Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations

[2608.08085] Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Distributed, Parallel, and Cluster Computing arXiv:2608.08085 (cs) [Submitted on 8 Aug 2026 ( v1 ), last revised 15 Aug 2026 (this version, v2)] Title: Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations Authors: Jiří Klepl , Matyáš Brabec , Martin Kruliš View a PDF of the paper titled Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations, by Ji\v{r}\'i Klepl and 2 other authors View PDF HTML (experimental) Abstract: Code performance optimization is a vital aspect of modern software development, as it enables faster response times and reduced resource usage. These optimizations require a deep understanding of low-level hardware details and the intricacies of parallel processing, making them challenging even for experienced developers. With the advent of Large Language Models (LLMs), which are increasingly capable of generating and understanding code, there is growing interest in incorporating these models into automated code optimization processes. Traditionally, this automation involves transcribing the source code into a domain-specific representation that can be auto-tuned using grid search or machine learning algorithms, while adhering to strict rules and a limited set of feasible transformations to ensure verifiability. LLMs incorporate high-level code semantics and can thus perform transformations that go beyond verifiable automated optimizations. This paper investigates whether the traditional abstractions used in automated code optimization improve the performance and correctness of LLM-guided optimizations of parallel HPC applications. We evaluate this using the PolyBench benchmark suite and demonstrate that, in our evaluated setting, LLMs provided with specific optimization goals achieve better measured performance and validity rates when generating C code compared to creating computation pipelines and optimization schedules with established frameworks, suggesting that future development should explore alternative approaches for verifiable LLM-guided code optimization. Comments: This preprint has not undergone peer review or any post-submission improvements or corrections Subjects: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2608.08085 [cs.DC] (or arXiv:2608.08085v2 [cs.DC] for this version) https://doi.org/10.48550/arXiv.2608.08085 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jiří Klepl [ view email ] [v1] Sat, 8 Aug 2026 12:12:28 UTC (112 KB) [v2] Sat, 15 Aug 2026 13:14:31 UTC (112 KB) Full-text links: Access Paper: View a PDF of the paper titled Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations, by Ji\v{r}\'i Klepl and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.DC < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations#608969
• Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations#441770
• BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design#13131
• Pseudo2CodeQA: A Benchmark for LLM-Based Structured Algorithmic Reasoning in Code Generation#441873
• Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals#363280