{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 90372,
  "matchedSampleCount": 88428,
  "profileSpanCycles": 856230,
  "profileSpanMs": 0.57082,
  "atOffset": null,
  "groups": [
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 21996,
      "tileCount": 1472,
      "phaseCount": 15,
      "phaseCycles": 583308,
      "phaseMs": 0.388872,
      "workCycles": 509247174,
      "averageActiveTiles": 873.0330700076117,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 23151.80823786143,
      "p50Cycles": 23322,
      "p95Cycles": 40470,
      "maximumCycles": 83142,
      "firstOffset": 0,
      "lastOffset": 853068
    },
    {
      "name": "sync",
      "dimensions": {},
      "sampleCount": 84,
      "tileCount": 14,
      "phaseCount": 6,
      "phaseCycles": 279786,
      "phaseMs": 0.186524,
      "workCycles": 3892428,
      "averageActiveTiles": 13.91216143767022,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 46338.42857142857,
      "p50Cycles": 6906,
      "p95Cycles": 88338,
      "maximumCycles": 88338,
      "firstOffset": 0,
      "lastOffset": 659826
    },
    {
      "name": "copy_strided_u64",
      "dimensions": {},
      "sampleCount": 14601,
      "tileCount": 1472,
      "phaseCount": 72,
      "phaseCycles": 220686,
      "phaseMs": 0.147124,
      "workCycles": 86044044,
      "averageActiveTiles": 389.89353198662354,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 5893.024039449353,
      "p50Cycles": 2748,
      "p95Cycles": 15402,
      "maximumCycles": 16590,
      "firstOffset": 0,
      "lastOffset": 846570
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k192_c144_r180_r184",
      "dimensions": {},
      "sampleCount": 2760,
      "tileCount": 920,
      "phaseCount": 21,
      "phaseCycles": 193176,
      "phaseMs": 0.128784,
      "workCycles": 134748720,
      "averageActiveTiles": 697.5437942601566,
      "usefulCycles": 106911360.0,
      "estimatedWorkCycles": 134748720,
      "usefulUtilization": 0.7934128057023473,
      "workLaneOccupancy": 0.9746376811594203,
      "deviceUsefulUtilization": 0.3759783824077525,
      "meanCycles": 48822.0,
      "p50Cycles": 48822,
      "p95Cycles": 48822,
      "maximumCycles": 48822,
      "firstOffset": 167508,
      "lastOffset": 802440
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k192_c144_r180_r184",
      "dimensions": {},
      "sampleCount": 1656,
      "tileCount": 552,
      "phaseCount": 36,
      "phaseCycles": 187146,
      "phaseMs": 0.124764,
      "workCycles": 79815888,
      "averageActiveTiles": 426.4899490237569,
      "usefulCycles": 62519904.0,
      "estimatedWorkCycles": 79815888,
      "usefulUtilization": 0.7833014900491992,
      "workLaneOccupancy": 0.971027911969941,
      "deviceUsefulUtilization": 0.22694987266393735,
      "meanCycles": 48198.0,
      "p50Cycles": 48198,
      "p95Cycles": 48198,
      "maximumCycles": 48198,
      "firstOffset": 167178,
      "lastOffset": 800100
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k192_c160_r160_r164",
      "dimensions": {},
      "sampleCount": 1872,
      "tileCount": 624,
      "phaseCount": 6,
      "phaseCycles": 155178,
      "phaseMs": 0.103452,
      "workCycles": 90698400,
      "averageActiveTiles": 584.4797587286857,
      "usefulCycles": 71660160.0,
      "estimatedWorkCycles": 90698400,
      "usefulUtilization": 0.7900928792569659,
      "workLaneOccupancy": 0.996875,
      "deviceUsefulUtilization": 0.3137182713596224,
      "meanCycles": 48450.0,
      "p50Cycles": 48450,
      "p95Cycles": 48450,
      "maximumCycles": 48450,
      "firstOffset": 37308,
      "lastOffset": 659574
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k192_c160_r160_r164",
      "dimensions": {},
      "sampleCount": 2340,
      "tileCount": 780,
      "phaseCount": 6,
      "phaseCycles": 152730,
      "phaseMs": 0.10182,
      "workCycles": 115549200,
      "averageActiveTiles": 756.5586328815557,
      "usefulCycles": 92102400.0,
      "estimatedWorkCycles": 115549200,
      "usefulUtilization": 0.7970838396111786,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.40967436140503705,
      "meanCycles": 49380.0,
      "p50Cycles": 49380,
      "p95Cycles": 49380,
      "maximumCycles": 49380,
      "firstOffset": 37716,
      "lastOffset": 659166
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k192_c144_r160_r164",
      "dimensions": {},
      "sampleCount": 72,
      "tileCount": 24,
      "phaseCount": 6,
      "phaseCycles": 142866,
      "phaseMs": 0.095244,
      "workCycles": 3141936,
      "averageActiveTiles": 21.99218848431397,
      "usefulCycles": 2480544.0,
      "estimatedWorkCycles": 3141936,
      "usefulUtilization": 0.7894953939227279,
      "workLaneOccupancy": 0.996875,
      "deviceUsefulUtilization": 0.01179533390668909,
      "meanCycles": 43638.0,
      "p50Cycles": 43638,
      "p95Cycles": 43638,
      "maximumCycles": 43638,
      "firstOffset": 36582,
      "lastOffset": 654750
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k192_c144_r160_r164",
      "dimensions": {},
      "sampleCount": 90,
      "tileCount": 30,
      "phaseCount": 6,
      "phaseCycles": 140346,
      "phaseMs": 0.093564,
      "workCycles": 4002480,
      "averageActiveTiles": 28.518661023470564,
      "usefulCycles": 3188160.0,
      "estimatedWorkCycles": 4002480,
      "usefulUtilization": 0.7965461413923367,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.015432356926577111,
      "meanCycles": 44472.0,
      "p50Cycles": 44472,
      "p95Cycles": 44472,
      "maximumCycles": 44472,
      "firstOffset": 36984,
      "lastOffset": 654306
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 8790,
      "tileCount": 1472,
      "phaseCount": 51,
      "phaseCycles": 133956,
      "phaseMs": 0.089304,
      "workCycles": 87094746,
      "averageActiveTiles": 650.1742811072293,
      "usefulCycles": 51316080.0,
      "estimatedWorkCycles": 87094746,
      "usefulUtilization": 0.5891983426876289,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.26024565821093754,
      "meanCycles": 9908.38976109215,
      "p50Cycles": 8394,
      "p95Cycles": 12318,
      "maximumCycles": 12318,
      "firstOffset": 100902,
      "lastOffset": 848016
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 10515,
      "tileCount": 1464,
      "phaseCount": 72,
      "phaseCycles": 119880,
      "phaseMs": 0.07992,
      "workCycles": 16005870,
      "averageActiveTiles": 133.51576576576576,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 1522.1940085592012,
      "p50Cycles": 1410,
      "p95Cycles": 2496,
      "maximumCycles": 2496,
      "firstOffset": 110262,
      "lastOffset": 854478
    },
    {
      "name": "gelu_tanh_approx_f16",
      "dimensions": {},
      "sampleCount": 4374,
      "tileCount": 1458,
      "phaseCount": 15,
      "phaseCycles": 112410,
      "phaseMs": 0.07494,
      "workCycles": 102162024,
      "averageActiveTiles": 908.8339471577261,
      "usefulCycles": 56477088.0,
      "estimatedWorkCycles": 102162024,
      "usefulUtilization": 0.5528188047644789,
      "workLaneOccupancy": 0.9986301369863013,
      "deviceUsefulUtilization": 0.34131827200891146,
      "meanCycles": 23356.65843621399,
      "p50Cycles": 24306,
      "p95Cycles": 24306,
      "maximumCycles": 24306,
      "firstOffset": 112248,
      "lastOffset": 720258
    },
    {
      "name": "cast_f16_f8",
      "dimensions": {},
      "sampleCount": 8790,
      "tileCount": 1472,
      "phaseCount": 57,
      "phaseCycles": 88338,
      "phaseMs": 0.058892,
      "workCycles": 20819148,
      "averageActiveTiles": 235.67601711607688,
      "usefulCycles": 2983068.0,
      "estimatedWorkCycles": 20819148,
      "usefulUtilization": 0.14328482606492832,
      "workLaneOccupancy": 0.9959974037213327,
      "deviceUsefulUtilization": 0.022940758913146835,
      "meanCycles": 2368.5037542662117,
      "p50Cycles": 1770,
      "p95Cycles": 3678,
      "maximumCycles": 3678,
      "firstOffset": 130944,
      "lastOffset": 856230
    },
    {
      "name": "fill_zero_u64",
      "dimensions": {},
      "sampleCount": 10488,
      "tileCount": 240,
      "phaseCount": 115,
      "phaseCycles": 86682,
      "phaseMs": 0.057788,
      "workCycles": 3139920,
      "averageActiveTiles": 36.223437391846055,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 3139920,
      "usefulUtilization": 0.0,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": 0.0,
      "meanCycles": 299.3821510297483,
      "p50Cycles": 246,
      "p95Cycles": 246,
      "maximumCycles": 3186,
      "firstOffset": 89280,
      "lastOffset": 726606
    }
  ],
  "samples": []
}
