{
 "returncode": 0,
 "stdout": "ladder_d3.py:custom_kernel at 2.70% error: 15 timed calls, each in a fresh process\n  review flag: 18,670 bytes, close to the 20,480-byte limit\n  NVIDIA A100-SXM4-80GB, torch 2.12.0+cu130, sandbox on\n  call  1/15: 1,731.575 ms, scorer's clock 1,736.057 ms\n  call  2/15: 1,732.105 ms, scorer's clock 1,735.813 ms\n  call  3/15: 1,731.940 ms, scorer's clock 1,735.748 ms\n  call  4/15: 1,731.569 ms, scorer's clock 1,734.783 ms\n  call  5/15: 1,731.710 ms, scorer's clock 1,735.846 ms\n  call  6/15: 1,732.441 ms, scorer's clock 1,736.820 ms\n  call  7/15: 1,732.035 ms, scorer's clock 1,736.162 ms\n  call  8/15: 1,732.184 ms, scorer's clock 1,735.580 ms\n  call  9/15: 1,732.423 ms, scorer's clock 1,736.081 ms\n  call 10/15: 1,732.236 ms, scorer's clock 1,736.455 ms\n  call 11/15: 1,732.038 ms, scorer's clock 1,735.838 ms\n  call 12/15: 1,732.336 ms, scorer's clock 1,735.670 ms\n  call 13/15: 1,733.401 ms, scorer's clock 1,736.690 ms\n  call 14/15: 1,732.667 ms, scorer's clock 1,736.253 ms\n  call 15/15: 1,731.638 ms, scorer's clock 1,735.360 ms\nMNIST 97.42% (107,164/110,000), 1732.218 ms/call; hold-out (kmnist) 96.14%, 1731.974 ms/call; score 1732.218 ms\nenergy: one more fresh process runs the method back to back on fresh MNIST draws for 20 s, between idle windows in which it is frozen\n  NVIDIA A100-SXM4-80GB: idle 69.7 W with the method frozen; telemetry reference 18.1 TFLOP/s at 8.34 J/TFLOP above idle (a healthy NVIDIA A100-SXM4-80GB reads 6-11)\n  the round trip alone: 13.8 mJ per call over 2,027 empty calls, subtracted\n  the method: 12 calls in 20.9 s, MNIST 97.38%, 1,730.319 ms per call, 215.7 W on average\nenergy 253760.696 mJ per call above idle\n",
 "stderr": "",
 "record": {
  "version": "mnist-a100/1.2.0 (protections of sutro-mnist-medium/3.0.0, tightened; energy column)",
  "file": "ladder_d3.py",
  "function": "custom_kernel",
  "source_sha256": "d3d8da2d2b0420ab69848943107bfea2a11b5c725956a5c726879707f854c07c",
  "band_bp": 270,
  "sandboxed": true,
  "holdout": "kmnist",
  "device": "NVIDIA A100-SXM4-80GB",
  "torch": "2.12.0+cu130",
  "calls": [
   {
    "dataset": "mnist",
    "ms": 1731.5748291015625,
    "parent_ms": 1738.5044809999997,
    "correct": 9745,
    "total": 10000,
    "overhead_ms": 2.4470269995160407
   },
   {
    "dataset": "kmnist",
    "ms": 1732.105224609375,
    "parent_ms": 1739.0082370000002,
    "correct": 9595,
    "total": 10000,
    "overhead_ms": 3.1948840013808137
   },
   {
    "dataset": "mnist",
    "ms": 1731.9403076171875,
    "parent_ms": 1738.8296780000019,
    "correct": 9740,
    "total": 10000,
    "overhead_ms": 3.082125498608292
   },
   {
    "dataset": "kmnist",
    "ms": 1731.568603515625,
    "parent_ms": 1737.6629870000074,
    "correct": 9591,
    "total": 10000,
    "overhead_ms": 2.87953999799862
   },
   {
    "dataset": "mnist",
    "ms": 1731.7099609375,
    "parent_ms": 1738.5420760000015,
    "correct": 9791,
    "total": 10000,
    "overhead_ms": 2.6957290002559944
   },
   {
    "dataset": "mnist",
    "ms": 1732.4410400390625,
    "parent_ms": 1739.4043629999915,
    "correct": 9742,
    "total": 10000,
    "overhead_ms": 2.584640000389072
   },
   {
    "dataset": "mnist",
    "ms": 1732.0345458984375,
    "parent_ms": 1739.1877919999956,
    "correct": 9720,
    "total": 10000,
    "overhead_ms": 3.025740501461428
   },
   {
    "dataset": "kmnist",
    "ms": 1732.18408203125,
    "parent_ms": 1738.617067000007,
    "correct": 9646,
    "total": 10000,
    "overhead_ms": 3.036836000339804
   },
   {
    "dataset": "mnist",
    "ms": 1732.422607421875,
    "parent_ms": 1739.1316789999962,
    "correct": 9741,
    "total": 10000,
    "overhead_ms": 3.0502519970430058
   },
   {
    "dataset": "mnist",
    "ms": 1732.236328125,
    "parent_ms": 1739.576946999989,
    "correct": 9766,
    "total": 10000,
    "overhead_ms": 3.1214955008177867
   },
   {
    "dataset": "kmnist",
    "ms": 1732.03759765625,
    "parent_ms": 1738.3806199999867,
    "correct": 9624,
    "total": 10000,
    "overhead_ms": 2.542153003277349
   },
   {
    "dataset": "mnist",
    "ms": 1732.3355712890625,
    "parent_ms": 1738.7962829999992,
    "correct": 9728,
    "total": 10000,
    "overhead_ms": 3.1266930007072915
   },
   {
    "dataset": "mnist",
    "ms": 1733.400634765625,
    "parent_ms": 1739.3977280000001,
    "correct": 9739,
    "total": 10000,
    "overhead_ms": 2.7074824982497603
   },
   {
    "dataset": "mnist",
    "ms": 1732.6673583984375,
    "parent_ms": 1738.846701,
    "correct": 9741,
    "total": 10000,
    "overhead_ms": 2.5935219990033147
   },
   {
    "dataset": "mnist",
    "ms": 1731.6383056640625,
    "parent_ms": 1738.6076759999582,
    "correct": 9711,
    "total": 10000,
    "overhead_ms": 3.2479295011926297
   }
  ],
  "problems": [],
  "summary": "MNIST 97.42% (107,164/110,000), 1732.218 ms/call; hold-out (kmnist) 96.14%, 1731.974 ms/call",
  "ranked_ms": 1732.2183172052557,
  "energy": {
   "mj_per_call": 253760.69596170913,
   "problems": [],
   "net_mj_before_control": 253774.52628680787,
   "control_mj_per_call": 13.830325098734429,
   "control_calls": 2027,
   "gross_mj_per_call": 374899.1666666667,
   "idle_w": 69.70551301943215,
   "active_w": 215.74915443384089,
   "calls": 12,
   "seconds": 20.85194730799998,
   "ms_median": 1730.3193969726562,
   "timed_mnist_ms_median": 1732.236328125,
   "correct": 116861,
   "total": 120000,
   "reference": {
    "tflops_per_s": 18.10927742550259,
    "j_per_tflop": 8.338004411437991,
    "exact": true,
    "band": [
     [
      6.0,
      11.0
     ],
     [
      15.0,
      23.0
     ]
    ]
   },
   "device": {
    "name": "NVIDIA A100-SXM4-80GB",
    "uuid": "GPU-4ab75fd5-3e25-4989-d6ac-320cdb054731",
    "vbios": "92.00.9E.00.01",
    "driver": "580.95.05",
    "power_limit_w": 400.0
   },
   "windows": [
    {
     "name": "idle 1",
     "seconds": 5.01183594500003,
     "joules": 340.808,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "reference",
     "seconds": 5.221522525000012,
     "joules": 1147.923,
     "matmuls": 688,
     "dim": 4096,
     "exact": true
    },
    {
     "name": "idle 2",
     "seconds": 5.0047851609999725,
     "joules": 348.823,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "control",
     "seconds": 5.0191920429999755,
     "joules": 377.329,
     "calls": 2027
    },
    {
     "name": "idle 3",
     "seconds": 5.004358332999971,
     "joules": 347.732,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "method",
     "seconds": 20.85194730799998,
     "joules": 4498.79,
     "calls": 12,
     "ms": [
      1761.00244140625,
      1730.298828125,
      1730.4278564453125,
      1730.3153076171875,
      1730.2261962890625,
      1730.4422607421875,
      1729.798095703125,
      1730.1063232421875,
      1730.1473388671875,
      1730.556884765625,
      1730.323486328125,
      1730.6060791015625
     ],
     "correct": [
      9708,
      9743,
      9754,
      9755,
      9706,
      9758,
      9731,
      9763,
      9719,
      9716,
      9781,
      9727
     ]
    },
    {
     "name": "idle 4",
     "seconds": 5.005005740999991,
     "joules": 349.976,
     "utilization_max": 0,
     "contexts": 1
    }
   ]
  }
 }
}
