ACC_TEST: Hybrid Testing Techniques for MPI-Based Programs

Abstract

Recently, MPI has become widely used in many scientific applications, including different non-computer science fields, for parallelizing their applications. An MPI programming model is used for supporting parallelism in several programming languages, including C, C++, and Fortran. MPI also supports integration with some programming models and has several implementations from different vendors, including open-source and commercial implementations. However, testing parallel programs is a difficult task, especially when using programming models with different behaviours and types of error based on the programming model type. In addition, the increased use of these programming models by non-computer science specialists can cause several errors due to lack of experience in programming, which needs to be considered when using any testing tools. We noticed that dynamic testing techniques have been used for testing the majority of MPI programs. The dynamic testing techniques detect errors by analyzing the source code during runtime, which will cause overheads, and this will affect the program's performance, especially when targeting massive parallel applications generating thousands or millions of threads. In this paper, we enhance ACC_TEST to have the ability to test MPI-based programs and detect runtime errors occurring with different types of MPI communications. We decided to use hybrid-testing techniques by combining both static and dynamic testing techniques to gain the benefit of each and reduce the cost. INDEX TERMS MPI, MPI testing tool, hybrid testing techniques, parallel programming, ACC_TEST.

Prediction and Correction of Software Defects in Message-Passing Interfaces Using a Static Analysis Tool and Machine Learning

“…The SA also detects point-to-point non-blocking communication (i.e., MPI_Isend and MPI_Irecv). We selected these two MPI directives due to their popularity and because they are the most common MPI blocking calls in several relevant programs [21]. SA lexically analyzes the MPI calls and parses them to ensure they follow MPI call rules.…”

“…VOLUME 11, 2023 Among the features are the number of senders and the number of receivers; this feature is one of the causes of defects because, when there are more senders than receivers, it may lead to a race condition, as it implies a lack of resources. Alternatively, when there are more receivers than senders, it may lead to a deadlock, as they will be waiting for a message without receiving it [21] Another feature is the ability of two processes, P0 and P1, to read and write to the same buffer, as shown in Figure 10. P0 sends a non-blocking message to P1 and then returns to work on the same buffer it just sent.…”

Errors Classification and Static Detection Techniques for Dual-Programming Model (OpenMP and OpenACC)

“…In systems that contain the OpenACC directive, the ACC_TEST is an example of hybrid technology that is meant to test runtime faults in systems that contain the OpenACC. It has also been tested with systems that use the MPI in conjunction with OpenACC in ACC_TEST [6]. During this study, it was discovered that there had been little research into testing tools for the OpenACC; however, it was also found that there was an increasing number of research projects that were going to use it, which inspired us to create a testing tool for the OpenACC with OpenMP.…”

“…In parallel systems, there are various sorts of runtime errors that can arise after program run and the compiler is incapable of identifying them. When hybrid models are used, the percentage of these mistakes increases and the reasons for these errors are different from those of traditional models [5], [6], [8], [16], [30], [36], [56]- [59]. Parallel systems have many advantages, but in order to reap the benefits of these advantages, they must be error-free.…”

“…lelism within these languages have emerged. Open Accelerators (OpenACC) [5], [6], Compute Unified Device Architecture (CUDA) [7], Open Multi-Processing (OpenMP) [8], and Open Computing Language (OpenCL) [9] are examples of programming models that can be incorporated into programming languages and allow systems to run faster by utilizing parallelism and exploiting all available device resources, such as graphics processing unit (GPU)s, memory sharing, and multi-core CPUs. Each programming model has its own method of applying parallelism as well as the directives that implement parallelism in the system.…”