submission 556693 · KernelIndex

Use it

Vendorable · source mirrored · license unknownView source →

No package. Vendor the mirrored source: 18 lines, June 9 Researcher Reciprocity License v1.0.

submission.py

curl "https://kernelindex.com/api/v1/implementations/kernelbot-conv2d-v2-556693?include=source"

interfacepython

Compatibility

measured onNVIDIA A100

declared hardwareNVIDIA A100

architecturessm_80

dtypesfp32

Benchmark evidence

1 measurement across 1 GPU, fastest first.

Operation / workload

Hardware

Latency

Rank

Observed

2D convolutionsuite of 5 cases

NVIDIA A100

18.8ms

#6 of 40

2026-03-15

Run →

Reported · How evidence levels are derived →

Source and license

sourceavailable

revision digestsha256:0be9f6cc5c546e56613a0705ab9cf411b19d518b2e42359275c7dbe346b7db44

license declaredunknown

license concludedunknown

authorsidanbeck

imported2026-08-15

Kernel source

submission.py18 lines

#!POPCORN leaderboard conv2d_v2
#!POPCORN gpu A100
from task import input_t, output_t
import torch
import torch.nn.functional as F

@torch.inference_mode()
def custom_kernel(data: input_t) -> output_t:
    input_tensor, kernel, output = data
    torch.use_deterministic_algorithms(True)
    torch.set_float32_matmul_precision("highest")
    torch.backends.cudnn.benchmark = True
    torch.backends.cudnn.deterministic = True
    torch.backends.cuda.matmul.allow_tf32 = False
    torch.backends.cudnn.allow_tf32 = False
    output[...] = F.conv2d(input_tensor, kernel, stride=1, padding=0)
    return output

Source code from GPU Mode and the KernelBot dataset · June 9 Researcher Reciprocity License v1.0

Changes from previous submission

Against this author's previous submission submission 556202.

  ⋯ 3 unchanged lines
  import torch
  import torch.nn.functional as F
   
- torch.use_deterministic_algorithms(True)
- torch.set_float32_matmul_precision("highest")
- torch.backends.cudnn.benchmark = True
- torch.backends.cudnn.deterministic = True
- torch.backends.cuda.matmul.allow_tf32 = False
- torch.backends.cudnn.allow_tf32 = False
-  
- _CACHE_KEY = None
- _CACHE_Y = None
- _CALLS_FOR_KEY = 0
- _REFRESH_EVERY = 4
-  
-  
- def _make_key(x: torch.Tensor, w: torch.Tensor):
-     return (
-         int(x.data_ptr()),
-         int(w.data_ptr()),
-         tuple(x.shape),
-         tuple(w.shape),
-         str(x.dtype),
-         str(w.dtype),
-         x.device.index,
-     )
-  
-  
  @torch.inference_mode()
  def custom_kernel(data: input_t) -> output_t:
-     global _CACHE_KEY, _CACHE_Y, _CALLS_FOR_KEY
-     x, w, out = data
-     k = _make_key(x, w)
-     if _CACHE_KEY != k:
-         _CACHE_KEY = k
-         _CALLS_FOR_KEY = 0
-         _CACHE_Y = None
-     _CALLS_FOR_KEY += 1
-  
-     if _CACHE_Y is None or (_CALLS_FOR_KEY % _REFRESH_EVERY) == 1:
-         _CACHE_Y = F.conv2d(x, w, stride=1, padding=0)
-         return _CACHE_Y
-  
-     return _CACHE_Y
+     input_tensor, kernel, output = data
+     torch.use_deterministic_algorithms(True)
+     torch.set_float32_matmul_precision("highest")
+     torch.backends.cudnn.benchmark = True
+     torch.backends.cudnn.deterministic = True
+     torch.backends.cuda.matmul.allow_tf32 = False
+     torch.backends.cudnn.allow_tf32 = False
+     output[...] = F.conv2d(input_tensor, kernel, stride=1, padding=0)
+     return output

scrolls · 54 diff lines total

Best evidence level for this revision: reported

JSON