@inproceedings{gong-etal-2026-glare,
title = "{GLARE}: Repository-Level Code Optimization Agents for Heterogeneous {CPU}-{GPU} Systems",
author = "Gong, Junfeng and
Liu, Cheng and
Chen, Junying and
Li, Xiaowei and
Li, Huawei",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1870/",
pages = "42615--42629",
ISBN = "979-8-89176-459-0",
abstract = "Recent LLM-based GPU code generation methods have shown promising results on CUDA and Triton kernels, but they typically operate on pre-isolated operators. Such a pre-isolated setting falls short in real-world CPU-GPU heterogeneous optimization, where the target computation is embedded in a larger repository and must be discovered, contextualized, selectively offloaded, and integrated. Such optimization requires repository-level context{---}including data structure definitions, caller patterns, build configurations, and profiling signals{---}that is largely absent from operator-level tasks and benchmarks. In this work, we propose GLARE, a profiling-guided framework for repository-level CPU-GPU heterogeneous optimization. GLARE anchors repository context in dynamic profiling signals, builds a multi-granular code dependency graph, extracts hotspot-centered active subgraphs, and uses an agentic loop to decide CPU-GPU partitioning and refine heterogeneous patches with execution feedback. On a GPU-acceleration subset of GSO with 63 tasks, GLARE improves OPT@1 from 74.6{\%} to 87.3{\%} over the strongest baseline under GPT-5.2, and achieves an 11.6{\%} average end-to-end speedup. Ablation studies confirm that profiling-guided context construction is the primary driver of these gains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gong-etal-2026-glare">
<titleInfo>
<title>GLARE: Repository-Level Code Optimization Agents for Heterogeneous CPU-GPU Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junfeng</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaowei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huawei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Recent LLM-based GPU code generation methods have shown promising results on CUDA and Triton kernels, but they typically operate on pre-isolated operators. Such a pre-isolated setting falls short in real-world CPU-GPU heterogeneous optimization, where the target computation is embedded in a larger repository and must be discovered, contextualized, selectively offloaded, and integrated. Such optimization requires repository-level context—including data structure definitions, caller patterns, build configurations, and profiling signals—that is largely absent from operator-level tasks and benchmarks. In this work, we propose GLARE, a profiling-guided framework for repository-level CPU-GPU heterogeneous optimization. GLARE anchors repository context in dynamic profiling signals, builds a multi-granular code dependency graph, extracts hotspot-centered active subgraphs, and uses an agentic loop to decide CPU-GPU partitioning and refine heterogeneous patches with execution feedback. On a GPU-acceleration subset of GSO with 63 tasks, GLARE improves OPT@1 from 74.6% to 87.3% over the strongest baseline under GPT-5.2, and achieves an 11.6% average end-to-end speedup. Ablation studies confirm that profiling-guided context construction is the primary driver of these gains.</abstract>
<identifier type="citekey">gong-etal-2026-glare</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1870/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>42615</start>
<end>42629</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GLARE: Repository-Level Code Optimization Agents for Heterogeneous CPU-GPU Systems
%A Gong, Junfeng
%A Liu, Cheng
%A Chen, Junying
%A Li, Xiaowei
%A Li, Huawei
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F gong-etal-2026-glare
%X Recent LLM-based GPU code generation methods have shown promising results on CUDA and Triton kernels, but they typically operate on pre-isolated operators. Such a pre-isolated setting falls short in real-world CPU-GPU heterogeneous optimization, where the target computation is embedded in a larger repository and must be discovered, contextualized, selectively offloaded, and integrated. Such optimization requires repository-level context—including data structure definitions, caller patterns, build configurations, and profiling signals—that is largely absent from operator-level tasks and benchmarks. In this work, we propose GLARE, a profiling-guided framework for repository-level CPU-GPU heterogeneous optimization. GLARE anchors repository context in dynamic profiling signals, builds a multi-granular code dependency graph, extracts hotspot-centered active subgraphs, and uses an agentic loop to decide CPU-GPU partitioning and refine heterogeneous patches with execution feedback. On a GPU-acceleration subset of GSO with 63 tasks, GLARE improves OPT@1 from 74.6% to 87.3% over the strongest baseline under GPT-5.2, and achieves an 11.6% average end-to-end speedup. Ablation studies confirm that profiling-guided context construction is the primary driver of these gains.
%U https://aclanthology.org/2026.emnlp-main.1870/
%P 42615-42629
Markdown (Informal)
[GLARE: Repository-Level Code Optimization Agents for Heterogeneous CPU-GPU Systems](https://aclanthology.org/2026.emnlp-main.1870/) (Gong et al., EMNLP 2026)
ACL