Transparently resilient task parallelism for chapel

Konstantina Panagiotopoulou; Hans-Wolfgang Loidl

doi:10.1109/IPDPSW.2016.102

Transparently resilient task parallelism for chapel

Konstantina Panagiotopoulou, Hans-Wolfgang Loidl

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Hardware failure in High-Performance Computing systems is the norm. Failure data, collected over a nine year period across 22 large-scale systems of up to few thousands of NUMA or SMP nodes, at Los Alamos National laboratories, show averages of 20-1000 failures per year. This paper describes the design and outlines the implementation of transparent resilience for task parallelism in Chapel, a high-performance language developed for productive parallel programming. We detail the design directions and we implement a transparent resilience mechanism within Chapel's runtime system. Our primary goal is to ensure program termination in the presence of hardware failure of one or multiple nodes in the system. We evaluate our implementation using a set of five synthetic microbenchmarks covering Chapel's task parallel constructs and we quantify and discuss the small overheads and speedups noted for the resilient implementation compared to the latest non-resilient Chapel release.

Original language	English
Title of host publication	2016 IEEE International Parallel and Distributed Processing Symposium Workshops
Publisher	IEEE
Pages	1586-1595
Number of pages	10
ISBN (Electronic)	9781509036820
ISBN (Print)	9781509036837
DOIs	https://doi.org/10.1109/IPDPSW.2016.102
Publication status	Published - 4 Aug 2016
Event	30th IEEE International Parallel and Distributed Processing Symposium Workshops 2016 - Chicago, United States Duration: 23 May 2016 → 27 May 2016

Conference

Conference	30th IEEE International Parallel and Distributed Processing Symposium Workshops 2016
Abbreviated title	IPDPSW 2016
Country/Territory	United States
City	Chicago
Period	23/05/16 → 27/05/16

Keywords

Automatic task adoption
Fault detection
Fault recovery
Fault tolerance
Parallelism
PGAS
Resilience
Runtime system
Transparency

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Networks and Communications
Hardware and Architecture
Software

Access to Document

10.1109/IPDPSW.2016.102

Cite this

@inproceedings{fde8c90af9704606a3fd18130aa03660,

title = "Transparently resilient task parallelism for chapel",

abstract = "Hardware failure in High-Performance Computing systems is the norm. Failure data, collected over a nine year period across 22 large-scale systems of up to few thousands of NUMA or SMP nodes, at Los Alamos National laboratories, show averages of 20-1000 failures per year. This paper describes the design and outlines the implementation of transparent resilience for task parallelism in Chapel, a high-performance language developed for productive parallel programming. We detail the design directions and we implement a transparent resilience mechanism within Chapel's runtime system. Our primary goal is to ensure program termination in the presence of hardware failure of one or multiple nodes in the system. We evaluate our implementation using a set of five synthetic microbenchmarks covering Chapel's task parallel constructs and we quantify and discuss the small overheads and speedups noted for the resilient implementation compared to the latest non-resilient Chapel release.",

keywords = "Automatic task adoption, Fault detection, Fault recovery, Fault tolerance, Parallelism, PGAS, Resilience, Runtime system, Transparency",

author = "Konstantina Panagiotopoulou and Hans-Wolfgang Loidl",

year = "2016",

month = aug,

day = "4",

doi = "10.1109/IPDPSW.2016.102",

language = "English",

isbn = "9781509036837",

pages = "1586--1595",

booktitle = "2016 IEEE International Parallel and Distributed Processing Symposium Workshops",

publisher = "IEEE",

address = "United States",

note = "30th IEEE International Parallel and Distributed Processing Symposium Workshops 2016, IPDPSW 2016 ; Conference date: 23-05-2016 Through 27-05-2016",

}

TY - GEN

T1 - Transparently resilient task parallelism for chapel

AU - Panagiotopoulou, Konstantina

AU - Loidl, Hans-Wolfgang

PY - 2016/8/4

Y1 - 2016/8/4

N2 - Hardware failure in High-Performance Computing systems is the norm. Failure data, collected over a nine year period across 22 large-scale systems of up to few thousands of NUMA or SMP nodes, at Los Alamos National laboratories, show averages of 20-1000 failures per year. This paper describes the design and outlines the implementation of transparent resilience for task parallelism in Chapel, a high-performance language developed for productive parallel programming. We detail the design directions and we implement a transparent resilience mechanism within Chapel's runtime system. Our primary goal is to ensure program termination in the presence of hardware failure of one or multiple nodes in the system. We evaluate our implementation using a set of five synthetic microbenchmarks covering Chapel's task parallel constructs and we quantify and discuss the small overheads and speedups noted for the resilient implementation compared to the latest non-resilient Chapel release.

AB - Hardware failure in High-Performance Computing systems is the norm. Failure data, collected over a nine year period across 22 large-scale systems of up to few thousands of NUMA or SMP nodes, at Los Alamos National laboratories, show averages of 20-1000 failures per year. This paper describes the design and outlines the implementation of transparent resilience for task parallelism in Chapel, a high-performance language developed for productive parallel programming. We detail the design directions and we implement a transparent resilience mechanism within Chapel's runtime system. Our primary goal is to ensure program termination in the presence of hardware failure of one or multiple nodes in the system. We evaluate our implementation using a set of five synthetic microbenchmarks covering Chapel's task parallel constructs and we quantify and discuss the small overheads and speedups noted for the resilient implementation compared to the latest non-resilient Chapel release.

KW - Automatic task adoption

KW - Fault detection

KW - Fault recovery

KW - Fault tolerance

KW - Parallelism

KW - PGAS

KW - Resilience

KW - Runtime system

KW - Transparency

UR - http://www.scopus.com/inward/record.url?scp=84991570930&partnerID=8YFLogxK

U2 - 10.1109/IPDPSW.2016.102

DO - 10.1109/IPDPSW.2016.102

M3 - Conference contribution

AN - SCOPUS:84991570930

SN - 9781509036837

SP - 1586

EP - 1595

BT - 2016 IEEE International Parallel and Distributed Processing Symposium Workshops

PB - IEEE

T2 - 30th IEEE International Parallel and Distributed Processing Symposium Workshops 2016

Y2 - 23 May 2016 through 27 May 2016

ER -

Transparently resilient task parallelism for chapel

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this