| --- |
| library_name: kernels |
| license: apache-2.0 |
| tags: |
| - kernel |
| - webgpu |
| - wgsl |
| --- |
| # ai.onnx.ReduceSumSquare |
|
|
| `ai.onnx` · standard ONNX operator · ONNX opset ≥ 18 |
|
|
| ## Description |
|
|
| Computes the sum of squared elements of the input tensor along the specified axes. The output rank matches the input if `keepdims` is 1; otherwise the reduced dimensions are pruned. Reduction over an empty set of values yields 0. |
|
|
| See the [ONNX `ReduceSumSquare` spec](https://onnx.ai/onnx/operators/onnx__ReduceSumSquare.html) for the reference semantics. |
|
|
| ## Inputs |
|
|
| | Name | Upstream name | Logical dtype | Rank | Shape | Description | Presence | |
| | --- | --- | --- | --- | --- | --- | --- | |
| | `x` | `data` | `T` | — | — | The input tensor to reduce. | required | |
|
|
| ## Outputs |
|
|
| | Name | Upstream name | Logical dtype | Rank | Shape | Description | Presence | |
| | --- | --- | --- | --- | --- | --- | --- | |
| | `y` | `reduced` | `T` | derived | — | The reduced output tensor containing the sum of squares. | required | |
|
|
| ## Attributes |
|
|
| Default values (overridable per request): |
|
|
| | Attribute | Default | Description | |
| | --- | --- | --- | |
| | `axes` | `[]` | Values of the optional ONNX `axes` tensor input, supplied through this request attribute; an empty list follows `noop_with_empty_axes`. | |
| | `keepdims` | `1` | If 1 (default in spec), retain the reduced dimensions with size 1; if 0, remove them. | |
| | `noop_with_empty_axes` | `0` | If 1 and axes is empty, acts as a no-op that squares each element without reducing; if 0 (default), reduces over all axes when axes is empty. | |
|
|
| ## Type constraints |
|
|
| | Variable | Allowed dtypes | |
| | --- | --- | |
| | `T` | `float32`, `float16`, `int32` | |
|
|
| ## Implementation variants |
|
|
| One implementation is selected per call from the device capabilities, the request shapes and the dtypes; these notes say what each one covers. |
|
|
| - `axis0_splitk_i32` — Partitions a long rank-two axis-zero integer reduction across workgroups and combines exact int32 partials. It applies when the reduced row dimension is too large for one pass to expose enough parallelism. |
| - `subgroup_last_axis_vec4` — Reduces each contiguous last-axis row with subgroup collectives and vec4-packed reads. |
| - `subgroup_last_axis` — Reduces each contiguous last-axis row with subgroup collectives and scalar reads for an unaligned row width. |
| - `strided_axis_serial` — Flatten a single non-last reduction axis into outer/axis/inner geometry. Compile its strides and loop bound, keep one output per lane and float32 accumulation, and cap the workgroup by the device limits. |
|
|
| ## Device requirements |
|
|
| Some implementation variants require `subgroups`. These are route-specific capabilities, not package-wide requirements; availability also depends on the request shape and dtype. |
|
|
| ## Files |
|
|
| - [`metadata.json`](build/webgpu/metadata.json) — kernel metadata (id, digests, per-variant templates, 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 cases |
| - [`reduce-axis-split-reduce.wgsl.jinja`](build/webgpu/reduce-axis-split-reduce.wgsl.jinja) |
| - [`reduce-axis0-splitk-combine.wgsl.jinja`](build/webgpu/reduce-axis0-splitk-combine.wgsl.jinja) |
| - [`reduce-axis0-splitk-reduce.wgsl.jinja`](build/webgpu/reduce-axis0-splitk-reduce.wgsl.jinja) |
| - [`reduce-axis0-tilecols.wgsl.jinja`](build/webgpu/reduce-axis0-tilecols.wgsl.jinja) |
| - [`reduce-flat-partial.wgsl.jinja`](build/webgpu/reduce-flat-partial.wgsl.jinja) |
| - [`reduce-multi-axis-coop.wgsl.jinja`](build/webgpu/reduce-multi-axis-coop.wgsl.jinja) |
| - [`reduce-noop-empty-axes.wgsl.jinja`](build/webgpu/reduce-noop-empty-axes.wgsl.jinja) |
| - [`reduce-row-subgroup-rows.wgsl.jinja`](build/webgpu/reduce-row-subgroup-rows.wgsl.jinja) |
| - [`reduce-row-subgroup.wgsl.jinja`](build/webgpu/reduce-row-subgroup.wgsl.jinja) |
| - [`reduce-row-tree.wgsl.jinja`](build/webgpu/reduce-row-tree.wgsl.jinja) |
| - [`reduce-serial-axis.wgsl.jinja`](build/webgpu/reduce-serial-axis.wgsl.jinja) |
| - [`reduce-strided-axis.wgsl.jinja`](build/webgpu/reduce-strided-axis.wgsl.jinja) |
|
|
| ## Use with `@huggingface/kernels` |
|
|
| ```sh |
| npm install --save-exact @huggingface/kernels@0.0.1-preview.3 |
| ``` |
|
|
| Outputs with inferable metadata are allocated automatically. Explicit `outputs` entries request optional results or provide metadata that cannot be inferred from the supplied inputs and attributes. |
|
|
| This example supplies explicit metadata for: |
|
|
| - `y` |
|
|
| The `version: 1` option selects the published kernel contract; it is independent of any operator opset, contrib `since_version`, or model version. |
| It follows the `v1` branch as fixes land. To pin exact artifact bytes, pass a 40-character commit `revision` instead of `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.ReduceSumSquare", { version: 1 }); |
| // Explicit destinations request optional results or supply metadata that cannot be inferred. |
| const { y } = await kernel({ x: { data: xData, shape: [3, 2, 2] } }, { |
| outputs: { y: { shape: [1, 1, 1], dtype: "float32" } }, |
| }); |
| ``` |
|
|
