SimP is a program reduction framework that combines traditional reduction with LLM-based syntax- and semantic-guided reduction, and synergistically combines rule-based and LLM-based reduction stages to optimize the reduction performance.
Abstract
Compiler bugs are pervasive in modern compiler systems, but the test programs that trigger them are often too large for practical debugging. Program reduction addresses this by minimizing test program size while preserving the original bug-triggering behavior. Existing approaches mainly rely on syntax-guided, rule-based deletion strategies that iteratively remove parts of the program in a trial-and-error manner. While effective in reduction quality, these approaches suffer from slow reduction speed. This paper presents SimP, a program reduction framework that combines traditional reduction with LLM-based syntax- and semantic-guided reduction. SimP leverages customized prompt design to guide the reduction process. SimP synergistically combines rule-based and LLM-based reduction stages to optimize the reduction performance. The results show that SimP improves reduction efficiency while achieving comparable reduction quality, with negligible LLM monetary cost.
Reducing bug-triggering programs to their minimal essential form is a fundamental task in debugging language processors such as compilers and interpreters. Existing reduction techniques are limited by their reliance on predefined, syntax-driven transformations that lack semantic understanding of the target program, and by their inability to learn from past reduction experiences. We present a new approach that recasts program reduction as an autonomous reasoning task powered by agentic Large Language Models (LLMs). Instead of applying fixed transformation rules, our method enables an LLM to analyze program semantics, formulate reduction hypotheses, and iteratively refine its approach based on execution outcomes. Successful reduction experiences are further distilled into reusable strategies, allowing the system to continuously improve over time. We realize this approach in PROJ, a framework built around two collaborative components: a reducer agent that performs semantic-aware, case-specific program reduction, and a reflector agent that extracts and accumulates transferable reduction knowledge. Extensive experiments on 90 benchmarks spanning three programming languages show that PROJ consistently produces smaller reduced programs than all existing state-of-the-art reducers while maintaining high efficiency.
Xintong Zhou, Hongxu Xu, Chun-Feng Liao et al.· 0 citations
It is demonstrated that 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.
Jiří Klepl, Matyás Brabec, Martin Kruliš· 0 citations
Pointer analysis is a cornerstone of numerous static analysis applications, including compiler optimizations, slicing, bug detection, and verification. While offline simplification is a common approach to boosting performance, existing methods are often tightly coupled to specific analysis algorithms and limited to a set of simplification rules. This paper explores a new perspective: applying semantic-preserving compiler optimizations directly to intermediate representation (IR) before pointer analysis. This strategy is modular, analysis-agnostic, and easily integrates with existing tools. We conduct an empirical study using diverse programs and three pointer analyses. The results show substantial performance gains---up to 3.14x speedup and 1.94x memory reduction---while precision remains largely unchanged. We also analyze the trade-offs between optimization overhead and analysis speedup, quantify changes in IR structure, assess the characteristics of optimization configurations, and identify promising directions for future research.
Differential compiler testing requires automatically generated programs that are not only diverse and bug-revealing, but also semantically well-defined and reproducible. Rule-based generators provide strong validity guarantees but offer limited control over semantic variation, while large language models (LLMs) can synthesize expressive programs without principled mechanisms for balancing competing testing objectives. This paper proposes LMOEC, a constrained multi-objective evolutionary framework that integrates code language models as semantic genetic operators within an NSGA-II search process. Instead of using the LLM as a one-shot generator, we employ it for population initialization, crossover, and mutation at the program level, enabling semantics-aware recombination while preserving strict admissibility constraints. Compiler test generation is formulated as a multi-objective optimization problem that simultaneously promotes structural diversity, cross-configuration output inconsistency, semantic complexity, and robustness to mutation. A constraint-driven acceptance pipeline enforces syntactic validity, deterministic execution, bounded runtime, and avoidance of undefined behavior before evolutionary selection. By maintaining a Pareto front of non-dominated programs, LMOEC preserves multiple high-value test archetypes reflecting different trade-offs between bug exposure and reproducibility. The framework demonstrates how expressive code models can be systematically embedded into evolutionary multi-objective optimization for reliability-critical software testing.
Lang Hong Nguyet Anh, Ho Viet Duc Luong, Vu Van An· Annual Conference on Genetic...· 0 citations
To improve a program’s performance and avoid excessive binary-size growth, compiler optimizations can be applied on only the most frequently executed parts of the program, i.e. hot code. Ahead-of-time (AOT) compilation can benefit from profiles to determine the hot code, and to improve optimization decisions with respect to code hotness. In this article, we present a novel technique for reducing the size of AOT compiled programs by using fully-context-sensitive profiles to concentrate the optimizations on the hot code. These profiles enable capturing different behaviors of the same subroutine when invoked from different calling contexts. We use this information to identify those subroutines that contribute significantly to the program’s performance and compile them differently according to their calling contexts. We implemented this technique inside GraalVM Native Image, a state-of-the-art AOT compiler for Java, and performed an evaluation on 29 benchmarks from DaCapo, Scalabench, and Renaissance benchmarking suites. With this selective subroutine specialization, we achieved significant binary-size reductions, ranging from \(11\% \) to \(38\% \) compared to the Enterprise version of GraalVM Native Image with PGO, while retaining similar performance as the O3 optimization level with PGO.
Maja Vukasović, Petar Đekanović, B. Spasojević et al.· ACM Transactions on Architec...· 0 citations
