Add wasi-nn example as smoke test case (#3501)

core/iwasm/libraries/wasi-nn/README.md

@@ -16,23 +16,22 @@ By only including this file in your WASM application you will bind WASI-NN into
 
 To run the tests we assume that the current directory is the root of the repository.
 
-
 ### Build the runtime
 
 Build the runtime image for your execution target type.
 
 `EXECUTION_TYPE` can be:
-* `cpu`
-* `nvidia-gpu`
-* `vx-delegate`
-* `tpu`
+
+- `cpu`
+- `nvidia-gpu`
+- `vx-delegate`
+- `tpu`
 
 ```
 EXECUTION_TYPE=cpu
 docker build -t wasi-nn-${EXECUTION_TYPE} -f core/iwasm/libraries/wasi-nn/test/Dockerfile.${EXECUTION_TYPE} .
 ```
 
-
 ### Build wasm app
 
 ```
@@ -43,7 +42,6 @@ docker build -t wasi-nn-compile -f core/iwasm/libraries/wasi-nn/test/Dockerfile.
 docker run -v $PWD/core/iwasm/libraries/wasi-nn:/wasi-nn wasi-nn-compile
 ```
 
-
 ### Run wasm app
 
 If all the tests have run properly you will the the following message in the terminal,
@@ -52,7 +50,7 @@ If all the tests have run properly you will the the following message in the ter
 Tests: passed!
 ```
 
-* CPU
+- CPU
 
 ```
 docker run \
@@ -64,9 +62,9 @@ docker run \
     /assets/test_tensorflow.wasm
 ```
 
-* (NVIDIA) GPU
-    * Requirements:
-        * [NVIDIA docker](https://github.com/NVIDIA/nvidia-docker).
+- (NVIDIA) GPU
+  - Requirements:
+    - [NVIDIA docker](https://github.com/NVIDIA/nvidia-docker).
 
 ```
 docker run \
@@ -79,7 +77,7 @@ docker run \
     /assets/test_tensorflow.wasm
 ```
 
-* vx-delegate for NPU (x86 simulator)
+- vx-delegate for NPU (x86 simulator)
 
 ```
 docker run \
@@ -90,9 +88,9 @@ docker run \
     /assets/test_tensorflow_quantized.wasm
 ```
 
-* (Coral) TPU
-    * Requirements:
-        * [Coral USB](https://coral.ai/products/accelerator/).
+- (Coral) TPU
+  - Requirements:
+    - [Coral USB](https://coral.ai/products/accelerator/).
 
 ```
 docker run \
@@ -109,6 +107,45 @@ docker run \
 
 Supported:
 
-* Graph encoding: `tensorflowlite`.
-* Execution target: `cpu`, `gpu` and `tpu`.
-* Tensor type: `fp32`.
+- Graph encoding: `tensorflowlite`.
+- Execution target: `cpu`, `gpu` and `tpu`.
+- Tensor type: `fp32`.
+
+## Smoke test
+
+Use [classification-example](https://github.com/bytecodealliance/wasi-nn/tree/main/rust/examples/classification-example) as a smoke test case to make sure the wasi-nn support in WAMR is working properly.
+
+> [!Important]
+> It requires openvino.
+
+### Prepare the model and the wasm
+
+``` bash
+$ pwd
+/workspaces/wasm-micro-runtime/core/iwasm/libraries/wasi-nn/test
+
+$ docker build -t wasi-nn-example:v1.0 -f Dockerfile.wasi-nn-example .
+```
+
+There are model files(*mobilenet\**) and wasm files(*wasi-nn-example.wasm*) in the directory */workspaces/wasi-nn/rust/examples/classification-example/build* in the image of wasi-nn-example:v1.0.
+
+### build iwasm and test
+
+*TODO: May need alternative steps to build the iwasm and test in the container of wasi-nn-example:v1.0*
+
+``` bash
+$ pwd
+/workspaces/wasm-micro-runtime
+
+$ docker run --rm -it -v $(pwd):/workspaces/wasm-micro-runtime wasi-nn-example:v1.0 /bin/bash
+```
+
+> [!Caution]
+> The following steps are executed in the container of wasi-nn-example:v1.0.
+
+``` bash
+$ cd /workspaces/wasm-micro-runtime/product-mini/platforms/linux
+$ cmake -S . -B build -DWAMR_BUILD_WASI_NN=1 -DWAMR_BUILD_WASI_EPHEMERAL_NN=1
+$ cmake --build build
+$ ./build/iwasm -v=5 --map-dir=/workspaces/wasi-nn/rust/examples/classification-example/build/::fixture /workspaces/wasi-nn/rust/examples/classification-example/build/wasi-nn-example.wasm
+```

core/iwasm/libraries/wasi-nn/test/Dockerfile.wasi-nn-example

@@ -0,0 +1,57 @@
+# Copyright (C) 2019 Intel Corporation.  All rights reserved.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+FROM mcr.microsoft.com/devcontainers/rust:1-1-bullseye
+
+ARG DEBIAN_FRONTEND=noninteractive
+ENV TZ=Asian/Shanghai
+
+# hadolint ignore=DL3009
+RUN apt-get update \
+  && apt-get upgrade -y
+
+#
+# Rust targets
+RUN rustup target add wasm32-wasi wasm32-unknown-unknown
+
+#
+# Openvino
+# Refer to
+#   - https://docs.openvino.ai/2022.3/openvino_docs_install_guides_installing_openvino_from_archive_linux.html
+#   - https://docs.openvino.ai/2023.3/openvino_docs_install_guides_installing_openvino_from_archive_linux.html
+#   - https://docs.openvino.ai/2024/get-started/install-openvino/install-openvino-archive-linux.html
+#
+# FIXME: upgrade to 2024.1 or latest after wasi-nn(rust binding) is ready
+WORKDIR /opt/intel
+RUN wget -q https://storage.openvinotoolkit.org/repositories/openvino/packages/2022.3.2/linux/l_openvino_toolkit_ubuntu20_2022.3.2.9279.e2c7e4d7b4d_x86_64.tgz
+RUN tar -xf l_openvino_toolkit_ubuntu20_2022.3.2.9279.e2c7e4d7b4d_x86_64.tgz \
+  && rm l_openvino_toolkit_ubuntu20_2022.3.2.9279.e2c7e4d7b4d_x86_64.tgz \
+  && mv l_openvino_toolkit_ubuntu20_2022.3.2.9279.e2c7e4d7b4d_x86_64 /opt/intel/openvino
+
+WORKDIR /opt/intel/openvino
+RUN ./install_dependencies/install_openvino_dependencies.sh -y \
+  && ./setupvars.sh
+
+#
+# wasmtime
+WORKDIR /opt
+RUN wget -q https://github.com/bytecodealliance/wasmtime/releases/download/v21.0.0/wasmtime-v21.0.0-x86_64-linux.tar.xz
+RUN tar -xf wasmtime-v21.0.0-x86_64-linux.tar.xz \
+  && rm wasmtime-v21.0.0-x86_64-linux.tar.xz \
+  && ln -sf "$(realpath ./wasmtime-v21.0.0-x86_64-linux/wasmtime)" /usr/local/bin/wasmtime
+
+#
+# wasi-nn
+WORKDIR /workspaces/wasi-nn
+RUN git clone --depth 1 https://github.com/bytecodealliance/wasi-nn.git .
+# hadolint ignore=DL3059
+RUN ./build.sh rust
+
+# There are model files(mobilenet*) and wasm files(wasi-nn-example.wasm) in the directory,
+# /workspaces/wasi-nn/rust/examples/classification-example/build
+
+RUN apt-get autoremove -y \
+  && apt-get clean -y \
+  && rm -rf /tmp/*
+
+WORKDIR /workspaces