A programming model performance study using the NAS parallel benchmarks

Shan, Hongzhang; Blagojevic, Filip; Min, Seung-Jai; Hargrove, Paul; Jin, Haoqiang; Fuerlinger, Karl; Koniges, Alice; Wright, Nicholas J.

doi:10.3233/spr-2010-0306

Title: A programming model performance study using the NAS parallel benchmarks

Full Record
Other Related Research

Abstract

Harnessing the power of multicore platforms is challenging due to the additional levels of parallelism present. In this paper we use the NAS Parallel Benchmarks to study three programming models, MPI, OpenMP and PGAS to understand their performance and memory usage characteristics on current multicore architectures. To understand these characteristics we use the Integrated Performance Monitoring tool and other ways to measure communication versus computation time, as well as the fraction of the run time spent in OpenMP. The benchmarks are run on two different Cray XT5 systems and an Infiniband cluster. Our results show that in general the three programming models exhibit very similar performance characteristics. In a few cases, OpenMP is significantly faster because it explicitly avoids communication. For these particular cases, we were able to re-write the UPC versions and achieve equal performance to OpenMP. Using OpenMP was also the most advantageous in terms of memory usage. Also we compare performance differences between the two Cray systems, which have quad-core and hex-core processors.We show that at scale the performance is almost always slower on the hex-core system because of increased contention for network resources.

Authors:

Shan, Hongzhang ^[1]; Blagojevic, Filip ^[1]; Min, Seung-Jai ^[1]; Hargrove, Paul ^[1]; Jin, Haoqiang ^[2]; Fuerlinger, Karl ^[3]; Koniges, Alice ^[4]; Wright, Nicholas J. ^[4]

Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Computational Research Division
NASA Ames Research Center (ARC), Moffett Field, Mountain View, CA (United States)
Univ. of California, Berkeley, CA (United States). Electrical Engineering & Computer Sciences Dept.
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)

Publication Date:: 2010-01-01

Research Org.:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF), Oak Ridge, TN (United States): Univ. of California, Oakland, CA (United States); UT-Battelle LLC/ORNL, Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

OSTI Identifier:: 1564727

Grant/Contract Number:: AC02-05CH11231; AC05-00OR22725

Resource Type:: Journal Article: Accepted Manuscript

Journal Name:: Scientific Programming

Additional Journal Information:: Journal Volume: 18; Journal Issue: 3-4

Publisher:: Hindawi

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; Computer Science; Programming model; performance study; UPC; OpenMP; MPI; memory usage

Citation Formats


                    Shan, Hongzhang, Blagojevic, Filip, Min, Seung-Jai, Hargrove, Paul, Jin, Haoqiang, Fuerlinger, Karl, Koniges, Alice, and Wright, Nicholas J. A programming model performance study using the NAS parallel benchmarks.  United States: N. p., 2010. 
        Web.  doi:10.3233/spr-2010-0306.

Copy to clipboard


                    Shan, Hongzhang, Blagojevic, Filip, Min, Seung-Jai, Hargrove, Paul, Jin, Haoqiang, Fuerlinger, Karl, Koniges, Alice, & Wright, Nicholas J. A programming model performance study using the NAS parallel benchmarks.  United States.  https://doi.org/10.3233/spr-2010-0306

Copy to clipboard


                    Shan, Hongzhang, Blagojevic, Filip, Min, Seung-Jai, Hargrove, Paul, Jin, Haoqiang, Fuerlinger, Karl, Koniges, Alice, and Wright, Nicholas J. 2010.  
        "A programming model performance study using the NAS parallel benchmarks".  United States.  https://doi.org/10.3233/spr-2010-0306.  https://www.osti.gov/servlets/purl/1564727.

Copy to clipboard


                    
@article{osti_1564727,

  title        = {A programming model performance study using the NAS parallel benchmarks},

  author       = {Shan, Hongzhang and Blagojevic, Filip and Min, Seung-Jai and Hargrove, Paul and Jin, Haoqiang and Fuerlinger, Karl and Koniges, Alice and Wright, Nicholas J.},

  abstractNote = {Harnessing the power of multicore platforms is challenging due to the additional levels of parallelism present. In this paper we use the NAS Parallel Benchmarks to study three programming models, MPI, OpenMP and PGAS to understand their performance and memory usage characteristics on current multicore architectures. To understand these characteristics we use the Integrated Performance Monitoring tool and other ways to measure communication versus computation time, as well as the fraction of the run time spent in OpenMP. The benchmarks are run on two different Cray XT5 systems and an Infiniband cluster. Our results show that in general the three programming models exhibit very similar performance characteristics. In a few cases, OpenMP is significantly faster because it explicitly avoids communication. For these particular cases, we were able to re-write the UPC versions and achieve equal performance to OpenMP. Using OpenMP was also the most advantageous in terms of memory usage. Also we compare performance differences between the two Cray systems, which have quad-core and hex-core processors.We show that at scale the performance is almost always slower on the hex-core system because of increased contention for network resources.},

  doi          = {10.3233/spr-2010-0306},

  url          = {https://www.osti.gov/biblio/1564727},
  journal      = {Scientific Programming},
number       = 3-4,

  volume       = 18,

  place        = {United States},

  year         = {2010},

  month        = {1}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.3233/spr-2010-0306

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

A Programming Model Performance Study Using the NAS Parallel Benchmarks

Journal Article Shan, Hongzhang; Blagojević, Filip; Min, Seung-Jai; ... - Scientific Programming

Harnessing the power of multicore platforms is challenging due to the additional levels of parallelism present. In this paper we use the NAS Parallel Benchmarks to study three programming models, MPI, OpenMP and PGAS to understand their performance and memory usage characteristics on current multicore architectures. To understand these characteristics we use the Integrated Performance Monitoring tool and other ways to measure communication versus computation time, as well as the fraction of the run time spent in OpenMP. The benchmarks are run on two different Cray XT5 systems and an Infiniband cluster. Our results show that in general the threemore »« less
Cited by 11
https://doi.org/10.1155/2010/715637
Challenges of Algebraic Multigrid across Multicore Architectures

Conference Baker, A; Gamblin, T; Schulz, M; ...

Algebraic multigrid (AMG) is a popular solver for large-scale scientific computing and an essential component of many simulation codes. AMG has shown to be extremely efficient on distributed-memory architectures. However, when executed on modern multicore architectures, we face new challenges that can significantly deteriorate AMG's performance. We examine its performance and scalability on three disparate multicore architectures: a cluster with four AMD Opteron Quad-core processors per node (Hera), a Cray XT5 with two AMD Opteron Hex-core processors per node (Jaguar), and an IBM BlueGene/P system with a single Quad-core processor (Intrepid). We discuss our experiences on these platforms and presentmore »« less
Full Text Available
Quantum Monte Carlo Endstation for Petascale Computing

Technical Report Ceperley, David

The major achievements enabled by QMC Endstation grant include * Performance improvement on clusters of x86 multi-core systems, especially on Cray XT systems * New and improved methods for the wavefunction optimizations * New forms of trial wavefunctions * Implementation of the full application on NVIDIA GPUs using CUDA The scaling studies of QMCPACK on large-scale systems show excellent parallel efficiency up to 216K cores on Jaguarpf (Cray XT5). The GPU implementation shows speedups of 10-15x over the CPU implementation on older generation of x86. We have implemented hybrid OpenMP/MPI scheme in QMC to take advantage of multi-core shared memorymore »« less
https://doi.org/10.2172/1007216

Full Text Available
Efficient On-demand Connection Management Mechanisms with PGAS Models on InfiniBand

Conference Vishnu, Abhinav; Krishnan, Manoj

In the last decade or so, clusters have observed a tremendous rise in popularity due to the excellent price to performance ratio. A variety of Interconnects have been proposed during this period, with InfiniBand leading the way due to its high performance and open standard. At the same time, multiple programming models have emerged in order to meet the requirements of various applications and their programming models. To support requirements of multiple programming models, InfiniBand provides multiple transport semantics, ranging from unreliable connectionless to reliable connected characteristics. Among them, the reliable connection (RC) semantics is being widely due to itsmore »« less
https://doi.org/10.1109/CCGRID.2010.58
Tuning collective communication for Partitioned Global Address Space programming models

Journal Article Nishtala, Rajesh; Zheng, Yili; Hargrove, Paul; ... - Parallel Computing

Partitioned Global Address Space (PGAS) languages offer programmers the convenience of a shared memory programming style combined with locality control necessary to run on large-scale distributed memory systems. Even within a PGAS language programmers often need to perform global communication operations such as broadcasts or reductions, which are best performed as collective operations in which a group of threads work together to perform the operation. In this study we consider the problem of implementing collective communication within PGAS languages and explore some of the design trade-offs in both the interface and implementation. In particular, PGAS collectives have semantic issues thatmore »« less
Cited by 18
https://doi.org/10.1016/j.parco.2011.05.006

Full Text Available

Similar Records