Dependent partitioning
Abstract
A key problem in parallel programming is how data is partitioned: divided into subsets that can be operated on in parallel and, in distributed memory machines, spread across multiple address spaces.
Related papers
- Partitioning Dataflow Analyses Using Types POPL 1997
- Automatic Placement of Communications in Mesh-Partitioning Parallelization PPoPP 1997
- Graph partitioning applied to DAG scheduling to reduce NUMA effects PPoPP 2018
- Language support for dynamic, hierarchical data partitioning OOPSLA 2013
- Compiler-directed Data Partitioning for Multicluster Processors CGO 2006
- Welcome to the Parti(tioning) (Functional Pearl): Using Rewrite Rules and Specialisation to Partition Haskell Programs Haskell 2024
- Software partitioning of hardware transactions PPoPP 2015
- Automatically exploiting cross-invocation parallelism using runtime information CGO 2013