{
  "clockHz": 1500000000,
  "tileCount": 1472,
  "sampleCount": 271781,
  "matchedSampleCount": 271781,
  "profileSpanCycles": 993132,
  "profileSpanMs": 0.662088,
  "atOffset": null,
  "groups": [
    {
      "name": "exchange",
      "dimensions": {},
      "sampleCount": 89335,
      "tileCount": 1472,
      "phaseCount": 73,
      "phaseCycles": 691458,
      "phaseMs": 0.460972,
      "workCycles": 641518488,
      "averageActiveTiles": 927.7765070329651,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 7181.043129792354,
      "p50Cycles": 6072,
      "p95Cycles": 18072,
      "maximumCycles": 45240,
      "firstOffset": 0,
      "lastOffset": 992178
    },
    {
      "name": "sync",
      "dimensions": {},
      "sampleCount": 18121,
      "tileCount": 1472,
      "phaseCount": 31,
      "phaseCycles": 226500,
      "phaseMs": 0.151,
      "workCycles": 110314002,
      "averageActiveTiles": 487.03753642384106,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 6087.633243198499,
      "p50Cycles": 2568,
      "p95Cycles": 19338,
      "maximumCycles": 48534,
      "firstOffset": 38268,
      "lastOffset": 991980
    },
    {
      "name": "copy_u64",
      "dimensions": {},
      "sampleCount": 41506,
      "tileCount": 1472,
      "phaseCount": 267,
      "phaseCycles": 127044,
      "phaseMs": 0.084696,
      "workCycles": 25285692,
      "averageActiveTiles": 199.03098139227353,
      "usefulCycles": 0.0,
      "estimatedWorkCycles": 0,
      "usefulUtilization": null,
      "workLaneOccupancy": null,
      "deviceUsefulUtilization": null,
      "meanCycles": 609.2057051992483,
      "p50Cycles": 534,
      "p95Cycles": 1326,
      "maximumCycles": 10578,
      "firstOffset": 0,
      "lastOffset": 991626
    },
    {
      "name": "cast_f16_f8",
      "dimensions": {},
      "sampleCount": 16673,
      "tileCount": 1472,
      "phaseCount": 228,
      "phaseCycles": 94740,
      "phaseMs": 0.06316,
      "workCycles": 90125862,
      "averageActiveTiles": 951.2968334388854,
      "usefulCycles": 22135032.0,
      "estimatedWorkCycles": 90125862,
      "usefulUtilization": 0.2456013347201051,
      "workLaneOccupancy": 0.9831485866487771,
      "deviceUsefulUtilization": 0.15872267120081504,
      "meanCycles": 5405.497630900258,
      "p50Cycles": 4818,
      "p95Cycles": 12606,
      "maximumCycles": 12630,
      "firstOffset": 7062,
      "lastOffset": 985218
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k288_c80_r30_r32",
      "dimensions": {},
      "sampleCount": 3840,
      "tileCount": 640,
      "phaseCount": 124,
      "phaseCycles": 94266,
      "phaseMs": 0.062844,
      "workCycles": 50987520,
      "averageActiveTiles": 540.8898224174145,
      "usefulCycles": 22118400.0,
      "estimatedWorkCycles": 50987520,
      "usefulUtilization": 0.43380027112516945,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.15940091821570598,
      "meanCycles": 13278.0,
      "p50Cycles": 13278,
      "p95Cycles": 13278,
      "maximumCycles": 13278,
      "firstOffset": 90192,
      "lastOffset": 847248
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k288_c80_r30_r32",
      "dimensions": {},
      "sampleCount": 576,
      "tileCount": 96,
      "phaseCount": 75,
      "phaseCycles": 87330,
      "phaseMs": 0.05822,
      "workCycles": 7572096,
      "averageActiveTiles": 86.70669872895913,
      "usefulCycles": 3075840.0,
      "estimatedWorkCycles": 7572096,
      "usefulUtilization": 0.4062072113190324,
      "workLaneOccupancy": 0.9888888888888889,
      "deviceUsefulUtilization": 0.023927232536256778,
      "meanCycles": 13146.0,
      "p50Cycles": 13146,
      "p95Cycles": 13146,
      "maximumCycles": 13146,
      "firstOffset": 90222,
      "lastOffset": 847080
    },
    {
      "name": "gemm_f8_init_large_rows_interleaved_k288_c64_r30_r32",
      "dimensions": {},
      "sampleCount": 3840,
      "tileCount": 640,
      "phaseCount": 107,
      "phaseCycles": 80442,
      "phaseMs": 0.053628,
      "workCycles": 41034240,
      "averageActiveTiles": 510.1096442157082,
      "usefulCycles": 17694720.0,
      "estimatedWorkCycles": 41034240,
      "usefulUtilization": 0.4312184166198765,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.14943523986496346,
      "meanCycles": 10686.0,
      "p50Cycles": 10686,
      "p95Cycles": 10686,
      "maximumCycles": 10686,
      "firstOffset": 89040,
      "lastOffset": 843654
    },
    {
      "name": "gemm_f8_init_small_rows_interleaved_k288_c64_r30_r32",
      "dimensions": {},
      "sampleCount": 576,
      "tileCount": 96,
      "phaseCount": 73,
      "phaseCycles": 77310,
      "phaseMs": 0.05154,
      "workCycles": 6089472,
      "averageActiveTiles": 78.76693830034924,
      "usefulCycles": 2460672.0,
      "estimatedWorkCycles": 6089472,
      "usefulUtilization": 0.40408626560726446,
      "workLaneOccupancy": 0.9888888888888889,
      "deviceUsefulUtilization": 0.02162271599939262,
      "meanCycles": 10572.0,
      "p50Cycles": 10572,
      "p95Cycles": 10572,
      "maximumCycles": 10572,
      "firstOffset": 89070,
      "lastOffset": 844434
    },
    {
      "name": "reduce_sum_f16",
      "dimensions": {},
      "sampleCount": 15189,
      "tileCount": 1472,
      "phaseCount": 229,
      "phaseCycles": 62562,
      "phaseMs": 0.041708,
      "workCycles": 33086358,
      "averageActiveTiles": 528.857101755059,
      "usefulCycles": 13053880.0,
      "estimatedWorkCycles": 33086358,
      "usefulUtilization": 0.3945396468236244,
      "workLaneOccupancy": 1.0,
      "deviceUsefulUtilization": 0.1417493846104664,
      "meanCycles": 2178.3104878530517,
      "p50Cycles": 1404,
      "p95Cycles": 4902,
      "maximumCycles": 6606,
      "firstOffset": 28632,
      "lastOffset": 991356
    },
    {
      "name": "rearrange_row_major_to_amp_f16_o2_r729_p768_c16_p16_b768x16",
      "dimensions": {},
      "sampleCount": 160,
      "tileCount": 80,
      "phaseCount": 40,
      "phaseCycles": 54294,
      "phaseMs": 0.036196,
      "workCycles": 3710400,
      "averageActiveTiles": 68.33904298817549,
      "usefulCycles": 933120.0,
      "estimatedWorkCycles": 3710400,
      "usefulUtilization": 0.2514877102199224,
      "workLaneOccupancy": 0.94921875,
      "deviceUsefulUtilization": 0.01167556347806868,
      "meanCycles": 23190.0,
      "p50Cycles": 23190,
      "p95Cycles": 23190,
      "maximumCycles": 23190,
      "firstOffset": 240876,
      "lastOffset": 915186
    }
  ],
  "samples": []
}
