Performance characteristics of a cosmology package on leading HPC architectures

被引:0
|
作者
Carter, J [1 ]
Borrill, J [1 ]
Oliker, L [1 ]
机构
[1] Univ Calif Berkeley, Lawrence Berkeley Lab, NERSC, CRD, Berkeley, CA 94720 USA
来源
关键词
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The Cosmic Microwave Background (CMB) is a snapshot of the Universe some 400,000 years after the Big Bang. The pattern of anisotropies in the CMB carries a wealth of information about the fundamental parameters of cosmology. Extracting this information is an extremely computationally expensive endeavor, requiring massively parallel computers and software packages capable of exploiting them. One such package is the Microwave Anisotropy Dataset Computational Analysis Package (MADCAP) which has been used to analyze data from a number of CMB experiments. In this work, we compare MADCAP performance on the vector-based Earth Simulator (ES) and Cray X1 architectures and two leading superscalar systems, the IBM Power3 and Power4. Our results highlight the complex interplay between the problem size, architectural paradigm, interconnect, and vendor-supplied numerical libraries, while isolating the I/O filesystem as the key bottleneck across all the platforms.
引用
收藏
页码:176 / 188
页数:13
相关论文
共 50 条
  • [1] Performance analysis of leading hpc architectures with BeamBeam3D
    Shan, Hongzhang
    Strohmaier, Erich
    Qiang, Ji
    INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2008, 22 (01): : 21 - 32
  • [2] Performance modeling of emerging HPC architectures
    Bhatia, Nikhil
    Alam, Sadaf R.
    Vetter, Jeffrey S.
    PROCEEDINGS OF THE HPCMP USERS GROUP CONFERENCE 2006, 2006, : 367 - 373
  • [3] Performance Comparison of CFD Microbenchmarks on Diverse HPC Architectures
    Galeazzo, Flavio C. C.
    Garcia-Gasulla, Marta
    Boella, Elisabetta
    Pocurull, Josep
    Lesnik, Sergey
    Rusche, Henrik
    Bna, Simone
    Cerminara, Matteo
    Brogi, Federico
    Marchetti, Filippo
    Gregori, Daniele
    Weiss, R. Gregor
    Ruopp, Andreas
    COMPUTERS, 2024, 13 (05)
  • [4] Big Data Analytics on HPC Architectures: Performance and Cost
    Xenopoulos, Peter
    Daniel, Jamison
    Matheson, Michael
    Sukumar, Sreenivas
    2016 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2016, : 2295 - 2304
  • [5] Performance and Energy Efficiency Evaluation for HPC Applications in Heterogeneous Architectures
    Kloh, Vinicius
    Yokoyama, Daniel
    Yokoyama, Andre
    Silva, Gabrieli
    Ferro, Mariza
    Schulze, Bruno
    2018 SYMPOSIUM ON HIGH PERFORMANCE COMPUTING SYSTEMS (WSCAD 2018), 2018, : 162 - 169
  • [6] Performance Evaluation of the LBM Solver Musubi on Various HPC Architectures
    Qi, Jiaxing
    Jain, Kartik
    Klimiach, Harald
    Roller, Sabine
    PARALLEL COMPUTING: ON THE ROAD TO EXASCALE, 2016, 27 : 807 - 816
  • [7] Performance Characterisation and Evaluation of WRF Model on Cloud and HPC Architectures
    Krishnan, S. P. T.
    Veeravalli, Bharadwaj
    Krishna, Vetharenian Hari
    Sheng, Wu Chia
    2014 IEEE INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS, 2014 IEEE 6TH INTL SYMP ON CYBERSPACE SAFETY AND SECURITY, 2014 IEEE 11TH INTL CONF ON EMBEDDED SOFTWARE AND SYST (HPCC,CSS,ICESS), 2014, : 1280 - 1287
  • [8] Performance Characterization and Evaluation of HPC Algorithms on Dissimilar Multicore Architectures
    Krishnan, S. P. T.
    Veeravalli, Bharadwaj
    2014 IEEE INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS, 2014 IEEE 6TH INTL SYMP ON CYBERSPACE SAFETY AND SECURITY, 2014 IEEE 11TH INTL CONF ON EMBEDDED SOFTWARE AND SYST (HPCC,CSS,ICESS), 2014, : 1288 - 1295
  • [9] Integrated performance monitoring of a cosmology application on leading HEC platforms
    Borrill, J
    Carter, J
    Oliker, L
    Skinner, D
    Biswas, R
    2005 International Conference on Parallel Processsing, Proceedings, 2005, : 119 - 128
  • [10] Nix as HPC package management system
    Bzeznik, Bruno
    Henriot, Oliver
    Reis, Valentin
    Richard, Olivier
    Tavard, Laure
    HUST'17: PROCEEDINGS OF THE FOURTH INTERNATIONAL WORKSHOP ON HPC USER SUPPORT TOOLS, 2017,