{ "fixtureArrays": { "f16_scalar_cast_x": [-1.1103515625, 2.982421875, 1.248046875, -1.8544921875], "f16_scalar_cast_scale": [2.015625], "f16_scalar_cast_y": [-1.1513671875, 3.091796875, 1.2939453125, -1.921875] }, "cases": [ { "name": "legacy_last_axis_vec4_no_stats_2x8", "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 8], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.07 } }, "scale": { "dtype": "float32", "shape": [8], "data": { "kind": "fillFloat32", "sinStep": 0.23, "cosStep": 0.19, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [2, 8], "tolerance": 0.000002 } } }, { "name": "legacy_last_axis_scalar_no_stats_2x5", "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 5], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.07 } }, "scale": { "dtype": "float32", "shape": [5], "data": { "kind": "fillFloat32", "sinStep": 0.23, "cosStep": 0.19, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [2, 5], "tolerance": 0.000002 } } }, { "name": "legacy_last_axis_vec4_stats_2x8", "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 8], "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.21 } }, "scale": { "dtype": "float32", "shape": [8], "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.11, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [2, 8], "tolerance": 0.000002 }, "invStdVar": { "dtype": "float32", "shape": [2, 1], "tolerance": 0.00001 } } }, { "name": "legacy_last_axis_scalar_stats_2x33", "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 33], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.27 } }, "scale": { "dtype": "float32", "shape": [33], "data": { "kind": "fillFloat32", "sinStep": 0.21, "cosStep": 0.13, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [2, 33], "tolerance": 0.000002 }, "invStdVar": { "dtype": "float32", "shape": [2, 1], "tolerance": 0.00001 } } }, { "name": "legacy_scalar_scale_generic_stats_2x8", "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 8], "data": { "kind": "fillFloat32", "sinStep": 0.31, "cosStep": 0.09 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "values", "values": [0.75] } } }, "outputs": { "y": { "dtype": "float32", "shape": [2, 8], "tolerance": 0.000002 }, "invStdVar": { "dtype": "float32", "shape": [2, 1], "tolerance": 0.00001 } } }, { "name": "legacy_suffix_axis1_stats_2x3x4", "attrs": { "epsilon": 0.00001, "axis": 1 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 3, 4], "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.23 } }, "scale": { "dtype": "float32", "shape": [3, 4], "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.29, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [2, 3, 4], "tolerance": 0.000002 }, "invStdVar": { "dtype": "float32", "shape": [2, 1, 1], "tolerance": 0.00001 } } }, { "name": "legacy_mixed_f16_x_f32_scale_stats_2x4", "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "dtype": "float16", "shape": [2, 4], "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.21 } }, "scale": { "dtype": "float32", "shape": [4], "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.11, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [2, 4], "tolerance": 0.002 }, "invStdVar": { "dtype": "float32", "shape": [2, 1], "tolerance": 0.002 } } }, { "name": "legacy_mixed_f32_x_f16_scale_2x4", "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 4], "data": { "kind": "fillFloat32", "sinStep": 0.15, "cosStep": 0.25 } }, "scale": { "dtype": "float16", "shape": [4], "data": { "kind": "fillFloat32", "sinStep": 0.27, "cosStep": 0.09, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float16", "shape": [2, 4], "tolerance": 0.003 } } }, { "name": "legacy_f16_vec4_stats_4x32", "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "dtype": "float16", "shape": [4, 32], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.27 } }, "scale": { "dtype": "float16", "shape": [32], "data": { "kind": "fillFloat32", "sinStep": 0.21, "cosStep": 0.13, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float16", "shape": [4, 32], "tolerance": 0.005 }, "invStdVar": { "dtype": "float32", "shape": [4, 1], "tolerance": 0.002 } } }, { "name": "legacy_suffix_splitk_stats_2x64x512", "attrs": { "epsilon": 0.00001, "axis": 1 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 64, 512], "data": { "kind": "fillFloat32", "sinStep": 0.013, "cosStep": 0.017 } }, "scale": { "dtype": "float32", "shape": [64, 512], "data": { "kind": "fillFloat32", "sinStep": 0.011, "cosStep": 0.007, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [2, 64, 512], "tolerance": 0.00001 }, "invStdVar": { "dtype": "float32", "shape": [2, 1, 1], "tolerance": 0.00001 } } }, { "name": "legacy_suffix_splitk_no_stats_1x32x512", "attrs": { "epsilon": 0.00001, "axis": 1 }, "inputs": { "x": { "dtype": "float32", "shape": [1, 32, 512], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023 } }, "scale": { "dtype": "float32", "shape": [32, 512], "data": { "kind": "fillFloat32", "sinStep": 0.009, "cosStep": 0.019, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [1, 32, 512], "tolerance": 0.00001 } } }, { "name": "legacy_suffix_splitk_scalar_scale_no_stats_1x32x512", "attrs": { "epsilon": 0.00001, "axis": 1 }, "inputs": { "x": { "dtype": "float32", "shape": [1, 32, 512], "data": { "kind": "fillFloat32", "sinStep": 0.019, "cosStep": 0.013 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "values", "values": [0.75] } } }, "outputs": { "y": { "dtype": "float32", "shape": [1, 32, 512], "tolerance": 0.00001 } } }, { "name": "legacy_f16_scale_before_output_cast_vec4_exact", "provenance": { "source": "onnxruntime/core/providers/cpu/nn/layer_norm_impl.cc", "test": "SimplifiedLayerNormalization legacy f16 cast boundary", "notes": "The legacy op applies scale before its single output cast. The first value differs by one f16 ULP from standardized RMSNormalization, which casts the normalized stage before scale." }, "requires": { "features": ["shader-f16"] }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "dtype": "float16", "shape": [1, 4], "data": { "kind": "values", "values": [-1.4765625, -1.861328125, 1.4697265625, 1.0703125] } }, "scale": { "dtype": "float16", "shape": [4], "data": { "kind": "values", "values": [0.316162109375, -2.791015625, -0.0877685546875, 2.0859375] } } }, "outputs": { "y": { "dtype": "float16", "shape": [1, 4], "tolerance": 0, "relTolerance": 0, "data": { "kind": "values", "values": [-0.31201171875, 3.47265625, -0.08624267578125, 1.4921875] } } } }, { "name": "legacy_f16_scale_before_output_cast_generic_exact", "provenance": { "source": "onnxruntime/core/providers/cpu/nn/layer_norm_impl.cc", "test": "SimplifiedLayerNormalization scalar-scale cast boundary", "notes": "A scalar scale selects the generic path and requires multiplication before the final float16 cast, independently of optimized row handling." }, "requires": { "features": ["shader-f16"] }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "dtype": "float16", "shape": [1, 4], "data": { "kind": "values", "values": { "$ref": "#/fixtureArrays/f16_scalar_cast_x" } } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "values", "values": { "$ref": "#/fixtureArrays/f16_scalar_cast_scale" } } } }, "outputs": { "y": { "dtype": "float16", "shape": [1, 4], "tolerance": 0, "relTolerance": 0, "data": { "kind": "values", "values": { "$ref": "#/fixtureArrays/f16_scalar_cast_y" } } } } }, { "name": "legacy_f16_scale_before_output_cast_splitk_exact", "provenance": { "source": "onnxruntime/core/providers/cpu/nn/layer_norm_impl.cc", "test": "SimplifiedLayerNormalization split-K f16 cast boundary", "notes": "Forces the split-K shared kernel on the exact scalar-scale boundary and pins the legacy scale-before-output-cast ordering." }, "requires": { "features": ["shader-f16"] }, "tunables": { "SPLIT_MIN_HIDDEN": 1, "SPLIT_TARGET_ELEMENTS": 1 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "dtype": "float16", "shape": [1, 4], "data": { "kind": "values", "values": { "$ref": "#/fixtureArrays/f16_scalar_cast_x" } } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "values", "values": { "$ref": "#/fixtureArrays/f16_scalar_cast_scale" } } } }, "outputs": { "y": { "dtype": "float16", "shape": [1, 4], "tolerance": 0, "relTolerance": 0, "data": { "kind": "values", "values": { "$ref": "#/fixtureArrays/f16_scalar_cast_y" } } } } }, { "name": "legacy_rank1_default_attrs_8", "attrs": {}, "inputs": { "x": { "dtype": "float32", "shape": [8], "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.03 } }, "scale": { "dtype": "float32", "shape": [8], "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.41, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [8], "tolerance": 0.000002 } } }, { "name": "legacy_explicit_stash_type_float32", "attrs": { "epsilon": 0.00001, "axis": -1, "stash_type": 1 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 8], "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.13 } }, "scale": { "dtype": "float32", "shape": [8], "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.37, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [2, 8], "tolerance": 0.000002 } } }, { "name": "legacy_keep_dims_compatibility_attribute", "provenance": { "source": "onnxruntime/test/contrib_ops/layer_norm_test.cc", "test": "SimplifiedLayerNormalization keep_dims=1", "notes": "ONNX Runtime's legacy schema permits unchecked attributes and its own compatibility test emits keep_dims=1. The kernel ignores the attribute and always retains reduced dimensions for optional statistics." }, "attrs": { "epsilon": 0.00001, "axis": 1, "keep_dims": 1 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 3, 4], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "scale": { "dtype": "float32", "shape": [3, 4], "data": { "kind": "fillFloat32", "sinStep": 0.23, "cosStep": 0.09, "scale": 0.5 } } }, "outputs": { "y": { "dtype": "float32", "shape": [2, 3, 4], "tolerance": 0.000002 }, "invStdVar": { "dtype": "float32", "shape": [2, 1, 1], "tolerance": 0.00001 } } }, { "name": "legacy_zero_outer_rows_stats", "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "dtype": "float32", "shape": [0, 4], "data": { "kind": "values", "values": [] } }, "scale": { "dtype": "float32", "shape": [4], "data": { "kind": "constant", "value": 1.0 } } }, "outputs": { "y": { "dtype": "float32", "shape": [0, 4], "tolerance": 0.000002 }, "invStdVar": { "dtype": "float32", "shape": [0, 1], "tolerance": 0.00001 } } }, { "name": "split_f32-1x16384", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 16384], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 16384], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x16385", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 16385], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 16385], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x32769", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 32769], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 32769], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x65536", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 65536], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 65536], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x131072", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 131072], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 131072], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x262144", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 262144], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 262144], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x524288", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 524288], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 524288], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x1048576", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 1048576], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 1048576], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x2097152", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 2097152], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 2097152], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-2x131073", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [2, 131073], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [2, 131073], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [2, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-3x524289", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [3, 524289], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [3, 524289], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [3, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-4x1048576", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [4, 1048576], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [4, 1048576], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [4, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-8x16384", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [8, 16384], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [8, 16384], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [8, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-16x65536", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [16, 65536], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [16, 65536], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [16, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-32x32769", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [32, 32769], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [32, 32769], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [32, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-128x16384", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [128, 16384], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [128, 16384], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [128, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f16-1x16385", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float16", "shape": [1, 16385], "data": { "kind": "cycle", "values": [-0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0] } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 16385], "dtype": "float16", "tolerance": 0.01 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f16-1x131072", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float16", "shape": [1, 131072], "data": { "kind": "cycle", "values": [-0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0] } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 131072], "dtype": "float16", "tolerance": 0.01 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f16-1x524288", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float16", "shape": [1, 524288], "data": { "kind": "cycle", "values": [-0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0] } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 524288], "dtype": "float16", "tolerance": 0.01 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f16-1x2097152", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float16", "shape": [1, 2097152], "data": { "kind": "cycle", "values": [-0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0] } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 2097152], "dtype": "float16", "tolerance": 0.01 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f16-3x524289", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float16", "shape": [3, 524289], "data": { "kind": "cycle", "values": [-0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0] } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [3, 524289], "dtype": "float16", "tolerance": 0.01 }, "invStdVar": { "shape": [3, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f16-16x65536", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float16", "shape": [16, 65536], "data": { "kind": "fillFloat32", "sinStep": 0.000021, "cosStep": 0.000037, "scale": 0.5 } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [16, 65536], "dtype": "float16", "tolerance": 0.01 }, "invStdVar": { "shape": [16, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-f16-2x32769", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [2, 32769], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [2, 32769], "dtype": "float16", "tolerance": 0.01 }, "invStdVar": { "shape": [2, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f16-f32-2x32769", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float16", "shape": [2, 32769], "data": { "kind": "cycle", "values": [-0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0] } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [2, 32769], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [2, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x16384-split1", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "MAX_SPLITS": 1 }, "inputs": { "x": { "dtype": "float32", "shape": [1, 16384], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 16384], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x16385-split3", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "MAX_SPLITS": 3 }, "inputs": { "x": { "dtype": "float32", "shape": [1, 16385], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 16385], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [1, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-2x262145-wg64", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "WORKGROUP_SIZE": 64 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 262145], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [2, 262145], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [2, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-2x262145-wg128", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "WORKGROUP_SIZE": 128 }, "inputs": { "x": { "dtype": "float32", "shape": [2, 262145], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [2, 262145], "dtype": "float32", "tolerance": 0.00001 }, "invStdVar": { "shape": [2, 1], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x524288-no-stats", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 524288], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 524288], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f32-1x2097152-no-stats", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float32", "shape": [1, 2097152], "data": { "kind": "fillFloat32", "sinStep": 0.017, "cosStep": 0.023, "scale": 0.5, "offset": 0.0 } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 2097152], "dtype": "float32", "tolerance": 0.00001 } } }, { "name": "split_f16-1x524288-no-stats", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float16", "shape": [1, 524288], "data": { "kind": "cycle", "values": [-0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0] } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 524288], "dtype": "float16", "tolerance": 0.01 } } }, { "name": "split_f16-1x2097152-no-stats", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "dtype": "float16", "shape": [1, 2097152], "data": { "kind": "cycle", "values": [-0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0] } }, "scale": { "dtype": "float16", "shape": [], "data": { "kind": "fillFloat32", "sinStep": 0.031, "cosStep": 0.009, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "shape": [1, 2097152], "dtype": "float16", "tolerance": 0.01 } } }, { "name": "split_f32_suffix_broadcast_tail", "attrs": { "axis": 1, "epsilon": 0.000001 }, "inputs": { "x": { "dtype": "float32", "shape": [3, 17, 4097], "data": { "kind": "cycle", "values": [-0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0] } }, "scale": { "dtype": "float32", "shape": [1, 17, 1], "data": { "kind": "fillFloat32", "sinStep": 0.31, "cosStep": 0.09, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "dtype": "float32", "shape": [3, 17, 4097], "tolerance": 0.00001 }, "invStdVar": { "dtype": "float32", "shape": [3, 1, 1], "tolerance": 0.00001 } } }, { "name": "split_f16_suffix_broadcast_tail", "attrs": { "axis": 1, "epsilon": 0.000001 }, "inputs": { "x": { "dtype": "float16", "shape": [3, 17, 4097], "data": { "kind": "cycle", "values": [-0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 0.75, 1.0] } }, "scale": { "dtype": "float16", "shape": [1, 17, 1], "data": { "kind": "fillFloat32", "sinStep": 0.31, "cosStep": 0.09, "scale": 0.25, "offset": 1.0 } } }, "outputs": { "y": { "dtype": "float16", "shape": [3, 17, 4097], "tolerance": 0.01 }, "invStdVar": { "dtype": "float32", "shape": [3, 1, 1], "tolerance": 0.00001 } } }, { "name": "split_empty_outer_long_suffix", "attrs": { "axis": 1 }, "inputs": { "x": { "dtype": "float32", "shape": [0, 2, 16384], "data": { "kind": "values", "values": [] } }, "scale": { "dtype": "float32", "shape": [], "data": { "kind": "values", "values": [1.0] } } }, "outputs": { "y": { "dtype": "float32", "shape": [0, 2, 16384], "tolerance": 0 }, "invStdVar": { "dtype": "float32", "shape": [0, 1, 1], "tolerance": 0 } } } ] }