HACC: Extreme Scaling and Performance Across Diverse Architectures.
Supercomputing is evolving toward hybrid and accelerator-based architectures with millions of cores. The Hardware/Hybrid Accelerated Cosmology Code (HACC) framework exploits this diverse landscape at the largest scales of problem size, obtaining high scalability and sustained performance. Developed...
| Publicado en: | Communications of the ACM Vol. 60; no. 1; pp. 97 - 105 |
|---|---|
| Autores principales: | , , , , , , , , , , , , |
| Formato: | Artículo |
| Publicado: |
Association for Computing Machinery
Jan2017
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=120347693&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 120347693 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00010782 ACM jtl: Communications of the ACM issn: 00010782 maglogo: N pubinfo: dt: Jan2017 vid: 60 iid: 1 pid: 68 pub: Association for Computing Machinery artinfo: ui: 120347693 10.1145/3015569 ppf: 97 ppct: 8 formats: tig: atl: HACC: Extreme Scaling and Performance Across Diverse Architectures. aug: au: Habib, Salman Morozov, Vitali Frontiere, Nicholas Finkel, Hal Pope, Adrian Heitmann, Katrin Kumaran, Kalyan Vishwanath, Venkatram Peterka, Tom Insley, Joe Daniel, David Fasel, Patricia Lukić, Zarija affil: Argonne National Laboratory, Lemont, IL Los Alamos National Laboratory, Los Alamos, New Mexico Lawrence Berkeley National Laboratory, Berkeley, CA su: Scalability Computer architecture Motherboards Simulation methods & models Graphics processing units Supercomputers Computer performance Metaphysical cosmology sug: subj: Scalability Computer architecture Motherboards Simulation methods & models Graphics processing units Supercomputers Computer performance Metaphysical cosmology ab: Supercomputing is evolving toward hybrid and accelerator-based architectures with millions of cores. The Hardware/Hybrid Accelerated Cosmology Code (HACC) framework exploits this diverse landscape at the largest scales of problem size, obtaining high scalability and sustained performance. Developed to satisfy the science requirements of cosmological surveys, HACC melds particle and grid methods using a novel algorithmic structure that flexibly maps across architectures, including CPU/GPU, multi/many-core, and Blue Gene systems. In this Research Highlight, we demonstrate the success of HACC on two very different machines, the CPU/GPU system Titan and the BG/Q systems Sequoia and Mira, attaining very high levels of scalable performance. We demonstrate strong and weak scaling on Titan, obtaining up to 99.2% parallel efficiency, evolving 1.1 trillion particles. On Sequoia, we reach 13.94 PFlops (69.2% of peak) and 90% parallel efficiency on 1,572,864 cores, with 3.6 trillion particles, the largest cosmological benchmark yet performed. HACC design concepts are applicable to several other supercomputer applications. pubtype: Periodical doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2017 holdings: @attributes: islocal: N |
|---|