{
  "domain": "ai.onnx",
  "name": "DynamicQuantizeLinear",
  "sinceVersion": 11,
  "inputs": { "x": { "dtype": "T" } },
  "outputs": {
    "y": { "dtype": "TQ", "rank": "ranks.x", "shape": "shapes.x" },
    "y_scale": { "dtype": "T", "rank": 0, "shape": [] },
    "y_zero_point": { "dtype": "TQ", "rank": 0, "shape": [] }
  },
  "typeConstraints": { "T": ["float32"], "TQ": ["uint8"] },
  "tunables": {
    "WORKGROUP_SIZE": { "default": 256 },
    "ELEMENTS_PER_THREAD": { "default": 4 },
    "GRID_STRIDE_MIN_ELEMENTS": { "default": 262144 },
    "MAX_GRID_PARTIALS": { "default": 256 },
    "SERIAL_MAX_ELEMENTS": { "default": 8192 }
  },
  "derive": {
    "deviceWorkgroupCap": "min(device.limits.maxComputeInvocationsPerWorkgroup, device.limits.maxComputeWorkgroupSizeX)",
    "storageBufferLimit": "min(device.limits.maxStorageBufferBindingSize, device.limits.maxBufferSize)",
    "inputCount": "numel(shapes.x)",
    "elementsPerBlock": "tunables.WORKGROUP_SIZE * tunables.ELEMENTS_PER_THREAD",
    "fullPartials": "ceilDiv(inputCount, elementsPerBlock)",
    "gridPartials": "min(tunables.MAX_GRID_PARTIALS, fullPartials)",
    "baseContract": "ranks.x >= 1 and ranks.y == ranks.x and inputCount == numel(shapes.y) and ranks.y_scale == 0 and ranks.y_zero_point == 0",
    "serialContract": "ranks.x >= 0 and ranks.y == ranks.x and inputCount == numel(shapes.y) and ranks.y_scale == 0 and ranks.y_zero_point == 0",
    "parallelDeviceOk": "tunables.WORKGROUP_SIZE <= deviceWorkgroupCap and 8 * tunables.WORKGROUP_SIZE <= device.limits.maxComputeWorkgroupStorageSize",
    "fullScratchFits": "4 * fullPartials <= storageBufferLimit",
    "gridScratchFits": "4 * gridPartials <= storageBufferLimit",
    "fullDispatchFits": "ceilDiv(fullPartials, min(device.limits.maxComputeWorkgroupsPerDimension, 65535)) <= min(device.limits.maxComputeWorkgroupsPerDimension, 65535)",
    "gridDispatchFits": "gridPartials <= min(device.limits.maxComputeWorkgroupsPerDimension, 65535)",
    "parallelFullFits": "parallelDeviceOk and fullScratchFits and fullDispatchFits",
    "parallelGridFits": "parallelDeviceOk and gridScratchFits and gridDispatchFits and fullDispatchFits",
    "serialFallbackNeeded": "inputCount <= tunables.SERIAL_MAX_ELEMENTS or not parallelFullFits"
  },
  "bindings": {
    "y": { "buffer": "storage", "elementType": "u32" },
    "y_scale": { "buffer": "storage", "elementType": "f32", "length": 1 },
    "y_zero_point": { "buffer": "storage", "elementType": "u32", "length": 1 },
    "params": { "buffer": "uniform", "struct": [{ "name": "count", "type": "u32", "value": "numel(shapes.x)" }] },
    "x_2": { "name": "x", "buffer": "read-only-storage", "elementType": "$inputElement" },
    "partial_min": { "buffer": "storage", "elementType": "f32" },
    "partial_max": { "buffer": "storage", "elementType": "f32" },
    "partial_min_2": { "name": "partial_min", "buffer": "read-only-storage", "elementType": "f32" },
    "partial_max_2": { "name": "partial_max", "buffer": "read-only-storage", "elementType": "f32" },
    "y_scale_2": { "name": "y_scale", "buffer": "read-only-storage", "elementType": "f32", "length": 1 },
    "y_zero_point_2": { "name": "y_zero_point", "buffer": "read-only-storage", "elementType": "u32", "length": 1 }
  },
  "variants": [
    {
      "id": "single_invocation",
      "when": ["serialContract", "serialFallbackNeeded"],
      "passes": [
        {
          "id": "main",
          "name": "DynamicQuantizeLinear",
          "shader": "dynamic-quantize-linear.wgsl.jinja",
          "derive": { "fromPartials": false },
          "bindings": [{ "arg": "x", "elementType": "f32" }, "y", "y_scale", "y_zero_point", "params"],
          "dispatch": { "x": 1 }
        }
      ]
    },
    {
      "id": "parallel_subgroup_reduce_vec4",
      "priority": 11,
      "when": ["baseContract", "inputCount > 0", "inputCount % 4 == 0", "parallelFullFits"],
      "derive": {
        "workgroupSize": "tunables.WORKGROUP_SIZE",
        "elemsPerThread": "tunables.ELEMENTS_PER_THREAD",
        "vec4": true,
        "inputElement": "\"vec4<f32>\"",
        "useSubgroups": "device.features.has(\"subgroups\")"
      },
      "intermediates": [
        { "id": "partial_min", "dtype": "float32", "shape": "[fullPartials]" },
        { "id": "partial_max", "dtype": "float32", "shape": "[fullPartials]" }
      ],
      "passes": [
        {
          "id": "reduce",
          "name": "DynamicQuantizeLinear.ReduceMinMax",
          "shader": "dynamic-quantize-linear-reduce.wgsl.jinja",
          "subgroupCollectivesWidth": "portable",
          "bindings": ["x_2", "partial_min", "partial_max", "params"],
          "dispatch": { "x": "min(fullPartials, 65535)", "y": "ceilDiv(fullPartials, 65535)", "z": 1 }
        },
        {
          "id": "finalize",
          "name": "DynamicQuantizeLinear.Finalize",
          "shader": "dynamic-quantize-linear.wgsl.jinja",
          "derive": { "fromPartials": true },
          "bindings": [
            "partial_min_2",
            "partial_max_2",
            "y_scale",
            "y_zero_point",
            { "name": "params", "struct": [{ "name": "numPartials", "type": "u32", "value": "fullPartials" }] }
          ],
          "dispatch": { "x": 1 }
        },
        {
          "id": "quantize",
          "name": "DynamicQuantizeLinear.Quantize",
          "shader": "dynamic-quantize-linear-quantize.wgsl.jinja",
          "bindings": ["x_2", "y_scale_2", "y_zero_point_2", "y", "params"],
          "dispatch": {
            "x": "min(ceilDiv((ceilDiv(inputCount, tunables.ELEMENTS_PER_THREAD)), (tunables.WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((ceilDiv(inputCount, tunables.ELEMENTS_PER_THREAD)), (tunables.WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "parallel_subgroup_reduce",
      "priority": 10,
      "when": ["baseContract", "inputCount > 0", "true", "parallelFullFits"],
      "derive": {
        "workgroupSize": "tunables.WORKGROUP_SIZE",
        "elemsPerThread": "tunables.ELEMENTS_PER_THREAD",
        "vec4": false,
        "inputElement": "\"f32\"",
        "useSubgroups": "device.features.has(\"subgroups\")"
      },
      "intermediates": [
        { "id": "partial_min", "dtype": "float32", "shape": "[fullPartials]" },
        { "id": "partial_max", "dtype": "float32", "shape": "[fullPartials]" }
      ],
      "passes": [
        {
          "id": "reduce",
          "name": "DynamicQuantizeLinear.ReduceMinMax",
          "shader": "dynamic-quantize-linear-reduce.wgsl.jinja",
          "subgroupCollectivesWidth": "portable",
          "bindings": ["x_2", "partial_min", "partial_max", "params"],
          "dispatch": { "x": "min(fullPartials, 65535)", "y": "ceilDiv(fullPartials, 65535)", "z": 1 }
        },
        {
          "id": "finalize",
          "name": "DynamicQuantizeLinear.Finalize",
          "shader": "dynamic-quantize-linear.wgsl.jinja",
          "derive": { "fromPartials": true },
          "bindings": [
            "partial_min_2",
            "partial_max_2",
            "y_scale",
            "y_zero_point",
            { "name": "params", "struct": [{ "name": "numPartials", "type": "u32", "value": "fullPartials" }] }
          ],
          "dispatch": { "x": 1 }
        },
        {
          "id": "quantize",
          "name": "DynamicQuantizeLinear.Quantize",
          "shader": "dynamic-quantize-linear-quantize.wgsl.jinja",
          "bindings": ["x_2", "y_scale_2", "y_zero_point_2", "y", "params"],
          "dispatch": {
            "x": "min(ceilDiv((ceilDiv(inputCount, tunables.ELEMENTS_PER_THREAD)), (tunables.WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((ceilDiv(inputCount, tunables.ELEMENTS_PER_THREAD)), (tunables.WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "grid_stride_reduce_vec4",
      "priority": 12,
      "when": ["baseContract", "inputCount > 0", "inputCount % 4 == 0", "inputCount >= tunables.GRID_STRIDE_MIN_ELEMENTS", "parallelGridFits"],
      "derive": {
        "workgroupSize": "tunables.WORKGROUP_SIZE",
        "elemsPerThread": "tunables.ELEMENTS_PER_THREAD",
        "vec4": true,
        "inputElement": "\"vec4<f32>\"",
        "useSubgroups": "device.features.has(\"subgroups\")"
      },
      "intermediates": [
        { "id": "partial_min", "dtype": "float32", "shape": "[gridPartials]" },
        { "id": "partial_max", "dtype": "float32", "shape": "[gridPartials]" }
      ],
      "passes": [
        {
          "id": "reduce",
          "name": "DynamicQuantizeLinear.ReduceMinMax",
          "shader": "dynamic-quantize-linear-reduce.wgsl.jinja",
          "subgroupCollectivesWidth": "portable",
          "derive": { "gridStride": true },
          "bindings": ["x_2", "partial_min", "partial_max", "params"],
          "dispatch": { "x": "gridPartials" }
        },
        {
          "id": "finalize",
          "name": "DynamicQuantizeLinear.Finalize",
          "shader": "dynamic-quantize-linear.wgsl.jinja",
          "derive": { "fromPartials": true },
          "bindings": [
            "partial_min_2",
            "partial_max_2",
            "y_scale",
            "y_zero_point",
            { "name": "params", "struct": [{ "name": "numPartials", "type": "u32", "value": "gridPartials" }] }
          ],
          "dispatch": { "x": 1 }
        },
        {
          "id": "quantize",
          "name": "DynamicQuantizeLinear.Quantize",
          "shader": "dynamic-quantize-linear-quantize.wgsl.jinja",
          "bindings": ["x_2", "y_scale_2", "y_zero_point_2", "y", "params"],
          "dispatch": {
            "x": "min(ceilDiv((ceilDiv(inputCount, tunables.ELEMENTS_PER_THREAD)), (tunables.WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((ceilDiv(inputCount, tunables.ELEMENTS_PER_THREAD)), (tunables.WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "grid_stride_reduce",
      "priority": 12,
      "when": ["baseContract", "inputCount > 0", "inputCount % 4 != 0", "inputCount >= tunables.GRID_STRIDE_MIN_ELEMENTS", "parallelGridFits"],
      "derive": {
        "workgroupSize": "tunables.WORKGROUP_SIZE",
        "elemsPerThread": "tunables.ELEMENTS_PER_THREAD",
        "vec4": false,
        "inputElement": "\"f32\"",
        "useSubgroups": "device.features.has(\"subgroups\")"
      },
      "intermediates": [
        { "id": "partial_min", "dtype": "float32", "shape": "[gridPartials]" },
        { "id": "partial_max", "dtype": "float32", "shape": "[gridPartials]" }
      ],
      "passes": [
        {
          "id": "reduce",
          "name": "DynamicQuantizeLinear.ReduceMinMax",
          "shader": "dynamic-quantize-linear-reduce.wgsl.jinja",
          "subgroupCollectivesWidth": "portable",
          "derive": { "gridStride": true },
          "bindings": ["x_2", "partial_min", "partial_max", "params"],
          "dispatch": { "x": "gridPartials" }
        },
        {
          "id": "finalize",
          "name": "DynamicQuantizeLinear.Finalize",
          "shader": "dynamic-quantize-linear.wgsl.jinja",
          "derive": { "fromPartials": true },
          "bindings": [
            "partial_min_2",
            "partial_max_2",
            "y_scale",
            "y_zero_point",
            { "name": "params", "struct": [{ "name": "numPartials", "type": "u32", "value": "gridPartials" }] }
          ],
          "dispatch": { "x": 1 }
        },
        {
          "id": "quantize",
          "name": "DynamicQuantizeLinear.Quantize",
          "shader": "dynamic-quantize-linear-quantize.wgsl.jinja",
          "bindings": ["x_2", "y_scale_2", "y_zero_point_2", "y", "params"],
          "dispatch": {
            "x": "min(ceilDiv((ceilDiv(inputCount, tunables.ELEMENTS_PER_THREAD)), (tunables.WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((ceilDiv(inputCount, tunables.ELEMENTS_PER_THREAD)), (tunables.WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    }
  ]
}