### Description
This PR rewrite the backend resolve logic to support specifying multiple
EPs.
#### Backend
The first version of ONNX Runtime Web actually carried some existing
code from [ONNX.js](https://github.com/microsoft/onnxjs), which includes
the "backend" concept. The original "backend" in ONNX.js is designed in
a way assuming there is only one backend from user's backend hint list
will be used. For example, in ONNX.js, if user specify a backend hint as
`['webgl', 'wasm']`, ONNX.js will first try to use WebGL backend - if it
loads successfully (the browser supports webgl), then "webgl" backend
will be used and "wasm" will be ignored; otherwise, "webgl" will be
ignored and try to load "wasm" backend.
In short: only one backend will be used when initializing a session.
#### Execution Provider
Execution Provider, or EP, in ONNX Runtime is a different concept. One
of the differences is that users are allow to specify multiple EPs, and
if one does not support a particular kernel, it can fallback to other
EP. This is a very common case when using a GPU EP in ONNX Runtime.
#### Current Status: Backend v.s. EP
Because of the history reasons mentioned above, the current status is
quite confusing. There are **real backend**s, which means it's different
implementation in code; and there are **backend hint**s, which are used
as string names for backend hint; and there are **EP**s of the ONNX
Runtime concepts.
currently there are only 2 **backend**s in our code base: The "onnxjs
backend", and the "wasm backend". The "onnxjs backend" currently only
powers backend hint "webgl", which go into the old onnx.js code path.
All other backend hints including "wasm", "cpu"(alias to wasm), "webgpu"
and "webnn" are all powered by "wasm backend".
And because ORT Web treat "backend" as an internal concept and want to
align with ONNX Runtime, so those names of backend hints are becoming EP
names.
The following table shows today's status:
| Execution Provider Name (public) / Backend Hint (internal) | Backend |
EP in ORT
| -------- | ------- | ------- |
| "wasm"/"cpu" | WasmBackend | CPU EP
| "webgl" | OnnxjsBackend | \* technically not an EP
| "webgpu" | WasmBackend | JSEP
| "webnn" | WasmBackend | WebNN EP
#### Problem
While the API allows to specify multiple EPs, the backend resolving only
allows one backend. This causes issues when user specify multiple EP
names in session options, the backend resolve behavior and EP
registration behavior is inconsistent. Specifically, in this issue:
https://github.com/microsoft/onnxruntime/issues/15796#issuecomment-1925363908:
EP list `['webgpu', 'wasm']` on a browser without WebGPU support
resolves to 'wasm' backend, but the full EP list is passed in session
options, so JSEP is still enabled, causing the runtime error.
#### Solution
Since we still need WebGL backend, we cannot totally remove the backend
register/resolve system. In this PR I made the following changes:
- initialize every backend from the EP list, instead of only do that for
the first successful one.
- for the first resolved backend, filter all EP using the exact same
backend. Remove all EPs not using this backend from session options
- for every explicitly specified EP, if it's removed, show a warning
message in console
### Description
This PR expands the graph capture capability to JS EP, which is similar
to #16081. But for JS EP, we don't use the CUDA Graph, instead, we
records all gpu commands and replay them, which removes most of the cpu
overhead to avoid the the situation that gpu waiting for cpu.
mobilenetv2-12 becomes 3.7ms from 6ms on NV 3090 and becomes 3.38ms from
4.58ms on Intel A770.
All limitations are similar with CUDA EP:
1. Models with control-flow ops (i.e. If, Loop and Scan ops) are not
supported.
2. Usage of graph capture is limited to models where-in all ops in the
model can be partitioned to the JS EP or CPU EP and no memory copy
between them.
3. Shapes of inputs/outputs cannot change across inference calls.
4. IObinding is required.
The usage is like below:
Method 1: specify outputs buffers explicitly.
```
const sessionOptions = {
executionProviders: [
{
name: "webgpu",
},
],
enableGraphCapture: true,
};
const session = await ort.InferenceSession.create('./models/mobilenetv2-12.onnx', sessionOptions);
// prepare the inputBuffer/outputBuffer
... ...
const feeds = {
'input': ort.Tensor.fromGpuBuffer(inputBuffer, { dataType: 'float32', dims })
};
const fetches = {
'output': ort.Tensor.fromGpuBuffer(outputBuffer, { dataType: 'float32', dims: [1, 1000] })
};
let results = await session.run(feeds, fetches); // The first run will begin to capture the graph.
// update inputBuffer content
... ...
results = = await session.run(feeds, fetches); // The 2ed run and after will directly call replay to execute the graph.
... ...
session.release();
```
Method 2: Don't specify outputs buffers explicitly. Internally, when
graph capture is enabled, it will set all outputs location to
'gpu-buffer'.
```
const sessionOptions = {
executionProviders: [
{
name: "webgpu",
},
],
enableGraphCapture: true,
};
const session = await ort.InferenceSession.create('./models/mobilenetv2-12.onnx', sessionOptions);
// prepare the inputBuffer
... ...
const feeds = {
'input': ort.Tensor.fromGpuBuffer(inputBuffer, { dataType: 'float32', dims })
};
let results = await session.run(feeds); // The first run will begin to capture the graph.
// update inputBuffer content
... ...
results = = await session.run(feeds); // The 2ed run and after will directly call replay to execute the graph.
... ...
session.release();
### Description
<!-- Describe your changes. -->
`env.webgpu.profiling` is a global flag. It may change before each
session.run. So the best place is to update it in `onRunStart` event.
After this, we can directly check `this.queryType`'s value. Without this
pr, we need to make sure that `getCommandEncoder()` is called before
checking `this.queryType`. Otherwise, it may happen that
`pendingKernels`'s length is not equal to `pendingDispatchNumber`'s
length. See the two ugly workarounds
[1)](e630dbf528 (diff-006fc84d3997f96a29b8033bd2075d6a0a9509211bd5812a6b934fc74fedfd9dR267-R268))
and
[2)](e630dbf528 (diff-618fe297fbe7a1da586380163b8fd2627311ccc217640a3c5cdc9c17a33472c1R73-R80))
if we don't introduce `onRunStart`. Or we need to call `setQueryType` in
each kernel run.
### Description
enable external data loading for ort-web.
### Why
The ORT external data design is highly depending on the file system,
especially synchronous file I/O APIs. Those are not available in web
platforms. We need to have extra code to make external data working on
web.
### How
Considering there is no file system in web, an implementation for web to
support external data is to use pre-loaded data. Assume model file
a.onnx includes initializers that linked to ./b.bin, we require users to
pass a full data file list when creating the session. The user code will
be look like:
```js
const mySess = await ort.InferenceSession.create('./path/model/a.onnx', {
// session options
externalData: [
{
// relative or absolute path/URL of the file,
// or a pre-loaded Uint8Array containing the data of the external data file
data: './path/data/b.bin',
// the relative path of the external data. Should match initializers' "location" value defined in the model file
path: './b.bin'
},
// { } if multiple external data file
]
});
```
Currently, this feature only works with JSEP build enabled.
### Description
a replacement of #18683. try to resolve#18689.
By specifying "-s PTHREAD_POOL_SIZE" flag in emscripten, it forces the
threadpool to initialize before the webassembly instance is available.
### Description
* Adds TrainingSession.create() functionality following the web bindings
for training design doc
* Added 2 new training APIs to wasm/api.h:
* OrtTrainingGetInputOutputName
* OrtTrainingGetInputOutputCount
* Moved isOrtEnvInitialized boolean to the wasm-core-impl and added a
method that references it
### Motivation and Context
* Adding web bindings for training
#### Related work
* #16521 allowed for training artifacts to be built
* #17333 added interfaces for training
* #17474 allows for training package to be built + adds training backend
to web package **[MUST BE MERGED IN BEFORE THIS ONE]**
---------
Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com>
Co-authored-by: Ashwini Khade <askhade@microsoft.com>
<del>
**This PR is based on a few prerequisites PRs. They are listed as
below:**
- #17465
- #17469
- #17470
- #17472
- #17473
- #17484
Please review the current change by only looking at commit
e2e6623e673ec6de55a5c1f8edcbd3a46b535a89 and later.
</del>
### Description
This PR introduces WebGPU IO binding. This new feature allows
onnxruntime-web users to use tensors created from GPU as model
input/output so that a model inferencing can be done without unnecessary
data copy between CPU and GPU for model input/output.
### Examples
An E2E demo/example is being worked on.
Following is some simple demo with code snippet.
Let's first check today how we do:
```js
// STEP.1 - create an inference session:
const mySession = await ort.InferenceSession.create('./my_model.onnx', { executionProviders: ['webgpu'] });
// STEP.2 - create model input: (supposing myImageCpuData is a Float32Array)
const feeds = {
'input_image:0': new ort.Tensor('float32', myImageCpuData, [1, 224, 224, 3])
};
// STEP.3 - run model
const myResults = await mySession.run(feeds);
// STEP.4 - get output data
const myData = myResults['output_image:0'].data; // Float32Array
```
#### for inputs (GPU tensor):
Now, with IO binding, you can create a tensor from a GPU buffer, and
feed it to the model:
```js
// new STEP.2.A - create model input from a GPU buffer: (supposing myInputGpuBuffer is a `GPUBuffer` object with input data)
const feeds = {
'input_image:0': ort.Tensor.fromGpuBuffer(myInputGpuBuffer, { dataType: 'float32', dims: [1, 224, 224, 3] })
};
```
### for outputs (pre-allocated GPU tensor)
you can also do that for output, **if you know the output shape**:
```js
// new STEP.2.B - create model output from a GPU buffer: (supposing myOutputGpuBuffer is a pre-allocated `GPUBuffer` object)
const fetches = {
'output_image:0': ort.Tensor.fromGpuBuffer(myOutputGpuBuffer, { dataType: 'float32', dims: [1, 512, 512, 3] })
};
// new STEP.3 - run model with pre-allocated output (fetches)
const myResults = await mySession.run(feeds, fetches);
```
### for outputs (specify location)
if you do not know the output shape, you can specify the output location
when creating the session:
```js
// new STEP.1 - create an inference session with an option "preferredOutputLocation":
const mySession = await ort.InferenceSession.create('./my_model.onnx', {
executionProviders: ['webgpu'],
preferredOutputLocation: "gpu-buffer"
});
```
if the model has multiple outputs, you can specify them seperately:
```js
// new STEP.1 - create an inference session with an option "preferredOutputLocation":
const mySession = await ort.InferenceSession.create('./my_model.onnx', {
executionProviders: ['webgpu'],
preferredOutputLocation: {
"output_image:0": "gpu-buffer"
}
});
```
now you don't need to prepare the `fetches` object and onnxruntime-web
will prepare output data on the location that specified.
#### read data
when you get the output tensor, you can:
```js
// get the gpu buffer object:
const gpuBuffer = myOutputTensor.gpuBuffer; // GPUBuffer
// get the CPU data asynchronizely
const cpuData = await myOutputTensor.getData();
// get the CPU data asynchronizely and release the underlying GPU resources
const cpuData = await myOutputTensor.getData(true);
// dispose the tensor (release the underlying GPU resources). This tensor object will be invalid after dispose() is called.
myOutputTensor.dispose();
```
#### resource management
JavaScript has GC so you don't need to worry about managing JavaScript
objects. But there are 2 types of resources that are not managed by GC:
- GPU buffer that used in tensors
- Underlying ORT native resources
To simplify, most of the unmanaged resources and handled inside ORT web.
But there are a few resources that need users to manage:
- All external GPU resources, including GPU buffers inside all tensors
created by `Tensor.fromGpuBuffer()`, will not be managed by ORT. User
should manage those GPU buffers themselves.
- When a session is created with `preferredOutputLocation` ==
"gpu-buffer" specified in session options, and the corresponding output
is not pre-allocated, user need to call the output tensor's `dispose()`
or `getData(true)` to manually release the underlying GPU buffers.
- ORT internal errors (including providing a pre-allocated output tensor
with wrong type/dims) will invalidate the whole wasm memory and is not
recoverable. An exception is thrown in this situation.
### Description
* Created `wasm/training_api` source and header files & modified
WebAssembly CMake to include training flags
* The `wasm/training_api` files use an `OrtTrainingManager` handle which
is a struct of an OrtCheckpointState and an OrtTrainingSession, rather
than creating a CheckpointState handle & a separate TrainingSession
handle.
* This is so that the TypeScript side only has to manage one handle that
will be passed between TrainingSession & CheckpointState
representations, rather than the TypeScript side managing separate
CheckpointStateHandle and TrainingSessionHandle.
### Motivation and Context
WASM API needs to be updated with ORT training API function calls so
that ORT training web bindings can be added for on-device training.
---------
Co-authored-by: Baiju Meswani <bmeswani@microsoft.com>
Co-authored-by: carzh <carolinezhu@microsoft.com>
Co-authored-by: Ashwini Khade <askhade@microsoft.com>
### Description
This PR contains changes to support error pop and kernel name.
- Add a function `JsepGetNodeName` to allow reading kernel name from JS
to C++
- When in debug mode ( `env.debug = true;` ) or in profiling mode (
`env.webgpu.profilingMode = 'default';` ), kernel name will be read from
ORT; otherwise use the kernel pointer ( a number ) as kernel name to
save calls from JS to C++.
- When in debug mode, WebGPU validation errors will be recorded and if
any error occurs, `inferenceSession.run()` will fail (Promise get
rejected). Behavior when not in debug mode is not changed. This is
because recording errors are not zero-overhead, and GPU validation
errors should occur consistently in and not in debug mode.
- Add `jsepOnRunStart()` and `jsepOnRunEnd()` hook to:
- allow implementation of the features mentioned above.
- pass session ID to backend.
### Description
This change introduced the following new components into ONNX Runtime
Web:
- JavaScript Execution Provider (JSEP)
- Asynchronized inferencing execution powered by Emscripten's Asyncify
- WebGPU backend implemented in TypeScript
- initial implementation of kernels:
- elementwise operators (22)
- binary operators (5)
- tensor: Shape, Reshape, Transpose, Gemm
- nn: Conv, {Global}Maxpool, {Global}AveragePool
Code need to be polished. still working on it.
## Q&A
What is JSEP?
> JSEP, aka JavaScript Execution Provider, is a new ONNXRuntime
execution provider that specifically works on Web environment
(browsers). JSEP allows JavaScript code to kick in from various places
when ONNX Runtime inferences a model.
Why JSEP?
> JSEP is a hybrid mode EP that contains both C/C++ and
TypeScript/JavaScript implementation. There are 2 strong reasons why we
introduces JSEP:
> 1. the C/C++ part helps JSEP to leverage ONNX Runtime's capabilities
as much as possible including graph transformer, optimizers and also the
capabilities to fallback to CPU EP. TypeScript/JavaScript helps JSEP to
develop and debug much easier in the browser for the kernel
implementation.
> 2. the requirement of asynchronized execution from JavaScript API (eg.
`buffer.mapAsync()`) makes it impossible to run `OrtRun()` in a
synchronized context (see "async problem" section below). This is done
by using Emscripten's Asyncify.
What is WebGPU?
> WebGPU is the new GPU API that available in browser. It's one of the
only 2 APIs that currently available to access the GPU from browser (the
other is WebGL).
> WebGPU is designed with more advanced and stronger features comparing
to WebGL and is potentially solution that offer the best GPU performance
for model inferencing that currently available.
What is the async problem and why we have the problem?
> The "async problem" is a problem that you cannot call an async
function in a synchronous context. Think about the following C++ code:
> ```c
> // C-style declarations (API)
> typedef void (*ON_COMPLETE)(PVOID state, DATA *data);
> void read_data_from_file(FILEHANDLE file, ON_COMPLETE on_complete);
>
> // implementation
> DATA * my_impl_read_data_from_file_sync(FILEHANDLE file) {
> // how to implement?
> }
> ```
> The answer is, it's impossible to implement this function. Usually we
try to find a sync version API, or launch a thread to call the async
function and sync-wait on the main thread. Unfortunately, in browser
environment, neither is possible.
>
> WebGPU does not offer any synchronized API for data downloading (GPU
to CPU). This is the only operation that MUST be async. As `OrtRun()`
will eventually call into DataTransfer for copy data from GPU to CPU,
and `OrtRun()` is a synchronized function, this cannot be done in normal
way.
What is Emscripten? How is the Asyncify feature resolved the problem?
> Emscripten is the C/C++ compiler for WebAssembly. It's what we use to
compile ORT and generates the WebAssembly artifacts which runs on
browsers.
>
> Asyncify is a [compiler
feature](https://emscripten.org/docs/porting/asyncify.html) that allows
calling async functions from a synchronized context. In short, it
generates code to unwind and rewind call stack to emulate async
execution. With this feature, we are able to call the async function
inside `OrtRun()` call.
## Design Overview
**Inter-op**
JSEP is doing pretty much same thing to just another EP. It exposes an
interface for inter-op with JavaScript, which is defined in
onnxruntime/wasm/js_internal_api.js:
```js
// init JSEP
Module["jsepInit"] = function (backend, alloc, free, copy, copyAsync, createKernel, releaseKernel, run) {
Module.jsepBackend = backend;
Module.jsepAlloc = alloc;
Module.jsepFree = free;
Module.jsepCopy = copy;
Module.jsepCopyAsync = copyAsync;
Module.jsepCreateKernel = createKernel;
Module.jsepReleaseKernel = releaseKernel;
Module.jsepRun = run;
};
```
This simple JavaScript snippet defines all language barrier level
functions that requires by JSEP to achieve implementing kernels and data
transfers using JavaScript inside ONNX Runtime:
- `jsepBackend`: assign the singleton object to webassembly module
- `jsepAlloc` and `jsepFree`: implementation of data transfer's Alloc()
and Free()
- `jsepCopy`: synchronized copy ( GPU to GPU, CPU to GPU)
- `jsepCopyAsync`: asynchronized copy ( GPU to CPU)
- `jsepCreateKernel` and `jsepReleaseKernel`: a corresponding object
that maintained in JS to match lifecycle of Kernel in ORT
- `jsepRun`: OpKernel::Compute() should call into this
The abstraction above allows to tie as little as possible connections
and dependencies between C/C++ and TypeScript/JavaScript.
**Resource Management**
Lifecycle of tensor data and kernels are managed by ORT(C/C++) but the
implementation are left to JavaScript. JavaScript code are responsible
to implement the callbacks correctly.
For WebGPU, the GPU data is managed by JavaScript using a singleton map
(tensot_data_id => GPUBuffer). GPU pipeline is managed as singleton.
Shaders are managed using a singletonmap (shader_key => gpu_program),
while shader_key is generated by cache_key (OP specific, including
attributes) and input shapes.
**about data transfer**
`js::DataTransfer::CopyTensor` implemented to call either synchronized
or asynchronized copy callback, depending on the destination is GPU or
not. Emscripten's macro `EM_ASYNC_JS` is used to wrap the async function
to be called in the synchronized context.
**run kernel in JS**
Kernel class constructor calls once `jsepCreateKernel()` with an
optional per-kernel specific serialization to pass attributes into
JavaScript.
`Compute()` are implemented in a way that a metadata serialization is
performed in a base class and JavaScript code can access the data using
the Emscripten specific builtin macro `EM_ASM_*`.
**disabled features**
memory pattern is force disabled, because the WebGPU data is not
presented by a general memory model (a buffer can be represented by
offset + size).
concurrent run support is disabled. WebGPU is stateful and it also has
async function call. To support concurrent run will significantly
increase the complexity and we don't get any real benefit from it.
**prefer channels last**
JSEP prefers channels last and returns `DataLayout::NHWC` in method
`GetPreferredLayout()`. This will let the graph transformers to
preprocess the graph into a channels last form so that a more optimized
WebGPU shader can be used.
**Testing code**
It's impossible to test JSEP directly because JSEP itself does not
contain any kernel implementation. However, it has the kernel
registration which need to work together with the corresponding
JavaScript code. There are unit tests that run onnx models from
JavaScript API.
---------
Co-authored-by: Scott McKay <skottmckay@gmail.com>
### Description
* Support flag 'optimizedModelFilePath' in session options.
In Node.js, the model will be saved into filesystem just like its
behaviour on native platforms.
In browser, the new model is not saved to filesystem. the file path is
ignored. Instead, a new pop-up window will be launched in browser and
user can 'save' the file as onnx model.
* Add corresponding commandline args for the following session option
flags:
- optimizedModelFilePath
- graphOptimizationLevel
**Description**: This PR adds support for "XNNPACK EP" in ORTWeb and
changes the behavior of how ORTWeb deals with "backends", or "EPs" in
API.
**Background**: Term "backend" is introduced in ONNX.js to representing
a TypeScript type which implements a "backend" interface, which is a
similar but different concept to ORT's EP (execution provider). There
was 3 backends in ONNX.js: "cpu", "wasm" and "webgl".
When ORT Web is launched, the concept is derived to help users to
integrate smoothly. Technically, when "wasm" backend is used, users need
to also specify "EP" in the session options. Considering it may get
complicated and confused for users to figure out the difference between
"backend" and "EP", the JS API hide the "backend" concept and made a
mapping between names, backends and EPs:
"webgl" (Name) <==> "onnxjsBackend" (Backend)
"wasm" (Name) <==> "wasmBackend" (Backend) <==> "CPU" (EP)
**Details**:
The following changes are applied in this PR:
1. allow multi-registration for backends using the same name. This is
for use scenarios where both "onnxruntime-node" and "onnxruntime-web"
are consumed in a Node.js App ( so "cpu" will be registered twice in
this scenario. )
2. re-assign priority values to backends. I give 100 as base to "cpu"
for node and react_native, and 10 as base to "cpu" in web.
3. add "cpu", "xnnpack" as new names of backends.
4. update onnxruntime wasm exported functions to support EP
registration.
5. update implementations in ort web to handle execution providers in
session options.
6. add '--use_xnnpack' as default build flag for ort-web
* [js/web] support string tensor for wasm backend
* disable v9/test_cast_STRING_to_FLOAT: test data is wrong
* add non-string check
* Update session-handler.ts
* Update session-handler.ts
* add all session options and run options in C API except AddInitializer and AddFreeDimensionOverride
* remove unnecessary comment
* change extra session and run options to object notation
* resolve comments
* use an optional chaining for options
* resolve comments
* support session options and run options. use onnxruntime c api.
* fix lint errors
* add an error code on throwing an exception
* resolve comments. change remaining C++ APIs to C API
