{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 31596,
  "matchedSampleCount": 29652,
  "profileSpanCycles": 846120,
  "profileSpanMs": 0.56408,
  "atOffset": null,
  "groups": [
    {
      "name": "repeat-remainder",
      "dimensions": {},
      "sampleCount": 1472,
      "tileCount": 1472,
      "phaseCount": 1,
      "phaseCycles": 569076,
      "phaseMs": 0.379384,
      "workCycles": 828217026,
      "averageActiveTiles": 1455.3715602133987,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 562647.4361413043,
      "p50Cycles": 562686,
      "p95Cycles": 562692,
      "maximumCycles": 562692,
      "firstOffset": 277044,
      "lastOffset": 846120
    },
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 7332,
      "tileCount": 1472,
      "phaseCount": 5,
      "phaseCycles": 189276,
      "phaseMs": 0.126184,
      "workCycles": 164725002,
      "averageActiveTiles": 870.2899575223483,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 22466.58510638298,
      "p50Cycles": 21750,
      "p95Cycles": 40608,
      "maximumCycles": 82434,
      "firstOffset": 0,
      "lastOffset": 280362
    },
    {
      "name": "sync",
      "dimensions": {},
      "sampleCount": 28,
      "tileCount": 14,
      "phaseCount": 2,
      "phaseCycles": 87090,
      "phaseMs": 0.05806,
      "workCycles": 1219212,
      "averageActiveTiles": 13.999448846021357,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 43543.28571428572,
      "p50Cycles": 942,
      "p95Cycles": 86148,
      "maximumCycles": 86148,
      "firstOffset": 0,
      "lastOffset": 87090
    },
    {
      "name": "copy_strided_u64",
      "dimensions": {},
      "sampleCount": 4867,
      "tileCount": 1472,
      "phaseCount": 24,
      "phaseCycles": 70506,
      "phaseMs": 0.047004,
      "workCycles": 28679532,
      "averageActiveTiles": 406.7672538507361,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 5892.650914320937,
      "p50Cycles": 2748,
      "p95Cycles": 15402,
      "maximumCycles": 16590,
      "firstOffset": 0,
      "lastOffset": 273852
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k192_c144_r180_r184",
      "dimensions": {},
      "sampleCount": 920,
      "tileCount": 920,
      "phaseCount": 7,
      "phaseCycles": 64542,
      "phaseMs": 0.043028,
      "workCycles": 44916240,
      "averageActiveTiles": 695.9226550153388,
      "usefulCycles": 35637120.0,
      "estimatedWorkCycles": 44916240,
      "usefulUtilization": 0.7934128057023473,
      "workLaneOccupancy": 0.9746376811594203,
      "deviceUsefulUtilization": 0.3751045830621921,
      "meanCycles": 48822.0,
      "p50Cycles": 48822,
      "p95Cycles": 48822,
      "maximumCycles": 48822,
      "firstOffset": 165180,
      "lastOffset": 229722
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k192_c144_r180_r184",
      "dimensions": {},
      "sampleCount": 552,
      "tileCount": 552,
      "phaseCount": 12,
      "phaseCycles": 62496,
      "phaseMs": 0.041664,
      "workCycles": 26605296,
      "averageActiveTiles": 425.71198156682027,
      "usefulCycles": 20839968.0,
      "estimatedWorkCycles": 26605296,
      "usefulUtilization": 0.7833014900491992,
      "workLaneOccupancy": 0.971027911969941,
      "deviceUsefulUtilization": 0.22653588960128232,
      "meanCycles": 48198.0,
      "p50Cycles": 48198,
      "p95Cycles": 48198,
      "maximumCycles": 48198,
      "firstOffset": 164886,
      "lastOffset": 227382
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k192_c160_r160_r164",
      "dimensions": {},
      "sampleCount": 624,
      "tileCount": 624,
      "phaseCount": 2,
      "phaseCycles": 50382,
      "phaseMs": 0.033588,
      "workCycles": 30232800,
      "averageActiveTiles": 600.0714540907467,
      "usefulCycles": 23886720.0,
      "estimatedWorkCycles": 30232800,
      "usefulUtilization": 0.7900928792569659,
      "workLaneOccupancy": 0.996875,
      "deviceUsefulUtilization": 0.32208708078972303,
      "meanCycles": 48450.0,
      "p50Cycles": 48450,
      "p95Cycles": 48450,
      "maximumCycles": 48450,
      "firstOffset": 36450,
      "lastOffset": 86832
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k192_c160_r160_r164",
      "dimensions": {},
      "sampleCount": 780,
      "tileCount": 780,
      "phaseCount": 2,
      "phaseCycles": 49932,
      "phaseMs": 0.033288,
      "workCycles": 38516400,
      "averageActiveTiles": 771.3770728190339,
      "usefulCycles": 30700800.0,
      "estimatedWorkCycles": 38516400,
      "usefulUtilization": 0.7970838396111786,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.41769850474906745,
      "meanCycles": 49380.0,
      "p50Cycles": 49380,
      "p95Cycles": 49380,
      "maximumCycles": 49380,
      "firstOffset": 36876,
      "lastOffset": 86808
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k192_c144_r160_r164",
      "dimensions": {},
      "sampleCount": 30,
      "tileCount": 30,
      "phaseCount": 2,
      "phaseCycles": 45612,
      "phaseMs": 0.030408,
      "workCycles": 1334160,
      "averageActiveTiles": 29.250197316495658,
      "usefulCycles": 1062720.0,
      "estimatedWorkCycles": 1334160,
      "usefulUtilization": 0.7965461413923367,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.015828214543083627,
      "meanCycles": 44472.0,
      "p50Cycles": 44472,
      "p95Cycles": 44472,
      "maximumCycles": 44472,
      "firstOffset": 36282,
      "lastOffset": 81894
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k192_c144_r160_r164",
      "dimensions": {},
      "sampleCount": 24,
      "tileCount": 24,
      "phaseCount": 2,
      "phaseCycles": 45462,
      "phaseMs": 0.030308,
      "workCycles": 1047312,
      "averageActiveTiles": 23.03708591790946,
      "usefulCycles": 826848.0,
      "estimatedWorkCycles": 1047312,
      "usefulUtilization": 0.7894953939227279,
      "workLaneOccupancy": 0.996875,
      "deviceUsefulUtilization": 0.012355756264668246,
      "meanCycles": 43638.0,
      "p50Cycles": 43638,
      "p95Cycles": 43638,
      "maximumCycles": 43638,
      "firstOffset": 35784,
      "lastOffset": 81246
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 2930,
      "tileCount": 1472,
      "phaseCount": 17,
      "phaseCycles": 44658,
      "phaseMs": 0.029772,
      "workCycles": 29031582,
      "averageActiveTiles": 650.086927314255,
      "usefulCycles": 17105360.0,
      "estimatedWorkCycles": 29031582,
      "usefulUtilization": 0.5891983426876289,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.260210693054655,
      "meanCycles": 9908.38976109215,
      "p50Cycles": 8394,
      "p95Cycles": 12318,
      "maximumCycles": 12318,
      "firstOffset": 98712,
      "lastOffset": 275304
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 3505,
      "tileCount": 1464,
      "phaseCount": 24,
      "phaseCycles": 39060,
      "phaseMs": 0.02604,
      "workCycles": 5335290,
      "averageActiveTiles": 136.5921658986175,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 1522.1940085592012,
      "p50Cycles": 1410,
      "p95Cycles": 2496,
      "maximumCycles": 2496,
      "firstOffset": 108072,
      "lastOffset": 281772
    },
    {
      "name": "gelu_tanh_approx_f16",
      "dimensions": {},
      "sampleCount": 1458,
      "tileCount": 1458,
      "phaseCount": 5,
      "phaseCycles": 37470,
      "phaseMs": 0.02498,
      "workCycles": 34054008,
      "averageActiveTiles": 908.8339471577261,
      "usefulCycles": 18825696.0,
      "estimatedWorkCycles": 34054008,
      "usefulUtilization": 0.5528188047644789,
      "workLaneOccupancy": 0.9986301369863013,
      "deviceUsefulUtilization": 0.34131827200891146,
      "meanCycles": 23356.65843621399,
      "p50Cycles": 24306,
      "p95Cycles": 24306,
      "maximumCycles": 24306,
      "firstOffset": 110058,
      "lastOffset": 147528
    },
    {
      "name": "cast_f16_f8",
      "dimensions": {},
      "sampleCount": 2930,
      "tileCount": 1472,
      "phaseCount": 19,
      "phaseCycles": 29412,
      "phaseMs": 0.019608,
      "workCycles": 6840216,
      "averageActiveTiles": 232.5654834761322,
      "usefulCycles": 994356.0,
      "estimatedWorkCycles": 6840216,
      "usefulUtilization": 0.14536909360757028,
      "workLaneOccupancy": 0.9959974037213327,
      "deviceUsefulUtilization": 0.022967278218295993,
      "meanCycles": 2334.544709897611,
      "p50Cycles": 1752,
      "p95Cycles": 3642,
      "maximumCycles": 3642,
      "firstOffset": 128754,
      "lastOffset": 283524
    },
    {
      "name": "fill_zero_u64",
      "dimensions": {},
      "sampleCount": 2200,
      "tileCount": 240,
      "phaseCount": 37,
      "phaseCycles": 24420,
      "phaseMs": 0.01628,
      "workCycles": 727824,
      "averageActiveTiles": 29.804422604422605,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 727824,
      "usefulUtilization": 0.0,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": 0.0,
      "meanCycles": 330.8290909090909,
      "p50Cycles": 246,
      "p95Cycles": 246,
      "maximumCycles": 3186,
      "firstOffset": 87084,
      "lastOffset": 153840
    }
  ],
  "samples": []
}
