A mathematical model to calculate real cost/performance in software distributed shared memory on computing environments

One of the important factors in high-performance computing (HPC) is the cost/performance ratio. Calculation of cost/performance ratio is the main criterion for the separation of hardware computing systems (supercomputers) from software computing systems (Cluster, Grid, Peer-to-Peer). There are vario...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of supercomputing Vol. 74; no. 4; pp. 1715 - 1764
Main Authors: Khaneghah, Ehsan Mousavi, Shadnoush, Nosratollah, Ghobakhlou, Amir Hossein
Format: Journal Article
Language:English
Published: New York Springer US 01.04.2018
Springer Nature B.V
Subjects:
Compilers
Computer memory
Computer Science
Computing costs
Cost analysis
Distributed memory
Hardware
Interpreters
Mathematical models
Methods
Parameters
Processor Architectures
Programming Languages
Software
Software engineering
Supercomputers
Distributed shared memory (DSM)
Correlation
Cost model
False sharing
High-performance computing (HPC)
ISSN:0920-8542, 1573-0484
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:One of the important factors in high-performance computing (HPC) is the cost/performance ratio. Calculation of cost/performance ratio is the main criterion for the separation of hardware computing systems (supercomputers) from software computing systems (Cluster, Grid, Peer-to-Peer). There are various economic methods to calculate hardware cost. In addition, there are numerous methods in software engineering to calculate the cost of developing and programming the scientific and engineering software. The computing power in the aforementioned systems is basically calculated with programs like LINPACK and HPCL. The inter-process communication is considered as a variable in calculating the cost of executing the scientific programs, whose nature and amount depends on the program execution itself. As there is a high dependency of effective variables in cost calculation of inter-process communications during the program execution, it should be used for calculating the cost of any application. This paper complements the existing methods by presenting a more comprehensive and accurate method to calculate the real cost of distributed shared memory (DSM) mechanisms used by HPC Systems. Therefore, a systematic method has been used to achieve a whole equation for DSM costing, determine the effective factors of the cost, and propose a method based on costing economic methods. Effective parameters are classified into two groups, namely DSM-inhere dependent and application-specific dependent parameters. Each parameter is presented and discussed, and the correlation between them specifies the system’s weight on DSM real cost according to which the cost is modeled and validated analytically.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-017-2191-7