NVIDIA / NVIDIA/AMGX

Caught amgx exception: CUBLAS_STATUS_NOT_INITIALIZED

Open
#239 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Cuda
Stars
692
Forks
197
PR merge metrics
No merged PRs in 30d

Description

Running with CUDA_DISABLE_PTX_JIT=1 results in:

Compiled with CUDA Runtime 11.4, using CUDA driver 11.4
Caught amgx exception: CUBLAS_STATUS_NOT_INITIALIZED
 at: /home/user/3rd_party/AMGX/base/include/amgx_cublas.h:70
Stack trace:
 /home/user/.local/lib/libamgxsh.so : amgx::Cublas::get_handle()+0x650
 /home/user/.local/lib/libamgxsh.so : amgx::Resources::Resources(amgx::AMG_Configuration*, void*, int, int const*)+0xbda
 /home/user/.local/lib/libamgxsh.so : AMGX_resources_create()+0x9d

Not sure what goes wrong here? The code was compiled for the correct sm_XY and compute_XY.

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

Reproduce the failure with CUDA_DISABLE_PTX_JIT=1 and inspect amgx_cublas.h at line 70, following the AMGX_resources_create() path into Resources::Resources. Compare the failing configuration with a working run and document the cause and a verified resolution for the CUBLAS_STATUS_NOT_INITIALIZED error.

Written by the indexing model from the issue text.

Assessment

Domain
hpc
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.