| --- |
| library_name: kernels |
| license: apache-2.0 |
| tags: |
| - kernel |
| - webgpu |
| - wgsl |
| --- |
| # ai.onnx.GlobalMaxPool |
|
|
| `ai.onnx` · standard ONNX operator · ONNX opset ≥ 1 |
|
|
| ## Description |
|
|
| Applies max pooling across all spatial dimensions of `X`, producing one value per channel. Equivalent to MaxPool with kernel size equal to the full spatial extent of the input; output shape is `(N x C x 1 x ... x 1)`. |
|
|
| See the [ONNX `GlobalMaxPool` spec](https://onnx.ai/onnx/operators/onnx__GlobalMaxPool.html) for the reference semantics. |
|
|
| ## Inputs |
|
|
| | Name | Bind key | Logical dtype | Rank | Shape | Description | Presence | |
| | --- | --- | --- | --- | --- | --- | --- | |
| | `X` | `x` | `T` | — | — | Input tensor of shape `(N x C x D1 x ... x Dn)`, where `N` is the batch size and `C` is the number of channels. | required | |
|
|
| ## Outputs |
|
|
| | Name | Bind key | Logical dtype | Rank | Shape | Description | Presence | |
| | --- | --- | --- | --- | --- | --- | --- | |
| | `Y` | `y` | `T` | same as `X` | — | Output tensor of shape `(N x C x 1 x ... x 1)`; the maximum value over each spatial region per channel. | required | |
|
|
| ## Type constraints |
|
|
| | Variable | Allowed dtypes | |
| | --- | --- | |
| | `T` | `float32`, `float16` | |
|
|
| ## Files |
|
|
| - [`metadata.json`](build/webgpu/metadata.json) — kernel metadata (id, digests, provenance) |
| - [`manifest.json`](build/webgpu/manifest.json) — the op contract (source of truth) |
| - [`test.json`](build/webgpu/test.json) — correctness cases |
| - [`bench.json`](build/webgpu/bench.json) — benchmark + tuning cases |
| - [`pool-global-reduction.wgsl.jinja`](build/webgpu/pool-global-reduction.wgsl.jinja) |
| - [`pool-global-serial.wgsl.jinja`](build/webgpu/pool-global-serial.wgsl.jinja) |
|
|
| ## Use with `@huggingface/kernels` |
|
|
| The loader automatically allocates outputs whose metadata it can derive from the manifest contract and this call. |
|
|
| The explicit `outputs` entries provide shape and logical dtype metadata for the results listed below: |
|
|
| - `y` |
|
|
| Each entry either requests an optional result or supplies metadata that cannot be inferred from the inputs. |
|
|
| The `version: 1` option selects the published kernel contract; it is independent of any operator opset, contrib `since_version`, or model version. |
|
|
| Replace each `*Data` placeholder with a typed array containing the corresponding input data. |
|
|
| ```js |
| import { getKernel } from "@huggingface/kernels"; |
| |
| const kernel = await getKernel("webgpu-kernels/ai.onnx.GlobalMaxPool", { version: 1 }); |
| // Explicit destinations request optional results or supply metadata that cannot be inferred. |
| const { y } = await kernel({ x: { data: xData, shape: [1, 2, 3] } }, { |
| outputs: { y: { shape: [1, 2, 1], dtype: "float32" } }, |
| }); |
| ``` |
|
|
