EMNLP Findings2025
Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees
Ahmed Heakl, Sarim Hashmi, Chaimaa Abi, Celine Lee, Abdulrahman Mahmoud
Abstract
With a rapidly evolving hardware ecosystem, there is increasing interest in translating low-level programs across different instruction set architectures (ISAs) in a quick, flexible, and correct way to enhance the portability and longevity of existing code. A particularly challenging class of this transpilation 1 problem is translating between complex-(CISC) and reduced-(RISC) hardware architectures, due to fundamental differences in instruction complexity, memory models, and execution paradigms. In this work, we introduce GG (Guaranteed Guess), an ISA-centric transpilation pipeline that combines the translation power of pretrained large language models (LLMs) with the rigor of established software testing constructs.
Our method generates candidate translations using an LLM from one ISA to another, and embeds such translations within a software-testing framework to build quantifiable confidence in the translation. We evaluate our GG approach over two diverse datasets, enforce high code coverage (>98%) across unit tests, and achieve functional/semantic correctness of 99% on HumanEval programs and 49% on BringupBench programs, respectively. Further, we compare our approach to the state-of-the-art Rosetta 2 framework on Apple Silicon, showcasing 1.73× faster runtime performance, 1.47× better energy efficiency, and 2.41× better memory usage for our transpiled code, demonstrating the effectiveness of GG for real-world CISC-to-RISC translation tasks.We have open-sourced our code, data, models, and benchmarks to establish a common foundation for ISA-level code translation research.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on14
- FlashAttention-2: Faster Attention with Better Parallelism and Work PartitioningTri DaoICLR 2024 · 2,600 citations
- CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and GenerationYue Wang, Weishi Wang, Shafiq R. Joty, Steven C. H. HoiEMNLP 2021 · 1,224 citations
- Unsupervised Translation of Programming LanguagesBaptiste Rozière, Marie-Anne Lachaux, Lowik Chanussot, Guillaume LampleNeurIPS 2020 · 606 citations
- Order Matters: Semantic-Aware Neural Networks for Binary Code Similarity DetectionZeping Yu, Rui Cao, Qiyi Tang, Sen Nie et al.AAAI 2020 · 265 citations
- Debin: Predicting Debug Information in Stripped BinariesJingxuan He, Pesho Ivanov, Petar Tsankov, Veselin Raychev et al.CCS 2018 · 148 citations
Related papers
- Guess & Sketch: Language Model Guided TranspilationCeline Lee, Abdulrahman Mahmoud, Michal Kurek, Simone Campanoni et al.ICLR 2024 · 8 citations
- Introducing Compiler Semantics into Large Language Models as Programming Language Translators: A Case Study of C to x86 AssemblyShuoming Zhang, Jiacheng Zhao, Chunwei Xia, Zheng Wang et al.EMNLP Findings 2024 · 1 citation
- Exploring and Unleashing the Power of Large Language Models in Automated Code TranslationZhen Yang, Fang Liu, Zhongxing Yu, Jacky Wai Keung et al.FSE 2024 · 72 citations
- Verified Code Transpilation with LLMsSahil Bhatia, Jie Qiu, Niranjan Hasabnis, Sanjit A. Seshia et al.NeurIPS 2024 · 36 citations
- SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based VerificationTianyang Zhou, Ziyi Zhang, Haowen Lin, Somesh Jha et al.ACL 2026 · 8 citations
