NVIDIA / NVIDIA/cutlass

[QST] How to understand kernel name cutlass_75_tensorop_bf16_s1688gemm_bf16_256x128_nn_align1?

Open
#2,286 2 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

? - Needs Triage inactive-30d inactive-90d question
Dominant language
C++
Stars
10.5k
Forks
2.1k
Avg merge
3d 11h
Merged PRs (30d)
7

Description

What is your question?

I profiled a tensorflow model training on A30, and found this kernel name: cutlass_75_tensorop_bf16_s1688gemm_bf16_256x128_nn_align1

Does 75 here means SM75 capability? But bf16 is only supported after Ampere, why can SM75 have bf16?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names only the CUTLASS kernel cutlass_75_tensorop_bf16_s1688gemm_bf16_256x128_nn_align1 and an A30 TensorFlow profile; no file, test, or entry point is provided. Start by locating the code or documentation that defines CUTLASS kernel-name components, then verify what 75 and bf16 represent. Done means the naming and apparent SM75/BF16 mismatch are clearly explained.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
hpc, machine-learning
Issue type
Documentation
Difficulty
1/5
Estimated time
Under an hour
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.