Engineering parallel symbolic programs in GPH

SUMMARYThis paper provides an assessment of high-level parallel programming models for multi-core programming by implementing two versions of the n-body problem. We compare three different parallel programming models based on parallel Haskell, differing in the ways how potential parallelism is identified and managed. We assess the performance of each implementation, discuss the sequential and parallel tuning steps leading to the final versions, and draw general conclusions on the suitability of high-level parallel programming models for multi-core programming. We achieve speed-ups of up to 7.2 for the all-pairs algorithm and up to 6.5 for the Barnes-Hut algorithm on an 8-core machine.

show abstract

“…We follow guidelines established in [31,Sec 3] with some flexibility. The approach we use is as follows:…”

Section: Parallelisation Methodologymentioning

confidence: 96%

Parallel Haskell implementations of the N‐body problem

Totoo

Loidl

2013

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Here, the programmer does not need to adapt the program to different computational GRID architectures and only needs to structure the sumTotient function appropriately and add the architecture-neutral evaluation strategy at the last line of the function. A thorough account of how one can engineer efficient parallel programs in GPH is given in [39]. The cost of providing the programmer with such a highlevel abstraction is that GPH requires an elaborate RTE to dynamically manage parallel execution on complex architectures, and these are described next.…”

Section: Glasgow Parallel Haskell (Gph)mentioning

confidence: 99%

“…The GUM implementation of GPH delivers good performance for a range of parallel benchmark applications on a variety of parallel architectures, including shared-memory and distributed-memory architectures [39]. GUM's performance is also comparable with other mature parallel functional languages [7].…”

Section: Gum Performancementioning

confidence: 99%

Evaluating a High-Level Parallel Language (GpH) for Computational GRIDs

Zain¹,

Trinder²,

Michaelson

et al. 2008

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Abstract-Computational GRIDs potentially offer low-cost, readily available, and large-scale high-performance platforms. For the parallel execution of programs, however, computational GRIDs pose serious challenges: they are heterogeneous and have hierarchical and often shared interconnects, with high and variable latencies between clusters. This paper investigates whether a programming language with high-level parallel coordination and a Distributed Shared Memory (DSM) model can deliver good and scalable performance on a range of computational GRID configurations. The high-level language Glasgow parallel Haskell (GpH) abstracts over the architectural complexities of the computational GRID, and we have developed GRID-GUM2, a sophisticated grid-specific implementation of GpH, to produce the first high-level DSM parallel language implementation for computational GRIDs. We report a systematic performance evaluation of GRID-GUM2 on combinations of high/low and homogeneous/heterogeneous computational GRIDs. We measure the performance of a small set of kernel parallel programs representing a variety of application areas, two parallel paradigms, and ranges of communication degree and parallel irregularity. We investigate GRI D-GUM2's performance scalability on medium-scale heterogeneous and high-latency computational GRIDs and analyze the performance with respect to the program characteristics of communication frequency and degree of irregular parallelism.

show abstract

“…The GUM implementation delivers good performance for a range of parallel benchmark applications written using the GPH parallel dialect of Haskell. These benchmarks have been tested on a variety of parallel architectures, including shared and distributed-memory architectures [26], and a wide-area computational Grid [3].…”

Section: Figure 3 Load Distribution In Gummentioning

confidence: 99%