NVIDIA / NVIDIA/cutlass

[BUG] Example 09_turing_tensorop_conv2dfprop does not work

Open
#1,952 6 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Describe the bug
A clear and concise description of what the bug is.
When I compile and execute the example 09_turing_tensorop_conv2dfprop I get an error. My environment is Ubuntu 18.04, cuda 12, GPU Nvidia A100 ampere, make 3.25 and GCC version 8.4.

Steps/Code to reproduce bug
izcagal@cmts10:~/cutlass/build/examples/09_turing_tensorop_conv2dfprop$ ./09_turing_tensorop_conv2dfprop --n=32 --h=224 --w=224 --c=128 --k=256 --r=1 --s=1

09_turing_tensorop_conv2dfprop: /mnt/beegfs/gap/izcagal/cutlass/include/cutlass/integer_subbyte.h:96: cutlass::integer_subbyte<Bits, Signed>::integer_subbyte(int) [with int Bits = 4; bool Signed = true]: Assertion `value < upper_bound' failed.
Aborted (core dumped)

Any idea why this error happens or what it means?

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

Start by reproducing the command in examples/09_turing_tensorop_conv2dfprop and inspect the assertion at include/cutlass/integer_subbyte.h:96. Trace which input reaches the signed 4-bit integer conversion and compare it with the supplied convolution parameters and environment. Done means the reported failure is explained and the example has a verified resolution.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.