{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 36249,
  "matchedSampleCount": 35997,
  "profileSpanCycles": 1084056,
  "profileSpanMs": 0.722704,
  "atOffset": null,
  "groups": [
    {
      "name": "repeat-remainder",
      "dimensions": {},
      "sampleCount": 1472,
      "tileCount": 1472,
      "phaseCount": 1,
      "phaseCycles": 725136,
      "phaseMs": 0.483424,
      "workCycles": 1060257114,
      "averageActiveTiles": 1462.1493264711723,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 720283.3654891305,
      "p50Cycles": 720276,
      "p95Cycles": 720294,
      "maximumCycles": 720456,
      "firstOffset": 358920,
      "lastOffset": 1084056
    },
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 10304,
      "tileCount": 1472,
      "phaseCount": 7,
      "phaseCycles": 217008,
      "phaseMs": 0.144672,
      "workCycles": 221332890,
      "averageActiveTiles": 1019.9296339305463,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 21480.28823757764,
      "p50Cycles": 22782,
      "p95Cycles": 32814,
      "maximumCycles": 50574,
      "firstOffset": 0,
      "lastOffset": 361770
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 6272,
      "tileCount": 1472,
      "phaseCount": 36,
      "phaseCycles": 59466,
      "phaseMs": 0.039644,
      "workCycles": 9697506,
      "averageActiveTiles": 163.0764806780345,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 1546.158482142857,
      "p50Cycles": 834,
      "p95Cycles": 3204,
      "maximumCycles": 3204,
      "firstOffset": 0,
      "lastOffset": 362604
    },
    {
      "name": "copy_strided_u64",
      "dimensions": {},
      "sampleCount": 3040,
      "tileCount": 1472,
      "phaseCount": 20,
      "phaseCycles": 50658,
      "phaseMs": 0.033772,
      "workCycles": 38709372,
      "averageActiveTiles": 764.1314698566861,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 12733.34605263158,
      "p50Cycles": 984,
      "p95Cycles": 26418,
      "maximumCycles": 26418,
      "firstOffset": 29568,
      "lastOffset": 356244
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k288_c96_r180_r184",
      "dimensions": {},
      "sampleCount": 468,
      "tileCount": 468,
      "phaseCount": 4,
      "phaseCycles": 50562,
      "phaseMs": 0.033708,
      "workCycles": 22522968,
      "averageActiveTiles": 445.45247419010326,
      "usefulCycles": 18128448.0,
      "estimatedWorkCycles": 22522968,
      "usefulUtilization": 0.8048871711756639,
      "workLaneOccupancy": 0.9962962962962963,
      "deviceUsefulUtilization": 0.2435726778832015,
      "meanCycles": 48126.0,
      "p50Cycles": 48126,
      "p95Cycles": 48126,
      "maximumCycles": 48126,
      "firstOffset": 55362,
      "lastOffset": 105924
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k288_c96_r180_r184",
      "dimensions": {},
      "sampleCount": 780,
      "tileCount": 780,
      "phaseCount": 2,
      "phaseCycles": 50328,
      "phaseMs": 0.033552,
      "workCycles": 38025000,
      "averageActiveTiles": 755.5436337625179,
      "usefulCycles": 31000320.0,
      "estimatedWorkCycles": 38025000,
      "usefulUtilization": 0.8152615384615385,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.4184549356223176,
      "meanCycles": 48750.0,
      "p50Cycles": 48750,
      "p95Cycles": 48750,
      "maximumCycles": 48750,
      "firstOffset": 56046,
      "lastOffset": 106374
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k192_c144_r180_r184",
      "dimensions": {},
      "sampleCount": 920,
      "tileCount": 920,
      "phaseCount": 4,
      "phaseCycles": 48966,
      "phaseMs": 0.032644,
      "workCycles": 44916240,
      "averageActiveTiles": 917.2944492096557,
      "usefulCycles": 35637120.0,
      "estimatedWorkCycles": 44916240,
      "usefulUtilization": 0.7934128057023473,
      "workLaneOccupancy": 0.9746376811594203,
      "deviceUsefulUtilization": 0.49442470285504225,
      "meanCycles": 48822.0,
      "p50Cycles": 48822,
      "p95Cycles": 48822,
      "maximumCycles": 48822,
      "firstOffset": 263136,
      "lastOffset": 312102
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k192_c144_r180_r184",
      "dimensions": {},
      "sampleCount": 552,
      "tileCount": 552,
      "phaseCount": 10,
      "phaseCycles": 48294,
      "phaseMs": 0.032196,
      "workCycles": 26605296,
      "averageActiveTiles": 550.9027208348863,
      "usefulCycles": 20839968.0,
      "estimatedWorkCycles": 26605296,
      "usefulUtilization": 0.7833014900491992,
      "workLaneOccupancy": 0.971027911969941,
      "deviceUsefulUtilization": 0.29315415903676934,
      "meanCycles": 48198.0,
      "p50Cycles": 48198,
      "p95Cycles": 48198,
      "maximumCycles": 48198,
      "firstOffset": 263172,
      "lastOffset": 311466
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 2944,
      "tileCount": 1472,
      "phaseCount": 17,
      "phaseCycles": 46050,
      "phaseMs": 0.0307,
      "workCycles": 25813830,
      "averageActiveTiles": 560.5609120521173,
      "usefulCycles": 13963440.0,
      "estimatedWorkCycles": 25813830,
      "usefulUtilization": 0.5409286417397186,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.20599419345701742,
      "meanCycles": 8768.28464673913,
      "p50Cycles": 8208,
      "p95Cycles": 12834,
      "maximumCycles": 12834,
      "firstOffset": 113856,
      "lastOffset": 357690
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r92_p92_c80_p192",
      "dimensions": {},
      "sampleCount": 40,
      "tileCount": 40,
      "phaseCount": 2,
      "phaseCycles": 44352,
      "phaseMs": 0.029568,
      "workCycles": 1642320,
      "averageActiveTiles": 37.02922077922078,
      "usefulCycles": 294400.0,
      "estimatedWorkCycles": 1642320,
      "usefulUtilization": 0.1792586097715427,
      "workLaneOccupancy": 0.4166666666666667,
      "deviceUsefulUtilization": 0.004509379509379509,
      "meanCycles": 41058.0,
      "p50Cycles": 41058,
      "p95Cycles": 41058,
      "maximumCycles": 41058,
      "firstOffset": 198954,
      "lastOffset": 243306
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k288_c80_r180_r184",
      "dimensions": {},
      "sampleCount": 140,
      "tileCount": 140,
      "phaseCount": 2,
      "phaseCycles": 43398,
      "phaseMs": 0.028932,
      "workCycles": 5695200,
      "averageActiveTiles": 131.2318540024886,
      "usefulCycles": 4636800.0,
      "estimatedWorkCycles": 5695200,
      "usefulUtilization": 0.8141592920353983,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.07258399004562423,
      "meanCycles": 40680.0,
      "p50Cycles": 40680,
      "p95Cycles": 40680,
      "maximumCycles": 40680,
      "firstOffset": 54912,
      "lastOffset": 98310
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k288_c80_r180_r184",
      "dimensions": {},
      "sampleCount": 84,
      "tileCount": 84,
      "phaseCount": 4,
      "phaseCycles": 42564,
      "phaseMs": 0.028376,
      "workCycles": 3372768,
      "averageActiveTiles": 79.23992106005075,
      "usefulCycles": 2711520.0,
      "estimatedWorkCycles": 3372768,
      "usefulUtilization": 0.8039450089659295,
      "workLaneOccupancy": 0.9962962962962963,
      "deviceUsefulUtilization": 0.04327754011350682,
      "meanCycles": 40152.0,
      "p50Cycles": 40152,
      "p95Cycles": 40152,
      "maximumCycles": 40152,
      "firstOffset": 54210,
      "lastOffset": 96774
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r90_p90_c80_p192",
      "dimensions": {},
      "sampleCount": 16,
      "tileCount": 16,
      "phaseCount": 4,
      "phaseCycles": 39828,
      "phaseMs": 0.026552,
      "workCycles": 616320,
      "averageActiveTiles": 15.474540524254293,
      "usefulCycles": 115200.0,
      "estimatedWorkCycles": 616320,
      "usefulUtilization": 0.18691588785046728,
      "workLaneOccupancy": 0.4166666666666667,
      "deviceUsefulUtilization": 0.0019649711149246104,
      "meanCycles": 38520.0,
      "p50Cycles": 38520,
      "p95Cycles": 38520,
      "maximumCycles": 38520,
      "firstOffset": 199914,
      "lastOffset": 239742
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r89_p90_c80_p192",
      "dimensions": {},
      "sampleCount": 8,
      "tileCount": 8,
      "phaseCount": 2,
      "phaseCycles": 39030,
      "phaseMs": 0.02602,
      "workCycles": 312240,
      "averageActiveTiles": 8.0,
      "usefulCycles": 56960.0,
      "estimatedWorkCycles": 312240,
      "usefulUtilization": 0.1824237765821163,
      "workLaneOccupancy": 0.41203703703703703,
      "deviceUsefulUtilization": 0.000991433568381067,
      "meanCycles": 39030.0,
      "p50Cycles": 39030,
      "p95Cycles": 39030,
      "maximumCycles": 39030,
      "firstOffset": 189102,
      "lastOffset": 228132
    },
    {
      "name": "cast_f16_f8",
      "dimensions": {},
      "sampleCount": 2930,
      "tileCount": 1472,
      "phaseCount": 20,
      "phaseCycles": 33984,
      "phaseMs": 0.022656,
      "workCycles": 20155632,
      "averageActiveTiles": 593.0918079096045,
      "usefulCycles": 6485184.0,
      "estimatedWorkCycles": 20155632,
      "usefulUtilization": 0.32175542796177264,
      "workLaneOccupancy": 0.9741445195898886,
      "deviceUsefulUtilization": 0.12964029108327194,
      "meanCycles": 6879.055290102389,
      "p50Cycles": 12324,
      "p95Cycles": 12636,
      "maximumCycles": 12636,
      "firstOffset": 225456,
      "lastOffset": 363780
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r92_p92_c192_p192",
      "dimensions": {},
      "sampleCount": 880,
      "tileCount": 880,
      "phaseCount": 4,
      "phaseCycles": 33552,
      "phaseMs": 0.022368,
      "workCycles": 25317600,
      "averageActiveTiles": 754.5779685264664,
      "usefulCycles": 15544320.0,
      "estimatedWorkCycles": 25317600,
      "usefulUtilization": 0.6139728884254432,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.3147353361945637,
      "meanCycles": 28770.0,
      "p50Cycles": 28770,
      "p95Cycles": 28770,
      "maximumCycles": 28770,
      "firstOffset": 198426,
      "lastOffset": 231978
    },
    {
      "name": "gelu_tanh_approx_f16",
      "dimensions": {},
      "sampleCount": 1458,
      "tileCount": 1458,
      "phaseCount": 8,
      "phaseCycles": 32544,
      "phaseMs": 0.021696,
      "workCycles": 33950988,
      "averageActiveTiles": 1043.233407079646,
      "usefulCycles": 18825696.0,
      "estimatedWorkCycles": 33950988,
      "usefulUtilization": 0.5544962638495233,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.39298167564447867,
      "meanCycles": 23286.0,
      "p50Cycles": 23286,
      "p95Cycles": 23286,
      "maximumCycles": 23286,
      "firstOffset": 147624,
      "lastOffset": 180168
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r89_p90_c192_p192",
      "dimensions": {},
      "sampleCount": 176,
      "tileCount": 176,
      "phaseCount": 5,
      "phaseCycles": 32334,
      "phaseMs": 0.021556,
      "workCycles": 4976928,
      "averageActiveTiles": 153.92243458897755,
      "usefulCycles": 3007488.0,
      "estimatedWorkCycles": 4976928,
      "usefulUtilization": 0.6042860173986845,
      "workLaneOccupancy": 0.9888888888888889,
      "deviceUsefulUtilization": 0.063188298224241,
      "meanCycles": 28278.0,
      "p50Cycles": 28278,
      "p95Cycles": 28278,
      "maximumCycles": 28278,
      "firstOffset": 198312,
      "lastOffset": 230646
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r90_p90_c192_p192",
      "dimensions": {},
      "sampleCount": 352,
      "tileCount": 352,
      "phaseCount": 3,
      "phaseCycles": 30942,
      "phaseMs": 0.020628,
      "workCycles": 9504000,
      "averageActiveTiles": 307.15532286212914,
      "usefulCycles": 6082560.0,
      "estimatedWorkCycles": 9504000,
      "usefulUtilization": 0.64,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.1335457925487518,
      "meanCycles": 27000.0,
      "p50Cycles": 27000,
      "p95Cycles": 27000,
      "maximumCycles": 27000,
      "firstOffset": 198456,
      "lastOffset": 229398
    },
    {
      "name": "fill_zero_u64",
      "dimensions": {},
      "sampleCount": 3060,
      "tileCount": 170,
      "phaseCount": 18,
      "phaseCycles": 4404,
      "phaseMs": 0.002936,
      "workCycles": 746688,
      "averageActiveTiles": 169.54768392370573,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 710940,
      "usefulUtilization": 0.0,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": 0.0,
      "meanCycles": 244.01568627450982,
      "p50Cycles": 246,
      "p95Cycles": 246,
      "maximumCycles": 246,
      "firstOffset": 0,
      "lastOffset": 4404
    },
    {
      "name": "static_copy_u32",
      "dimensions": {},
      "sampleCount": 101,
      "tileCount": 101,
      "phaseCount": 4,
      "phaseCycles": 2694,
      "phaseMs": 0.001796,
      "workCycles": 29694,
      "averageActiveTiles": 11.022271714922049,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 294.0,
      "p50Cycles": 294,
      "p95Cycles": 294,
      "maximumCycles": 294,
      "firstOffset": 121974,
      "lastOffset": 132348
    }
  ],
  "samples": []
}
