{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 28646,
  "matchedSampleCount": 27354,
  "profileSpanCycles": 350886,
  "profileSpanMs": 0.233924,
  "atOffset": null,
  "groups": [
    {
      "name": "sync",
      "dimensions": {},
      "sampleCount": 134,
      "tileCount": 44,
      "phaseCount": 6,
      "phaseCycles": 338922,
      "phaseMs": 0.225948,
      "workCycles": 7784010,
      "averageActiveTiles": 22.966965850549684,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 58089.62686567164,
      "p50Cycles": 52530,
      "p95Cycles": 142068,
      "maximumCycles": 142764,
      "firstOffset": 10668,
      "lastOffset": 349590
    },
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 10170,
      "tileCount": 1472,
      "phaseCount": 7,
      "phaseCycles": 173736,
      "phaseMs": 0.115824,
      "workCycles": 148244724,
      "averageActiveTiles": 853.2757977621218,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 14576.669026548672,
      "p50Cycles": 10998,
      "p95Cycles": 35592,
      "maximumCycles": 54750,
      "firstOffset": 0,
      "lastOffset": 350538
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k288_c320_r56",
      "dimensions": {},
      "sampleCount": 1344,
      "tileCount": 1344,
      "phaseCount": 4,
      "phaseCycles": 82086,
      "phaseMs": 0.054724,
      "workCycles": 92147328,
      "averageActiveTiles": 1122.5705723265844,
      "usefulCycles": 52061184.0,
      "estimatedWorkCycles": 92147328,
      "usefulUtilization": 0.5649776844316093,
      "workLaneOccupancy": 0.9607142857142857,
      "deviceUsefulUtilization": 0.43086095282889947,
      "meanCycles": 68562.0,
      "p50Cycles": 68562,
      "p95Cycles": 68562,
      "maximumCycles": 68562,
      "firstOffset": 70644,
      "lastOffset": 152730
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k288_c320_r57",
      "dimensions": {},
      "sampleCount": 112,
      "tileCount": 112,
      "phaseCount": 4,
      "phaseCycles": 69666,
      "phaseMs": 0.046444,
      "workCycles": 7733376,
      "averageActiveTiles": 111.0064593919559,
      "usefulCycles": 4415904.0,
      "estimatedWorkCycles": 7733376,
      "usefulUtilization": 0.5710189185163116,
      "workLaneOccupancy": 0.9607142857142857,
      "deviceUsefulUtilization": 0.043061676895597506,
      "meanCycles": 69048.0,
      "p50Cycles": 69048,
      "p95Cycles": 69048,
      "maximumCycles": 69048,
      "firstOffset": 83550,
      "lastOffset": 153216
    },
    {
      "name": "rearrange_row_major_to_amp_f8_o0_r56_p56_c288_p288",
      "dimensions": {},
      "sampleCount": 1344,
      "tileCount": 1344,
      "phaseCount": 4,
      "phaseCycles": 61854,
      "phaseMs": 0.041236,
      "workCycles": 64955520,
      "averageActiveTiles": 1050.142593850034,
      "usefulCycles": 5419008.0,
      "estimatedWorkCycles": 64955520,
      "usefulUtilization": 0.08342644320297951,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.05951743305764908,
      "meanCycles": 48330.0,
      "p50Cycles": 48330,
      "p95Cycles": 48330,
      "maximumCycles": 48330,
      "firstOffset": 22314,
      "lastOffset": 84168
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k256_c192_r104",
      "dimensions": {},
      "sampleCount": 1224,
      "tileCount": 1224,
      "phaseCount": 16,
      "phaseCycles": 57030,
      "phaseMs": 0.03802,
      "workCycles": 67601520,
      "averageActiveTiles": 1185.3677012098894,
      "usefulCycles": 48342528.0,
      "estimatedWorkCycles": 67601520,
      "usefulUtilization": 0.7151100744480302,
      "workLaneOccupancy": 0.9889705882352942,
      "deviceUsefulUtilization": 0.5758616746334881,
      "meanCycles": 55230.0,
      "p50Cycles": 55230,
      "p95Cycles": 55230,
      "maximumCycles": 55230,
      "firstOffset": 266820,
      "lastOffset": 323850
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k256_c192_r105",
      "dimensions": {},
      "sampleCount": 204,
      "tileCount": 204,
      "phaseCount": 10,
      "phaseCycles": 56892,
      "phaseMs": 0.037928,
      "workCycles": 11319552,
      "averageActiveTiles": 198.96561906770722,
      "usefulCycles": 8134560.0,
      "estimatedWorkCycles": 11319552,
      "usefulUtilization": 0.7186291471605943,
      "workLaneOccupancy": 0.9889705882352942,
      "deviceUsefulUtilization": 0.09713484588648515,
      "meanCycles": 55488.0,
      "p50Cycles": 55488,
      "p95Cycles": 55488,
      "maximumCycles": 55488,
      "firstOffset": 267210,
      "lastOffset": 324102
    },
    {
      "name": "rearrange_row_major_to_amp_f8_o0_r57_p57_c288_p288",
      "dimensions": {},
      "sampleCount": 112,
      "tileCount": 112,
      "phaseCount": 4,
      "phaseCycles": 48948,
      "phaseMs": 0.032632,
      "workCycles": 5412960,
      "averageActiveTiles": 110.58592792351067,
      "usefulCycles": 459648.0,
      "estimatedWorkCycles": 5412960,
      "usefulUtilization": 0.08491620111731843,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.006379440826289479,
      "meanCycles": 48330.0,
      "p50Cycles": 48330,
      "p95Cycles": 48330,
      "maximumCycles": 48330,
      "firstOffset": 35220,
      "lastOffset": 84168
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 2884,
      "tileCount": 1456,
      "phaseCount": 24,
      "phaseCycles": 29790,
      "phaseMs": 0.01986,
      "workCycles": 27931212,
      "averageActiveTiles": 937.6036253776435,
      "usefulCycles": 11424888.0,
      "estimatedWorkCycles": 27931212,
      "usefulUtilization": 0.40903660034516226,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.2605395376329962,
      "meanCycles": 9684.886269070736,
      "p50Cycles": 8634,
      "p95Cycles": 11706,
      "maximumCycles": 11706,
      "firstOffset": 162414,
      "lastOffset": 349338
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r104_p104_c208_p256",
      "dimensions": {},
      "sampleCount": 72,
      "tileCount": 72,
      "phaseCount": 7,
      "phaseCycles": 27564,
      "phaseMs": 0.018376,
      "workCycles": 1727568,
      "averageActiveTiles": 62.67479320853287,
      "usefulCycles": 778752.0,
      "estimatedWorkCycles": 1727568,
      "usefulUtilization": 0.45077936150704345,
      "workLaneOccupancy": 0.8125,
      "deviceUsefulUtilization": 0.019193276674679637,
      "meanCycles": 23994.0,
      "p50Cycles": 23994,
      "p95Cycles": 23994,
      "maximumCycles": 23994,
      "firstOffset": 211536,
      "lastOffset": 239100
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r104_p104_c256_p256",
      "dimensions": {},
      "sampleCount": 1152,
      "tileCount": 1152,
      "phaseCount": 9,
      "phaseCycles": 25752,
      "phaseMs": 0.017168,
      "workCycles": 24157440,
      "averageActiveTiles": 938.0801491146319,
      "usefulCycles": 15335424.0,
      "estimatedWorkCycles": 24157440,
      "usefulUtilization": 0.6348116356700048,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.40455447951699824,
      "meanCycles": 20970.0,
      "p50Cycles": 20970,
      "p95Cycles": 20970,
      "maximumCycles": 20970,
      "firstOffset": 211242,
      "lastOffset": 236994
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r105_p105_c208_p256",
      "dimensions": {},
      "sampleCount": 12,
      "tileCount": 12,
      "phaseCount": 2,
      "phaseCycles": 24492,
      "phaseMs": 0.016328,
      "workCycles": 287928,
      "averageActiveTiles": 11.756001959823616,
      "usefulCycles": 131040.0,
      "estimatedWorkCycles": 287928,
      "usefulUtilization": 0.45511377844461115,
      "workLaneOccupancy": 0.8125,
      "deviceUsefulUtilization": 0.003634727222376073,
      "meanCycles": 23994.0,
      "p50Cycles": 23994,
      "p95Cycles": 23994,
      "maximumCycles": 23994,
      "firstOffset": 214836,
      "lastOffset": 239328
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r105_p105_c256_p256",
      "dimensions": {},
      "sampleCount": 192,
      "tileCount": 192,
      "phaseCount": 8,
      "phaseCycles": 23556,
      "phaseMs": 0.015704,
      "workCycles": 4026240,
      "averageActiveTiles": 170.92205807437597,
      "usefulCycles": 2580480.0,
      "estimatedWorkCycles": 4026240,
      "usefulUtilization": 0.6409155937052933,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.07442025294026446,
      "meanCycles": 20970.0,
      "p50Cycles": 20970,
      "p95Cycles": 20970,
      "maximumCycles": 20970,
      "firstOffset": 213930,
      "lastOffset": 237486
    },
    {
      "name": "gelu_tanh_approx_f16",
      "dimensions": {},
      "sampleCount": 1458,
      "tileCount": 1458,
      "phaseCount": 8,
      "phaseCycles": 22614,
      "phaseMs": 0.015076,
      "workCycles": 30792960,
      "averageActiveTiles": 1361.6768373573893,
      "usefulCycles": 18825696.0,
      "estimatedWorkCycles": 30792960,
      "usefulUtilization": 0.6113636363636363,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.5655432763851558,
      "meanCycles": 21120.0,
      "p50Cycles": 21120,
      "p95Cycles": 21120,
      "maximumCycles": 21120,
      "firstOffset": 180174,
      "lastOffset": 202788
    },
    {
      "name": "cast_f16_f8",
      "dimensions": {},
      "sampleCount": 1428,
      "tileCount": 1428,
      "phaseCount": 9,
      "phaseCycles": 19872,
      "phaseMs": 0.013248,
      "workCycles": 18215568,
      "averageActiveTiles": 916.6449275362319,
      "usefulCycles": 4706424.0,
      "estimatedWorkCycles": 18215568,
      "usefulUtilization": 0.2583737163727203,
      "workLaneOccupancy": 0.9889705882352942,
      "deviceUsefulUtilization": 0.16089467155009451,
      "meanCycles": 12756.0,
      "p50Cycles": 12756,
      "p95Cycles": 12756,
      "maximumCycles": 12756,
      "firstOffset": 232212,
      "lastOffset": 252084
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 1478,
      "tileCount": 1263,
      "phaseCount": 13,
      "phaseCycles": 14412,
      "phaseMs": 0.009608,
      "workCycles": 793296,
      "averageActiveTiles": 55.04412989175687,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 536.7361299052774,
      "p50Cycles": 378,
      "p95Cycles": 2538,
      "maximumCycles": 3150,
      "firstOffset": 0,
      "lastOffset": 203166
    },
    {
      "name": "fill_zero_u64",
      "dimensions": {},
      "sampleCount": 1112,
      "tileCount": 182,
      "phaseCount": 21,
      "phaseCycles": 13938,
      "phaseMs": 0.009292,
      "workCycles": 649974,
      "averageActiveTiles": 46.63323288850624,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 584.5089928057554,
      "p50Cycles": 300,
      "p95Cycles": 3096,
      "maximumCycles": 6540,
      "firstOffset": 0,
      "lastOffset": 255684
    },
    {
      "name": "static_copy_u32",
      "dimensions": {},
      "sampleCount": 114,
      "tileCount": 106,
      "phaseCount": 3,
      "phaseCycles": 6714,
      "phaseMs": 0.004476,
      "workCycles": 92022,
      "averageActiveTiles": 13.705987488829312,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 807.2105263157895,
      "p50Cycles": 450,
      "p95Cycles": 1758,
      "maximumCycles": 1758,
      "firstOffset": 0,
      "lastOffset": 6714
    },
    {
      "name": "copy_strided_u64",
      "dimensions": {},
      "sampleCount": 2808,
      "tileCount": 1454,
      "phaseCount": 21,
      "phaseCycles": 5712,
      "phaseMs": 0.003808,
      "workCycles": 1838196,
      "averageActiveTiles": 321.81302521008405,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 654.6282051282051,
      "p50Cycles": 378,
      "p95Cycles": 1038,
      "maximumCycles": 1038,
      "firstOffset": 180168,
      "lastOffset": 350886
    }
  ],
  "samples": []
}
