LLM Translation of Compiler Intermediate Representation

• URL: http://arxiv.org/abs/2605.08247v1
• Date: Thu, 07 May 2026 13:22:23 GMT
• Title: LLM Translation of Compiler Intermediate Representation
• Abstract summary: This paper presents IRIS-14B, a transformer model fine-tuned to translate GIMPLE to LLVM IR.<n>To the best of our knowledge, IRIS-14B is the first model trained explicitly for IR-to-IR translation.<n>It outperforms the accuracy of widely used models, including the largest state-of-the-art open models available today, ranging from 13 to 1,000 billion parameters, by up to 44 percentage points.
• Score: 2.614444430580024
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: GCC and LLVM underpin much of modern software infrastructure, relying on distinct Intermediate Representations (IRs) to drive optimizations and code generation. However, the semantic and structural differences between these IRs create significant barriers for cross-toolchain interaction, limiting the reuse of compiler frontends, backends, and optimization pipelines across programming languages and compilation ecosystems. Traditional rule-based translators have attempted to bridge this gap, but their complexity and maintenance cost have hindered practical adoption. In this context, Large Language Models (LLMs) appear to be an emerging technology that offers a data-driven alternative, capable of learning complex mappings between heterogeneous compiler IRs directly from sufficiently representative examples. To explore this approach, this paper presents IRIS-14B, a 14-billion-parameter transformer model fine-tuned to translate GIMPLE (as emitted by GCC) to LLVM IR (as emitted by LLVM). The model is trained on paired IRs extracted from C sources and evaluated on the GIMPLE-to-LLVM IR transformation applied to IRs derived from real-world C code and competitive programming problems. To the best of our knowledge, IRIS-14B is the first model trained explicitly for IR-to-IR translation. It outperforms the accuracy of widely used models, including the largest state-of-the-art open models available today, ranging from 13 to 1,000 billion parameters, by up to 44 percentage points. The proposed transformation supports the integration of LLMs as complementary components within hybrid neuro-symbolic compiler architectures, where models such as IRIS-14B act as interoperability layers enabling cross-toolchain workflows without modifying existing compiler passes, while traditional compiler infrastructure continues to perform deterministic compilation and optimization.

Related papers

• RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning [49.24254347822435]
  Remote Sensing Image Change Captioning (RSICC) aims to describe changes between bi-temporal remote sensing images.<n>We propose RSICCLLM, the first post-training framework for large vision-language models in RSICC.
  arXiv  Detail & Related papers  (2026-06-26T16:57:40Z)
• PEAK: A Performance Engineering AI-Assistant for GPU Kernels Powered by Natural Language Transformations [0.8699280339422538]
  We introduce PEAK, a Performance Engineering AI-Assistant for Kernels powered by natural language transformations.<n>We show that our implementations are competitive with vendor libraries when available, and for HLSL (without a library) our documented FLOPS.
  arXiv  Detail & Related papers  (2025-12-22T04:15:24Z)
• VecIntrinBench: Benchmarking Cross-Architecture Intrinsic Code Migration for RISC-V Vector [8.59222474360646]
  Translating intrinsic functions to RISC-V Vector (RVV) intrinsic functions across architectures is currently a mainstream approach.<n>There is currently no benchmark that comprehensively evaluates the intrinsic migration capabilities for the RVV extension.<n>We propose VecIntrinBench, the first intrinsic benchmark encompassing RVV extensions.
  arXiv  Detail & Related papers  (2025-11-24T08:11:10Z)
• OMPILOT: Harnessing Transformer Models for Auto Parallelization to Shared Memory Computing Paradigms [13.343925256921722]
  We introduce OMPILOT, a domain-specific encoder-decoder transformer tailored for translating C++ code into OpenMP.<n>OMPBLEU is a novel composite metric crafted to assess the correctness and quality of OpenMP parallel constructs.
  arXiv  Detail & Related papers  (2025-11-05T21:21:15Z)
• QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code [52.66657751895655]
  Large Language Models (LLMs) offer a compelling new paradigm: Neural Compilation.<n>This paper introduces NeuComBack, a novel benchmark dataset specifically designed for IR-to-assembly compilation.<n>We propose a self-evolving prompt optimization method that enables LLMs to evolve their internal prompt strategies.
  arXiv  Detail & Related papers  (2025-11-03T03:20:26Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving [6.19179006129561]
  We introduce a novel compilation framework (dubbed Reasoning) that formulates optimization as a sequential, context-aware decision process.<n>Our approach demonstrates the potential of LLM-guided reasoning to transform the landscape of compiler optimization.
  arXiv  Detail & Related papers  (2025-06-02T07:02:46Z)
• Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo [90.78001821963008]
  A wide range of LM applications require generating text that conforms to syntactic or semantic constraints.<n>We develop an architecture for controlled LM generation based on sequential Monte Carlo (SMC)<n>Our system builds on the framework of Lew et al. (2023) and integrates with its language model probabilistic programming language.
  arXiv  Detail & Related papers  (2025-04-17T17:49:40Z)
• VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations [17.974013479973774]
  VecTrans is a framework that leverages large language models to enhance compiler-based code vectorization.<n>VecTrans achieves an geomean speedup of 1.77x and successfully vectorizes 24 of 51 test cases.
  arXiv  Detail & Related papers  (2025-03-25T08:39:35Z)
• Universal In-Context Approximation By Prompting Fully Recurrent Models [86.61942787684272]
  We show that RNNs, LSTMs, GRUs, Linear RNNs, and linear gated architectures can serve as universal in-context approximators. We introduce a programming language called LSRL that compiles to fully recurrent architectures.
  arXiv  Detail & Related papers  (2024-06-03T15:25:13Z)
• Enabling Retargetable Optimizing Compilers for Quantum Accelerators via a Multi-Level Intermediate Representation [78.8942067357231]
  We present a multi-level quantum-classical intermediate representation (IR) that enables an optimizing, retargetable, ahead-of-time compiler. We support the entire gate-based OpenQASM 3 language and provide custom extensions for common quantum programming patterns and improved syntax. Our work results in compile times that are 1000x faster than standard Pythonic approaches, and 5-10x faster than comparative standalone quantum language compilers.
  arXiv  Detail & Related papers  (2021-09-01T17:29:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.