{
 "returncode": 0,
 "stdout": "a_k2t_600.py:ladder_kernel at 1.90% error: 15 timed calls, each in a fresh process\n  review flag: 20,474 bytes, close to the 20,480-byte limit\n  NVIDIA A100-SXM4-80GB, torch 2.12.0+cu130, sandbox on\n  call  1/15: 633.435 ms, scorer's clock 636.734 ms\n  call  2/15: 632.495 ms, scorer's clock 635.404 ms\n  call  3/15: 628.400 ms, scorer's clock 632.133 ms\n  call  4/15: 633.312 ms, scorer's clock 636.093 ms\n  call  5/15: 633.943 ms, scorer's clock 637.038 ms\n  call  6/15: 629.281 ms, scorer's clock 633.005 ms\n  call  7/15: 633.226 ms, scorer's clock 635.841 ms\n  call  8/15: 629.482 ms, scorer's clock 631.655 ms\n  call  9/15: 633.896 ms, scorer's clock 636.720 ms\n  call 10/15: 633.122 ms, scorer's clock 635.863 ms\n  call 11/15: 629.668 ms, scorer's clock 631.900 ms\n  call 12/15: 633.277 ms, scorer's clock 636.200 ms\n  call 13/15: 629.461 ms, scorer's clock 632.260 ms\n  call 14/15: 633.771 ms, scorer's clock 637.034 ms\n  call 15/15: 633.558 ms, scorer's clock 636.267 ms\nMNIST 98.15% (107,965/110,000), 631.998 ms/call; hold-out (kmnist) 97.26%, 632.089 ms/call; score 632.089 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 68.3 W with the method frozen; telemetry reference 18.3 TFLOP/s at 7.89 J/TFLOP above idle (a healthy NVIDIA A100-SXM4-80GB reads 6-11)\n  the round trip alone: 14.8 mJ per call over 1,597 empty calls, subtracted\n  the method: 32 calls in 20.3 s, MNIST 98.19%, 629.081 ms per call, 245.9 W on average\nenergy 112580.541 mJ per call above idle\n",
 "stderr": "uards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:14:35.903000 1122 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:15:36.218000 1341 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:16:19.030000 1560 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:17:00.416000 1779 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:17:41.500000 1998 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:18:23.385000 2217 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:19:04.191000 2436 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:19:44.681000 2655 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:20:26.801000 2874 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:21:08.152000 3093 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\nW1019 22:22:14.655000 3313 site-packages/torch/_logging/_internal.py:1311] [1/0] Profiler record function <class 'torch.autograd.profiler.record_function'> will be ignored\n/usr/local/lib/python3.13/site-packages/torch/_dynamo/guards.py:1317: RuntimeWarning: Guards may run slower on Python 3.13.0. Consider upgrading to Python 3.13.1+.\n  warnings.warn(\n",
 "record": {
  "version": "mnist-a100/1.2.0 (protections of sutro-mnist-medium/3.0.0, tightened; energy column)",
  "file": "a_k2t_600.py",
  "function": "ladder_kernel",
  "source_sha256": "cc423b95ed940a5bcd5dc3b08f71502dddbcee3b42cbc34fc5322819378aef2a",
  "band_bp": 190,
  "sandboxed": true,
  "holdout": "kmnist",
  "device": "NVIDIA A100-SXM4-80GB",
  "torch": "2.12.0+cu130",
  "calls": [
   {
    "dataset": "mnist",
    "ms": 633.4351196289062,
    "parent_ms": 640.1673820000013,
    "correct": 9813,
    "total": 10000,
    "overhead_ms": 3.433359499730507
   },
   {
    "dataset": "kmnist",
    "ms": 632.4951171875,
    "parent_ms": 638.6999409999987,
    "correct": 9721,
    "total": 10000,
    "overhead_ms": 3.2957079989544127
   },
   {
    "dataset": "mnist",
    "ms": 628.400146484375,
    "parent_ms": 635.4342749999944,
    "correct": 9807,
    "total": 10000,
    "overhead_ms": 3.301194000422072
   },
   {
    "dataset": "mnist",
    "ms": 633.312255859375,
    "parent_ms": 639.4276340000147,
    "correct": 9827,
    "total": 10000,
    "overhead_ms": 3.3345419984279943
   },
   {
    "dataset": "mnist",
    "ms": 633.9430541992188,
    "parent_ms": 640.4226179999739,
    "correct": 9831,
    "total": 10000,
    "overhead_ms": 3.384188000931772
   },
   {
    "dataset": "mnist",
    "ms": 629.28076171875,
    "parent_ms": 636.7024999999842,
    "correct": 9795,
    "total": 10000,
    "overhead_ms": 3.697328497551325
   },
   {
    "dataset": "mnist",
    "ms": 633.2262573242188,
    "parent_ms": 639.4491780000067,
    "correct": 9813,
    "total": 10000,
    "overhead_ms": 3.6076819981365134
   },
   {
    "dataset": "mnist",
    "ms": 629.4824829101562,
    "parent_ms": 635.474658000021,
    "correct": 9827,
    "total": 10000,
    "overhead_ms": 3.8200789978304783
   },
   {
    "dataset": "mnist",
    "ms": 633.8959350585938,
    "parent_ms": 639.9871379999809,
    "correct": 9819,
    "total": 10000,
    "overhead_ms": 3.2672224981699856
   },
   {
    "dataset": "kmnist",
    "ms": 633.1217651367188,
    "parent_ms": 639.181246000021,
    "correct": 9727,
    "total": 10000,
    "overhead_ms": 3.3183944984366462
   },
   {
    "dataset": "mnist",
    "ms": 629.6678466796875,
    "parent_ms": 635.6285100000036,
    "correct": 9812,
    "total": 10000,
    "overhead_ms": 3.7289254981833437
   },
   {
    "dataset": "kmnist",
    "ms": 633.2774658203125,
    "parent_ms": 639.4769859999769,
    "correct": 9713,
    "total": 10000,
    "overhead_ms": 3.2771789981129587
   },
   {
    "dataset": "kmnist",
    "ms": 629.4609985351562,
    "parent_ms": 635.5534320000515,
    "correct": 9743,
    "total": 10000,
    "overhead_ms": 3.293874997970761
   },
   {
    "dataset": "mnist",
    "ms": 633.77099609375,
    "parent_ms": 640.3956619999462,
    "correct": 9821,
    "total": 10000,
    "overhead_ms": 3.361414498645445
   },
   {
    "dataset": "mnist",
    "ms": 633.5580444335938,
    "parent_ms": 639.5886130000008,
    "correct": 9800,
    "total": 10000,
    "overhead_ms": 3.3218114980772953
   }
  ],
  "problems": [],
  "summary": "MNIST 98.15% (107,965/110,000), 631.998 ms/call; hold-out (kmnist) 97.26%, 632.089 ms/call",
  "ranked_ms": 632.0888366699219,
  "energy": {
   "mj_per_call": 112580.5413191393,
   "problems": [],
   "net_mj_before_control": 112595.36753437888,
   "control_mj_per_call": 14.826215239575529,
   "control_calls": 1597,
   "gross_mj_per_call": 155894.28125,
   "idle_w": 68.29643352306843,
   "active_w": 245.8958551695949,
   "calls": 32,
   "seconds": 20.287519675999988,
   "ms_median": 629.0810852050781,
   "timed_mnist_ms_median": 633.312255859375,
   "correct": 314213,
   "total": 320000,
   "reference": {
    "tflops_per_s": 18.330042305596574,
    "j_per_tflop": 7.89113738323268,
    "exact": true,
    "band": [
     [
      6.0,
      11.0
     ],
     [
      15.0,
      23.0
     ]
    ]
   },
   "device": {
    "name": "NVIDIA A100-SXM4-80GB",
    "uuid": "GPU-7053d9c2-0208-173c-fbf0-6349c93771d6",
    "vbios": "92.00.45.00.0E",
    "driver": "610.57.04",
    "power_limit_w": 400.0
   },
   "windows": [
    {
     "name": "idle 1",
     "seconds": 5.007743655000013,
     "joules": 336.413,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "reference",
     "seconds": 5.158635119999985,
     "joules": 1093.857,
     "matmuls": 688,
     "dim": 4096,
     "exact": true
    },
    {
     "name": "idle 2",
     "seconds": 5.005365697999991,
     "joules": 338.46,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "control",
     "seconds": 5.00768921100007,
     "joules": 362.679,
     "calls": 1597
    },
    {
     "name": "idle 3",
     "seconds": 5.00501921,
     "joules": 339.205,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "method",
     "seconds": 20.287519675999988,
     "joules": 4988.617,
     "calls": 32,
     "ms": [
      653.56494140625,
      629.44970703125,
      628.548583984375,
      629.5828247070312,
      630.20849609375,
      628.6090087890625,
      628.262939453125,
      628.4677124023438,
      628.1400146484375,
      628.443115234375,
      628.833251953125,
      629.080078125,
      629.2254638671875,
      629.228515625,
      629.7272338867188,
      629.391357421875,
      629.3330078125,
      629.3903198242188,
      628.8834838867188,
      628.56396484375,
      628.490234375,
      629.012451171875,
      628.2127075195312,
      629.375,
      629.2418823242188,
      628.5783081054688,
      629.0575561523438,
      629.0820922851562,
      629.4046630859375,
      629.2572021484375,
      629.2879638671875,
      628.9285278320312
     ],
     "correct": [
      9808,
      9814,
      9796,
      9814,
      9805,
      9794,
      9822,
      9825,
      9822,
      9825,
      9818,
      9823,
      9810,
      9817,
      9837,
      9790,
      9818,
      9829,
      9824,
      9806,
      9816,
      9843,
      9833,
      9831,
      9798,
      9830,
      9824,
      9843,
      9818,
      9806,
      9840,
      9834
     ]
    },
    {
     "name": "idle 4",
     "seconds": 5.0311610160000555,
     "joules": 346.244,
     "utilization_max": 0,
     "contexts": 1
    }
   ]
  }
 }
}
