**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
* consume onnx test data from github
* ensure tests
* update script and allow opset specification
* fix python format
* fix python format
* consume new filter format
* fix linting error
* es2017 by default for ort-common
* add visualizer and define plugin
* es2017 for ort-web. also add build target for es5
* add multiple reduced size build for ort-web
* resolve comments, add e2e tests and add docs
* add p50 in test
* support opset-13 of softmax
* update a operators.md
* resolve comments
* fix lint and format
Co-authored-by: Yulong Wang <yulongw@microsoft.com>
* Support opset-13 for squeeze, unsqueeze, maxpool, pad, cast, clip
* merge master and update a operators.md
* resolve comment. revise pool and cast kernel implementation.
* skip fusion when clip min and max is not in initializer
* [js/web] Add wasm SIMD backend to onnxruntime-web
* Import SIMD wasm artifacts enabled by PR #7839
* Detect SIMD capability of web engine
* Use SIMD wasm backend in both single-thread and multi-thread cases
* update optimized SIMD loading from ort web
* code lint and format
* fix WasmFileName in CI
* replace deprecated wasm SIMD functions
* fix unittest for simd
* optimize CI pipeline to merge build matrix
* make clean build for each config
* fix simd wasm to enable it.
* update script/pull-prebuilt-wasm-artifacts.ts
Co-authored-by: Yulong Wang <yulongw@microsoft.com>
Co-authored-by: Lei Zhang <zhang.huanning@hotmail.com>
* [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
* fixed bugs in packed mode and enable pack mode tests in ci
* removed unnecessary space
* pr comments
* pr comments
* disable an average pool test
* try disabling another avg pool
* disable more avg pool tests
* disable maxpool tests
* migrated changes to support running super resolution model using ortweb
* reverted benchmarking tool related changes which will be in a separate pr
* added kernel tests to op and node tests
* minor change to the order of variables
* added one more unit test for packed matmul