Negative Perceptions About the Applicability of Source-to-Source Compilers in HPC: A Literature Review

Milewicz, Reed; Pirkelbauer, Peter; Soundararajan, Prema; Ahmed, Hadia; Skjellum, Anthony

doi:10.1007/978-3-030-90539-2_16

Cited by 2 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We discuss two key pitfalls below. A more detailed analysis of the limitations of these tools, such as leading to fragile software development workflows, interference with downstream compiler optimizations, etc., is already discussed in detail in literature [5,[16][17][18].…”

Section: Introductionmentioning

confidence: 99%

PragFormer: Data-driven Parallel Source Code Classification with Transformers

Harel,

Kadosh,

Hasabnis

et al. 2023

Preprint

View full text Add to dashboard Cite

Multi-core shared memory architectures have become ubiquitous in computing hardware nowadays. As a result, there is a growing need to fully utilize these architectures by introducing appropriate parallelization schemes, such as OpenMP worksharing-loop constructs, to applications. However, most developers find introducing OpenMP directives to their code hard due to pervasive pitfalls in managing parallel shared memory. To assist developers in this process, many compilers, as well as source-to-source (S2S) translation tools, have been developed over the years, tasked with inserting OpenMP directives into code automatically. In addition to having limited robustness to their input format, these compilers still do not achieve satisfactory coverage and precision in locating parallelizable code and generating appropriate directives. Recently, many data-driven AI-based code completion (CC) tools, such as GitHub CoPilot, have been developed to ease and improve programming productivity. Leveraging the insights from existing AI-based programming-assistance tools, this work presents a novel AI model that can serve as a parallel-programming assistant∗. Specifically, our model, named PragFormer, is tasked with identifying for loops that can benefit from conversion to parallel worksharing-loop construct (OpenMP directive) and even predict the need for specific data-sharing attributes clauses on the fly. We created a unique database, named Open-OMP, specifically for this goal. Open-OMP contains over 32,000 unique code snippets from different domains, half of which contain OpenMP directives, while the other half do not. We experimented with different model design parameters for these tasks and showed that our best-performing model outperforms a statistically-trained baseline as well as a state-of-the-art S2S compiler. In fact, it even outperforms the popular generative AI model of ChatGPT. In the spirit of advancing research on this topic, we have already released source code for PragFormer as well as Open-OMP dataset to public†. Moreover, an interactive demo of our tool, as well as a Hugging Face webpage ‡to experiment with our tool, are already available.

show abstract

Section: Introductionmentioning

confidence: 99%

PragFormer: Data-driven Parallel Source Code Classification with Transformers

Harel,

Kadosh,

Hasabnis

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

PragFormer: Data-Driven Parallel Source Code Classification with Transformers

Harel,

Kadosh,

Hasabnis

et al. 2024

Int J Parallel Prog

View full text Add to dashboard Cite

Multi-core shared memory architectures have become ubiquitous in computing hardware nowadays. As a result, there is a growing need to fully utilize these architectures by introducing appropriate parallelization schemes, such as OpenMP worksharing-loop constructs, to applications. However, most developers find introducing OpenMP directives to their code hard due to pervasive pitfalls in managing parallel shared memory. To assist developers in this process, many compilers, as well as source-to-source (S2S) translation tools, have been developed over the years, tasked with inserting OpenMP directives into code automatically. In addition to having limited robustness to their input format, these compilers still do not achieve satisfactory coverage and precision in locating parallelizable code and generating appropriate directives. Recently, many data-driven AI-based code completion (CC) tools, such as GitHub CoPilot, have been developed to ease and improve programming productivity. Leveraging the insights from existing AI-based programming-assistance tools, this work presents a novel AI model that can serve as a parallel-programming assistant. Specifically, our model, named PragFormer, is tasked with identifying loops that can benefit from conversion to parallel worksharing-loop construct (OpenMP directive) and even predict the need for specific data-sharing attributes clauses on the fly. We created a unique database, named Open-OMP, specifically for this goal. Open-OMP contains over 32,000 unique code snippets from different domains, half of which contain OpenMP directives, while the other half do not. We experimented with different model design parameters for these tasks and showed that our best-performing model outperforms a statistically-trained baseline as well as a state-of-the-art S2S compiler. In fact, it even outperforms the popular generative AI model of ChatGPT. In the spirit of advancing research on this topic, we have already released source code for PragFormer as well as Open-OMP dataset to public. Moreover, an interactive demo of our tool, as well as a Hugging Face webpage to experiment with our tool, are already available.

show abstract

Negative Perceptions About the Applicability of Source-to-Source Compilers in HPC: A Literature Review

Cited by 2 publications

References 38 publications

PragFormer: Data-driven Parallel Source Code Classification with Transformers

PragFormer: Data-driven Parallel Source Code Classification with Transformers

PragFormer: Data-Driven Parallel Source Code Classification with Transformers

Contact Info

Product

Resources

About