how can i implement multilevel parallelism on a parallel cluster distribute shared-memory?

Question

ROSALBA CACCIAPUOTI 2020-6-8

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/544400-how-can-i-implement-multilevel-parallelism-on-a-parallel-cluster-distribute-shared-memory

评论： Walter Roberson 2020-6-11

i am using a HPC architecture that it's made of 8 nodes, each blade consists of 2 quadcore processors sharing memory for a total of 8 cores and of 64 cores, in total. how can I set up a cluster profile to run my code on p (1=<p<=8) nodes? and fixed a node, how can I set up another cluster profile to run my (sequential) code on c (1=<c<=8) cores ? how many workers should I consider in both cases?

thanks

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Walter Roberson 2020-6-8

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/544400-how-can-i-implement-multilevel-parallelism-on-a-parallel-cluster-distribute-shared-memory#answer_448061

MATLAB does not support multi-level parallelism with the Parallel Computing Toolbox.

What it does support is allocating more than one thread (core) to a parallel worker. These threads can be used by MKL or LAPACK high performance libraries that automatically act in parallel without starting new processes.

You cannot, however, have a parallel worker run a parfor in order to have workers for workers.

2 个评论
显示无隐藏无

ROSALBA CACCIAPUOTI 2020-6-11

thanks, but can i run my sequential code (without parfor / spmd) on a fixed number of cores?

Walter Roberson 2020-6-11

https://www.mathworks.com/help/matlab/ref/maxnumcompthreads.html

You asked about cluster profiles, and clusters are only involved for parfor, spmd, parfEeval, parfEvalOnAll, and batch. For hpc clusters, batch would seem most likely for what you are asking about. For clusters you would not use the above link: you would edit the cluster profile to control the number of threads given to each worker.

请先登录，再进行评论。