parallel code execution on MATLAB cluster

As I run a code on a cluster using spmd, sometimes a worker gets disconnected and the execution stops. In another instance, the job became 'queued' after running for multiple hours and then eventually the execution stopped. What could be potential reasons for these?

1 件のコメント

Kojiro Saito
Kojiro Saito 2018 年 1 月 11 日
Are you using Linux? Could you cofirm the maximum process is sufficient?
ulimit -a

サインインしてコメントする。

回答 (0 件)

カテゴリ

ヘルプ センター および File ExchangeMATLAB Parallel Server についてさらに検索

タグ

質問済み:

2018 年 1 月 10 日

コメント済み:

2018 年 1 月 11 日

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by