| Title: |
Phase-TA: Periodicity Detection and Characterization for HPC Applications |
| Authors: |
Stoffel, Mathieu; Broquedis, François; Desprez, Frédéric; Mazouz, Abdelhafid |
| Contributors: |
Atos; Compiler Optimization and Run-time Systems (CORSE); Centre Inria de l'Université Grenoble Alpes; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Informatique de Grenoble (LIG); Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP); Université Grenoble Alpes (UGA)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP); Université Grenoble Alpes (UGA); Institut National de Recherche en Informatique et en Automatique (Inria); Experiments presented in this paper were carried out using the Grid’5000 testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations (see https://www.grid5000.fr). |
| Source: |
HPCS 2020 - 18th IEEE International Conference on High Performance Computing and Simulation ; https://hal.science/hal-03185251 ; HPCS 2020 - 18th IEEE International Conference on High Performance Computing and Simulation, Mar 2021, Barcelone / Virtual, Spain. pp.1-12 |
| Publisher Information: |
CCSD; IEEE |
| Publication Year: |
2021 |
| Collection: |
Université Grenoble Alpes: HAL |
| Subject Terms: |
Representative Patterns; Software Monitoring and Measurement; Periodicity; Characterization; Iterative Applications; High-Performance Computing; [INFO.INFO-DC]Computer Science [cs]/Distributed; Parallel; and Cluster Computing [cs.DC] |
| Subject Geographic: |
Spain |
| Time: |
Barcelone / Virtual, Spain |
| Description: |
International audience ; The world of High-Performance Computing (HPC) currently stands on the edge of the ExaScale. The supercomputers are growing ever more powerful, requiring power-efficient components and ever smarter tool-suites to operate them. One of the key features of those frameworks will be their ability to monitor and predict the behavior of executed applications to optimize resources utilization, and abide by the operating constraints, notably on power consumption. In this context, this article presents Phase-TA, an offline tool which detects and characterizes the inherent periodicities of iterative HPC applications, with no prior knowledge of the latter. To do so, it analyzes the evolution of several performance counters at the scale of the compute node, and infers patterns representing the identified periodicities. As a result, Phase-TA offers a nonintrusive mean to gain insights on the processor use associated with an application, and paves the way to predicting its behavior. Phase-TA was tested on a panel of 3 applications and benchmarks from the supercomputing field: HPCG, NEMO, and OpenFoam. For all of them, periodicities, accountable for on average 78% of their execution time, were detected and represented by accurate patterns. Furthermore, it was demonstrated that there is no need to analyze the whole profile of an application to precisely characterize its periodic behaviors. Indeed, an extract of the aforementioned profile is enough for Phase-TA to infer representative patterns on-the-fly, opening the way to energyefficiency optimization through Dynamic Voltage-Frequency Scaling (DVFS). |
| Document Type: |
conference object |
| Language: |
English |
| Availability: |
https://hal.science/hal-03185251; https://hal.science/hal-03185251v1/document; https://hal.science/hal-03185251v1/file/hpcs-camera_ready.pdf |
| Rights: |
info:eu-repo/semantics/OpenAccess |
| Accession Number: |
edsbas.4D223E70 |
| Database: |
BASE |