{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 187394,
  "matchedSampleCount": 8689,
  "profileSpanCycles": 10131456,
  "profileSpanMs": 6.754304,
  "atOffset": null,
  "groups": [
    {
      "name": "sync",
      "dimensions": {},
      "sampleCount": 28,
      "tileCount": 14,
      "phaseCount": 2,
      "phaseCycles": 60870,
      "phaseMs": 0.04058,
      "workCycles": 852120,
      "averageActiveTiles": 13.999014292755051,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 30432.85714285714,
      "p50Cycles": 18690,
      "p95Cycles": 42180,
      "maximumCycles": 42180,
      "firstOffset": 320658,
      "lastOffset": 381528
    },
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 2916,
      "tileCount": 1458,
      "phaseCount": 2,
      "phaseCycles": 33570,
      "phaseMs": 0.02238,
      "workCycles": 41721372,
      "averageActiveTiles": 1242.8171581769436,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 14307.74074074074,
      "p50Cycles": 14454,
      "p95Cycles": 17442,
      "maximumCycles": 17616,
      "firstOffset": 337398,
      "lastOffset": 395244
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k160_c128_r120_r122",
      "dimensions": {},
      "sampleCount": 1215,
      "tileCount": 1215,
      "phaseCount": 33,
      "phaseCycles": 28188,
      "phaseMs": 0.018792,
      "workCycles": 31871880,
      "averageActiveTiles": 1130.6896551724137,
      "usefulCycles": 23628960.0,
      "estimatedWorkCycles": 31871880,
      "usefulUtilization": 0.7413732732427456,
      "workLaneOccupancy": 0.9962962962962963,
      "deviceUsefulUtilization": 0.5694722083402743,
      "meanCycles": 26232.0,
      "p50Cycles": 26232,
      "p95Cycles": 26232,
      "maximumCycles": 26232,
      "firstOffset": 353076,
      "lastOffset": 381264
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k160_c128_r120_r122",
      "dimensions": {},
      "sampleCount": 243,
      "tileCount": 243,
      "phaseCount": 19,
      "phaseCycles": 26682,
      "phaseMs": 0.017788,
      "workCycles": 6349590,
      "averageActiveTiles": 237.9727906453789,
      "usefulCycles": 4609584.0,
      "estimatedWorkCycles": 6349590,
      "usefulUtilization": 0.7259656135278025,
      "workLaneOccupancy": 0.9879938271604938,
      "deviceUsefulUtilization": 0.11736417320910042,
      "meanCycles": 26130.0,
      "p50Cycles": 26130,
      "p95Cycles": 26130,
      "maximumCycles": 26130,
      "firstOffset": 354402,
      "lastOffset": 381084
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 1458,
      "tileCount": 1458,
      "phaseCount": 35,
      "phaseCycles": 12432,
      "phaseMs": 0.008288,
      "workCycles": 7262220,
      "averageActiveTiles": 584.1554054054054,
      "usefulCycles": 5458752.0,
      "estimatedWorkCycles": 7262220,
      "usefulUtilization": 0.7516643670943596,
      "workLaneOccupancy": 0.9986301369863013,
      "deviceUsefulUtilization": 0.2982940238375021,
      "meanCycles": 4980.9465020576135,
      "p50Cycles": 5580,
      "p95Cycles": 6144,
      "maximumCycles": 6894,
      "firstOffset": 389274,
      "lastOffset": 401706
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 152,
      "tileCount": 152,
      "phaseCount": 28,
      "phaseCycles": 6972,
      "phaseMs": 0.004648,
      "workCycles": 123678,
      "averageActiveTiles": 17.73924268502582,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 813.671052631579,
      "p50Cycles": 858,
      "p95Cycles": 924,
      "maximumCycles": 924,
      "firstOffset": 389106,
      "lastOffset": 396126
    },
    {
      "name": "cast_f16_f8",
      "dimensions": {},
      "sampleCount": 1458,
      "tileCount": 1458,
      "phaseCount": 35,
      "phaseCycles": 6018,
      "phaseMs": 0.004012,
      "workCycles": 8013168,
      "averageActiveTiles": 1331.5333998005983,
      "usefulCycles": 392202.0,
      "estimatedWorkCycles": 8013168,
      "usefulUtilization": 0.048944687045123725,
      "workLaneOccupancy": 0.9889705882352942,
      "deviceUsefulUtilization": 0.04427410702674585,
      "meanCycles": 5496.0,
      "p50Cycles": 5496,
      "p95Cycles": 5496,
      "maximumCycles": 5496,
      "firstOffset": 331902,
      "lastOffset": 337920
    },
    {
      "name": "fill_zero_u64",
      "dimensions": {},
      "sampleCount": 1215,
      "tileCount": 243,
      "phaseCount": 32,
      "phaseCycles": 1698,
      "phaseMs": 0.001132,
      "workCycles": 298890,
      "averageActiveTiles": 176.02473498233215,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 287820,
      "usefulUtilization": 0.0,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": 0.0,
      "meanCycles": 246.0,
      "p50Cycles": 246,
      "p95Cycles": 246,
      "maximumCycles": 246,
      "firstOffset": 337398,
      "lastOffset": 339096
    },
    {
      "name": "copy_strided_u64",
      "dimensions": {},
      "sampleCount": 4,
      "tileCount": 4,
      "phaseCount": 3,
      "phaseCycles": 1554,
      "phaseMs": 0.001036,
      "workCycles": 1920,
      "averageActiveTiles": 1.2355212355212355,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 480.0,
      "p50Cycles": 432,
      "p95Cycles": 432,
      "maximumCycles": 624,
      "firstOffset": 392256,
      "lastOffset": 394350
    }
  ],
  "samples": [
    {
      "physicalTile": 61,
      "offset": 339342,
      "duration": 42180,
      "phase": 2147483673,
      "epoch": 1,
      "kind": "synchronization",
      "operation": "operation.21",
      "kernel": "sync",
      "metadata": [
        {
          "name": "reason",
          "value": "ExchangeBarrier"
        },
        {
          "name": "value",
          "value": "427"
        },
        {
          "name": "invocations",
          "value": "1"
        }
      ]
    },
    {
      "physicalTile": 63,
      "offset": 339342,
      "duration": 42180,
      "phase": 2147483673,
      "epoch": 1,
      "kind": "synchronization",
      "operation": "operation.21",
      "kernel": "sync",
      "metadata": [
        {
          "name": "reason",
          "value": "ExchangeBarrier"
        },
        {
          "name": "value",
          "value": "427"
        },
        {
          "name": "invocations",
          "value": "1"
        }
      ]
    },
    {
      "physicalTile": 125,
      "offset": 339342,
      "duration": 42180,
      "phase": 2147483673,
      "epoch": 1,
      "kind": "synchronization",
      "operation": "operation.21",
      "kernel": "sync",
      "metadata": [
        {
          "name": "reason",
          "value": "ExchangeBarrier"
        },
        {
          "name": "value",
          "value": "427"
        },
        {
          "name": "invocations",
          "value": "1"
        }
      ]
    },
    {
      "physicalTile": 127,
      "offset": 339342,
      "duration": 42180,
      "phase": 2147483673,
      "epoch": 1,
      "kind": "synchronization",
      "operation": "operation.21",
      "kernel": "sync",
      "metadata": [
        {
          "name": "reason",
          "value": "ExchangeBarrier"
        },
        {
          "name": "value",
          "value": "427"
        },
        {
          "name": "invocations",
          "value": "1"
        }
      ]
    }
  ]
}
