OpenMathLib / OpenMathLib/OpenBLAS

`BIGNUMA` and `NUM_THREADS>256` on 2×192-core AmpereOne (AArch64)

Open
#5,555 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C
Stars
7.6k
Forks
1.7k
Avg merge
1d 3h
Merged PRs (30d)
42

Description

Hi,

I’d like clarification on using OpenBLAS on a 2×192-core AmpereOne (384 cores total), AArch64 Linux.

Planned build:

make TARGET=ARMV8 USE_OPENMP=1 NUM_THREADS=384 BIGNUMA=1

Docs mention a default 256-core limit, and BIGNUMA=1 extending support to 1024 cores, but this seems described mainly for x86_64.

Questions:

  1. On AmpereOne (AArch64), is BIGNUMA=1 NUM_THREADS=384 a supported/validated configuration for a single process?
  2. Or should AArch64 builds be treated as limited to 256 threads per process (keep NUM_THREADS <= 256 and use multiple MPI ranks)?
  3. Is BIGNUMA intended to be x86_64-only, or is it expected to work on Arm as well?

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 with the OpenBLAS documentation for BIGNUMA and NUM_THREADS, then investigate the ARMV8 build configuration using the stated make command on AArch64. Done means establishing whether 384 threads per process is supported and validated, whether BIGNUMA applies to Arm, and documenting the recommended alternative if it is not.

Written by the indexing model from the issue text.

Assessment

Tech stack
c, linux
Domain
operating-systems, performance
Issue type
Feature
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.