From CISC to RISC: language-model guided assembly transpilation

TL;DR

This paper presents CRT, a lightweight LLM-based assembler transpiler that converts x86 CISC assembly to ARM RISC assembly, improving cross-architecture compatibility, performance, and efficiency with high accuracy and practical deployment results.

Contribution

CRT is the first LLM-based tool that effectively bridges x86 and ARM architectures, enabling accurate and optimized assembly translation across diverse platforms.

Findings

Achieves 79.25% accuracy from x86 to ARMv5

Achieves 88.68% accuracy from x86 to RISC-V

Provides 1.73× speedup and 2.41× memory efficiency on Apple M2

Abstract

The transition from x86 to ARM architecture is becoming increasingly common across various domains, primarily driven by ARM's energy efficiency and improved performance across traditional sectors. However, this ISA shift poses significant challenges, mainly due to the extensive legacy ecosystem of x86 software and lack of portability across proprietary ecosystems and software stacks. This paper introduces CRT, a lightweight LLM-based transpiler that automatically converts x86 assembly to ARM assembly. Our approach bridges the fundamental architectural gap between x86's CISC-based and ARM's RISC-based computing paradigms while preserving program semantics and optimizing performance. We evaluate CRT on diverse real-world applications, achieving 79.25% translation accuracy from x86 to ARMv5 on our comprehensive test suite, and an 88.68% accuracy from x86 to RISC-V. In practical deployments on Apple M2 hardware (ARMv8), our transpiled code achieves 1.73$\times$ speedup compared to Apple's Rosetta 2 virtualization engine, while delivering 2.41$\times$ memory efficiency and 1.47$\times$ better energy consumption. Through testing and analysis, we show that CRT successfully navigates the CISC/RISC divide and generates correctly executable RISC code despite machine ``language'' barriers. We release our code, models, training datasets, and benchmarks at: \url{https://ahmedheakl.github.io/asm2asm/}.