{
 "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 80GB PCIe, torch 2.12.0+cu130, sandbox on\n  call  1/15: 636.430 ms, scorer's clock 641.130 ms\n  call  2/15: 636.333 ms, scorer's clock 639.568 ms\n  call  3/15: 636.635 ms, scorer's clock 639.740 ms\n  call  4/15: 636.751 ms, scorer's clock 640.116 ms\n  call  5/15: 632.359 ms, scorer's clock 636.363 ms\n  call  6/15: 635.927 ms, scorer's clock 639.801 ms\n  call  7/15: 632.773 ms, scorer's clock 637.509 ms\n  call  8/15: 632.992 ms, scorer's clock 637.270 ms\n  call  9/15: 633.328 ms, scorer's clock 638.072 ms\n  call 10/15: 632.229 ms, scorer's clock 636.099 ms\n  call 11/15: 636.661 ms, scorer's clock 640.315 ms\n  call 12/15: 632.913 ms, scorer's clock 636.479 ms\n  call 13/15: 636.717 ms, scorer's clock 640.661 ms\n  call 14/15: 632.532 ms, scorer's clock 638.045 ms\n  call 15/15: 636.804 ms, scorer's clock 640.735 ms\nMNIST 98.29% (108,121/110,000), 635.290 ms/call; hold-out (kmnist) 97.27%, 636.150 ms/call (floored by the scorer's clock); score 636.150 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 80GB PCIe: idle 78.7 W with the method frozen; telemetry reference 18.4 TFLOP/s at 7.66 J/TFLOP above idle (a healthy NVIDIA A100 80GB PCIe reads 6-11)\n  the round trip alone: 21.4 mJ per call over 3,789 empty calls, subtracted\n  the method: 32 calls in 20.3 s, MNIST 98.23%, 631.903 ms per call, 253.2 W on average\nenergy 110724.900 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 22:14:55.247000 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 22:15:39.805000 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 22:16:24.273000 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 22:17:08.847000 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 22:17:51.889000 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 22:18:34.561000 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 22:19:18.358000 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 22:20:03.019000 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 22:20:47.777000 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 22:21:34.186000 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 22:22:43.997000 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 80GB PCIe",
  "torch": "2.12.0+cu130",
  "calls": [
   {
    "dataset": "mnist",
    "ms": 636.4303588867188,
    "parent_ms": 643.6823060000023,
    "correct": 9822,
    "total": 10000,
    "overhead_ms": 2.5525075012881437
   },
   {
    "dataset": "mnist",
    "ms": 636.3330688476562,
    "parent_ms": 642.625124999995,
    "correct": 9855,
    "total": 10000,
    "overhead_ms": 3.0570030016335465
   },
   {
    "dataset": "kmnist",
    "ms": 636.6351318359375,
    "parent_ms": 642.3932940000157,
    "correct": 9732,
    "total": 10000,
    "overhead_ms": 2.6534440000760355
   },
   {
    "dataset": "mnist",
    "ms": 636.7508544921875,
    "parent_ms": 642.9405789999976,
    "correct": 9816,
    "total": 10000,
    "overhead_ms": 2.82467599834672
   },
   {
    "dataset": "mnist",
    "ms": 632.35888671875,
    "parent_ms": 638.4055569999987,
    "correct": 9802,
    "total": 10000,
    "overhead_ms": 2.0425719975772836
   },
   {
    "dataset": "kmnist",
    "ms": 635.926513671875,
    "parent_ms": 642.3514829999704,
    "correct": 9724,
    "total": 10000,
    "overhead_ms": 2.5505530020750484
   },
   {
    "dataset": "kmnist",
    "ms": 632.7725830078125,
    "parent_ms": 640.301710000017,
    "correct": 9727,
    "total": 10000,
    "overhead_ms": 2.792629000410898
   },
   {
    "dataset": "mnist",
    "ms": 632.9917602539062,
    "parent_ms": 639.5247720000157,
    "correct": 9850,
    "total": 10000,
    "overhead_ms": 2.2551974995360524
   },
   {
    "dataset": "mnist",
    "ms": 633.32763671875,
    "parent_ms": 640.8315709999783,
    "correct": 9812,
    "total": 10000,
    "overhead_ms": 2.759777999101516
   },
   {
    "dataset": "mnist",
    "ms": 632.2288818359375,
    "parent_ms": 638.1608689999894,
    "correct": 9835,
    "total": 10000,
    "overhead_ms": 2.061785500749693
   },
   {
    "dataset": "mnist",
    "ms": 636.6607055664062,
    "parent_ms": 642.3396690000232,
    "correct": 9847,
    "total": 10000,
    "overhead_ms": 2.0244634984444474
   },
   {
    "dataset": "mnist",
    "ms": 632.9129028320312,
    "parent_ms": 638.5305370000651,
    "correct": 9813,
    "total": 10000,
    "overhead_ms": 2.051313999745844
   },
   {
    "dataset": "kmnist",
    "ms": 636.717041015625,
    "parent_ms": 643.6177920001,
    "correct": 9726,
    "total": 10000,
    "overhead_ms": 2.9572109999662644
   },
   {
    "dataset": "mnist",
    "ms": 632.531982421875,
    "parent_ms": 640.1155369999287,
    "correct": 9825,
    "total": 10000,
    "overhead_ms": 2.0703190016256485
   },
   {
    "dataset": "mnist",
    "ms": 636.8040771484375,
    "parent_ms": 643.2989599999246,
    "correct": 9844,
    "total": 10000,
    "overhead_ms": 2.5641595010383753
   }
  ],
  "problems": [],
  "summary": "MNIST 98.29% (108,121/110,000), 635.290 ms/call; hold-out (kmnist) 97.27%, 636.150 ms/call (floored by the scorer's clock)",
  "ranked_ms": 636.1500464124796,
  "energy": {
   "mj_per_call": 110724.90038012275,
   "problems": [],
   "net_mj_before_control": 110746.34861319595,
   "control_mj_per_call": 21.448233073200228,
   "control_calls": 3789,
   "gross_mj_per_call": 160668.40625,
   "idle_w": 78.66387723719079,
   "active_w": 253.17065007808068,
   "calls": 32,
   "seconds": 20.30799778100004,
   "ms_median": 631.9027404785156,
   "timed_mnist_ms_median": 633.32763671875,
   "correct": 314346,
   "total": 320000,
   "reference": {
    "tflops_per_s": 18.372377969663,
    "j_per_tflop": 7.655255694891218,
    "exact": true,
    "band": [
     [
      6.0,
      11.0
     ],
     [
      15.0,
      23.0
     ]
    ]
   },
   "device": {
    "name": "NVIDIA A100 80GB PCIe",
    "uuid": "GPU-e1d60568-f502-42e5-02d2-3e3d3b63bb77",
    "vbios": "92.00.68.00.01",
    "driver": "610.57.04",
    "power_limit_w": 300.0
   },
   "windows": [
    {
     "name": "idle 1",
     "seconds": 5.006384365000031,
     "joules": 388.065,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "reference",
     "seconds": 5.20659392999994,
     "joules": 1137.936,
     "matmuls": 696,
     "dim": 4096,
     "exact": true
    },
    {
     "name": "idle 2",
     "seconds": 5.0058564130000605,
     "joules": 392.003,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "control",
     "seconds": 5.004999909999924,
     "joules": 467.739,
     "calls": 3789
    },
    {
     "name": "idle 3",
     "seconds": 5.006059195000034,
     "joules": 381.088,
     "utilization_max": 0,
     "contexts": 1
    },
    {
     "name": "method",
     "seconds": 20.30799778100004,
     "joules": 5141.389,
     "calls": 32,
     "ms": [
      632.2390747070312,
      632.2042846679688,
      632.1069946289062,
      631.841796875,
      631.8141479492188,
      631.8714599609375,
      631.784423828125,
      631.7936401367188,
      631.8858032226562,
      631.85205078125,
      632.4930419921875,
      631.8745727539062,
      631.9032592773438,
      631.8981323242188,
      631.9093627929688,
      632.195068359375,
      631.89404296875,
      631.8540649414062,
      631.9513549804688,
      631.7783203125,
      631.8694458007812,
      631.8981323242188,
      631.8345947265625,
      631.9022216796875,
      632.2432250976562,
      632.342529296875,
      632.237060546875,
      632.25341796875,
      632.0609130859375,
      631.9820556640625,
      632.0660400390625,
      632.0045776367188
     ],
     "correct": [
      9835,
      9831,
      9824,
      9811,
      9811,
      9829,
      9803,
      9824,
      9838,
      9817,
      9840,
      9838,
      9815,
      9824,
      9826,
      9816,
      9836,
      9850,
      9807,
      9847,
      9815,
      9830,
      9809,
      9806,
      9815,
      9847,
      9803,
      9830,
      9837,
      9798,
      9851,
      9783
     ]
    },
    {
     "name": "idle 4",
     "seconds": 5.005097993000049,
     "joules": 406.426,
     "utilization_max": 0,
     "contexts": 1
    }
   ]
  }
 }
}
