Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees

TL;DR

This paper presents GG, a novel CISC-to-RISC transpilation method combining large language models with testing to ensure high correctness and efficiency, outperforming existing frameworks like Rosetta 2.

Contribution

Introduces GG, an ISA-centric transpilation pipeline that integrates LLMs with testing frameworks to improve correctness and performance in CISC-to-RISC translation.

Findings

Achieves 99% correctness on HumanEval programs.

Enforces over 98% code coverage in testing.

Outperforms Rosetta 2 in speed, energy, and memory efficiency.

Abstract

The hardware ecosystem is rapidly evolving, with 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 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 pre-trained 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 1.73x faster runtime performance, 1.47x better energy efficiency, and 2.41x better memory usage for our transpiled code, demonstrating the effectiveness of GG for real-world CISC-to-RISC translation tasks. We will open-source our codes, data, models, and benchmarks to establish a common foundation for ISA-level code translation research.