{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 69894,
  "matchedSampleCount": 68427,
  "profileSpanCycles": 820914,
  "profileSpanMs": 0.547276,
  "atOffset": null,
  "groups": [
    {
      "name": "sync",
      "dimensions": {},
      "sampleCount": 120,
      "tileCount": 42,
      "phaseCount": 4,
      "phaseCycles": 686868,
      "phaseMs": 0.457912,
      "workCycles": 23830464,
      "averageActiveTiles": 34.694386694386694,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 198587.2,
      "p50Cycles": 269004,
      "p95Cycles": 281490,
      "maximumCycles": 281490,
      "firstOffset": 17100,
      "lastOffset": 817746
    },
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 10184,
      "tileCount": 1472,
      "phaseCount": 7,
      "phaseCycles": 309228,
      "phaseMs": 0.206152,
      "workCycles": 260708562,
      "averageActiveTiles": 843.094939656176,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 25599.819520816967,
      "p50Cycles": 18678,
      "p95Cycles": 58848,
      "maximumCycles": 108546,
      "firstOffset": 0,
      "lastOffset": 820008
    },
    {
      "name": "gemm_f8_accumulate_rows_interleaved_k32_c16_r66",
      "dimensions": {},
      "sampleCount": 15600,
      "tileCount": 1040,
      "phaseCount": 303,
      "phaseCycles": 270066,
      "phaseMs": 0.180044,
      "workCycles": 244483200,
      "averageActiveTiles": 905.2720446113173,
      "usefulCycles": 73903104.0,
      "estimatedWorkCycles": 244483200,
      "usefulUtilization": 0.3022829544115915,
      "workLaneOccupancy": 0.8972307692307693,
      "deviceUsefulUtilization": 0.18590238328215422,
      "meanCycles": 15672.0,
      "p50Cycles": 15672,
      "p95Cycles": 15672,
      "maximumCycles": 15672,
      "firstOffset": 503208,
      "lastOffset": 773274
    },
    {
      "name": "gemm_f8_accumulate_rows_interleaved_k32_c16_r67",
      "dimensions": {},
      "sampleCount": 5850,
      "tileCount": 390,
      "phaseCount": 301,
      "phaseCycles": 266202,
      "phaseMs": 0.177468,
      "workCycles": 91821600,
      "averageActiveTiles": 344.9320440868213,
      "usefulCycles": 28133568.0,
      "estimatedWorkCycles": 91821600,
      "usefulUtilization": 0.30639378969654196,
      "workLaneOccupancy": 0.8972307692307693,
      "deviceUsefulUtilization": 0.07179689957577165,
      "meanCycles": 15696.0,
      "p50Cycles": 15696,
      "p95Cycles": 15696,
      "maximumCycles": 15696,
      "firstOffset": 507522,
      "lastOffset": 773724
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k32_c16_r66",
      "dimensions": {},
      "sampleCount": 15600,
      "tileCount": 1040,
      "phaseCount": 303,
      "phaseCycles": 210060,
      "phaseMs": 0.14004,
      "workCycles": 25178400,
      "averageActiveTiles": 119.86289631533847,
      "usefulCycles": 7907328.0,
      "estimatedWorkCycles": 25178400,
      "usefulUtilization": 0.3140520446096654,
      "workLaneOccupancy": 0.96,
      "deviceUsefulUtilization": 0.02557281770425841,
      "meanCycles": 1614.0,
      "p50Cycles": 1614,
      "p95Cycles": 1614,
      "maximumCycles": 1614,
      "firstOffset": 501594,
      "lastOffset": 757602
    },
    {
      "name": "rearrange_row_major_to_amp_f8_o0_r121_p121_c384_p384",
      "dimensions": {},
      "sampleCount": 720,
      "tileCount": 720,
      "phaseCount": 5,
      "phaseCycles": 153528,
      "phaseMs": 0.102352,
      "workCycles": 96716160,
      "averageActiveTiles": 629.9577927153354,
      "usefulCycles": 8363520.0,
      "estimatedWorkCycles": 96716160,
      "usefulUtilization": 0.08647489726639271,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.03700783655381939,
      "meanCycles": 134328.0,
      "p50Cycles": 134328,
      "p95Cycles": 134328,
      "maximumCycles": 134328,
      "firstOffset": 24978,
      "lastOffset": 178506
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k32_c16_r67",
      "dimensions": {},
      "sampleCount": 5850,
      "tileCount": 390,
      "phaseCount": 301,
      "phaseCycles": 145530,
      "phaseMs": 0.09702,
      "workCycles": 9477000,
      "averageActiveTiles": 65.12059369202227,
      "usefulCycles": 3010176.0,
      "estimatedWorkCycles": 9477000,
      "usefulUtilization": 0.31762962962962965,
      "workLaneOccupancy": 0.96,
      "deviceUsefulUtilization": 0.014051786722594176,
      "meanCycles": 1620.0,
      "p50Cycles": 1620,
      "p95Cycles": 1620,
      "maximumCycles": 1620,
      "firstOffset": 505902,
      "lastOffset": 758028
    },
    {
      "name": "rearrange_row_major_to_amp_f8_o0_r122_p122_c384_p384",
      "dimensions": {},
      "sampleCount": 720,
      "tileCount": 720,
      "phaseCount": 5,
      "phaseCycles": 136614,
      "phaseMs": 0.091076,
      "workCycles": 96716160,
      "averageActiveTiles": 707.95204005446,
      "usefulCycles": 8432640.0,
      "estimatedWorkCycles": 96716160,
      "usefulUtilization": 0.08718956583884224,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.04193344497762977,
      "meanCycles": 134328.0,
      "p50Cycles": 134328,
      "p95Cycles": 134328,
      "maximumCycles": 134328,
      "firstOffset": 41694,
      "lastOffset": 178308
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k384_c224_r121",
      "dimensions": {},
      "sampleCount": 720,
      "tileCount": 720,
      "phaseCount": 5,
      "phaseCycles": 127212,
      "phaseMs": 0.084808,
      "workCycles": 77768640,
      "averageActiveTiles": 611.3310065088199,
      "usefulCycles": 56244672.0,
      "estimatedWorkCycles": 77768640,
      "usefulUtilization": 0.7232307521386513,
      "workLaneOccupancy": 0.9607142857142857,
      "deviceUsefulUtilization": 0.3003623530183781,
      "meanCycles": 108012.0,
      "p50Cycles": 108012,
      "p95Cycles": 108012,
      "maximumCycles": 108012,
      "firstOffset": 159306,
      "lastOffset": 286518
    },
    {
      "name": "gemm_f8_init_rows_interleaved_k384_c224_r122",
      "dimensions": {},
      "sampleCount": 720,
      "tileCount": 720,
      "phaseCount": 5,
      "phaseCycles": 110502,
      "phaseMs": 0.073668,
      "workCycles": 77915520,
      "averageActiveTiles": 705.1050659716566,
      "usefulCycles": 56709504.0,
      "estimatedWorkCycles": 77915520,
      "usefulUtilization": 0.7278332224440008,
      "workLaneOccupancy": 0.9607142857142857,
      "deviceUsefulUtilization": 0.3486405518530847,
      "meanCycles": 108216.0,
      "p50Cycles": 108216,
      "p95Cycles": 108216,
      "maximumCycles": 108216,
      "firstOffset": 176022,
      "lastOffset": 286524
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r67_p67_c80_p352",
      "dimensions": {},
      "sampleCount": 30,
      "tileCount": 30,
      "phaseCount": 6,
      "phaseCycles": 60264,
      "phaseMs": 0.040176,
      "workCycles": 1790280,
      "averageActiveTiles": 29.707287933094385,
      "usefulCycles": 160800.0,
      "estimatedWorkCycles": 1790280,
      "usefulUtilization": 0.08981835243649038,
      "workLaneOccupancy": 0.22727272727272727,
      "deviceUsefulUtilization": 0.0018126763977628867,
      "meanCycles": 59676.0,
      "p50Cycles": 59676,
      "p95Cycles": 59676,
      "maximumCycles": 59676,
      "firstOffset": 401208,
      "lastOffset": 461472
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r66_p66_c80_p352",
      "dimensions": {},
      "sampleCount": 80,
      "tileCount": 80,
      "phaseCount": 8,
      "phaseCycles": 56004,
      "phaseMs": 0.037336,
      "workCycles": 4379040,
      "averageActiveTiles": 78.1915577458753,
      "usefulCycles": 422400.0,
      "estimatedWorkCycles": 4379040,
      "usefulUtilization": 0.09645949797215828,
      "workLaneOccupancy": 0.22727272727272727,
      "deviceUsefulUtilization": 0.005123857612654997,
      "meanCycles": 54738.0,
      "p50Cycles": 54738,
      "p95Cycles": 54738,
      "maximumCycles": 54738,
      "firstOffset": 400638,
      "lastOffset": 456642
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 2870,
      "tileCount": 1440,
      "phaseCount": 44,
      "phaseCycles": 54654,
      "phaseMs": 0.036436,
      "workCycles": 46641996,
      "averageActiveTiles": 853.4049840816774,
      "usefulCycles": 16352928.0,
      "estimatedWorkCycles": 46641996,
      "usefulUtilization": 0.3506052356764492,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.20326647796970984,
      "meanCycles": 16251.566550522648,
      "p50Cycles": 15642,
      "p95Cycles": 19524,
      "maximumCycles": 19524,
      "firstOffset": 299070,
      "lastOffset": 817500
    },
    {
      "name": "cast_f16_f8",
      "dimensions": {},
      "sampleCount": 1430,
      "tileCount": 1430,
      "phaseCount": 13,
      "phaseCycles": 45714,
      "phaseMs": 0.030476,
      "workCycles": 27563670,
      "averageActiveTiles": 602.9590497440608,
      "usefulCycles": 7844040.0,
      "estimatedWorkCycles": 27563670,
      "usefulUtilization": 0.2845789403225332,
      "workLaneOccupancy": 0.9405594405594405,
      "deviceUsefulUtilization": 0.11656891809378156,
      "meanCycles": 19275.293706293705,
      "p50Cycles": 19134,
      "p95Cycles": 19662,
      "maximumCycles": 19662,
      "firstOffset": 435420,
      "lastOffset": 481134
    },
    {
      "name": "gelu_tanh_approx_f16",
      "dimensions": {},
      "sampleCount": 1472,
      "tileCount": 1472,
      "phaseCount": 11,
      "phaseCycles": 45606,
      "phaseMs": 0.030404,
      "workCycles": 62806074,
      "averageActiveTiles": 1377.1449809235628,
      "usefulCycles": 37651392.0,
      "estimatedWorkCycles": 62806074,
      "usefulUtilization": 0.5994864764194622,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.5608558370466129,
      "meanCycles": 42667.16983695652,
      "p50Cycles": 42390,
      "p95Cycles": 43254,
      "maximumCycles": 43782,
      "firstOffset": 331812,
      "lastOffset": 377418
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r67_p67_c352_p352",
      "dimensions": {},
      "sampleCount": 360,
      "tileCount": 360,
      "phaseCount": 13,
      "phaseCycles": 38124,
      "phaseMs": 0.025416,
      "workCycles": 13500000,
      "averageActiveTiles": 354.10764872521247,
      "usefulCycles": 8490240.0,
      "estimatedWorkCycles": 13500000,
      "usefulUtilization": 0.6289066666666666,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.15129120991911976,
      "meanCycles": 37500.0,
      "p50Cycles": 37500,
      "p95Cycles": 37500,
      "maximumCycles": 37500,
      "firstOffset": 401358,
      "lastOffset": 439482
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o0_r66_p66_c352_p352",
      "dimensions": {},
      "sampleCount": 960,
      "tileCount": 960,
      "phaseCount": 11,
      "phaseCycles": 35124,
      "phaseMs": 0.023416,
      "workCycles": 33033600,
      "averageActiveTiles": 940.4851383669286,
      "usefulCycles": 22302720.0,
      "estimatedWorkCycles": 33033600,
      "usefulUtilization": 0.6751525719267655,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.43136614132291556,
      "meanCycles": 34410.0,
      "p50Cycles": 34410,
      "p95Cycles": 34410,
      "maximumCycles": 34410,
      "firstOffset": 401010,
      "lastOffset": 436134
    },
    {
      "name": "fill_zero_u64",
      "dimensions": {},
      "sampleCount": 1920,
      "tileCount": 375,
      "phaseCount": 25,
      "phaseCycles": 32448,
      "phaseMs": 0.021632,
      "workCycles": 2243430,
      "averageActiveTiles": 69.13923816568047,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 619344,
      "usefulUtilization": 0.0,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": 0.0,
      "meanCycles": 1168.453125,
      "p50Cycles": 750,
      "p95Cycles": 2346,
      "maximumCycles": 8628,
      "firstOffset": 0,
      "lastOffset": 492270
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 566,
      "tileCount": 384,
      "phaseCount": 18,
      "phaseCycles": 21270,
      "phaseMs": 0.01418,
      "workCycles": 700164,
      "averageActiveTiles": 32.917912552891394,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 1237.0388692579506,
      "p50Cycles": 342,
      "p95Cycles": 4650,
      "maximumCycles": 5130,
      "firstOffset": 0,
      "lastOffset": 377256
    },
    {
      "name": "copy_strided_u64",
      "dimensions": {},
      "sampleCount": 2471,
      "tileCount": 1412,
      "phaseCount": 31,
      "phaseCycles": 16656,
      "phaseMs": 0.011104,
      "workCycles": 9134970,
      "averageActiveTiles": 548.4492074927954,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 3696.8717118575473,
      "p50Cycles": 4056,
      "p95Cycles": 7206,
      "maximumCycles": 7926,
      "firstOffset": 331920,
      "lastOffset": 820914
    }
  ],
  "samples": []
}
