Application of a development time productivity metric to parallel software development

Authors:
Andrew Funk;Victor Basili;Lorin Hochstein;Jeremy Kepner
Affiliations:
MIT Lincoln Laboratory, Lexington, MA;University of Maryland, College Park, MD;University of Maryland, College Park, MD;MIT Lincoln Laboratory, Lexington, MA
Venue:
Proceedings of the second international workshop on Software engineering for high performance computing system applications
Year:
2005

Citing 2
Cited 4

A Discipline for Software Engineering

A Discipline for Software Engineering
High Performance Computing Productivity Model Synthesis

International Journal of High Performance Computing Applications

Evaluation of UPC programmability using classroom studies

Proceedings of the Third Conference on Partitioned Global Address Space Programing Models
Automatic mining of change set size information from repository for precise productivity estimation

Proceedings of the 2011 International Conference on Software and Systems Process
An effective speedup metric for measuring productivity in large-scale parallel computer systems

The Journal of Supercomputing
Optimization strategies in different CUDA architectures using llCoMP

Microprocessors & Microsystems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Evaluation of High Performance Computing (HPC) systems should take into account software development time productivity in addition to hardware performance, cost, and other factors. We propose a new metric for HPC software development time productivity, defined as the ratio of relative runtime performance to relative programmer effort. This formula has been used to analyze several HPC benchmark codes and classroom programming assignments. The results of this analysis show consistent trends for various programming models. This method enables a high-level evaluation of development time productivity for a given code implementation, which is essential to the task of estimating cost associated with HPC software development.