{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 42335,
  "matchedSampleCount": 42171,
  "profileSpanCycles": 198426,
  "profileSpanMs": 0.132284,
  "atOffset": null,
  "groups": [
    {
      "name": "sync",
      "dimensions": {},
      "sampleCount": 63,
      "tileCount": 32,
      "phaseCount": 4,
      "phaseCycles": 134370,
      "phaseMs": 0.08958,
      "workCycles": 2305092,
      "averageActiveTiles": 17.15481134181737,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 36588.76190476191,
      "p50Cycles": 40374,
      "p95Cycles": 54360,
      "maximumCycles": 54366,
      "firstOffset": 13242,
      "lastOffset": 196914
    },
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 10241,
      "tileCount": 1472,
      "phaseCount": 7,
      "phaseCycles": 112110,
      "phaseMs": 0.07474,
      "workCycles": 99634254,
      "averageActiveTiles": 888.7187048434573,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 9728.957523679328,
      "p50Cycles": 8706,
      "p95Cycles": 16452,
      "maximumCycles": 29388,
      "firstOffset": 0,
      "lastOffset": 197844
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k160_c384_r41",
      "dimensions": {},
      "sampleCount": 729,
      "tileCount": 729,
      "phaseCount": 9,
      "phaseCycles": 38676,
      "phaseMs": 0.025784,
      "workCycles": 28111698,
      "averageActiveTiles": 726.8512255662426,
      "usefulCycles": 14293584.0,
      "estimatedWorkCycles": 28111698,
      "usefulUtilization": 0.5084567997279994,
      "workLaneOccupancy": 0.9962962962962963,
      "deviceUsefulUtilization": 0.2510682391506698,
      "meanCycles": 38562.0,
      "p50Cycles": 38562,
      "p95Cycles": 38562,
      "maximumCycles": 38562,
      "firstOffset": 130794,
      "lastOffset": 169470
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k160_c384_r40",
      "dimensions": {},
      "sampleCount": 729,
      "tileCount": 729,
      "phaseCount": 13,
      "phaseCycles": 38634,
      "phaseMs": 0.025756,
      "workCycles": 28107324,
      "averageActiveTiles": 727.5281876067712,
      "usefulCycles": 13944960.0,
      "estimatedWorkCycles": 28107324,
      "usefulUtilization": 0.49613260942236975,
      "workLaneOccupancy": 0.9962962962962963,
      "deviceUsefulUtilization": 0.24521090906635515,
      "meanCycles": 38556.0,
      "p50Cycles": 38556,
      "p95Cycles": 38556,
      "maximumCycles": 38556,
      "firstOffset": 130854,
      "lastOffset": 169488
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k192_c64_r214",
      "dimensions": {},
      "sampleCount": 576,
      "tileCount": 576,
      "phaseCount": 4,
      "phaseCycles": 34212,
      "phaseMs": 0.022808,
      "workCycles": 14231808,
      "averageActiveTiles": 415.9887758681165,
      "usefulCycles": 11232432.0,
      "estimatedWorkCycles": 14231808,
      "usefulUtilization": 0.789248421563866,
      "workLaneOccupancy": 0.94921875,
      "deviceUsefulUtilization": 0.22304244887377428,
      "meanCycles": 24708.0,
      "p50Cycles": 24708,
      "p95Cycles": 24708,
      "maximumCycles": 24708,
      "firstOffset": 19086,
      "lastOffset": 53298
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k192_c64_r216",
      "dimensions": {},
      "sampleCount": 864,
      "tileCount": 864,
      "phaseCount": 3,
      "phaseCycles": 32586,
      "phaseMs": 0.021724,
      "workCycles": 21622464,
      "averageActiveTiles": 663.5507273062051,
      "usefulCycles": 17006112.0,
      "estimatedWorkCycles": 21622464,
      "usefulUtilization": 0.7865020378806041,
      "workLaneOccupancy": 0.94921875,
      "deviceUsefulUtilization": 0.354540760369217,
      "meanCycles": 25026.0,
      "p50Cycles": 25026,
      "p95Cycles": 25026,
      "maximumCycles": 25026,
      "firstOffset": 21030,
      "lastOffset": 53616
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 2898,
      "tileCount": 1458,
      "phaseCount": 18,
      "phaseCycles": 28194,
      "phaseMs": 0.018796,
      "workCycles": 28874340,
      "averageActiveTiles": 1024.13066609917,
      "usefulCycles": 9380772.0,
      "estimatedWorkCycles": 28874340,
      "usefulUtilization": 0.3248826466682875,
      "workLaneOccupancy": 0.9960014575674592,
      "deviceUsefulUtilization": 0.22603415851661315,
      "meanCycles": 9963.540372670808,
      "p50Cycles": 13794,
      "p95Cycles": 13794,
      "maximumCycles": 13794,
      "firstOffset": 59550,
      "lastOffset": 196680
    },
    {
      "name": "copy_strided_u64",
      "dimensions": {},
      "sampleCount": 13942,
      "tileCount": 1458,
      "phaseCount": 33,
      "phaseCycles": 19854,
      "phaseMs": 0.013236,
      "workCycles": 16411956,
      "averageActiveTiles": 826.6322151707465,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 1177.1593745517143,
      "p50Cycles": 546,
      "p95Cycles": 2358,
      "maximumCycles": 2358,
      "firstOffset": 13512,
      "lastOffset": 198426
    },
    {
      "name": "gelu_tanh_approx_f16",
      "dimensions": {},
      "sampleCount": 1472,
      "tileCount": 1472,
      "phaseCount": 8,
      "phaseCycles": 13596,
      "phaseMs": 0.009064,
      "workCycles": 16898664,
      "averageActiveTiles": 1242.9143865842896,
      "usefulCycles": 9412848.0,
      "estimatedWorkCycles": 16898664,
      "usefulUtilization": 0.5570172884673014,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.4703293487854484,
      "meanCycles": 11480.070652173914,
      "p50Cycles": 11370,
      "p95Cycles": 11874,
      "maximumCycles": 12354,
      "firstOffset": 82548,
      "lastOffset": 96144
    },
    {
      "name": "unpack_amp_to_row_major_f16_o1_r64_p64_c36_p36",
      "dimensions": {},
      "sampleCount": 1120,
      "tileCount": 1120,
      "phaseCount": 2,
      "phaseCycles": 11940,
      "phaseMs": 0.00796,
      "workCycles": 11854080,
      "averageActiveTiles": 992.8040201005025,
      "usefulCycles": 1290240.0,
      "estimatedWorkCycles": 11854080,
      "usefulUtilization": 0.10884353741496598,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.0734105309154468,
      "meanCycles": 10584.0,
      "p50Cycles": 10584,
      "p95Cycles": 10584,
      "maximumCycles": 10584,
      "firstOffset": 68022,
      "lastOffset": 79962
    },
    {
      "name": "unpack_amp_to_row_major_f16_o1_r41_p48_c36_p36",
      "dimensions": {},
      "sampleCount": 112,
      "tileCount": 112,
      "phaseCount": 1,
      "phaseCycles": 11430,
      "phaseMs": 0.00762,
      "workCycles": 1101408,
      "averageActiveTiles": 96.36115485564305,
      "usefulCycles": 82656.0,
      "estimatedWorkCycles": 1101408,
      "usefulUtilization": 0.075045759609518,
      "workLaneOccupancy": 0.8541666666666666,
      "deviceUsefulUtilization": 0.004912701129750086,
      "meanCycles": 9834.0,
      "p50Cycles": 9834,
      "p95Cycles": 9834,
      "maximumCycles": 9834,
      "firstOffset": 64392,
      "lastOffset": 75822
    },
    {
      "name": "unpack_amp_to_row_major_f16_o1_r64_p64_c34_p34",
      "dimensions": {},
      "sampleCount": 80,
      "tileCount": 80,
      "phaseCount": 1,
      "phaseCycles": 10704,
      "phaseMs": 0.007136,
      "workCycles": 803520,
      "averageActiveTiles": 75.06726457399103,
      "usefulCycles": 87040.0,
      "estimatedWorkCycles": 803520,
      "usefulUtilization": 0.10832337714058145,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.005524143757717554,
      "meanCycles": 10044.0,
      "p50Cycles": 10044,
      "p95Cycles": 10044,
      "maximumCycles": 10044,
      "firstOffset": 67746,
      "lastOffset": 78450
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 6247,
      "tileCount": 1449,
      "phaseCount": 23,
      "phaseCycles": 10572,
      "phaseMs": 0.007048,
      "workCycles": 3839298,
      "averageActiveTiles": 363.1572077185017,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 614.5826796862494,
      "p50Cycles": 270,
      "p95Cycles": 1866,
      "maximumCycles": 1866,
      "firstOffset": 0,
      "lastOffset": 96348
    },
    {
      "name": "unpack_amp_to_row_major_f16_o1_r41_p48_c34_p34",
      "dimensions": {},
      "sampleCount": 8,
      "tileCount": 8,
      "phaseCount": 2,
      "phaseCycles": 9648,
      "phaseMs": 0.006432,
      "workCycles": 74592,
      "averageActiveTiles": 7.731343283582089,
      "usefulCycles": 5576.0,
      "estimatedWorkCycles": 74592,
      "usefulUtilization": 0.07475332475332476,
      "workLaneOccupancy": 0.8541666666666666,
      "deviceUsefulUtilization": 0.000392624738625712,
      "meanCycles": 9324.0,
      "p50Cycles": 9324,
      "p95Cycles": 9324,
      "maximumCycles": 9324,
      "firstOffset": 65232,
      "lastOffset": 74880
    },
    {
      "name": "unpack_amp_to_row_major_f16_o1_r48_p48_c36_p36",
      "dimensions": {},
      "sampleCount": 112,
      "tileCount": 112,
      "phaseCount": 2,
      "phaseCycles": 7842,
      "phaseMs": 0.005228,
      "workCycles": 799680,
      "averageActiveTiles": 101.97398622800306,
      "usefulCycles": 96768.0,
      "estimatedWorkCycles": 799680,
      "usefulUtilization": 0.12100840336134454,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.008382954658860317,
      "meanCycles": 7140.0,
      "p50Cycles": 7140,
      "p95Cycles": 7140,
      "maximumCycles": 7140,
      "firstOffset": 66180,
      "lastOffset": 74022
    },
    {
      "name": "unpack_amp_to_row_major_f16_o1_r48_p48_c34_p34",
      "dimensions": {},
      "sampleCount": 8,
      "tileCount": 8,
      "phaseCount": 2,
      "phaseCycles": 7080,
      "phaseMs": 0.00472,
      "workCycles": 54240,
      "averageActiveTiles": 7.661016949152542,
      "usefulCycles": 6528.0,
      "estimatedWorkCycles": 54240,
      "usefulUtilization": 0.12035398230088495,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.0006263817243920412,
      "meanCycles": 6780.0,
      "p50Cycles": 6780,
      "p95Cycles": 6780,
      "maximumCycles": 6780,
      "firstOffset": 65904,
      "lastOffset": 72984
    },
    {
      "name": "cast_f16_f8",
      "dimensions": {},
      "sampleCount": 1458,
      "tileCount": 1458,
      "phaseCount": 13,
      "phaseCycles": 6498,
      "phaseMs": 0.004332,
      "workCycles": 7741980,
      "averageActiveTiles": 1191.4404432132965,
      "usefulCycles": 1176606.0,
      "estimatedWorkCycles": 7741980,
      "usefulUtilization": 0.1519774011299435,
      "workLaneOccupancy": 0.9962962962962963,
      "deviceUsefulUtilization": 0.12301088462001686,
      "meanCycles": 5310.0,
      "p50Cycles": 5310,
      "p95Cycles": 5310,
      "maximumCycles": 5310,
      "firstOffset": 108660,
      "lastOffset": 115158
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r41_p41_c144_p160",
      "dimensions": {},
      "sampleCount": 27,
      "tileCount": 27,
      "phaseCount": 5,
      "phaseCycles": 6444,
      "phaseMs": 0.004296,
      "workCycles": 160542,
      "averageActiveTiles": 24.91340782122905,
      "usefulCycles": 79704.0,
      "estimatedWorkCycles": 160542,
      "usefulUtilization": 0.496468213925328,
      "workLaneOccupancy": 0.9,
      "deviceUsefulUtilization": 0.00840265970366772,
      "meanCycles": 5946.0,
      "p50Cycles": 5946,
      "p95Cycles": 5946,
      "maximumCycles": 5946,
      "firstOffset": 103404,
      "lastOffset": 109848
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r40_p40_c144_p160",
      "dimensions": {},
      "sampleCount": 27,
      "tileCount": 27,
      "phaseCount": 7,
      "phaseCycles": 6414,
      "phaseMs": 0.004276,
      "workCycles": 160542,
      "averageActiveTiles": 25.029934518241348,
      "usefulCycles": 77760.0,
      "estimatedWorkCycles": 160542,
      "usefulUtilization": 0.4843592330978809,
      "workLaneOccupancy": 0.9,
      "deviceUsefulUtilization": 0.008236059706348884,
      "meanCycles": 5946.0,
      "p50Cycles": 5946,
      "p95Cycles": 5946,
      "maximumCycles": 5946,
      "firstOffset": 103224,
      "lastOffset": 109638
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r40_p40_c160_p160",
      "dimensions": {},
      "sampleCount": 702,
      "tileCount": 702,
      "phaseCount": 13,
      "phaseCycles": 6378,
      "phaseMs": 0.004252,
      "workCycles": 3879252,
      "averageActiveTiles": 608.2238946378175,
      "usefulCycles": 2246400.0,
      "estimatedWorkCycles": 3879252,
      "usefulUtilization": 0.579080709373869,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.2392735899218782,
      "meanCycles": 5526.0,
      "p50Cycles": 5526,
      "p95Cycles": 5526,
      "maximumCycles": 5526,
      "firstOffset": 103134,
      "lastOffset": 109512
    }
  ],
  "samples": []
}
