Parallel Coordination Made Explicit in a Functional Setting

Berthold, Jost; Loogen, Rita

doi:10.1007/978-3-540-74130-5_5

Cited by 8 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some parts of the implementation which were originally implemented directly in the runtime system have now been lifted to the Haskell level, relying on simpler and more modular runtime system support (Berthold et al, 2003). This refinement ultimately led to factoring out the EdI language: all Eden language constructs are now implemented in Haskell, using the simpler primitive operations that implement EdI directly (Berthold & Loogen, 2007;Berthold, 2008).…”

Section: Implementations Of Gph and Edenmentioning

confidence: 99%

PAEAN: Portable and scalable runtime support for parallel Haskell dialects

Berthold

Loidl²,

Hammond

2016

J. Funct. Prog.

Self Cite

View full text Add to dashboard Cite

Over time, several competing approaches to parallel Haskell programming have emerged. Different approaches support parallelism at various different scales, ranging from small multicores to massively parallel high-performance computing systems. They also provide varying degrees of control, ranging from completely implicit approaches to ones providing full programmer control. Most current designs assume a shared memory model at the programmer, implementation and hardware levels. This is, however, becoming increasingly divorced from the reality at the hardware level. It also imposes significant unwanted runtime overheads in the form of garbage collection synchronisation etc. What is needed is an easy way to abstract over the implementation and hardware levels, while presenting a simple parallelism model to the programmer.The PAEAN (PArallEl shAred Nothing) runtime system design aims to provide a portable and high-level shared-nothing implementation platform for parallel Haskell dialects. It abstracts over major issues such as work distribution and data serialisation, consolidating existing, successful designs into a single framework. It also provides an optional virtual shared-memory programming abstraction for (possibly) shared-nothing parallel machines, such as modern multicore/manycore architectures or cluster/cloud computing systems. It builds on, unifies, and extends, existing well-developed support for shared-memory parallelism that is provided by the widely-used GHC Haskell compiler. This paper summarises the state-of-the-art in shared-nothing parallel Haskell implementations, introduces the PAEAN abstractions, shows how they can be used to implement three distinct parallel Haskell dialects, and demonstrates that good scalability can be obtained on recent parallel machines. * Corresponding author. Reported work performed while at the University of Copenhagen (DIKU).

show abstract

Section: Implementations Of Gph and Edenmentioning

confidence: 99%

PAEAN: Portable and scalable runtime support for parallel Haskell dialects

Berthold

Loidl²,

Hammond

2016

J. Funct. Prog.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In principle, it shares its parallel runtime system (PRTS) with Glasgow parallel Haskell [58] but due to the disjoint address spaces of its processes does not need to implement a virtual shared memory and global garbage collection in contrast to GpH. In the following, we abstract from low-level implementation details like graph reduction and thread management which are explained elsewhere [47,58,14,34] and describe Eden's implementation on top of the module This module provides primitive monadic operations which are used to implement the Eden constructs on a higher-level of abstraction [10]. …”

Section: Behind the Scenes: Eden's Implementationmentioning

confidence: 99%

“…Basic information on its design, semantics, and implementation as well as the underlying programming methodology can be found in [39,13]. Details on the parallel runtime system and Eden's concept of implementation can best be found in [8,10,4]. The technique of layered parallel runtime environments has been further developed and generalised by Berthold, Loidl and Al Zain [3,12].…”

Section: Further Readingmentioning

confidence: 99%

Eden – Parallel Functional Programming with Haskell

Loogen

2012

Central European Functional Programming School

Self Cite

View full text Add to dashboard Cite

Abstract. Eden is a parallel functional programming language which extends Haskell with constructs for the definition and instantiation of parallel processes. Processes evaluate function applications remotely in parallel. The programmer has control over process granularity, data distribution, communication topology, and evaluation site, but need not manage synchronisation and data exchange between processes. The latter are performed by the parallel runtime system through implicit communication channels, transparent to the programmer. Common and sophisticated parallel communication patterns and topologies, so-called algorithmic skeletons, are provided as higher-order functions in a user-extensible skeleton library written in Eden. Eden is geared toward distributed settings, i.e. processes do not share any data, but can equally well be used on multicore systems. This tutorial gives an up-to-date introduction into Eden's programming methodology based on algorithmic skeletons, its language constructs, and its layered implementation on top of the Glasgow Haskell compiler.

show abstract

“…If the originating cluster is weaker or equally strong, the FISH message is served as usual. In Figure 9, after updating the dynamic information (1), the sender cluster is compared to the receiver cluster (2), and a bigger amount of sparks is retrieved and sent if appropriate (3). In this case the RTE temporarily switches from passive to active load distribution.…”

Section: Adaptive Load Distribution Mechanismsmentioning

confidence: 99%

“…In this sense, ArTCoP provides a generic and adaptive system for parallel computation, combining features of our existing parallel RTEs for GpH [19] and Eden [2,3]. We present a prototype implementation of key concepts in such a system in the form of an executable specification, amenable to formal reasoning.…”

Section: Introductionmentioning

confidence: 99%

Scheduling Light-Weight Parallelism in ArTCoP

Berthold

Zain²,

Loidl

Practical Aspects of Declarative Languages

Self Cite

View full text Add to dashboard Cite

Abstract. We present the design and prototype implementation of the scheduling component in ArTCoP (architecture transparent control of parallelism), a novel run-time environment (RTE) for parallel execution of high-level languages. A key feature of ArTCoP is its support for deep process and memory hierarchies, shown in the scheduler by supporting light-weight threads. To realise a system with easily exchangeable components, the system defines a micro-kernel , providing basic infrastructure, such as garbage collection. All complex RTE operations, including the handling of parallelism, are implemented at a separate system level. By choosing Concurrent Haskell as high-level system language, we obtain a prototype in the form of an executable specification that is easier to maintain and more flexible than conventional RTEs. We demonstrate the flexibility of this approach by presenting implementations of a scheduler for light-weight threads in ArTCoP, based on GHC Version 6.6.

show abstract

Parallel Coordination Made Explicit in a Functional Setting

Cited by 8 publications

References 10 publications

PAEAN: Portable and scalable runtime support for parallel Haskell dialects

PAEAN: Portable and scalable runtime support for parallel Haskell dialects

Eden – Parallel Functional Programming with Haskell

Scheduling Light-Weight Parallelism in ArTCoP

Contact Info

Product

Resources

About