The automation of testing is critical in software development to improve quality assurance (QA), but today 80% of testing is manual (Gartner) and $32b is spent annually on QA (IDC/Nelson Hall). Coding standards in automotive and cybersecurity (e.g. CWE, MISRA) provide developers with rules and recommendations to prevent faulty code patterns. Parallel programming is challenging and, thus, QA and coding standards are critical for HPC programmers, particularly for industry and novice programmers. The ever-increasing complexity of HPC software and hardware pushes the developers to critically reevaluate testing methods, but, there is no coding standard for parallel programming yet. We will present an ongoing effort to collect the best practices of parallel programming experts and to develop new static code analysis tools specialized in parallelism to ensure code compliance on POWER systems.
Continue the conversation in Slack