{
 "returncode": 0,
 "stdout": "x_k5cFdt450.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: 404.380 ms, scorer's clock 408.175 ms\n  call  2/15: 401.998 ms, scorer's clock 406.521 ms\n  call  3/15: 402.326 ms, scorer's clock 405.937 ms\n  call  4/15: 401.396 ms, scorer's clock 405.287 ms\n  call  5/15: 403.141 ms, scorer's clock 406.984 ms\n  call  6/15: 401.383 ms, scorer's clock 405.030 ms\n  call  7/15: 401.602 ms, scorer's clock 405.315 ms\n  call  8/15: 402.449 ms, scorer's clock 407.353 ms\n  call  9/15: 402.714 ms, scorer's clock 407.574 ms\n  call 10/15: 401.295 ms, scorer's clock 405.194 ms\n  call 11/15: 401.422 ms, scorer's clock 405.355 ms\n  call 12/15: 401.483 ms, scorer's clock 405.461 ms\n  call 13/15: 401.419 ms, scorer's clock 405.384 ms\n  call 14/15: 401.577 ms, scorer's clock 405.789 ms\n  call 15/15: 401.478 ms, scorer's clock 405.550 ms\nMNIST 98.28% (108,108/110,000), 403.997 ms/call; hold-out (kmnist) 97.30%, 403.822 ms/call (floored by the scorer's clock); score 403.997 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 66.6 W with the method frozen; telemetry reference 18.4 TFLOP/s at 7.74 J/TFLOP above idle (a healthy NVIDIA A100-SXM4-80GB reads 6-11)\n  the round trip alone: 15.5 mJ per call over 2,940 empty calls, subtracted\n  the method: 50 calls in 20.4 s, MNIST 98.32%, 401.968 ms per call, 224.3 W on average\nenergy 64250.015 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(\nW1020 12:23:22.988000 1107 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(\nW1020 12:24:08.327000 1323 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(\nW1020 12:24:52.810000 1539 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(\nW1020 12:25:37.039000 1755 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(\nW1020 12:26:21.455000 1971 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(\nW1020 12:27:05.871000 2187 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(\nW1020 12:27:50.019000 2403 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(\nW1020 12:28:34.232000 2619 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(\nW1020 12:29:17.520000 2835 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(\nW1020 12:30:01.568000 3051 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(\nW1020 12:31:10.457000 3268 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": "x_k5cFdt450.py",
  "function": "ladder_kernel",
  "source_sha256": "98e310b12031555088ee47e6f8170ad001fad1b6f0be28dcead493ff7682f5c3",
  "band_bp": 190,
  "sandboxed": true,
  "holdout": "kmnist",
  "device": "NVIDIA A100-SXM4-80GB",
  "torch": "2.12.0+cu130",
  "calls": [
   {
    "dataset": "mnist",
    "ms": 404.379638671875,
    "parent_ms": 411.415673999997,
    "correct": 9844,
    "total": 10000,
    "overhead_ms": 3.2407085027632974
   },
   {
    "dataset": "kmnist",
    "ms": 401.9978332519531,
    "parent_ms": 409.5935889999964,
    "correct": 9732,
    "total": 10000,
    "overhead_ms": 3.07261149843265
   },
   {
    "dataset": "mnist",
    "ms": 402.32550048828125,
    "parent_ms": 408.9816400000075,
    "correct": 9834,
    "total": 10000,
    "overhead_ms": 3.0445789989415175
   },
   {
    "dataset": "mnist",
    "ms": 401.3957214355469,
    "parent_ms": 408.0311649999828,
    "correct": 9814,
    "total": 10000,
    "overhead_ms": 2.7440404987897864
   },
   {
    "dataset": "kmnist",
    "ms": 403.1405944824219,
    "parent_ms": 409.716431999982,
    "correct": 9740,
    "total": 10000,
    "overhead_ms": 2.732725501891423
   },
   {
    "dataset": "kmnist",
    "ms": 401.3834228515625,
    "parent_ms": 407.776062000039,
    "correct": 9731,
    "total": 10000,
    "overhead_ms": 2.746169998432265
   },
   {
    "dataset": "mnist",
    "ms": 401.6015319824219,
    "parent_ms": 408.1894910000301,
    "correct": 9840,
    "total": 10000,
    "overhead_ms": 2.874187503122812
   },
   {
    "dataset": "mnist",
    "ms": 402.44940185546875,
    "parent_ms": 410.10800399999425,
    "correct": 9822,
    "total": 10000,
    "overhead_ms": 2.7550914997245854
   },
   {
    "dataset": "mnist",
    "ms": 402.7135925292969,
    "parent_ms": 410.488053999984,
    "correct": 9840,
    "total": 10000,
    "overhead_ms": 2.913802497399729
   },
   {
    "dataset": "kmnist",
    "ms": 401.29534912109375,
    "parent_ms": 407.890239999972,
    "correct": 9716,
    "total": 10000,
    "overhead_ms": 2.696103997245473
   },
   {
    "dataset": "mnist",
    "ms": 401.4223327636719,
    "parent_ms": 408.1279560000439,
    "correct": 9826,
    "total": 10000,
    "overhead_ms": 2.7726345002438393
   },
   {
    "dataset": "mnist",
    "ms": 401.4827575683594,
    "parent_ms": 408.1019620000461,
    "correct": 9819,
    "total": 10000,
    "overhead_ms": 2.640980498760655
   },
   {
    "dataset": "mnist",
    "ms": 401.41925048828125,
    "parent_ms": 408.192793000012,
    "correct": 9825,
    "total": 10000,
    "overhead_ms": 2.808375496495046
   },
   {
    "dataset": "mnist",
    "ms": 401.57696533203125,
    "parent_ms": 408.42555000006087,
    "correct": 9819,
    "total": 10000,
    "overhead_ms": 2.636673499978315
   },
   {
    "dataset": "mnist",
    "ms": 401.4776306152344,
    "parent_ms": 408.14332000002196,
    "correct": 9825,
    "total": 10000,
    "overhead_ms": 2.5936984989798475
   }
  ],
  "problems": [],
  "summary": "MNIST 98.28% (108,108/110,000), 403.997 ms/call; hold-out (kmnist) 97.30%, 403.822 ms/call (floored by the scorer's clock)",
  "ranked_ms": 403.9972377623935,
  "energy": {
   "mj_per_call": 64250.01518101275,
   "problems": [],
   "net_mj_before_control": 64265.552280939024,
   "control_mj_per_call": 15.53709992627262,
   "control_calls": 2940,
   "gross_mj_per_call": 91425.16,
   "idle_w": 66.64639326178238,
   "active_w": 224.3462877081659,
   "calls": 50,
   "seconds": 20.37590212300006,
   "ms_median": 401.9676208496094,
   "timed_mnist_ms_median": 401.57696533203125,
   "correct": 491616,
   "total": 500000,
   "reference": {
    "tflops_per_s": 18.35202218506661,
    "j_per_tflop": 7.739734000838282,
    "exact": true,
    "band": [
     [
      6.0,
      11.0
     ],
     [
      15.0,
      23.0
     ]
    ]
   },
   "device": {
    "name": "NVIDIA A100-SXM4-80GB",
    "uuid": "GPU-3e087321-412b-e43f-1f02-396e6e521d7b",
    "vbios": "92.00.9E.00.01",
    "driver": "610.57.04",
    "power_limit_w": 400.0
   },
   "windows": [
    {
     "name": "idle 1",
     "seconds": 5.009752044000038,
     "joules": 335.335,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "reference",
     "seconds": 5.212369004999914,
     "joules": 1087.085,
     "matmuls": 696,
     "dim": 4096,
     "exact": true
    },
    {
     "name": "idle 2",
     "seconds": 5.005639040999995,
     "joules": 330.88,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "control",
     "seconds": 5.0041910200000075,
     "joules": 375.058,
     "calls": 2940
    },
    {
     "name": "idle 3",
     "seconds": 5.006120097000007,
     "joules": 328.1,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "method",
     "seconds": 20.37590212300006,
     "joules": 4571.258,
     "calls": 50,
     "ms": [
      443.3653869628906,
      402.2272033691406,
      401.9824523925781,
      402.2374267578125,
      402.0684814453125,
      401.9783630371094,
      401.8902893066406,
      402.00909423828125,
      401.9599304199219,
      401.8831481933594,
      402.6910705566406,
      402.0746154785156,
      402.03057861328125,
      402.0899963378906,
      402.55487060546875,
      402.2456359863281,
      402.06744384765625,
      401.96710205078125,
      401.9681396484375,
      401.95379638671875,
      401.9097595214844,
      402.0889587402344,
      402.3971862792969,
      401.9374084472656,
      401.9230651855469,
      401.870849609375,
      401.86163330078125,
      402.0101013183594,
      402.19647216796875,
      401.9158935546875,
      401.8944091796875,
      401.8524169921875,
      401.9374084472656,
      401.7315979003906,
      402.1903381347656,
      402.06951904296875,
      401.9681396484375,
      401.944580078125,
      401.78790283203125,
      402.30810546875,
      401.8974609375,
      401.9701843261719,
      401.9455871582031,
      401.7633361816406,
      401.8554992675781,
      401.6936950683594,
      402.4432678222656,
      401.9210205078125,
      401.7152099609375,
      401.92205810546875
     ],
     "correct": [
      9857,
      9845,
      9858,
      9805,
      9815,
      9837,
      9824,
      9833,
      9833,
      9835,
      9839,
      9809,
      9823,
      9826,
      9838,
      9839,
      9839,
      9832,
      9845,
      9831,
      9843,
      9834,
      9833,
      9855,
      9828,
      9825,
      9854,
      9830,
      9840,
      9827,
      9828,
      9824,
      9844,
      9833,
      9846,
      9815,
      9820,
      9843,
      9808,
      9831,
      9819,
      9824,
      9840,
      9804,
      9833,
      9827,
      9843,
      9848,
      9828,
      9826
     ]
    },
    {
     "name": "idle 4",
     "seconds": 5.005578462000017,
     "joules": 339.143,
     "utilization_max": 0,
     "contexts": 1
    }
   ]
  }
 }
}
