{
 "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: 402.149 ms, scorer's clock 405.951 ms\n  call  2/15: 402.800 ms, scorer's clock 406.751 ms\n  call  3/15: 403.724 ms, scorer's clock 407.657 ms\n  call  4/15: 404.669 ms, scorer's clock 409.128 ms\n  call  5/15: 402.778 ms, scorer's clock 406.537 ms\n  call  6/15: 401.910 ms, scorer's clock 405.323 ms\n  call  7/15: 402.850 ms, scorer's clock 406.531 ms\n  call  8/15: 402.418 ms, scorer's clock 406.920 ms\n  call  9/15: 402.258 ms, scorer's clock 406.217 ms\n  call 10/15: 401.987 ms, scorer's clock 406.166 ms\n  call 11/15: 402.835 ms, scorer's clock 407.857 ms\n  call 12/15: 406.881 ms, scorer's clock 411.020 ms\n  call 13/15: 402.111 ms, scorer's clock 405.840 ms\n  call 14/15: 402.423 ms, scorer's clock 407.073 ms\n  call 15/15: 404.351 ms, scorer's clock 408.379 ms\nMNIST 98.31% (108,139/110,000), 405.073 ms/call; hold-out (kmnist) 97.41%, 404.954 ms/call (floored by the scorer's clock); score 405.073 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 65.3 W with the method frozen; telemetry reference 18.3 TFLOP/s at 8.41 J/TFLOP above idle (a healthy NVIDIA A100-SXM4-80GB reads 6-11)\n  the round trip alone: 14.1 mJ per call over 2,229 empty calls, subtracted\n  the method: 49 calls in 20.0 s, MNIST 98.33%, 402.071 ms per call, 235.6 W on average\nenergy 69649.308 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 12:23:28.247000 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 12:24:13.318000 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 12:24:59.079000 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 12:25:44.523000 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 12:26:30.060000 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 12:27:16.286000 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 12:28:03.300000 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 12:28:48.047000 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 12:29:32.900000 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 12:30:17.820000 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 12:31:28.379000 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": 402.1493835449219,
    "parent_ms": 408.8986840000004,
    "correct": 9844,
    "total": 10000,
    "overhead_ms": 2.9472390021549444
   },
   {
    "dataset": "kmnist",
    "ms": 402.79962158203125,
    "parent_ms": 409.9857249999985,
    "correct": 9751,
    "total": 10000,
    "overhead_ms": 3.234894499125147
   },
   {
    "dataset": "mnist",
    "ms": 403.7242736816406,
    "parent_ms": 410.56180300000733,
    "correct": 9844,
    "total": 10000,
    "overhead_ms": 2.905141496956105
   },
   {
    "dataset": "kmnist",
    "ms": 404.66943359375,
    "parent_ms": 412.0882960000074,
    "correct": 9742,
    "total": 10000,
    "overhead_ms": 2.9601205015402456
   },
   {
    "dataset": "mnist",
    "ms": 402.7781066894531,
    "parent_ms": 409.8237979999908,
    "correct": 9833,
    "total": 10000,
    "overhead_ms": 3.287084501977006
   },
   {
    "dataset": "kmnist",
    "ms": 401.9097595214844,
    "parent_ms": 408.3508570000163,
    "correct": 9736,
    "total": 10000,
    "overhead_ms": 3.0276280006783054
   },
   {
    "dataset": "mnist",
    "ms": 402.84979248046875,
    "parent_ms": 409.3774250000024,
    "correct": 9810,
    "total": 10000,
    "overhead_ms": 2.8462834991091768
   },
   {
    "dataset": "mnist",
    "ms": 402.41766357421875,
    "parent_ms": 409.96146000003364,
    "correct": 9816,
    "total": 10000,
    "overhead_ms": 3.0417244984314493
   },
   {
    "dataset": "mnist",
    "ms": 402.2579345703125,
    "parent_ms": 409.21540800002276,
    "correct": 9833,
    "total": 10000,
    "overhead_ms": 2.998564997394624
   },
   {
    "dataset": "mnist",
    "ms": 401.986572265625,
    "parent_ms": 409.0664480000328,
    "correct": 9806,
    "total": 10000,
    "overhead_ms": 2.900707996244819
   },
   {
    "dataset": "mnist",
    "ms": 402.83544921875,
    "parent_ms": 410.97640200001706,
    "correct": 9845,
    "total": 10000,
    "overhead_ms": 3.1193685028663367
   },
   {
    "dataset": "mnist",
    "ms": 406.88128662109375,
    "parent_ms": 414.1750229999843,
    "correct": 9838,
    "total": 10000,
    "overhead_ms": 3.1553715006148195
   },
   {
    "dataset": "mnist",
    "ms": 402.1114807128906,
    "parent_ms": 408.82031699993604,
    "correct": 9844,
    "total": 10000,
    "overhead_ms": 2.9805939993698303
   },
   {
    "dataset": "kmnist",
    "ms": 402.42279052734375,
    "parent_ms": 410.0908970000319,
    "correct": 9736,
    "total": 10000,
    "overhead_ms": 3.0175204990614475
   },
   {
    "dataset": "mnist",
    "ms": 404.3509826660156,
    "parent_ms": 411.113089999958,
    "correct": 9826,
    "total": 10000,
    "overhead_ms": 2.7336374996903032
   }
  ],
  "problems": [],
  "summary": "MNIST 98.31% (108,139/110,000), 405.073 ms/call; hold-out (kmnist) 97.41%, 404.954 ms/call (floored by the scorer's clock)",
  "ranked_ms": 405.07294780682264,
  "energy": {
   "mj_per_call": 69649.30811734122,
   "problems": [],
   "net_mj_before_control": 69663.37786690613,
   "control_mj_per_call": 14.069749564910305,
   "control_calls": 2229,
   "gross_mj_per_call": 96353.44897959183,
   "idle_w": 65.25723578659434,
   "active_w": 235.58422577316614,
   "calls": 49,
   "seconds": 20.040896136000015,
   "ms_median": 402.0705261230469,
   "timed_mnist_ms_median": 402.7781066894531,
   "correct": 481798,
   "total": 490000,
   "reference": {
    "tflops_per_s": 18.296702535610585,
    "j_per_tflop": 8.414050939410217,
    "exact": true,
    "band": [
     [
      6.0,
      11.0
     ],
     [
      15.0,
      23.0
     ]
    ]
   },
   "device": {
    "name": "NVIDIA A100-SXM4-80GB",
    "uuid": "GPU-9339b11b-d76e-0a2c-0bae-7f31e82fbe01",
    "vbios": "92.00.9E.00.01",
    "driver": "610.57.04",
    "power_limit_w": 400.0
   },
   "windows": [
    {
     "name": "idle 1",
     "seconds": 5.007114356999978,
     "joules": 326.083,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "reference",
     "seconds": 5.228128479999896,
     "joules": 1146.458,
     "matmuls": 696,
     "dim": 4096,
     "exact": true
    },
    {
     "name": "idle 2",
     "seconds": 5.004920631999994,
     "joules": 328.074,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "control",
     "seconds": 5.006066849000035,
     "joules": 358.679,
     "calls": 2229
    },
    {
     "name": "idle 3",
     "seconds": 5.005776721000075,
     "joules": 326.467,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "method",
     "seconds": 20.040896136000015,
     "joules": 4721.319,
     "calls": 49,
     "ms": [
      445.1799011230469,
      402.0244445800781,
      402.1268615722656,
      402.5999450683594,
      402.0705261230469,
      403.156982421875,
      402.1370849609375,
      403.0382080078125,
      402.1585998535156,
      402.02239990234375,
      402.8037109375,
      402.0633544921875,
      402.05413818359375,
      406.1378479003906,
      403.02081298828125,
      402.01727294921875,
      401.94866943359375,
      402.0981750488281,
      401.9824523925781,
      401.94049072265625,
      402.0480041503906,
      402.0653991699219,
      402.0367431640625,
      402.1585998535156,
      402.03265380859375,
      401.90667724609375,
      402.05926513671875,
      401.9660949707031,
      402.0203552246094,
      402.39410400390625,
      402.0254821777344,
      402.0715637207031,
      401.9927062988281,
      402.113525390625,
      402.04595947265625,
      402.0295715332031,
      402.01727294921875,
      402.0254821777344,
      402.0439147949219,
      402.0019226074219,
      402.2958068847656,
      409.7658996582031,
      404.8506774902344,
      402.3060607910156,
      403.5389404296875,
      403.3617858886719,
      402.4012756347656,
      402.11865234375,
      402.2528076171875
     ],
     "correct": [
      9841,
      9838,
      9842,
      9846,
      9833,
      9831,
      9823,
      9837,
      9822,
      9851,
      9833,
      9860,
      9829,
      9848,
      9791,
      9836,
      9825,
      9849,
      9820,
      9819,
      9825,
      9820,
      9827,
      9823,
      9841,
      9836,
      9828,
      9833,
      9819,
      9828,
      9832,
      9826,
      9840,
      9851,
      9846,
      9844,
      9831,
      9823,
      9815,
      9838,
      9841,
      9843,
      9839,
      9869,
      9821,
      9826,
      9805,
      9836,
      9818
     ]
    },
    {
     "name": "idle 4",
     "seconds": 5.005236054999955,
     "joules": 326.824,
     "utilization_max": 0,
     "contexts": 1
    }
   ]
  }
 }
}
