Source-to-Source Parallelization Compilers for Scientific Shared-Memory Multi-core and Accelerated Multiprocessing: Analysis, Pitfalls, Enhancement and Potential

Harel, Re'em; Mosseri, Idan; Levin, Harel; Alon, Lee-or; Rusanovsky, Matan; Oren, Gal

doi:10.1007/s10766-019-00640-3

Cited by 18 publications

(18 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The automatic parallelization of serial programs has achieved some good results, but these have been mainly targeted at certain research directions or fields, 17 and they are unable to be applied to automatic parallelization in other fields. However, the emergence of the open‐source Par4All automatic parallelization platform has improved the practicality of automatic parallelization to a new level 18‐20 . Although Par4All implements the automatic parallelization of an algorithm, it has been found through experiments that Par4All's automatic conversion process takes a long time; meanwhile, according to our experiments in this study, some generated RS image‐enhancement automatic parallel algorithms were only minimally accelerated.…”

Section: Introductionmentioning

confidence: 69%

“…However, the emergence of the open-source Par4All automatic parallelization platform has improved the practicality of automatic parallelization to a new level. [18][19][20] Although Par4All implements the automatic parallelization of an algorithm, it has been found through experiments that Par4All's automatic conversion process takes a long time; meanwhile, according to our experiments in this study, some generated RS image-enhancement automatic parallel algorithms were only minimally accelerated. In order to resolve these problems, it is particularly important to study automatic parallel optimization models.…”

mentioning

confidence: 78%

See 1 more Smart Citation

Preliminary study on the automatic parallelism optimization model for image enhancement algorithms based on Intel's® Xeon Phi

Huang

Yang

Jian

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

In unmanned aerial vehicle (UAV) image-processing applications, one needs to implement different parallel image-enhancement algorithms on several high-performance computing platforms utilizing various programming models. To speed up the parallelization procedure and improve its efficiency, the automatic parallel software package, Par4All, is applied in this work. We find that the performance of the original automatic parallelization algorithm produced with Par4All is inefficient. To resolve this problem, we propose different optimization approaches for Par4All based on Intel®'s Xeon Phi high-performance computing platform that are based on the structural features of the image-enhancement algorithms, which can further optimize the original parallel algorithm. These approaches mainly include: (1) Par4All automatic parallel search module optimization, (2) dynamic thread setting optimization, and (3) the collaborative parallelization of both CPU and many integrated core (MIC) processors.According to the results of the comparison experiments involving different algorithms, it is shown that the proposed optimization approaches for these kinds of algorithms can significantly improve the performance of automatic parallel algorithms. The acceleration ratio increases approximately by 30%, 70%, and 80% for the multiscale Retinex, Gaussian-filtering and median-filtering algorithms, respectively. As continuation and deepening of our previous research work, this research has the potential to be beneficial for other researchers in image-processing applications with image-enhancement algorithms. K E Y W O R D Sautomatic parallelism, image-enhancement algorithms, Par4All, Intel® Xeon Phi, unmanned aerial vehicles INTRODUCTIONAs mentioned by References 1, it is known that some image-enhancement algorithms, for example, median filtering, Gaussian filtering, wavelet transform, and the multiscale Retinex (MSR) algorithm, are used when preprocessing large amounts of unmanned aerial vehicle (UAV) remote-sensing (RS) images to solve the problems of poor clarity, insufficient contrast and low adaptability. In addition, many-cores computing platforms, e.g., graphics processing units (GPUs) and many integrate cores (MICs), have been involved in the development of some parallel algorithms to speed up the processing times 2 ; such approaches are expected to become mainstream in the near future. Experimental results have shown that parallelized algorithms can significantly improve computation speed and provide better acceleration efficiency. [3][4][5] Usually, there are different kinds of serial

show abstract

Section: Introductionmentioning

confidence: 69%

mentioning

confidence: 78%

Preliminary study on the automatic parallelism optimization model for image enhancement algorithms based on Intel's® Xeon Phi

Huang

Yang

Jian

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Compiladores paralelizadores ignoram reduções cuja paralelização exigiria refatoração significativa do código. Eles geralmente operam exigindo nenhuma ou mínima intervenção manual do programador [Harel et al 2020]. Também existem ferramentas que apenas detectam reduções, sem fazer esforço para paralelizá-las.…”

Section: Estado Da Arteunclassified

Uma proposta de algoritmo de detecção automática de operações de redução em programas C sequenciais

Rezende¹,

Santos²,

Cavalheiro³

2021

Anais Da XXI Escola Regional De Alto Desempenho Da Região Sul (ERAD RS 2021)

View full text Add to dashboard Cite

Compiladores paralelizadores buscam otimizar programas sequenciais pela exploração dos recursos paralelos oferecidos pelo hardware. As estratégias atualmente empregadas, no entanto, não são eﬁcientes na detecção de paralelismo em laços cujo corpo das iterações seja representado por um bloco de comandos. Este artigo propõe uma heurística de detecção de paralelismo em laços contendo reduções de variáveis em um bloco de comandos.

show abstract

“…They observed that Par4All requires no manual intervention, while Cetus and AutoPar require minimal manual intervention, thus allowing us to consider them for this work. Harel et al [1] focused on Cetus, Par4All, and AutoPar [20] while eliminating the need for the rest of the S2S automatic parallelization compilers. [1] briefly discussed these compilers (regarding both history and work fashion) and presented each compiler's strengths and weaknesses.…”

Section: Related Workmentioning

confidence: 99%

“…Harel et al [1] focused on Cetus, Par4All, and AutoPar [20] while eliminating the need for the rest of the S2S automatic parallelization compilers. [1] briefly discussed these compilers (regarding both history and work fashion) and presented each compiler's strengths and weaknesses. Moreover, [1] tested the performance of these compilers in the Matrix Multiplication kernel and the NAS benchmark [18].…”

Section: Related Workmentioning

confidence: 99%

ComPar: Optimized Multi-Compiler for Automatic OpenMP S2S Parallelization

Mosseri

Alon

Harel

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Parallelization schemes are essential in order to exploit the full benefits of multi-core architectures, which have become widespread in recent years. In shared-memory architectures, the most comprehensive parallelization API is OpenMP. However, the introduction of correct and optimal OpenMP parallelization to applications is not always a simple task, due to common parallel shared-memory management pitfalls, architecture heterogeneity and the current necessity for human expertise in order to comprehend many fine details and abstract correlations. To ease this process, many automatic parallelization compilers were created over the last decade. [1] tested several source-to-source compilers and concluded that each has its advantages and disadvantages and no compiler is superior to all other compilers in all tests. This indicates that a fusion of the compilersâĂŹ best outputs under the best hyper-parameters for the current hardware setups can yield greater speedups. To create such a fusion, one should execute a computationally intensive hyper-parameter sweep, in which the performance of each option is estimated and the best option is chosen. We created a novel parallelization source-to-source multi-compiler named ComPar, which uses code segmentation-and-fusion with hyper-parameters tuning to achieve the best parallel code possible without any human intervention while maintaining the program's validity. In this paper we present ComPar and analyze its results on NAS and PolyBench benchmarks. We conclude that although the resources ComPar requires to produce parallel code are greater than other source-to-source parallelization compilers -as it depends on the number of parameters the user wishes to consider, and their combinations -ComPar achieves superior performance overall compared to the serial code version and other tested parallelization compilers. ComPar is publicly available at: https: //github.com/Scientific-Computing-Lab-NRCN/compar.

show abstract

Source-to-Source Parallelization Compilers for Scientific Shared-Memory Multi-core and Accelerated Multiprocessing: Analysis, Pitfalls, Enhancement and Potential

Cited by 18 publications

References 20 publications

Preliminary study on the automatic parallelism optimization model for image enhancement algorithms based on Intel's® Xeon Phi

Preliminary study on the automatic parallelism optimization model for image enhancement algorithms based on Intel's® Xeon Phi

Uma proposta de algoritmo de detecção automática de operações de redução em programas C sequenciais

ComPar: Optimized Multi-Compiler for Automatic OpenMP S2S Parallelization

Contact Info

Product

Resources

About