{
  "domain": "ai.onnx",
  "name": "BatchNormalization",
  "sinceVersion": 15,
  "inputs": {
    "x": { "onnx": "X", "dtype": "T" },
    "scale": { "dtype": "T", "rank": 1 },
    "b": { "onnx": "B", "dtype": "T", "rank": 1 },
    "inputMean": { "onnx": "input_mean", "dtype": "T", "rank": 1 },
    "inputVar": { "onnx": "input_var", "dtype": "T", "rank": 1 }
  },
  "outputs": { "y": { "onnx": "Y", "dtype": "T", "rank": "ranks.x", "shape": "shapes.x" } },
  "attributes": { "epsilon": { "default": 0.00001 }, "momentum": { "default": 0.9 }, "training_mode": { "default": 0 } },
  "attributeConstraints": { "momentum": { "values": [0.9] }, "training_mode": { "values": [0] } },
  "typeConstraints": { "T": ["float32", "float16"] },
  "tunables": { "WORKGROUP_SIZE": { "default": 256 } },
  "derive": {
    "normalizationParamsOk": "ranks.scale == 1 and ranks.b == 1 and ranks.inputMean == 1 and ranks.inputVar == 1 and dim(shapes.scale, 0) == dim(shapes.x, 1) and dim(shapes.b, 0) == dim(shapes.x, 1) and dim(shapes.inputMean, 0) == dim(shapes.x, 1) and dim(shapes.inputVar, 0) == dim(shapes.x, 1)",
    "inferenceContractOk": "f16Ok(dtypes.T) and ranks.x >= 2 and ranks.y == ranks.x and sameShape(shapes.y, shapes.x) and normalizationParamsOk"
  },
  "when": ["inferenceContractOk"],
  "bindings": {
    "scale": { "elementType": "$T" },
    "bias": { "arg": "b", "elementType": "$T" },
    "input_mean": { "arg": "inputMean", "elementType": "$T" },
    "input_var": { "arg": "inputVar", "elementType": "$T" },
    "x_main": { "name": "x", "elementType": "vec4<f32>" },
    "scale_main": { "name": "scale", "elementType": "vec4<f32>" },
    "bias_b": { "arg": "b", "name": "bias", "elementType": "vec4<f32>" },
    "input_mean_main": { "arg": "inputMean", "name": "input_mean", "elementType": "vec4<f32>" },
    "input_var_main": { "arg": "inputVar", "name": "input_var", "elementType": "vec4<f32>" },
    "y_main": { "name": "y", "elementType": "vec4<f32>" },
    "params_main": {
      "name": "params",
      "struct": [
        { "name": "count4", "type": "u32", "value": "numel(shapes.y) / 4" },
        { "name": "channels4", "type": "u32", "value": "dim(shapes.x, 1) / 4" },
        { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
      ]
    },
    "params__uniform": {
      "name": "params",
      "struct": [
        { "name": "count4", "type": "u32", "value": "numel(shapes.y) / 4" },
        { "name": "spatial", "type": "u32", "value": "inner(shapes.x, 1)" },
        { "name": "channels", "type": "u32", "value": "dim(shapes.x, 1)" },
        { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
      ]
    },
    "params_nchw_inference_vec4": {
      "name": "params",
      "struct": [
        { "name": "count4", "type": "u32", "value": "numel(shapes.y) / 4" },
        { "name": "spatial4", "type": "u32", "value": "inner(shapes.x, 1) / 4" },
        { "name": "channels", "type": "u32", "value": "dim(shapes.x, 1)" },
        { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
      ]
    }
  },
  "variants": [
    {
      "id": "inference_scalar",
      "derive": { "scalar": "dtypes.T", "usesF16": "dtypes.T == \"f16\"" },
      "passes": [
        {
          "id": "main",
          "name": "BatchNormalization.InferenceScalar",
          "shader": "batch-normalization-nchw.wgsl.jinja",
          "bindings": [
            "x",
            "scale",
            "bias",
            "input_mean",
            "input_var",
            "y",
            {
              "name": "params",
              "struct": [
                { "name": "channels", "type": "u32", "value": "dim(shapes.x, 1)" },
                { "name": "height", "type": "u32", "value": "1 if ranks.x == 2 else dim(shapes.x, 2)" },
                { "name": "width", "type": "u32", "value": "1 if ranks.x == 2 else inner(shapes.x, 2)" },
                { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" },
                { "name": "count", "type": "u32", "value": "numel(shapes.y)" }
              ]
            }
          ],
          "dispatch": {
            "x": "min(ceilDiv((numel(shapes.y)), (tunables.WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((numel(shapes.y)), (tunables.WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "nc_inference_vec4",
      "priority": 110,
      "when": ["dtypes.T == \"f32\"", "ranks.x == 2", "dim(shapes.x, 1) % 4 == 0"],
      "passes": [
        {
          "id": "main",
          "name": "BatchNormalization.NcInferenceVec4",
          "shader": "batch-normalization-nc-vec4.wgsl.jinja",
          "bindings": ["x_main", "scale_main", "bias_b", "input_mean_main", "input_var_main", "y_main", "params_main"],
          "dispatch": {
            "x": "min(ceilDiv((numel(shapes.y) / 4), (tunables.WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((numel(shapes.y) / 4), (tunables.WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "nchw_inference_flat_vec4",
      "priority": 90,
      "when": ["dtypes.T == \"f32\"", "ranks.x >= 3", "inner(shapes.x, 1) % 4 != 0 and numel(shapes.x) % 4 == 0"],
      "passes": [
        {
          "id": "main",
          "name": "BatchNormalization.InferenceFlatVec4",
          "shader": "batch-normalization-nchw-flat-vec4.wgsl.jinja",
          "bindings": ["x_main", "scale", "bias", "input_mean", "input_var", "y_main", "params__uniform"],
          "dispatch": {
            "x": "min(ceilDiv((numel(shapes.y) / 4), (tunables.WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((numel(shapes.y) / 4), (tunables.WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "nchw_inference_vec4",
      "priority": 100,
      "when": ["dtypes.T == \"f32\"", "ranks.x >= 3", "inner(shapes.x, 1) % 4 == 0"],
      "passes": [
        {
          "id": "main",
          "name": "BatchNormalization.InferenceVec4",
          "shader": "batch-normalization-nchw-vec4.wgsl.jinja",
          "bindings": ["x_main", "scale", "bias", "input_mean", "input_var", "y_main", "params_nchw_inference_vec4"],
          "dispatch": {
            "x": "min(ceilDiv((numel(shapes.y) / 4), (tunables.WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((numel(shapes.y) / 4), (tunables.WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    }
  ]
}