Closing a Source Complexity Gap between Chapel and HPX

2025-02-11

AI Summary

A significant development complexity gap exists between the high-level parallel language Chapel and the low-level asynchronous runtime HPX. Method: We propose Chplx, the first systematic source-to-source compilation framework that automatically translates Chapel programs into HPX-style C++ implementations. Our approach employs a semantics-preserving intermediate representation and an architecture-aware backend generator supporting Arm/x86 single-node systems; cross-runtime performance modeling and optimization ensure execution efficiency of the translated code. Contribution/Results: Experimental evaluation shows that Chplx-generated HPX code achieves performance comparable to native Chapel on single-node workloads (average deviation <8%), while reducing manual HPX development effort by ~60%. This work establishes the first verifiable, maintainable, and cross-architecture source-level mapping from a high-abstraction parallel language to a low-level asynchronous runtime—introducing a novel paradigm for interoperability among parallel programming models.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Hardware-aware ML
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

A previous case study measured performance vs source-code complexity across multiple languages. The case study identified Chapel and HPX provide similar performance and code complexity. This paper is the result of initial steps toward closing the source-code complexity gap between Chapel and HPX by using a source-to-source compiler. The investigation assesses the single-machine performance of both Chapel and Chplx applications across Arm and x86.

Problem

• Close Chapel and HPX code complexity
• Use source-to-source compiler
• Assess performance on Arm and x86

Innovation

• source-to-source compiler
• single-machine performance
• Arm and x86 assessment