About: Simplifying Communication Overlap in OpenSHMEM Through Integrated User-Level Thread Scheduling

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Simplifying Communication Overlap in OpenSHMEM Through Integrated User-Level Thread Scheduling Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Simplifying Communication Overlap in OpenSHMEM Through Integrated User-Level Thread Scheduling
Creator	Ozog, David Dinan, James Wasi-Ur-Rahman, Md
Source	PMC
abstract	Overlap of communication with computation is a key optimization for high performance computing (HPC) applications. In this paper, we explore the usage of user-level threading to enable productive and efficient communication overlap and pipelining. We extend OpenSHMEM with integrated user-level thread scheduling, enabling applications to leverage fine-grain threading as an alternative to non-blocking communication. Our solution introduces communication-aware thread scheduling that utilizes the communication state of threads to minimize context switching overheads. We identify several patterns common to multi-threaded OpenSHMEM applications, leverage user-level threads to increase overlap of communication and computation, and explore the impact of different thread scheduling policies. Results indicate that user-level threading can enable blocking communication to meet the performance of highly-optimized, non-blocking, single-threaded codes with significantly lower application-level complexity. In one case, we observe a 28.7% performance improvement for the Smith-Waterman DNA sequence alignment benchmark.
has issue date	2020-05-22(xsd:dateTime)
bibo:doi	10.1007/978-3-030-50743-5_25
has license	cc-by
sha1sum (hex)	60d42c14998ba6c08e0f51a8c10524a06ad1e2cf
schema:url	https://doi.org/10.1007/978-3-030-50743-5_25
resource representing a document's title	Simplifying Communication Overlap in OpenSHMEM Through Integrated User-Level Thread Scheduling
has PubMed Central identifier	PMC7295360
schema:publication	High Performance Computing
resource representing a document's body	covid:60d42c14998ba6c08e0f51a8c10524a06ad1e2cf#body_text
is schema:about of	named entity 'context switching' named entity 'enabling' named entity 'Communication' named entity 'COMMUNICATION STATE' named entity 'POLICIES' named entity 'FINE' named entity 'HIGH PERFORMANCE COMPUTING' named entity 'PATTERNS' named entity 'DIFFERENT' named entity 'ENABLE' named entity 'integrated' named entity 'non-blocking' named entity 'pipelining' named entity 'performance improvement' named entity 'computation' named entity 'threading' named entity 'applications' named entity 'communication' named entity 'single-threaded' named entity 'user-level' named entity 'pipelining' named entity 'non-blocking' named entity 'OpenSHMEM' named entity 'Smith-Waterman' named entity 'scheduling policies' named entity 'OpenSHMEM' named entity 'callback' named entity 'user-level' named entity '7.5' named entity 'user-level' named entity 'PEs' named entity 'cooperative scheduling' named entity 'user-level' named entity 'user-level' named entity 'user-level' named entity 'runnable' named entity 'user-level' named entity 'asynchronous data' named entity 'OpenSHMEM' named entity 'APIs' named entity 'user-level' named entity 'Xeon' named entity 'OpenSHMEM' named entity 'Red Hat Enterprise Linux' named entity 'Intel' named entity 'Intel' named entity 'multithreaded' named entity 'user-level' named entity 'user-level' named entity 'loop index' named entity 'runnable' named entity 'non-blocking communication' named entity 'Intel' named entity 'MPI' named entity 'user-level' named entity 'Charm++' named entity 'User-level' named entity 'PEs' named entity 'user-level' named entity 'APIs' named entity 'Creative Commons license' named entity 'deadlock' named entity 'Latency' named entity 'user-level' named entity 'ult' named entity 'user-level' named entity 'Communication latency' named entity 'user-level' named entity 'round-robin' named entity 'context switching' named entity 'user-level' named entity 'runnable' named entity 'pseudocode' named entity 'microprocessors' named entity 'user-level' named entity 'OpenSHMEM' named entity 'OpenSHMEM' named entity 'generic extension' named entity 'multithreaded' named entity 'preemptive scheduling' named entity 'runnable'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software