A stream-computing extension to OpenMP

Pop, Antoniu; Cohen, Albert

doi:10.1145/1944862.1944867

Cited by 37 publications

(28 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of languages adopted to describe pipelined applications are StreamIt [9] and OpenMP, extended as proposed by Pop et al [10]. The former is a high level java-based language proposed for the design of streaming applications that allows only to describe the structure of a SDF graph without mapping nor scheduling information.…”

Section: Related Workmentioning

confidence: 99%

“…Since the ordering of the actor activations which compose a PSOS is absolute, this can be described by simply specifying the order between each pair of activations: all the other relative orderings will be implied by these. DSM forces the actor of choice of a decision state to be executed before all the other active actors, but to guarantee the satisfaction of the required schedule it is sufficient to impose that in each decision state the actor of choice is executed before the actor which follows it in the schedule (lines [8][9][10][11][12][13][14][15][16][17][18][19]). This optimization, like the ones proposed in [2], aims at reducing the size of the produced graph, but since they are not equivalent, they have all to be applied in order to produce the smallest graph.…”

Section: A Modeling Of Mapping and Schedulingmentioning

confidence: 99%

See 1 more Smart Citation

Modeling pipelined application with Synchronous Data Flow graphs

Lattuada

Ferrandi

2013

2013 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS)

View full text Add to dashboard Cite

Abstract-Streaming applications can efficiently exploit multiprocessors architectures by means of pipelined parallelism, but designing this type of applications can be an hard task. Different subproblems have indeed to be solved: partitioning, mapping, scheduling and pipeline stage assignment. For this reason, high level abstraction models are adopted during design flow since they simplify this process by hiding most of the architectural details. Synchronous Data Flow (SDF) graphs, widely adopted to describe streaming applications, naturally model only their partitioning, so they usually have to be integrated with other types of representations.In this paper Pipelined Application Modeling (PAM), a methodology to create a Synchronous Data Flow graph describing all the aspects of a pipelined application, is presented. The methodology starts from the SDF graph describing the partitioning of the application and enriches it with new actors and channels detailing the mapping, the scheduling and the pipeline stage assignment of the considered solution. The obtained SDF graph, describing all the aspects of the solution in a formal and compact way, facilitates the evaluation of different solutions during design space exploration.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: A Modeling Of Mapping and Schedulingmentioning

confidence: 99%

Modeling pipelined application with Synchronous Data Flow graphs

Lattuada

Ferrandi

2013

2013 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS)

View full text Add to dashboard Cite

show abstract

“…In contrast with common streaming frameworks, the communication patterns can be dynamic, while preserving the determinism of arbitrarily merging and splitting data streams. The GCC prototype implementation of the OpenMP extension for stream-computing has been shown to be efficient to exploit mixed pipeline-and data-parallelism, even in dynamic task graphs [Pop and Cohen 2011]. It relies on compiler and runtime optimizations to improve cache locality and relies on a highly efficient lock-free and atomic operation-free synchronization algorithm for streams.…”

Section: Openmp Stream Extensionmentioning

confidence: 99%

Synchronous programming in audio processing

Barkati

Jouvelot

2013

ACM Comput. Surv.

View full text Add to dashboard Cite

The adequacy of a programming language to a given software project or application domain is often considered a key factor of success in software development and engineering, even though little theoretical or practical information is readily available to help make an informed decision. In this paper, we address a particular version of this issue by comparing the adequacy of general-purpose synchronous programming languages to more domain-specific languages (DSL) in the field of computer music. More precisely, we implemented and tested the same lookup table oscillator example program, one of the most classical algorithms for sound synthesis, using a selection of significant synchronous programming languages, half of which designed as specific music languages -Csound, Pure Data, SuperCollider, ChucK, Faust -and the other half being general synchronous formalisms -Signal, Lustre, Esterel, Lucid Synchrone and C with the OpenMP Stream Extension (Matlab/Octave is used for the initial specification). The advantages of these two approaches are discussed, providing insights to language designers and possibly software developers of both communities regarding programming languages design for the audio domain.

show abstract

“…The closest work to our approach towards automatic streaming of task based programs is through extensions to OpenMP [21], but the OpenMP annotations, even though simple, are not easy to automatically infer and the generality of streaming graphs that can be expressed is limited by the use of OpenMP as foundation. Furthermore, the resulting program is not deadlock-free.…”

Section: Related Workmentioning

confidence: 99%

SCnC: Efficient Unification of Streaming with Dynamic Task Parallelism

Sbîrlea

Shirako

Newton

et al. 2011

2011 First Workshop on Data-Flow Execution Models for Extreme Scale Computing

View full text Add to dashboard Cite

Stream processing is a special form of the dataflow execution model that offers extensive opportunities for optimization and automatic parallelization. To take full advantage of the paradigm, however, typically requires programmers to learn a new language and re-implement their applications. This work shows that it is possible to exploit streaming as a safe and automatic optimization of a more general dataflow-based model-one in which computation kernels are written in standard, general-purpose languages and organized as a coordination graph.We propose Streaming Concurrent Collections (SCnC), a streaming system that can efficiently run a subset of programs supported by Concurrent Collections (CnC). CnC is a general purpose parallel programming paradigm with a task-parallel look and feel but based on dataflow graph principles. Its expressivity extends to any arbitrary task graph. Integration of these models would allow application developers to benefit from the performance and tight memory footprint of stream parallelism for eligible subgraphs of their application.In this paper we formally define the requirements (streaming access patterns) needed for using SCnC, and outline a static decision procedure for identifying and processing eligible SCnC subgraphs. We present initial results on an prototype implementation that show that transitioning from general CnC to SCnC leads to a throughput increase of up to 40× for certain benchmarks, and also enable programs with large data sizes to execute in available memory for cases where CnC execution may run out of memory.

show abstract

A stream-computing extension to OpenMP

Cited by 37 publications

References 14 publications

Modeling pipelined application with Synchronous Data Flow graphs

Modeling pipelined application with Synchronous Data Flow graphs

Synchronous programming in audio processing

SCnC: Efficient Unification of Streaming with Dynamic Task Parallelism

Contact Info

Product

Resources

About