhas_path = os.path.join(
+            self.tmp_dir, f"optrace_{graph_idx}_qnn_htp_analysis_summary.json"
+        )
+        assert os.path.isfile(optrace_path) and os.path.isfile(qhas_path), (
+            "Error: Required files not found - either "
+            f"{os.path.basename(optrace_path)} or {os.path.basename(qhas_path)} is missing."
+        )
+
+        return optrace_path, qhas_path
+
+
+def generate_optrace(
+    artifact, soc_id: QcomChipset, adb, pte_path: str, inputs: Tuple[torch.Tensor]
+):
+    """
+    Generate optrace and QHAS (QNN HTP Analysis Summary) JSON files.
+
+    Args:
+        artifact (str): Path to the artifact folder.
+        adb (SimpleADB): An object for communicating with Android device
+        pte_path (str): The path to the generated PTE file, including the file extension (e.g., model.pte).
+        inputs (Tuple[torch.Tensor]): The input tensors for the model.
+
+
+    Returns:
+        dict: A dictionary where keys are the dumped file paths and values are tuples containing the paths
+        to the generated optrace and QHAS JSON files.
+    """
+    filename, _ = os.path.splitext(pte_path.split(os.sep)[-1])
+
+    # Dump compiled binaries
+    dumpfiles = dump_context_from_pte(pte_path)
+
+    # Generate optrace and QHAS
+    qnn_tool = QnnTool(
+        artifact,
+        inputs,
+        soc_id,
+        adb,
+        build_folder=adb.build_path,
+        workspace=adb.workspace,
+    )
+
+    binaries_trace = {}
+    for file in dumpfiles:
+        filename = file.split(os.sep)[-1]
+        optrace, qhas = qnn_tool.generate_optrace(filename)
+        binaries_trace[file] = (optrace, qhas)
+    return binaries_trace