A data parallel view on polyhedral process networks

Balevic, Ana; Kienhuis, Bart

doi:10.1145/1988932.1988939

Search citation statements

Order By: Relevance

Paper Sections

Select...

Related Work1

Phase Iii: Mapping To Thread Hierarchy1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2011

2018

Publication Types

Select...

Other4

Article1

Relationship

Self Cite1

Independent4

Authors

Journals

Cited by 5 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the authors of [36] propose an execution model for single program multiple data (SPMD) on GPUs, based on a polyhedral model based formulation. They propose a way to extract "thread parallelism" from actual (non fully polyhedral) applications.…”

Section: Related Workmentioning

confidence: 99%

Polyhedral Dataflow Programming: A Case Study

Fontaine

Gonnord

Morel

2018

2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Polyhedral Dataflow Programming: A Case Study

Fontaine

Gonnord

Morel

2018

2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)

View full text Add to dashboard Cite

“…The result of this phase is a model called Data Parallel View (DPV) on PPNs [3], which introduces abstractions required to capture and exploit data parallelism on top of the PPN model. The DPV model exposes identified data parallelism, adopts the PPN components for mapping onto shared memory architectures, and enables generation of data parallel source code for different parallel programming models.…”

Section: Phase Iii: Mapping To Thread Hierarchymentioning

confidence: 99%

Kpn2gpu

Balevic

Kienhuis

2011

SIGARCH Comput. Archit. News

Self Cite

View full text Add to dashboard Cite

With advances in manycore and accelerator architectures, the high performance and embedded spaces are rapidly converging. Emerging architectures feature different forms of parallelism. The Polyhedral Processes Networks (PPNs) are a proven model of choice for automated generation of pipeline and task parallel programs from sequential source code, however data parallelism is not addressed. In this paper, we present a systematic approach for identification and extraction of fine grain data parallelism from the PPN specification. The approach is implemented in a tool, called kpn2gpu, which produces fine-grain data parallel CUDA kernels for graphics processing units (GPUs). First experiments indicate that generated applications have a potential to exploit different forms of parallelism provided by the architecture and that kernels feature a highly regular structure that allows subsequent optimizations.

show abstract