{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 90372,
  "matchedSampleCount": 88428,
  "profileSpanCycles": 1038666,
  "profileSpanMs": 0.692444,
  "atOffset": null,
  "groups": [
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 21996,
      "tileCount": 1472,
      "phaseCount": 15,
      "phaseCycles": 629154,
      "phaseMs": 0.419436,
      "workCycles": 546736386,
      "averageActiveTiles": 869.0024795201175,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 24856.17321331151,
      "p50Cycles": 23898,
      "p95Cycles": 41436,
      "maximumCycles": 90246,
      "firstOffset": 0,
      "lastOffset": 1035504
    },
    {
      "name": "sync",
      "dimensions": {},
      "sampleCount": 84,
      "tileCount": 14,
      "phaseCount": 6,
      "phaseCycles": 422184,
      "phaseMs": 0.281456,
      "workCycles": 5886156,
      "averageActiveTiles": 13.942157921664487,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 70073.28571428571,
      "p50Cycles": 7410,
      "p95Cycles": 135282,
      "maximumCycles": 135282,
      "firstOffset": 0,
      "lastOffset": 828912
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 20466,
      "tileCount": 1472,
      "phaseCount": 255,
      "phaseCycles": 231732,
      "phaseMs": 0.154488,
      "workCycles": 59664006,
      "averageActiveTiles": 257.46986173683393,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 2915.274406332454,
      "p50Cycles": 2496,
      "p95Cycles": 5616,
      "maximumCycles": 6576,
      "firstOffset": 146898,
      "lastOffset": 1036914
    },
    {
      "name": "copy_strided_u64",
      "dimensions": {},
      "sampleCount": 4650,
      "tileCount": 1458,
      "phaseCount": 30,
      "phaseCycles": 220890,
      "phaseMs": 0.14726,
      "workCycles": 271441452,
      "averageActiveTiles": 1228.8535107972293,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 58374.50580645161,
      "p50Cycles": 62748,
      "p95Cycles": 62748,
      "maximumCycles": 62748,
      "firstOffset": 0,
      "lastOffset": 1024188
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k192_c144_r180_r184",
      "dimensions": {},
      "sampleCount": 2760,
      "tileCount": 920,
      "phaseCount": 75,
      "phaseCycles": 194940,
      "phaseMs": 0.12996,
      "workCycles": 134748720,
      "averageActiveTiles": 691.2317636195753,
      "usefulCycles": 106911360.0,
      "estimatedWorkCycles": 134748720,
      "usefulUtilization": 0.7934128057023473,
      "workLaneOccupancy": 0.9746376811594203,
      "deviceUsefulUtilization": 0.37257617728531855,
      "meanCycles": 48822.0,
      "p50Cycles": 48822,
      "p95Cycles": 48822,
      "maximumCycles": 48822,
      "firstOffset": 222132,
      "lastOffset": 979224
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k192_c144_r180_r184",
      "dimensions": {},
      "sampleCount": 1656,
      "tileCount": 552,
      "phaseCount": 81,
      "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": 221802,
      "lastOffset": 976296
    },
    {
      "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": 85638,
      "lastOffset": 828660
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k192_c160_r160_r164",
      "dimensions": {},
      "sampleCount": 1872,
      "tileCount": 624,
      "phaseCount": 6,
      "phaseCycles": 150984,
      "phaseMs": 0.100656,
      "workCycles": 90698400,
      "averageActiveTiles": 600.7153075822604,
      "usefulCycles": 71660160.0,
      "estimatedWorkCycles": 90698400,
      "usefulUtilization": 0.7900928792569659,
      "workLaneOccupancy": 0.996875,
      "deviceUsefulUtilization": 0.32243266778627855,
      "meanCycles": 48450.0,
      "p50Cycles": 48450,
      "p95Cycles": 48450,
      "maximumCycles": 48450,
      "firstOffset": 83400,
      "lastOffset": 825840
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 8790,
      "tileCount": 1472,
      "phaseCount": 153,
      "phaseCycles": 141408,
      "phaseMs": 0.094272,
      "workCycles": 87094746,
      "averageActiveTiles": 615.9110234215885,
      "usefulCycles": 51316080.0,
      "estimatedWorkCycles": 87094746,
      "usefulUtilization": 0.5891983426876289,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.24653108304554444,
      "meanCycles": 9908.38976109215,
      "p50Cycles": 8394,
      "p95Cycles": 12318,
      "maximumCycles": 12318,
      "firstOffset": 148422,
      "lastOffset": 1027368
    },
    {
      "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": 84906,
      "lastOffset": 823800
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k192_c144_r160_r164",
      "dimensions": {},
      "sampleCount": 72,
      "tileCount": 24,
      "phaseCount": 6,
      "phaseCycles": 138600,
      "phaseMs": 0.0924,
      "workCycles": 3141936,
      "averageActiveTiles": 22.669090909090908,
      "usefulCycles": 2480544.0,
      "estimatedWorkCycles": 3141936,
      "usefulUtilization": 0.7894953939227279,
      "workLaneOccupancy": 0.996875,
      "deviceUsefulUtilization": 0.012158385093167702,
      "meanCycles": 43638.0,
      "p50Cycles": 43638,
      "p95Cycles": 43638,
      "maximumCycles": 43638,
      "firstOffset": 82692,
      "lastOffset": 821004
    },
    {
      "name": "gelu_tanh_approx_f16",
      "dimensions": {},
      "sampleCount": 4374,
      "tileCount": 1458,
      "phaseCount": 39,
      "phaseCycles": 135306,
      "phaseMs": 0.090204,
      "workCycles": 102162024,
      "averageActiveTiles": 755.0442995876015,
      "usefulCycles": 56477088.0,
      "estimatedWorkCycles": 102162024,
      "usefulUtilization": 0.5528188047644789,
      "workLaneOccupancy": 0.9986301369863013,
      "deviceUsefulUtilization": 0.28356160818087695,
      "meanCycles": 23356.65843621399,
      "p50Cycles": 24306,
      "p95Cycles": 24306,
      "maximumCycles": 24306,
      "firstOffset": 159768,
      "lastOffset": 896982
    },
    {
      "name": "cast_f16_f8",
      "dimensions": {},
      "sampleCount": 8790,
      "tileCount": 1472,
      "phaseCount": 177,
      "phaseCycles": 111252,
      "phaseMs": 0.074168,
      "workCycles": 20819148,
      "averageActiveTiles": 187.13504476324022,
      "usefulCycles": 2983068.0,
      "estimatedWorkCycles": 20819148,
      "usefulUtilization": 0.14328482606492832,
      "workLaneOccupancy": 0.9959974037213327,
      "deviceUsefulUtilization": 0.018215769252414027,
      "meanCycles": 2368.5037542662117,
      "p50Cycles": 1770,
      "p95Cycles": 3678,
      "maximumCycles": 3678,
      "firstOffset": 178464,
      "lastOffset": 1038666
    },
    {
      "name": "fill_zero_u64",
      "dimensions": {},
      "sampleCount": 10488,
      "tileCount": 240,
      "phaseCount": 148,
      "phaseCycles": 98262,
      "phaseMs": 0.065508,
      "workCycles": 3139920,
      "averageActiveTiles": 31.95457043414545,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 3139920,
      "usefulUtilization": 0.0,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": 0.0,
      "meanCycles": 299.3821510297483,
      "p50Cycles": 246,
      "p95Cycles": 246,
      "maximumCycles": 3186,
      "firstOffset": 136794,
      "lastOffset": 902808
    }
  ],
  "samples": []
}
