[
https://issues.apache.org/jira/browse/SYSTEMML-1310?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Matthias Boehm updated SYSTEMML-1310:
-------------------------------------
Description:
This task aims to add basic support for block partitioning of fixed size
batches of rows or columns in the parfor optimizer and runtime. For now, we
will only apply this for the spark execution backend. The basic supported form
looks as follows, where we require that batches are aligned with the systemml
blocksize.
{code}
N = 20;
parfor(bi in 1 : nrow(X)/N) {
Xbi = X[((bi-1)*N+1):(bi*N), ];
R[bi, 1] = sum(Xbi);
}
{code}
> Parfor block partitioning (mini batches)
> ----------------------------------------
>
> Key: SYSTEMML-1310
> URL: https://issues.apache.org/jira/browse/SYSTEMML-1310
> Project: SystemML
> Issue Type: Sub-task
> Components: APIs, Runtime
> Reporter: Matthias Boehm
>
> This task aims to add basic support for block partitioning of fixed size
> batches of rows or columns in the parfor optimizer and runtime. For now, we
> will only apply this for the spark execution backend. The basic supported
> form looks as follows, where we require that batches are aligned with the
> systemml blocksize.
> {code}
> N = 20;
> parfor(bi in 1 : nrow(X)/N) {
> Xbi = X[((bi-1)*N+1):(bi*N), ];
> R[bi, 1] = sum(Xbi);
> }
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
