mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-08 17:17:15 +00:00
d9b9c5a537
### Description support using uniform buffer. This PR allows to use uniform buffer in shader program, so that some runtime information (eg. input/output shape) is no longer need to be hardcoded into shader code. There are 2 commits in this PR: - [667f31c](667f31c83d): framework changes to support uniform buffer, as well as updates in program manager, gpu data manager and indices helper. - [09e1d2a](09e1d2ad1d): an example change for operator `Transpose` to use input's rank-only instead of dims as shader key. With this change, model mobilenetv2-12 shader compile times dropped from 71 to 52.
27 lines
1 KiB
TypeScript
27 lines
1 KiB
TypeScript
// Copyright (c) Microsoft Corporation. All rights reserved.
|
|
// Licensed under the MIT License.
|
|
|
|
import {TensorView} from '../../tensor-view';
|
|
import {BroadcastUtil} from '../../util';
|
|
import {ComputeContext} from '../types';
|
|
|
|
import {createMatmulProgramInfo} from './3rd-party/matmul_packed_webgpu';
|
|
|
|
const validateInputs = (inputs: readonly TensorView[]): void => {
|
|
if (!inputs || inputs.length !== 2) {
|
|
throw new Error('MatMul requires 2 inputs.');
|
|
}
|
|
|
|
if (inputs[0].dims[inputs[0].dims.length - 1] !== inputs[1].dims[inputs[1].dims.length - 2]) {
|
|
throw new Error('shared dimension does not match.');
|
|
}
|
|
};
|
|
|
|
export const matMul = (context: ComputeContext): void => {
|
|
validateInputs(context.inputs);
|
|
const outputShape = BroadcastUtil.calcShape(context.inputs[0].dims, context.inputs[1].dims, true);
|
|
if (!outputShape) {
|
|
throw new Error('Can\'t use matmul on the given tensors');
|
|
}
|
|
context.compute(createMatmulProgramInfo(context.inputs, {activation: '', activationCacheKey: ''}, outputShape));
|
|
};
|