Fast and Faithful Performance Prediction of MPI Applications: the HPL Case Study - Archive ouverte HAL Access content directly
Conference Papers Year :

Fast and Faithful Performance Prediction of MPI Applications: the HPL Case Study

(1) , (2) , (3)
1
2
3

Abstract

Finely tuning MPI applications (number of processes, granularity, collective operation algorithms, topology and process placement) is critical to obtain good performance on supercomputers. With a rising cost of modern supercomputers, running parallel applications at scale solely to optimize their performance is extremely expensive. Having inexpensive but faithful predictions of expected performance could be a great help for researchers and system administrators. The methodology we propose captures the complexity of adaptive applications by emulating the MPI code while skipping insignificant parts. We demonstrate its capability with High Performance Linpack (HPL), the benchmark used to rank supercomputers in the TOP500 and which requires a careful tuning. We explain (1) how we both extended the SimGrid's SMPI simulator and slightly modified the open-source version of HPL to allow a fast emulation on a single commodity server at the scale of a supercomputer and (2) how to model the different components (network, BLAS, ...) of the system. We show that a careful modeling of both spatial and temporal node variability allows us to obtain predictions within a few percents of real experiments (see Figure 1).
Fichier principal
Vignette du fichier
paper.pdf (996.47 Ko) Télécharger le fichier
Vignette du fichier
slides.pdf (2.83 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Presentation
Comment : Slides used to present this work at Cluster'19 conference (Albuquerque, New Mexico, 25/09/2019)
Loading...

Dates and versions

hal-02096571 , version 1 (11-04-2019)
hal-02096571 , version 2 (27-05-2019)
hal-02096571 , version 3 (27-05-2019)
hal-02096571 , version 4 (26-09-2019)

Identifiers

Cite

Tom Cornebize, Arnaud Legrand, Franz C Heinrich. Fast and Faithful Performance Prediction of MPI Applications: the HPL Case Study. 2019 IEEE International Conference on Cluster Computing (CLUSTER), Sep 2019, Albuquerque, United States. ⟨10.1109/CLUSTER.2019.8891011⟩. ⟨hal-02096571v4⟩
402 View
1217 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More