Skip to content
KernelIndex
Search⌘K
Sign in

submission 513118

JordanNanos · python · License unknown
Kernel source · 13 lines ↓

Use it

Vendorable · source mirrored · license unknownView source →

No package. Vendor the mirrored source: 13 lines, June 9 Researcher Reciprocity License v1.0.

submission.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-matmul-v2-513118?include=source"
interfacepython
Compatibility
measured onNVIDIA B200
declared hardwareNVIDIA B200
architecturessm_100
dtypesfp16

Benchmark evidence

1 measurement across 1 GPU, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
FP16 matmulsuite of 8 cases
NVIDIA B200
136.4µs
#25 of 53
2026-03-06
Run →

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:9f4ff1f1ef75010b9f1059d3ddb3691447942eea56b2f3ec14f3f9ace912dad2
license declaredunknown
license concludedunknown
authorsJordanNanos
imported2026-08-15

Kernel source

submission.py13 lines
import os
os.environ.setdefault("CUBLAS_WORKSPACE_CONFIG", ":4096:8")

import torch
from task import input_t, output_t

torch.backends.cuda.matmul.allow_tf32 = True
torch.backends.cudnn.allow_tf32 = True

def custom_kernel(data: input_t) -> output_t:
    a, b, c = data
    torch.mm(a, b, out=c)
    return c

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 512855.

  import os
+ os.environ.setdefault("CUBLAS_WORKSPACE_CONFIG", ":4096:8")
+  
  import torch
  from task import input_t, output_t
   
- os.environ.setdefault("CUBLAS_WORKSPACE_CONFIG", ":4096:8")
+ torch.backends.cuda.matmul.allow_tf32 = True
+ torch.backends.cudnn.allow_tf32 = True
   
-  
  def custom_kernel(data: input_t) -> output_t:
      a, b, c = data
      torch.mm(a, b, out=c)

Best evidence level for this revision: reported

JSON