2014/10/31 by Paul Madden, Madden, Paul, Eduardo G. Valente +1
Computer Science · Decision Sciences · #Distributed and Parallel Computing Systems #FOS: Computer and information sciences #Scientific Computing and Data Management #Software Engineering (cs.SE) #Software System Performance and Reliability
paper · pdf · doi:10.48550/arxiv.1410.8844
openalex publication_date 2014/10/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Many scientific-software projects test their codes inadequately, or not at all. Despite its well-known benefits, adopting routine testing is often not easy. Development teams may have doubts about establishing effective test procedures, writing test software, or handling the ever-growing complexity of test cases. They may need to run (and test) on restrictive HPC platforms. They almost certainly face time and budget pressures that can keep testing languishing near the bottom of their to-do lists. This paper presents DDTS, a framework for building test suite applications, designed to fit scientific-software projects' requirements. DDTS aims to simplify introduction of rigorous testing, and to ease growing pains as needs mature. It decomposes the testing problem into practical, intuitive phases; makes configuration and extension easy; is portable and suitable to HPC platforms; and exploits parallelism. DDTS is currently used for automated regression and developer pre-commit testing for several scientific-software projects with disparate testing requirements.