Methodology for modelling SPMD hybrid parallel computation

Liebrock, L. M.; Goudy, S. P.

doi:10.1002/cpe.1214

Cited by 7 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this sense, this parallelism has permitted developing a set of techniques in order to take advantage of the computational power of these multi-core clusters. A particular method has been developed by Liedbrock et al [12], where he defined a method to create a performance model for hybrid SPMD applications (MPI/OpenMP). The main focus of this work was to improve three main performance metrics: adaptability, fidelity and scalability.…”

Section: Related Workmentioning

confidence: 99%

An approach for an efficient execution of SPMD applications on Multi-core environments

Muresano

Meyer

Rexachs

et al. 2017

Future Generation Computer Systems

View full text Add to dashboard Cite

Executing traditional Message Passing Interface (MPI) applications on multi-core cluster balancing speed and computational efficiency is a difficult task that parallel programmers have to deal with. For this reason, communications on multi-core clusters ought to be handled carefully in order to improve performance metrics such as efficiency, speedup, execution time and scalability. In this paper we focus our attention on SPMD (Single Program Multiple Data) applications with high communication volume and synchronicity and also following characteristics such as: static, local and regular. This work proposes a method for SPMD applications, which is focused on managing the communication heterogeneity (different cache level, RAM memory, network, etc.) on homogeneous multi-core computing platform in order to improve the application efficiency. In this sense, the main objective of this work is to find analytically the ideal number of cores necessary that allows us to obtain the maximum speedup, while the computational efficiency is maintained over a defined threshold (strong scalability). This method also allows us to determine how the problem size must be increased in order to maintain an execution time constant while the number of cores are expanded (weak scalability) considering the tradeoff between speed and efficiency. This methodology has been tested with different benchmarks and applications and we achieved an average improvement around 30.35% of efficiency in applications tested using different problems sizes and multi-core clusters. In addition, results show that maximum speedup with a defined efficiency is located close to the values calculated with our analytical model with an error rate lower than 5% for the applications tested.This research has been supported by the MINECO (MICINN) Spain under contracts TIN2011-24384 and TIN2014-\ud 53172-PPeer ReviewedPostprint (author's final draft

show abstract

Section: Related Workmentioning

confidence: 99%

An approach for an efficient execution of SPMD applications on Multi-core environments

Muresano

Meyer

Rexachs

et al. 2017

Future Generation Computer Systems

View full text Add to dashboard Cite

show abstract

“…A two-level model that characterizes the impact of contention and cache effects and, at the same time, develops and studies a graph model of the application is presented in [18]. There exist similar works for hybrid MPI/OpenMP computation, that can help to decide the best combination of MPI processes and OpenMP threads depending on the characteristics of the machine and the code [19], [20], [21].…”

Section: Related Workmentioning

confidence: 99%

Constructing Performance Models for Dense Linear Algebra Algorithms on Cray XE Systems

González-Domínguez,

Georganas,

Zheng

et al. 2014

Preprint

View full text Add to dashboard Cite

Hiding or minimizing the communication cost is key in order to obtain good performance on large-scale systems. While communication overlapping attempts to hide communications cost, 2.5D communication avoiding algorithms improve performance scalability by reducing the volume of data transfers at the cost of extra memory usage. Both approaches can be used together or separately and the best choice depends on the machine, the algorithm and the problem size. Thus, the development of performance models is crucial to determine the best option for each scenario. In this paper, we present a methodology for constructing performance models for parallel numerical routines on Cray XE systems. Our models use portable benchmarks that measure computational cost and network characteristics, as well as performance degradation caused by simultaneous accesses to the network. We validate our methodology by constructing the performance models for the 2D and 2.5D approaches, with and without overlapping, of two matrix multiplication algorithms (Cannon's and SUMMA), triangular solve (TRSM) and Cholesky. We compare the estimations provided by these models with the experimental results using up to 24,576 cores of a Cray XE6 system and predict the performance of the algorithms on larger systems. Results prove that the estimations significantly improve when taking into account network contention.

show abstract