{ "op": "ai.onnx.LayerNormalization", "cases": [ { "name": "layernorm-f32-256x1024", "preset": "smoke", "vars": { "dtype": "float32", "rows": 256, "dim": 1024 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "shape": [256, 1024], "dtype": "float32", "dist": "normal", "seed": 720, "scale": 0.5 }, "scale": { "shape": [1024], "dtype": "float32", "dist": "uniform", "seed": 721, "scale": 0.25, "offset": 1 }, "b": { "shape": [1024], "dtype": "float32", "dist": "normal", "seed": 722, "scale": 0.1 } }, "outputs": { "y": { "shape": [256, 1024], "dtype": "float32" } }, "bench": { "primary": true, "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim * 2) * dtypeBytes(args.dtype)" } ] } }, { "name": "layernorm-f32-4096x4096", "preset": "smoke", "vars": { "dtype": "float32", "rows": 4096, "dim": 4096 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "shape": [4096, 4096], "dtype": "float32", "dist": "normal", "seed": 730, "scale": 0.5 }, "scale": { "shape": [4096], "dtype": "float32", "dist": "uniform", "seed": 731, "scale": 0.25, "offset": 1 }, "b": { "shape": [4096], "dtype": "float32", "dist": "normal", "seed": 732, "scale": 0.1 } }, "outputs": { "y": { "shape": [4096, 4096], "dtype": "float32" } }, "bench": { "primary": true, "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim * 2) * dtypeBytes(args.dtype)" } ] } }, { "name": "layernorm-f16-4096x4096", "preset": "smoke", "vars": { "dtype": "float16", "rows": 4096, "dim": 4096 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "shape": [4096, 4096], "dtype": "float16", "dist": "normal", "seed": 733, "scale": 0.5 }, "scale": { "shape": [4096], "dtype": "float16", "dist": "uniform", "seed": 734, "scale": 0.25, "offset": 1 }, "b": { "shape": [4096], "dtype": "float16", "dist": "normal", "seed": 735, "scale": 0.1 } }, "outputs": { "y": { "shape": [4096, 4096], "dtype": "float16" } }, "bench": { "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim * 2) * dtypeBytes(args.dtype)" } ] } }, { "name": "layernorm-f32-4096x2050-unaligned-cliff", "preset": "smoke", "vars": { "dtype": "float32", "rows": 4096, "dim": 2050 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "shape": [4096, 2050], "dtype": "float32", "dist": "normal", "seed": 740, "scale": 0.5 }, "scale": { "shape": [2050], "dtype": "float32", "dist": "uniform", "seed": 741, "scale": 0.25, "offset": 1 }, "b": { "shape": [2050], "dtype": "float32", "dist": "normal", "seed": 742, "scale": 0.1 } }, "outputs": { "y": { "shape": [4096, 2050], "dtype": "float32" } }, "bench": { "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim * 2) * dtypeBytes(args.dtype)" } ] } }, { "name": "layernorm-f32-4096x1022-subgroup-nonvec4", "preset": "smoke", "vars": { "dtype": "float32", "rows": 4096, "dim": 1022 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "shape": [4096, 1022], "dtype": "float32", "dist": "normal", "seed": 743, "scale": 0.5 }, "scale": { "shape": [1022], "dtype": "float32", "dist": "uniform", "seed": 744, "scale": 0.25, "offset": 1 }, "b": { "shape": [1022], "dtype": "float32", "dist": "normal", "seed": 745, "scale": 0.1 } }, "outputs": { "y": { "shape": [4096, 1022], "dtype": "float32" } }, "bench": { "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim * 2) * dtypeBytes(args.dtype)" } ] } }, { "name": "layernorm-f16-1x4096-rows1-decode", "preset": "smoke", "vars": { "dtype": "float16", "rows": 1, "dim": 4096 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "shape": [1, 4096], "dtype": "float16", "dist": "normal", "seed": 746, "scale": 0.5 }, "scale": { "shape": [4096], "dtype": "float16", "dist": "uniform", "seed": 747, "scale": 0.25, "offset": 1 }, "b": { "shape": [4096], "dtype": "float16", "dist": "normal", "seed": 748, "scale": 0.1 } }, "outputs": { "y": { "shape": [1, 4096], "dtype": "float16" } }, "bench": { "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim * 2) * dtypeBytes(args.dtype)" } ] } }, { "name": "layernorm-f32-512x4096-suffix-axis1-rank3", "preset": "smoke", "vars": { "dtype": "float32", "outer": 512, "hidden": 4096 }, "attrs": { "epsilon": 0.00001, "axis": 1 }, "inputs": { "x": { "shape": [512, 256, 16], "dtype": "float32", "dist": "normal", "seed": 749, "scale": 0.5 }, "scale": { "shape": [256, 16], "dtype": "float32", "dist": "uniform", "seed": 750, "scale": 0.25, "offset": 1 }, "b": { "shape": [256, 16], "dtype": "float32", "dist": "normal", "seed": 751, "scale": 0.1 } }, "outputs": { "y": { "shape": [512, 256, 16], "dtype": "float32" } }, "bench": { "metrics": [ { "type": "bandwidth", "value": "(args.outer * args.hidden * 2 + args.hidden * 2) * dtypeBytes(args.dtype)" } ] } }, { "name": "layernorm-f32-8192x4096-broadcast-scale-generic-fallback", "preset": "stress", "vars": { "dtype": "float32", "rows": 8192, "dim": 4096 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "shape": [8192, 4096], "dtype": "float32", "dist": "normal", "seed": 760, "scale": 0.5 }, "scale": { "shape": [8192, 4096], "dtype": "float32", "dist": "uniform", "seed": 761, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [8192, 4096], "dtype": "float32", "dist": "empty" } }, "bench": { "primary": true, "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.rows * args.dim) * dtypeBytes(args.dtype)" } ] } }, { "name": "layernorm-f32-65536x64-broadcast-scale-narrow-hidden-launchbound", "preset": "stress", "vars": { "dtype": "float32", "rows": 65536, "dim": 64 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "shape": [65536, 64], "dtype": "float32", "dist": "normal", "seed": 762, "scale": 0.5 }, "scale": { "shape": [65536, 64], "dtype": "float32", "dist": "uniform", "seed": 763, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [65536, 64], "dtype": "float32", "dist": "empty" } }, "bench": { "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.rows * args.dim) * dtypeBytes(args.dtype)" } ] } }, { "name": "layernorm-f32-4096x4096-broadcast-bias-generic-fallback", "preset": "stress", "vars": { "dtype": "float32", "rows": 4096, "dim": 4096 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "shape": [4096, 4096], "dtype": "float32", "dist": "normal", "seed": 764, "scale": 0.5 }, "scale": { "shape": [4096, 4096], "dtype": "float32", "dist": "uniform", "seed": 765, "scale": 0.25, "offset": 1 }, "b": { "shape": [4096, 4096], "dtype": "float32", "dist": "normal", "seed": 766, "scale": 0.1 } }, "outputs": { "y": { "shape": [4096, 4096], "dtype": "float32", "dist": "empty" } }, "bench": { "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.rows * args.dim * 2) * dtypeBytes(args.dtype)" } ] } } ] }