{ "cases": [ { "name": "simplifiedln-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": 720, "scale": 0.5 }, "scale": { "shape": [4096], "dtype": "float32", "dist": "uniform", "seed": 721, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [4096, 4096], "dtype": "float32" } }, "bench": { "primary": true, "metrics": [{ "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype)" }] } }, { "name": "simplifiedln-f32-4096x4096-stats", "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": 722, "scale": 0.5 }, "scale": { "shape": [4096], "dtype": "float32", "dist": "uniform", "seed": 723, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [4096, 4096], "dtype": "float32" }, "invStdVar": { "shape": [4096, 1], "dtype": "float32" } }, "bench": { "primary": true, "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype) + args.rows * 4" } ] } }, { "name": "simplifiedln-f16-8192x3072-stats", "preset": "smoke", "vars": { "dtype": "float16", "rows": 8192, "dim": 3072 }, "attrs": { "epsilon": 0.00001, "axis": -1 }, "inputs": { "x": { "shape": [8192, 3072], "dtype": "float16", "dist": "normal", "seed": 724, "scale": 0.5 }, "scale": { "shape": [3072], "dtype": "float16", "dist": "uniform", "seed": 725, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [8192, 3072], "dtype": "float16" }, "invStdVar": { "shape": [8192, 1], "dtype": "float32" } }, "bench": { "primary": true, "metrics": [ { "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype) + args.rows * 4" } ] } }, { "name": "split_f32-1x16384", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 16384], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 16384], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 131080 }] } }, { "name": "split_f32-1x16385", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 16385], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 16385], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 131088 }] } }, { "name": "split_f32-1x32769", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 32769], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 32769], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 262160 }] } }, { "name": "split_f32-1x65536", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 65536], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 65536], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 524296 }] } }, { "name": "split_f32-1x131072", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 131072], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 131072], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 1048584 }] } }, { "name": "split_f32-1x262144", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 262144], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 262144], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 2097160 }] } }, { "name": "split_f32-1x524288", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 524288], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 524288], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 4194312 }] } }, { "name": "split_f32-1x1048576", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 1048576], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 1048576], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 8388616 }] } }, { "name": "split_f32-1x2097152", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 2097152], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 2097152], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 16777224 }] } }, { "name": "split_f32-2x131073", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [2, 131073], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [2, 131073], "dtype": "float32" }, "invStdVar": { "shape": [2, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 2097180 }] } }, { "name": "split_f32-3x524289", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [3, 524289], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [3, 524289], "dtype": "float32" }, "invStdVar": { "shape": [3, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 12582952 }] } }, { "name": "split_f32-4x1048576", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [4, 1048576], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [4, 1048576], "dtype": "float32" }, "invStdVar": { "shape": [4, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 33554452 }] } }, { "name": "split_f32-8x16384", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [8, 16384], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [8, 16384], "dtype": "float32" }, "invStdVar": { "shape": [8, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 1048612 }] } }, { "name": "split_f32-16x65536", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [16, 65536], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [16, 65536], "dtype": "float32" }, "invStdVar": { "shape": [16, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 8388676 }] } }, { "name": "split_f32-32x32769", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [32, 32769], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [32, 32769], "dtype": "float32" }, "invStdVar": { "shape": [32, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 8388996 }] } }, { "name": "split_f32-128x16384", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [128, 16384], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [128, 16384], "dtype": "float32" }, "invStdVar": { "shape": [128, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 16777732 }] } }, { "name": "split_f16-1x16385", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 16385], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 16385], "dtype": "float16" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 65546 }] } }, { "name": "split_f16-1x131072", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 131072], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 131072], "dtype": "float16" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 524294 }] } }, { "name": "split_f16-1x524288", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 524288], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 524288], "dtype": "float16" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 2097158 }] } }, { "name": "split_f16-1x2097152", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 2097152], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 2097152], "dtype": "float16" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 8388614 }] } }, { "name": "split_f16-3x524289", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [3, 524289], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [3, 524289], "dtype": "float16" }, "invStdVar": { "shape": [3, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 6291482 }] } }, { "name": "split_f16-16x65536", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [16, 65536], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [16, 65536], "dtype": "float16" }, "invStdVar": { "shape": [16, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 4194370 }] } }, { "name": "split_f32-f16-2x32769", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [2, 32769], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [2, 32769], "dtype": "float16" }, "invStdVar": { "shape": [2, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 393238 }] } }, { "name": "split_f16-f32-2x32769", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [2, 32769], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [2, 32769], "dtype": "float32" }, "invStdVar": { "shape": [2, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 393240 }] } }, { "name": "split_f32-1x16384-split1", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "MAX_SPLITS": 1 }, "inputs": { "x": { "shape": [1, 16384], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 16384], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 131080 }] } }, { "name": "split_f32-1x16385-split3", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "MAX_SPLITS": 3 }, "inputs": { "x": { "shape": [1, 16385], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 16385], "dtype": "float32" }, "invStdVar": { "shape": [1, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 131088 }] } }, { "name": "split_f32-2x262145-wg64", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "WORKGROUP_SIZE": 64 }, "inputs": { "x": { "shape": [2, 262145], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [2, 262145], "dtype": "float32" }, "invStdVar": { "shape": [2, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 4194332 }] } }, { "name": "split_f32-2x262145-wg128", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "WORKGROUP_SIZE": 128 }, "inputs": { "x": { "shape": [2, 262145], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [2, 262145], "dtype": "float32" }, "invStdVar": { "shape": [2, 1], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 4194332 }] } }, { "name": "split_f32-1x524288-no-stats", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 524288], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 524288], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 4194308 }] } }, { "name": "split_f32-1x2097152-no-stats", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 2097152], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 2097152], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 16777220 }] } }, { "name": "split_f16-1x524288-no-stats", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 524288], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 524288], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 2097154 }] } }, { "name": "split_f16-1x2097152-no-stats", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 2097152], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 2097152], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 8388610 }] } } ] }