commit | 6e811d75facf0a6cbff0ee9ff93c15beedc1302f | [log] [tgz] |
---|---|---|
author | arnabp <arnab.phani@tugraz.at> | Sun May 03 16:26:05 2020 +0200 |
committer | Matthias Boehm <mboehm7@gmail.com> | Sun May 03 17:01:11 2020 +0200 |
tree | 4a2d601499b6fa45ba34cbd234fc3c8cef1acfc9 | |
parent | 1c40be6e31975ddc8e734b6613fdb32997ba0439 [diff] |
[SYSTEMDS-335] Weighted eviction policy in lineage cache This patch contains a new eviction policy for lineage cache. A min-heap based priority queue over a function of computation time and size is maintained to define the order of evictions.The idea is to evict large matrices, which take little time to recompute. This weighted scheme significantly reduces the number of evictions (including disk spilling). This patch also refactors the LineageCache class to hide the eviction policy related maintenance. Closes #905.
Overview: SystemDS is a versatile system for the end-to-end data science lifecycle from data integration, cleaning, and feature engineering, over efficient, local and distributed ML model training, to deployment and serving. To this end, we aim to provide a stack of declarative languages with R-like syntax for (1) the different tasks of the data-science lifecycle, and (2) users with different expertise. These high-level scripts are compiled into hybrid execution plans of local, in-memory CPU and GPU operations, as well as distributed operations on Apache Spark. In contrast to existing systems - that either provide homogeneous tensors or 2D Datasets - and in order to serve the entire data science lifecycle, the underlying data model are DataTensors, i.e., tensors (multi-dimensional arrays) whose first dimension may have a heterogeneous and nested schema.
Quick Start Install, Quick Start and Hello World
Documentation: SystemDS Documentation
Python Documentation Python SystemDS Documentation
Status and Build: SystemDS is still in pre-alpha status. The original code base was forked from Apache SystemML 1.2 in September 2018. We will continue to support linear algebra programs over matrices, while replacing the underlying data model and compiler, as well as substantially extending the supported functionalities. Until the first release, you can build your own snapshot via Apache Maven: mvn clean package -P distribution
.