{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 191887,
  "matchedSampleCount": 39519,
  "profileSpanCycles": 10996980,
  "profileSpanMs": 7.33132,
  "atOffset": null,
  "groups": [
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 7360,
      "tileCount": 1472,
      "phaseCount": 5,
      "phaseCycles": 81462,
      "phaseMs": 0.054308,
      "workCycles": 66177978,
      "averageActiveTiles": 812.3785077704943,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 8991.573097826087,
      "p50Cycles": 9408,
      "p95Cycles": 14688,
      "maximumCycles": 29376,
      "firstOffset": 111348,
      "lastOffset": 214698
    },
    {
      "name": "fill_zero_u64",
      "dimensions": {},
      "sampleCount": 15280,
      "tileCount": 1472,
      "phaseCount": 51,
      "phaseCycles": 27342,
      "phaseMs": 0.018228,
      "workCycles": 5594880,
      "averageActiveTiles": 204.62585034013605,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 3122496,
      "usefulUtilization": 0.0,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": 0.0,
      "meanCycles": 366.15706806282725,
      "p50Cycles": 306,
      "p95Cycles": 660,
      "maximumCycles": 756,
      "firstOffset": 111078,
      "lastOffset": 219816
    },
    {
      "name": "attention_softmax_d72_p768_tail_f16",
      "dimensions": {},
      "sampleCount": 1472,
      "tileCount": 1472,
      "phaseCount": 20,
      "phaseCycles": 25602,
      "phaseMs": 0.017068,
      "workCycles": 33833376,
      "averageActiveTiles": 1321.5130067963441,
      "usefulCycles": 15816384.0,
      "estimatedWorkCycles": 33833376,
      "usefulUtilization": 0.46747874051942084,
      "workLaneOccupancy": 0.9970588235294118,
      "deviceUsefulUtilization": 0.4196869809763504,
      "meanCycles": 22984.630434782608,
      "p50Cycles": 22986,
      "p95Cycles": 22986,
      "maximumCycles": 22986,
      "firstOffset": 156978,
      "lastOffset": 182580
    },
    {
      "name": "gemm_f16_init_small_rows_interleaved_k80_c80_r81_r81",
      "dimensions": {},
      "sampleCount": 864,
      "tileCount": 864,
      "phaseCount": 12,
      "phaseCycles": 19236,
      "phaseMs": 0.012824,
      "workCycles": 11062656,
      "averageActiveTiles": 575.101684341859,
      "usefulCycles": 6298560.0,
      "estimatedWorkCycles": 11062656,
      "usefulUtilization": 0.5693533270852859,
      "workLaneOccupancy": 0.9,
      "deviceUsefulUtilization": 0.2224429737720036,
      "meanCycles": 12804.0,
      "p50Cycles": 12804,
      "p95Cycles": 12804,
      "maximumCycles": 12804,
      "firstOffset": 131724,
      "lastOffset": 150960
    },
    {
      "name": "gemm_f16_init_small_rows_interleaved_k80_c64_r81_r81",
      "dimensions": {},
      "sampleCount": 576,
      "tileCount": 576,
      "phaseCount": 11,
      "phaseCycles": 17268,
      "phaseMs": 0.011512,
      "workCycles": 5944320,
      "averageActiveTiles": 344.23905489923555,
      "usefulCycles": 3267378.0,
      "estimatedWorkCycles": 5944320,
      "usefulUtilization": 0.5496638808139535,
      "workLaneOccupancy": 0.875390625,
      "deviceUsefulUtilization": 0.12854332530138685,
      "meanCycles": 10320.0,
      "p50Cycles": 10320,
      "p95Cycles": 10320,
      "maximumCycles": 10320,
      "firstOffset": 131118,
      "lastOffset": 148386
    },
    {
      "name": "gemm_f16_init_small_rows_interleaved_k112_c80_r56_r57",
      "dimensions": {},
      "sampleCount": 1344,
      "tileCount": 1344,
      "phaseCount": 20,
      "phaseCycles": 16872,
      "phaseMs": 0.011248,
      "workCycles": 19184256,
      "averageActiveTiles": 1137.0469416785206,
      "usefulCycles": 8817984.0,
      "estimatedWorkCycles": 19184256,
      "usefulUtilization": 0.45964691046658257,
      "workLaneOccupancy": 0.8368622448979591,
      "deviceUsefulUtilization": 0.3550544251345167,
      "meanCycles": 14274.0,
      "p50Cycles": 14274,
      "p95Cycles": 14274,
      "maximumCycles": 14274,
      "firstOffset": 194718,
      "lastOffset": 211590
    },
    {
      "name": "gemm_f16_init_large_rows_interleaved_k112_c80_r56_r57",
      "dimensions": {},
      "sampleCount": 112,
      "tileCount": 112,
      "phaseCount": 7,
      "phaseCycles": 15180,
      "phaseMs": 0.01012,
      "workCycles": 1608768,
      "averageActiveTiles": 105.97944664031621,
      "usefulCycles": 747954.0,
      "estimatedWorkCycles": 1608768,
      "usefulUtilization": 0.4649234693877551,
      "workLaneOccupancy": 0.8368622448979591,
      "deviceUsefulUtilization": 0.03347305164117546,
      "meanCycles": 14364.0,
      "p50Cycles": 14364,
      "p95Cycles": 14364,
      "maximumCycles": 14364,
      "firstOffset": 196572,
      "lastOffset": 211752
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 5231,
      "tileCount": 1472,
      "phaseCount": 47,
      "phaseCycles": 11730,
      "phaseMs": 0.00782,
      "workCycles": 4724598,
      "averageActiveTiles": 402.7790281329923,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 903.1921238768878,
      "p50Cycles": 1008,
      "p95Cycles": 1236,
      "maximumCycles": 1236,
      "firstOffset": 112668,
      "lastOffset": 220332
    },
    {
      "name": "copy_strided_u64",
      "dimensions": {},
      "sampleCount": 3176,
      "tileCount": 1472,
      "phaseCount": 41,
      "phaseCycles": 7842,
      "phaseMs": 0.005228,
      "workCycles": 2254656,
      "averageActiveTiles": 287.5103289977047,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 709.904282115869,
      "p50Cycles": 420,
      "p95Cycles": 1140,
      "maximumCycles": 1140,
      "firstOffset": 119544,
      "lastOffset": 220752
    },
    {
      "name": "attention_merge_v72_p80_k768_out16_f16",
      "dimensions": {},
      "sampleCount": 1472,
      "tileCount": 1472,
      "phaseCount": 27,
      "phaseCycles": 6066,
      "phaseMs": 0.004044,
      "workCycles": 4398336,
      "averageActiveTiles": 725.080118694362,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 2988.0,
      "p50Cycles": 2988,
      "p95Cycles": 2988,
      "maximumCycles": 2988,
      "firstOffset": 217674,
      "lastOffset": 223740
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o2_r64_p64_c16_p16_b64x16",
      "dimensions": {},
      "sampleCount": 880,
      "tileCount": 880,
      "phaseCount": 13,
      "phaseCycles": 4434,
      "phaseMs": 0.002956,
      "workCycles": 2143680,
      "averageActiveTiles": 483.4641407307172,
      "usefulCycles": 450560.0,
      "estimatedWorkCycles": 2143680,
      "usefulUtilization": 0.21018062397372742,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.06903178992371203,
      "meanCycles": 2436.0,
      "p50Cycles": 2436,
      "p95Cycles": 2436,
      "maximumCycles": 2436,
      "firstOffset": 118746,
      "lastOffset": 123180
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 1472,
      "tileCount": 1472,
      "phaseCount": 23,
      "phaseCycles": 3540,
      "phaseMs": 0.00236,
      "workCycles": 3272640,
      "averageActiveTiles": 924.4745762711865,
      "usefulCycles": 1278144.0,
      "estimatedWorkCycles": 3272640,
      "usefulUtilization": 0.39055441478439423,
      "workLaneOccupancy": 0.9131687242798354,
      "deviceUsefulUtilization": 0.2452837140751658,
      "meanCycles": 2223.2608695652175,
      "p50Cycles": 2220,
      "p95Cycles": 2406,
      "maximumCycles": 2406,
      "firstOffset": 214614,
      "lastOffset": 218154
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o2_r0_p64_c16_p16_b64x16",
      "dimensions": {},
      "sampleCount": 80,
      "tileCount": 80,
      "phaseCount": 8,
      "phaseCycles": 3306,
      "phaseMs": 0.002204,
      "workCycles": 157440,
      "averageActiveTiles": 47.62250453720508,
      "usefulCycles": 16000.0,
      "estimatedWorkCycles": 157440,
      "usefulUtilization": 0.1016260162601626,
      "workLaneOccupancy": 0.390625,
      "deviceUsefulUtilization": 0.0032878297693258634,
      "meanCycles": 1968.0,
      "p50Cycles": 1968,
      "p95Cycles": 1968,
      "maximumCycles": 1968,
      "firstOffset": 118800,
      "lastOffset": 122106
    },
    {
      "name": "static_copy_u32",
      "dimensions": {},
      "sampleCount": 200,
      "tileCount": 190,
      "phaseCount": 11,
      "phaseCycles": 1512,
      "phaseMs": 0.001008,
      "workCycles": 59250,
      "averageActiveTiles": 39.18650793650794,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 296.25,
      "p50Cycles": 294,
      "p95Cycles": 294,
      "maximumCycles": 492,
      "firstOffset": 119232,
      "lastOffset": 120744
    }
  ],
  "samples": []
}
