Communication-hiding programming for clusters with multi-coprocessor nodes

Summary Future exascale systems are expected to adopt compute nodes that incorporate many accelerators. To shed some light on the upcoming software challenge, this paper investigates the particular topic of programming clusters that have multiple Xeon Phi coprocessors in each compute node. A new off...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Concurrency and computation Jg. 27; H. 16; S. 4172 - 4185
Hauptverfasser: Dong, Xinnan, Wen, Mei, Chai, Jun, Cai, Xing, Zhao, Mandan, Zhang, Chunyuan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Blackwell Publishing Ltd 01.11.2015
Schlagworte:
Clusters
Computation
Computer programs
Coprocessors
hybrid programming
Intel Xeon Phi coprocessor
offload model
Programming
SCIF
Sheds
Symmetry
Three dimensional
Tianhe-2
ISSN:1532-0626, 1532-0634
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Summary Future exascale systems are expected to adopt compute nodes that incorporate many accelerators. To shed some light on the upcoming software challenge, this paper investigates the particular topic of programming clusters that have multiple Xeon Phi coprocessors in each compute node. A new offload approach is considered for intra‐node communication, which combines Intel's APIs of coprocessor offload infrastructure (COI) and symmetric communication interface (SCIF) for achieving low latency. While the conventional pragma‐based offload approach allows simpler programming, the COI‐SCIF approach has three advantages in (1) lower overhead associated with launching offloaded code, (2) higher data transfer bandwidths, and (3) more advanced asynchrony between computation and data movement. The low‐level COI‐SCIF approach is also shown to have benefits over the MPI‐OpenMP counterpart, which belongs to the symmetric usage mode. Moreover, a hybird programming strategy based on COI‐SCIF is presented for joining the computational force of all CPUs and coprocessors, while realizing communication hiding. All the programming approaches are tested by a real‐world 3D application, for which the COI‐SCIF‐based approach shows a performance advantage on Tianhe‐2. Copyright © 2015 John Wiley & Sons, Ltd.
Bibliographie:istex:1AC1249C406D5A6A6CFC73793C2B958E37760C5E
ark:/67375/WNG-LNQSH4PP-B
National 863 Program - No. 2012AA012706
National Natural Science Foundation of China - No. 61033008; No. 61272145
FRINATEK program of the Research Council of Norway - No. 214113
ArticleID:CPE3507
Innovation Program of NUDT Graduate School - No. B100603; No. B120605; No. CJ11-06-01
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1532-0626
1532-0634
DOI:10.1002/cpe.3507