paper-with-me

Papers

QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code

2025-11-03 · Hainan Fang, Yuanbo Wen, Jun Bi, Yihan Wang, Tonghui He, Yanlin Tang, Di Huang, Jiaming Guo, Rui Zhang, Qi Guo, Yunji Chen arxiv

Compilers, while essential, are notoriously complex systems that demand prohibitively expensive human expertise to develop and maintain. The recent advancements in Large Language Models (LLMs) offer a compelling new paradigm: Neural Compilation, which could potentially simplify compiler development for new architectures and facilitate the discovery of innovative optimization techniques. However, several critical obstacles impede its practical adoption. Firstly, a significant lack of dedicated benchmarks and robust evaluation methodologies hinders objective assessment and tracking of progress in the field. Secondly, systematically enhancing the reliability and performance of LLM-generated assembly remains a critical challenge. Addressing these challenges, this paper introduces NeuComBack, a novel benchmark dataset specifically designed for IR-to-assembly compilation. Leveraging this dataset, we first define a foundational Neural Compilation workflow and conduct a comprehensive evaluation of the capabilities of recent frontier LLMs on Neural Compilation, establishing new performance baselines. We further propose a self-evolving prompt optimization method that enables LLMs to iteratively evolve their internal prompt strategies by extracting insights from prior self-debugging traces, thereby enhancing their neural compilation capabilities. Experiments demonstrate that our method significantly improves both the functional correctness and the performance of LLM-generated assembly code. Compared to baseline prompts, the functional correctness rates improved from 44% to 64% on x86_64 and from 36% to 58% on aarch64, respectively. More significantly, among the 16 correctly generated x86_64 programs using our method, 14 (87.5%) surpassed clang-O3 performance.

📄 PDF Abstract BibTeX arXiv:2511.01183

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation

2025-10-22 · Yang Zhang, Rui Zhang, Jiaming Guo, Lei Huang 외 arxiv

The remarkable progress of Large Language Models (LLMs) presents promising opportunities for Verilog code generation which is significantly important for automated circuit design. The lacking of meaningful functional rew…

Reinforcement LearningCode Generation

QiMeng: Fully Automated Hardware and Software Design for Processor Chip

2025-06-05 · Rui Zhang, Yuanbo Wen, Shuyao Cheng, Di Huang 외

Processor chip design technology serves as a key frontier driving breakthroughs in computer science and related fields. With the rapid advancement of information technology, conventional design paradigms face three major…

Ribosome self-assembly leads to overlapping reproduction cycles and increases growth rate

2018-07-08 · Rami Pugatch, Yinon M. Bar-On

In permissive environments, E. coli can double its dry mass every 21 minutes. During this time, ribosomes, RNA polymerases, and the proteome are all doubled. Yet, the question of how to relate bacterial doubling time to …

Engineered Self-Organization for Resilient Robot Self-Assembly with Minimal Surprise

2019-02-14 · Tanja Katharina Kaiser, Heiko Hamann

In collective robotic systems, the automatic generation of controllers for complex tasks is still a challenging problem. Open-ended evolution of complex robot behaviors can be a possible solution whereby an intrinsic dri…

MDDM: A Molecular Dynamics Diffusion Model to Predict Particle Self-Assembly

2025-01-28 · Kevin Ferguson, Yu-Hsuan Chen, Levent Burak Kara

The discovery and study of new material systems relies on molecular simulations that often come with significant computational expense. We propose MDDM, a Molecular Dynamics Diffusion Model, which is capable of predictin…

valid