Skip to content
KernelIndex
Search⌘K
Sign in

submission 555513

idanbeck · python · License unknown
Kernel source · 18 lines ↓

Use it

Vendorable · source mirrored · license unknownView source →

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

probe_v1_direct.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-conv2d-v2-555513?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
19.4ms
#12 of 40
2026-03-15
Run →

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:dcfa44e02fb9fab10988acf8afae69d4687f13f8627423933c6f75a4cc8d16df
license declaredunknown
license concludedunknown
authorsidanbeck
imported2026-08-15

Kernel source

probe_v1_direct.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 554690.

  ⋯ 5 unchanged lines
   
  @torch.inference_mode()
  def custom_kernel(data: input_t) -> output_t:
-     x, w, out = data
+     input_tensor, kernel, output = data
      torch.use_deterministic_algorithms(True)
-     torch.set_float32_matmul_precision('highest')
+     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
-     x_cl = x.contiguous(memory_format=torch.channels_last)
-     w_cl = w.contiguous(memory_format=torch.channels_last)
-     y = F.conv2d(x_cl, w_cl, stride=1, padding=0)
-     out[...] = y.contiguous()
-     return out
+     output[...] = F.conv2d(input_tensor, kernel, stride=1, padding=0)
+     return output

Best evidence level for this revision: reported

JSON