{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 24045,
  "matchedSampleCount": 24045,
  "profileSpanCycles": 400842,
  "profileSpanMs": 0.267228,
  "atOffset": null,
  "groups": [
    {
      "name": "sync",
      "dimensions": {},
      "sampleCount": 74,
      "tileCount": 32,
      "phaseCount": 4,
      "phaseCycles": 378318,
      "phaseMs": 0.252212,
      "workCycles": 7579692,
      "averageActiveTiles": 20.035240194756792,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 102428.27027027027,
      "p50Cycles": 116466,
      "p95Cycles": 146142,
      "maximumCycles": 146142,
      "firstOffset": 0,
      "lastOffset": 378318
    },
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 5814,
      "tileCount": 1458,
      "phaseCount": 4,
      "phaseCycles": 152826,
      "phaseMs": 0.101884,
      "workCycles": 150961278,
      "averageActiveTiles": 987.7983981783204,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 25965.13209494324,
      "p50Cycles": 17562,
      "p95Cycles": 60894,
      "maximumCycles": 81282,
      "firstOffset": 0,
      "lastOffset": 390594
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k480_c144_r144_r152",
      "dimensions": {},
      "sampleCount": 360,
      "tileCount": 360,
      "phaseCount": 6,
      "phaseCycles": 110538,
      "phaseMs": 0.073692,
      "workCycles": 37380960,
      "averageActiveTiles": 338.17293600390815,
      "usefulCycles": 29439360.0,
      "estimatedWorkCycles": 37380960,
      "usefulUtilization": 0.7875495974421203,
      "workLaneOccupancy": 0.9962962962962963,
      "deviceUsefulUtilization": 0.18092932039109902,
      "meanCycles": 103836.0,
      "p50Cycles": 103836,
      "p95Cycles": 103836,
      "maximumCycles": 103836,
      "firstOffset": 267534,
      "lastOffset": 378072
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k480_c144_r144_r152",
      "dimensions": {},
      "sampleCount": 1080,
      "tileCount": 1080,
      "phaseCount": 18,
      "phaseCycles": 106980,
      "phaseMs": 0.07132,
      "workCycles": 108293760,
      "averageActiveTiles": 1012.2804262478968,
      "usefulCycles": 83514816.0,
      "estimatedWorkCycles": 108293760,
      "usefulUtilization": 0.771187702781767,
      "workLaneOccupancy": 0.9944513031550068,
      "deviceUsefulUtilization": 0.5303384622887659,
      "meanCycles": 100272.0,
      "p50Cycles": 100272,
      "p95Cycles": 100272,
      "maximumCycles": 100272,
      "firstOffset": 267534,
      "lastOffset": 374514
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k384_c160_r160_r168",
      "dimensions": {},
      "sampleCount": 390,
      "tileCount": 390,
      "phaseCount": 1,
      "phaseCycles": 100818,
      "phaseMs": 0.067212,
      "workCycles": 39283920,
      "averageActiveTiles": 389.6518478843064,
      "usefulCycles": 31449600.0,
      "estimatedWorkCycles": 39283920,
      "usefulUtilization": 0.8005718370264474,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.2119186791178594,
      "meanCycles": 100728.0,
      "p50Cycles": 100728,
      "p95Cycles": 100728,
      "maximumCycles": 100728,
      "firstOffset": 15648,
      "lastOffset": 116466
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k384_c160_r160_r168",
      "dimensions": {},
      "sampleCount": 1014,
      "tileCount": 1014,
      "phaseCount": 1,
      "phaseCycles": 96390,
      "phaseMs": 0.06426,
      "workCycles": 97666452,
      "averageActiveTiles": 1013.2425770308123,
      "usefulCycles": 77725440.0,
      "estimatedWorkCycles": 97666452,
      "usefulUtilization": 0.795825366933571,
      "workLaneOccupancy": 0.9980769230769231,
      "deviceUsefulUtilization": 0.5478017293874071,
      "meanCycles": 96318.0,
      "p50Cycles": 96318,
      "p95Cycles": 96318,
      "maximumCycles": 96318,
      "firstOffset": 15708,
      "lastOffset": 112098
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k384_c144_r160_r168",
      "dimensions": {},
      "sampleCount": 15,
      "tileCount": 15,
      "phaseCount": 1,
      "phaseCycles": 90768,
      "phaseMs": 0.060512,
      "workCycles": 1360260,
      "averageActiveTiles": 14.986118455843469,
      "usefulCycles": 1088640.0,
      "estimatedWorkCycles": 1360260,
      "usefulUtilization": 0.8003175863437872,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.008147862874485549,
      "meanCycles": 90684.0,
      "p50Cycles": 90684,
      "p95Cycles": 90684,
      "maximumCycles": 90684,
      "firstOffset": 14118,
      "lastOffset": 104886
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k384_c144_r160_r168",
      "dimensions": {},
      "sampleCount": 39,
      "tileCount": 39,
      "phaseCount": 1,
      "phaseCycles": 86784,
      "phaseMs": 0.057856,
      "workCycles": 3382002,
      "averageActiveTiles": 38.97034015486726,
      "usefulCycles": 2690496.0,
      "estimatedWorkCycles": 3382002,
      "usefulUtilization": 0.7955335330966687,
      "workLaneOccupancy": 0.9980769230769231,
      "deviceUsefulUtilization": 0.021061285590611774,
      "meanCycles": 86718.0,
      "p50Cycles": 86718,
      "p95Cycles": 86718,
      "maximumCycles": 86718,
      "firstOffset": 14178,
      "lastOffset": 100962
    },
    {
      "name": "gelu_tanh_approx_f16",
      "dimensions": {},
      "sampleCount": 1458,
      "tileCount": 1458,
      "phaseCount": 5,
      "phaseCycles": 80112,
      "phaseMs": 0.053408,
      "workCycles": 67609380,
      "averageActiveTiles": 843.9357399640503,
      "usefulCycles": 37651392.0,
      "estimatedWorkCycles": 67609380,
      "usefulUtilization": 0.5568959810014528,
      "workLaneOccupancy": 0.9986301369863013,
      "deviceUsefulUtilization": 0.31928289525099646,
      "meanCycles": 46371.31687242798,
      "p50Cycles": 48270,
      "p95Cycles": 48270,
      "maximumCycles": 48270,
      "firstOffset": 145236,
      "lastOffset": 225348
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 4999,
      "tileCount": 1458,
      "phaseCount": 52,
      "phaseCycles": 66048,
      "phaseMs": 0.044032,
      "workCycles": 27582678,
      "averageActiveTiles": 417.61564316860466,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 5517.639127825565,
      "p50Cycles": 4734,
      "p95Cycles": 11130,
      "maximumCycles": 11130,
      "firstOffset": 124836,
      "lastOffset": 400842
    },
    {
      "name": "cast_f16_f8",
      "dimensions": {},
      "sampleCount": 1458,
      "tileCount": 1458,
      "phaseCount": 5,
      "phaseCycles": 47742,
      "phaseMs": 0.031828,
      "workCycles": 8106132,
      "averageActiveTiles": 169.79037325625237,
      "usefulCycles": 1568808.0,
      "estimatedWorkCycles": 8106132,
      "usefulUtilization": 0.1935334879816909,
      "workLaneOccupancy": 0.9949315068493151,
      "deviceUsefulUtilization": 0.022323453235051444,
      "meanCycles": 5559.761316872428,
      "p50Cycles": 5772,
      "p95Cycles": 5772,
      "maximumCycles": 5772,
      "firstOffset": 182286,
      "lastOffset": 231120
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 2898,
      "tileCount": 1458,
      "phaseCount": 28,
      "phaseCycles": 43626,
      "phaseMs": 0.029084,
      "workCycles": 35847936,
      "averageActiveTiles": 821.7103562095998,
      "usefulCycles": 13011520.0,
      "estimatedWorkCycles": 35847936,
      "usefulUtilization": 0.3629642721968707,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.20261650910207116,
      "meanCycles": 12369.888198757764,
      "p50Cycles": 13242,
      "p95Cycles": 17298,
      "maximumCycles": 17388,
      "firstOffset": 128292,
      "lastOffset": 399372
    },
    {
      "name": "fill_zero_u64",
      "dimensions": {},
      "sampleCount": 4440,
      "tileCount": 224,
      "phaseCount": 136,
      "phaseCycles": 39240,
      "phaseMs": 0.02616,
      "workCycles": 1158048,
      "averageActiveTiles": 29.511926605504588,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 1158048,
      "usefulUtilization": 0.0,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": 0.0,
      "meanCycles": 260.8216216216216,
      "p50Cycles": 240,
      "p95Cycles": 240,
      "maximumCycles": 840,
      "firstOffset": 192690,
      "lastOffset": 231930
    },
    {
      "name": "copy_strided_u64",
      "dimensions": {},
      "sampleCount": 6,
      "tileCount": 6,
      "phaseCount": 2,
      "phaseCycles": 3516,
      "phaseMs": 0.002344,
      "workCycles": 10980,
      "averageActiveTiles": 3.1228668941979523,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 1830.0,
      "p50Cycles": 1764,
      "p95Cycles": 2184,
      "maximumCycles": 2184,
      "firstOffset": 270726,
      "lastOffset": 274242
    }
  ],
  "samples": []
}
