onnxruntime/js/web/lib/wasm/proxy-worker/main.ts
Yulong Wang 036fcd93d4
[js/web] optimize module export and deployment (#20165)
### Description

This PR make numbers of optimizations to onnxruntime-web's module export
and deployment.

See each section below for more details.

#### Preview

>
[onnxruntime-web@1.19.0-esmtest.20240513-a16cd2bd21](https://www.npmjs.com/package/onnxruntime-web/v/1.19.0-esmtest.20240513-a16cd2bd21)

> ~~onnxruntime-web@1.19.0-esmtest.20240430-c7edbcc63d~~

> ~~onnxruntime-web@1.18.0-esmtest.20240428-624c681c83~~

> ~~onnxruntime-web@1.18.0-esmtest.20240411-1abb64e894~~

<details>
<summary><h4>Breaking changes</h4></summary>

There is no code change required, but there are a few differences
regarding **code import**, **flags**, **bundler config** and
**deployment steps**.

#### Importing:

Import table is changed. See following for details.

<details>
<summary><h5>Current import table:</h5></summary>

| Target Name | Path for "import" or "require" | WebGL | JSEP | wasm |
Proxy | Training |
  |------|-----|-----|-----|-----|-----|-----|
  | `ort` (default) | `onnxruntime-web` | ✔️ |  | ✔️ | ✔️ |  |
  | `ort.all` | `onnxruntime-web/experimental` | ✔️ | ✔️ | ✔️ | ✔️ |  |
  | `ort.node` | `onnxruntime-web` |  |  | ✔️ |  |  |
| `ort.training` | `onnxruntime-web/training` |  |  | ✔️ |
✔️<sup>\[1]</sup> | ✔️ |
  | `ort.wasm` | `onnxruntime-web/wasm` |  |  | ✔️ | ✔️ |  |
  | `ort.wasm-core` | `onnxruntime-web/wasm-core` |  |  | ✔️ |  |  |
| `ort.webgl` | `onnxruntime-web/webgl` | ✔️ |  |  | ✔️<sup>\[2]</sup>
|  |
  | `ort.webgpu` | `onnxruntime-web/webgpu` |  | ✔️ | ✔️ | ✔️ |  |

* [1] didn't test. may not actually work.
* [2] not working. this is a mistake in build config.

</details>

<details>
<summary><h5>Proposed update:</h5></summary>

| Target Name | Path for "import" or "require" | WebGL | JSEP | wasm |
Proxy | Training |
  |------|-----|-----|-----|-----|-----|-----|
  | `ort` (default) | `onnxruntime-web` | ✔️ |  | ✔️ | ✔️ |  |
| `ort.all` |
~~`onnxruntime-web/experimental`~~<br/>`onnxruntime-web/all` | ✔️ | ✔️ |
✔️ | ✔️ |  |
  | `ort.node` | `onnxruntime-web` |  |  | ✔️ |  |  |
  | `ort.training` | `onnxruntime-web/training` |  |  | ✔️ | ✔️ | ✔️ |
  | `ort.wasm` | `onnxruntime-web/wasm` |  |  | ✔️ | ✔️ |  |
| ~~`ort.wasm-core`~~ | ~~`onnxruntime-web/wasm-core`~~ | ~~~~ | ~~~~
| ~~✔️~~ | ~~~~ | ~~~~ |
  | `ort.webgl` | `onnxruntime-web/webgl` | ✔️ |  |  | ~~✔️~~  |  |
  | `ort.webgpu` | `onnxruntime-web/webgpu` |  | ✔️ | ✔️ | ✔️ |  |

</details>

#### Flags:

The following flags are deprecated:
- `env.wasm.simd` (boolean): will be ignored. SIMD is always enabled in
build.

The following flags changed their type:
- `env.wasm.wasmPaths`: When using this flag as a string ( for the URL
prefix ), nothing is changed. When using this flag as an object ( for
per-file path override ), the type changed:
  ```diff
  -  export interface Old_WasmFilePaths{
  -    'ort-wasm.wasm'?: string;
  -    'ort-wasm-threaded.wasm'?: string;
  -    'ort-wasm-simd.wasm'?: string;
  -    'ort-training-wasm-simd.wasm'?: string;
  -    'ort-wasm-simd-threaded.wasm'?: string;
  -  };
  +  export interface New_WasmFilePaths {
  +    /**
  +     * Specify the override path for the main .wasm file.
  +     *
  +     * This path should be an absolute path.
  +     *
  +     * If not modified, the filename of the .wasm file is:
  +     * - `ort-wasm-simd-threaded.wasm` for default build
+ * - `ort-wasm-simd-threaded.jsep.wasm` for JSEP build (with WebGPU and
WebNN)
  +     * - `ort-training-wasm-simd-threaded.wasm` for training build
  +     */
  +    wasm?: URL|string;
  +    /**
  +     * Specify the override path for the main .mjs file.
  +     *
  +     * This path should be an absolute path.
  +     *
  +     * If not modified, the filename of the .mjs file is:
  +     * - `ort-wasm-simd-threaded.mjs` for default build
+ * - `ort-wasm-simd-threaded.jsep.mjs` for JSEP build (with WebGPU and
WebNN)
  +     * - `ort-training-wasm-simd-threaded.mjs` for training build
  +     */
  +    mjs?: URL|string;
  +  }
  ```

#### Bundler compatibility:

Config changes are need for bundlers. See usage example in
/js/web/test/e2e/ for Webpack, parcel and rollup.

#### Deployment:

- if consuming from a CDN, there is no breaking change.
- if consuming from a local server, need to copy all `ort-*.wasm` and
`ort-*.mjs` files (totally 6 files) in the dist folder. (previously only
need to copy `ort-*.wasm` files.)

</details>
<details>
<summary><h4>Problems</h4></summary>

There are a few problems with the current module export and deployment:

- Script URL cannot be correctly inferred when imported as ESM.
- Workers are forcefully encoded using Blob URL, which makes
onnxruntime-web not working in CSP environment and Node.js, when using
proxy or multi-threading feature.
- Generated JS code (by Emscripten) is encoded using
`function.toString()`, which is unstable and error-prone.
- When running with a different Emscripten build, always need the build
step. Making it difficult to swap artifacts in deveopment/debug.
</details>
<details>
<summary><h4>Goals</h4></summary>

- Full ESM support
- Support variances of ways to import. Including:
- import from HTML's `<script>` tag (IIFE format, exporting to global
variable `ort`)
    ```html
<script
src="https://example.com/cdn-path-to-onnxruntime-web/dist/ort.min.js"></script>
    ```
  - import from source code inside `<script type="module">` tag (ESM)
    ```html
    <script type="module">
import * as ort from
"https://example.com/cdn-path-to-onnxruntime-web/dist/ort.min.mjs";

      // using 'ort'
    </script>
    ```
- import in a CommonJS project (CJS format, resolve from package.json
"exports" field)
    ```js
    // myProject/main.js
    const ort = require('onnxruntime-web');
    ```
- import in an ESM project (ESM format, resolve from package.json
"exports" field)
    ```js
    // myProject/main.js (or main.mjs)
    import * as ort from 'onnxruntime-web';
    ```
- Support popular bundlers when importing onnxruntime-web into a CJS/ESM
project.
  - webpack (esm requires extra post-process step)
  - rollup
  - parcel (esm requires extra post-process step)
  - More bundlers **TBD**
- Multi-threading support for Node.js

NOTE: keeping single JavaScript file (the all-in-one bundle) is no
longer a goal. This is because technically there is a conflict with the
other requirements.
</details>

<details>
<summary><h4>Important Design Decisions</h4></summary>

- Drop support of single JavaScript output.
- The current onnxruntime-web distribution uses a single JavaScript file
to include all code. While there are a few benefits, it also creates
problems as mentioned above. Since ESM is being used more and more
widely, and browsers are making more restricted security checks and
requirement, the old Blob based solution is going to be replaced.
- To achieve the requirement, specifically, the CSP environment support,
we have to offer a non Blob based solution. Therefore, we have to
distribute multiple files and drop the single file solution.

- Do not run parser/postprocess on Emscripten generated JavaScript.
- Emscripten is evolving quickly so we should only depends on what's in
its documentation instead of a certain implementation details. (for
example, currently we patch on its code to deal with a special variable
`_scriptDir`)
  - Keep the generated files as-is also helps to:
    - reduce the size of ort.min.js
- make it easier to replace build artifacts when in development/debug

- Drop support for non-SIMD and non-MultiThread. This helps to reduce
the number of artifacts in distribution.
  - (fixed-sized) SIMD is supported in any mainstream JS environment.
- Multi-thread as WebAssembly feature is supported in any mainstream JS
environment. In some environment the feature is guarded with cross
origin policy, but it can still work if not trying to create any worker.

- Use ESM output for Emscripten generated JavaScript.
- There are 2 ways to dynamically import classic (umd) modules and
neither of them are recommended:
- dynamically creating a <script> tag. This changes the HTML structure
and have quite a lot of compatibility issue
- use `fetch()` and `eval()`. However `eval` is strongly suggested to be
avoid because there is a great perf hit.
- importing ESM is super easy - just use the `import()` call.
Considering ESM is widely supported in modern browsers and Node.js this
is the better option.

- Add Blob based solution as a fallback for cross-origin workers.
- There are still wide use case of importing onnxruntime-web from CDN.
In this usage, make it able create worker by using `fetch()`+`Blob` to
create a same-origin Blob URL.

</details>

<details>
<summary><h4>Distribution File Manifest</h4></summary>

The distribution folder contains the following files:

- WebAssembly artifacts. These files are the result of compiling the
ONNX Runtime C++ code to WebAssembly by Emscripten.

  | File Name | Build Flags |
  |------|-----|
| ort-wasm-simd-threaded.mjs <br/> ort-wasm-simd-threaded.wasm |
`--enable_wasm_simd` <br/> `--enable_wasm_threads` |
| ort-training-wasm-simd-threaded.mjs <br/>
ort-training-wasm-simd-threaded.wasm | `--enable_training_apis` <br/>
`--enable_wasm_simd` <br/> `--enable_wasm_threads` |
| ort-wasm-simd-threaded.jsep.mjs <br/> ort-wasm-simd-threaded.jsep.wasm
| `--enable_wasm_simd` <br/> `--enable_wasm_threads` <br/> `--use_jsep`
<br/> `--use_webnn` |

- onnxruntime-web JavaScript artifacts. These files are generated by
ESBuild as the entry point for onnxruntime-web.

  There are multiple build targets for different use cases:
  | Target Name | Path for "import" or "require" | Description |
  |------|-----|-----|
  | `ort` | `onnxruntime-web` | The default target. |
  | `ort.all` | `onnxruntime-web/all` | The target including webgl. |
  | `ort.node` | `onnxruntime-web` | The default target for Node.js. |
| `ort.training` | `onnxruntime-web/training` | The target including
training APIs |
| `ort.wasm` | `onnxruntime-web/wasm` | The target including only
WebAssembly (CPU) EP |
| `ort.webgl` | `onnxruntime-web/webgl` | The target including only
WebGL EP |


  For each target, there are multiple files generated:
  | File Name | Description |
  |------|-----|
| [target].js | The entry point for the target. IIFE and CommonJS
format. |
  | [target].mjs | The entry point for the target. ESM format. |
| [target].min.js <br/> [target].min.js.map | The entry point for the
target. Minimized with sourcemap. IIFE and CommonJS format. |
| [target].min.mjs <br/> [target].min.mjs.map | The entry point for the
target. Minimized with sourcemap. ESM format. |
| [target].proxy.mjs | (if appliable) The proxy ESM module for the
target. |
| [target].proxy.min.mjs <br/> [target].proxy.min.mjs.map | (if
appliable) The proxy ESM module for the target. Minimized with
sourcemap. |

</details>

<details>
<summary><h4>Dynamic Import Explained</h4></summary>

- Local Served | No Proxy:
  ```
  [Bundle or ort.min.js]
    |
    + import()--> [ort-wasm-simd-threaded.mjs]
                    |
+ WebAssembly.instantiateStreaming()--> [ort-wasm-simd-threaded.wasm]
                    |
+ new Worker()--> [ort-wasm-simd-threaded.mjs (worker)]
                                        |
+ WebAssembly.instantiateStreaming()--> [ort-wasm-simd-threaded.wasm]
  ```
- Local Served | Proxy:
  ```
  [Bundle or ort.min.js]
    |
    + import()--> [ort.proxy.min.mjs]
                    |
                    + new Worker()--> [ort.proxy.min.mjs (worker)]
                                        |
+ import()--> [ort-wasm-simd-threaded.mjs]
                                                        |
+ WebAssembly.instantiateStreaming()--> [ort-wasm-simd-threaded.wasm]
                                                        |
+ new Worker()--> [ort-wasm-simd-threaded.mjs (worker)]
|
+ WebAssembly.instantiateStreaming()--> [ort-wasm-simd-threaded.wasm]
  ```
- Cross Origin | No Proxy:
  ```
  [Bundle or ort.min.js]
    |
    + fetch('ort-wasm-simd-threaded.mjs')
        |
        + URL.createObjectURL(res.blob())
        |
        + import()--> [blob:... (ort-wasm-simd-threaded)]
                        |
+ WebAssembly.instantiateStreaming()--> [ort-wasm-simd-threaded.wasm]
                        |
+ new Worker()--> [blob:... (ort-wasm-simd-threaded) (worker)]
                                            |
+ WebAssembly.instantiateStreaming()--> [ort-wasm-simd-threaded.wasm]
  ```

- Cross Origin | Proxy
  ```
  [Bundle or ort.min.js]
    |
    + fetch('ort.proxy.min.mjs')
        |
        + URL.createObjectURL(res.blob())
        |
        + import()--> [blob:... (ort.proxy)]
                        |
+ new Worker()--> [blob:... (ort.proxy) (worker)]
                                            |
+ fetch('ort-wasm-simd-threaded.mjs')
                                                |
+ URL.createObjectURL(res.blob())
                                                |
+ import()--> [blob:... (ort-wasm-simd-threaded)]
                                                                |
+ WebAssembly.instantiateStreaming()--> [ort-wasm-simd-threaded.wasm]
                                                                |
+ new Worker()--> [blob:... (ort-wasm-simd-threaded) (worker)]
|
+ WebAssembly.instantiateStreaming()--> [ort-wasm-simd-threaded.wasm]
  ```
</details>
2024-05-20 09:51:16 -07:00

183 lines
7.3 KiB
TypeScript

// Copyright (c) Microsoft Corporation. All rights reserved.
// Licensed under the MIT License.
/// <reference lib="webworker" />
//
// * type hack for "HTMLImageElement"
//
// in typescript, the type of "HTMLImageElement" is defined in lib.dom.d.ts, which is conflict with lib.webworker.d.ts.
// when we use webworker, the lib.webworker.d.ts will be used, which does not have HTMLImageElement defined.
//
// we will get the following errors complaining that HTMLImageElement is not defined:
//
// ====================================================================================================================
//
// ../common/dist/cjs/tensor-factory.d.ts:187:29 - error TS2552: Cannot find name 'HTMLImageElement'. Did you mean
// 'HTMLLIElement'?
//
// 187 fromImage(imageElement: HTMLImageElement, options?: TensorFromImageElementOptions):
// Promise<TypedTensor<'float32'> | TypedTensor<'uint8'>>;
// ~~~~~~~~~~~~~~~~
//
// node_modules/@webgpu/types/dist/index.d.ts:83:7 - error TS2552: Cannot find name 'HTMLImageElement'. Did you mean
// 'HTMLLIElement'?
//
// 83 | HTMLImageElement
// ~~~~~~~~~~~~~~~~
//
// ====================================================================================================================
//
// `HTMLImageElement` is only used in type declaration and not in real code. So we define it as `unknown` here to
// bypass the type check.
//
// * type hack for "document"
//
// in typescript, the type of "document" is defined in lib.dom.d.ts, so it's not available in webworker.
//
// we will get the following errors complaining that document is not defined:
//
// ====================================================================================================================
//
// lib/wasm/wasm-utils-import.ts:7:33 - error TS2584: Cannot find name 'document'. Do you need to change your target
// library? Try changing the 'lib' compiler option to include 'dom'.
//
// 7 export const scriptSrc = typeof document !== 'undefined' ? (document?.currentScript as HTMLScriptElement)?.src :
// ~~~~~~~~
//
// lib/wasm/wasm-utils-import.ts:7:61 - error TS2584: Cannot find name 'document'. Do you need to change your target
// library? Try changing the 'lib' compiler option to include 'dom'.
//
// 7 export const scriptSrc = typeof document !== 'undefined' ? (document?.currentScript as HTMLScriptElement)?.src :
// ~~~~~~~~
//
// lib/wasm/wasm-utils-import.ts:7:88 - error TS2552: Cannot find name 'HTMLScriptElement'. Did you mean
// 'HTMLLIElement'?
//
// 7 export const scriptSrc = typeof document !== 'undefined' ? (document?.currentScript as HTMLScriptElement)?.src :
// ~~~~~~~~~~~~~~~~~
// ====================================================================================================================
//
// `document` is used to get the current script URL, which is not available in webworker. This file is served as a
// "dual" file for entries of both webworker and the esm module.
//
declare global {
type HTMLImageElement = unknown;
type HTMLScriptElement = {src?: string};
const document: undefined|{currentScript?: HTMLScriptElement};
}
/**
* @summary
*
* This file is served as a "dual" file for both entries of the following:
* - The proxy worker itself.
* - When used as a worker, it listens to the messages from the main thread and performs the corresponding operations.
* - Should be imported directly using `new Worker()` in the main thread.
*
* - The ESM module that creates the proxy worker (as a worker launcher).
* - When used as a worker launcher, it creates the proxy worker and returns it.
* - Should be imported using `import()` in the main thread, with the query parameter `import=1`.
*
* This file will be always compiling into ESM format.
*/
import type {OrtWasmMessage, SerializableTensorMetadata} from '../proxy-messages.js';
import {createSession, copyFromExternalBuffer, endProfiling, extractTransferableBuffers, initEp, initRuntime, releaseSession, run} from '../wasm-core-impl.js';
import {initializeWebAssembly} from '../wasm-factory.js';
import {scriptSrc} from '../wasm-utils-import.js';
const WORKER_NAME = 'ort-wasm-proxy-worker';
const isProxyWorker = globalThis.self?.name === WORKER_NAME;
if (isProxyWorker) {
// Worker thread
self.onmessage = (ev: MessageEvent<OrtWasmMessage>): void => {
const {type, in : message} = ev.data;
try {
switch (type) {
case 'init-wasm':
initializeWebAssembly(message!.wasm)
.then(
() => {
initRuntime(message!).then(
() => {
postMessage({type});
},
err => {
postMessage({type, err});
});
},
err => {
postMessage({type, err});
});
break;
case 'init-ep': {
const {epName, env} = message!;
initEp(env, epName)
.then(
() => {
postMessage({type});
},
err => {
postMessage({type, err});
});
break;
}
case 'copy-from': {
const {buffer} = message!;
const bufferData = copyFromExternalBuffer(buffer);
postMessage({type, out: bufferData} as OrtWasmMessage);
break;
}
case 'create': {
const {model, options} = message!;
createSession(model, options)
.then(
sessionMetadata => {
postMessage({type, out: sessionMetadata} as OrtWasmMessage);
},
err => {
postMessage({type, err});
});
break;
}
case 'release':
releaseSession(message!);
postMessage({type});
break;
case 'run': {
const {sessionId, inputIndices, inputs, outputIndices, options} = message!;
run(sessionId, inputIndices, inputs, outputIndices, new Array(outputIndices.length).fill(null), options)
.then(
outputs => {
if (outputs.some(o => o[3] !== 'cpu')) {
postMessage({type, err: 'Proxy does not support non-cpu tensor location.'});
} else {
postMessage(
{type, out: outputs} as OrtWasmMessage,
extractTransferableBuffers([...inputs, ...outputs] as SerializableTensorMetadata[]));
}
},
err => {
postMessage({type, err});
});
break;
}
case 'end-profiling':
endProfiling(message!);
postMessage({type});
break;
default:
}
} catch (err) {
postMessage({type, err} as OrtWasmMessage);
}
};
}
export default isProxyWorker ?
null :
(urlOverride?: string) =>
new Worker(urlOverride ?? scriptSrc!, {type: BUILD_DEFS.IS_ESM ? 'module' : 'classic', name: WORKER_NAME});