Compiler Optimization

Latest papers

27 papers7 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Conjugate Compilation: Self-Improving Agentic Co-Compilation for Speculative Decoding
Oct 18, 2026Annabelle Sujun Tang, Rohan Mahapatra, Christopher Priebe +4LLM Inference Acceleration Speculative Decoding
University of California, San Diego · Massachusetts Institute of Technology · Systalyze +2
Pattern-Driven Evaluation of LLM Code Optimization: Isolating Compiler-Transcendent Semantic Reasoning
Oct 17, 2026Wesley Lu, Runzhou Liu, Hongru Du +1Large Language Model-Guided Optimization Compiler Optimization
Georgia Institute of Technology · University of Virginia
Peak-Memory Schedules You Can Trust: Exact Realization, Certified Optimality, and the Limits of Recomputation for Inference
Oct 16, 2026Ivan Fomin, Ivan Koryabkin, Boris SheludkoInference-Time Optimization Memory-Efficient Inference
Yandex, Moscow, Russia.
How to Train Your Little Dragon: Teaching a Small Language Model to Construct and Refine GPU Optimization Scripts
Oct 14, 2026Annabelle Sujun Tang, Wei Tang, Songyao Jiang +7Compiler Optimization Code Optimization
University of California, San Diego · Amazon Annapurna Labs
Cleave: Scaling Tensor Program Optimization via Decoupled Algebraic Search and Operator Scheduling
Oct 6, 2026David Pissarra, Jinkun Lin, Haitian Jiang +2Compiler Optimization GPU Kernel Optimization
New York University New York, USA
AI as a Compiler: Compiling Triton kernels without the Triton compiler
Sep 29, 2026François Costa, Charly Castes, Thomas Bourgeat +1GPU Kernel Optimization Large Language Model-Guided Optimization
Stanford University · EPFL
KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization
Sep 24, 2026Aheli Poddar, Sanskar Prasad, Arindam Samanta +3GPU Kernel Optimization Agentic Search
Red Hat
Tensor Seeks Layout: Formalizing Layout Selection for ML Compilers
Aug 21, 2026Clemens Eisenhofer, Yuwen Jia, Daniel Kroening +1Compiler Optimization Deep Learning Optimization
TU Wien, Vienna, Austria · Amazon, Cupertino, California, USA
T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework
Aug 15, 2026Zahra Fazel, Sunanda Gamage, Shayan Shirahmad Gale Bagi +5Code Optimization Compiler Optimization
Huawei Technologies, Heterogeneous Compiler Lab, Toronto, Canada
LLM-Based Embeddings for Program Analysis and Optimization
Aug 8, 2026Calvin Higgins, Marco AlvarezCompiler Optimization
Department of Computer Science and Statistics University of Rhode Island Kingston, United States of America
Can Large Language Models Recover Semantic Optimization Opportunities That Compilers Miss?
Aug 4, 2026Hailong Jiang, Feng Yu, Emran Hossain +4Compiler Optimization Large Language Model-Guided Optimization
School of Computer Science, Information, and Engineering Technology, Youngstown State University · Department of Computer Science, Kent State University · Department of Computer Science, Baylor University +1
Understanding Agent-Based Patching of Compiler Missed Optimizations
Jul 2, 2026Batu Guan, Zirui Wang, Shaohua LiCode Generation AI Coding Agents
The Chinese University of Hong Kong · Hong Kong SAR
Compiler-Driven Approximation Tuning for Hyperdimensional Computing
Jun 25, 2026Xavier Routh, Abdul Rafae Noor, Akash Kothari +4Compiler Optimization Hyperdimensional Computing
University of Illinois Urbana-Champaign Urbana, IL, USA · University of California San Diego La Jolla, CA, USA
AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning
Jun 18, 2026Zepeng Li, Jie Ren, Zhanyong Tang +2Compiler Optimization Large Language Model-Guided Optimization
Shaanxi Normal University · China · Northwest University +2
AgentCompile: An LLM-Guided Compiler for Direct CUDA Inference
Jun 4, 2026Xuanzhe Li, Ziyan Weng, Zhiyu Zhu +1High-Performance Computing GPU Kernel Generation
City University of Hong Kong (Dongguan) · City University of Hong Kong
AI-PROPELLER: Warehouse-Scale Interprocedural Code Layout Optimization with AlphaEvolve
May 28, 2026Chaitanya Mamatha Ananda, Rajiv Gupta, Mircea Trofin +4Compiler Optimization Code Optimization
University of California, Riverside · Google · Google DeepMind
PassNet: Scaling Large Language Models for Graph Compiler Pass Generation
May 28, 2026Yiqun Liu, Yingsheng Wu, Ruqi Yang +11Large Language Model-Guided Optimization Compiler Optimization
Baidu, Inc.
PopPy: Opportunistically Exploiting Parallelism in Python Agentic Workflows
May 18, 2026Stephen Mell, David Mell, Harry Y. H. Li +4Compiler Optimization Agentic Workflows
University of Pennsylvania Philadelphia, Pennsylvania, USA · Independent Researcher Juneau, Alaska, USA · University of California, Los Angeles Los Angeles, California, USA
LLM-Guided Strategy Synthesis for Scalable Equality Saturation
Apr 19, 2026Chenyun Yin, Youwei Xiao, Yuze Luo +2Compiler Optimization Large Language Model-Guided Optimization
Peking University Beijing, China · School of Integrated Circuits Peking University Beijing, China
Prism: Symbolic Superoptimization of Tensor Programs
Apr 16, 2026Mengdi Wu, Xiaoyu Jiang, Oded Padon +1GPU Kernel Optimization Compiler Optimization
Carnegie Mellon University USA · Tsinghua University China · Weizmann Institute of Science Israel
Forge-UGC: FX optimization and register-graph engine for universal graph compiler
Apr 14, 2026Satyam Kumar, Saurabh JhaCompiler Optimization AI Accelerator Inference
Automatic Identification of Parallelizable Loops Using Transformer-Based Source Code Representations
Mar 31, 2026Izavan dos S. Correia, Henrique C. T. Santos, Tiago A. E. FerreiraCompiler Optimization
Graduate Program in Applied Informatics (PPGIA), Federal Rural University of Pernambuco (UFRPE), Recife, Pernambuco, Brazil. · Undergraduate Program in Analysis and Systems Development (TADS), Federal Institute of Pernambuco (IFPE), Recife, Pernambuco, Brazil.
InCoder-32B: Code Foundation Model for Industrial Scenarios
Mar 17, 2026Jian Yang, Wei Zhang, Jiajun Wu +25Compiler Optimization Code Language Models
Beihang University · IQuest Research · Shanghai Jiao Tong University +6
PolyBlocks: A Compiler Infrastructure for AI Chips and Programming Frameworks
Mar 6, 2026Uday Bondhugula, Akshay Baviskar, Navdeep Katel +3Compiler Optimization GPU Kernel Generation
Polymage Labs and Indian Institute of Science, Bengaluru, Karnataka, India · Polymage Labs, Bengaluru, India
Beyond Pass-by-Pass Optimization: Intent-Driven IR Optimization with Large Language Models
Feb 19, 2026Lei Qiu, Zi Yang, Fang Lyu +3Compiler Optimization Code Optimization
SKLP, ICT, CAS, China · UCAS, China · Jiangnan University, China +1
MOSAIC: More LLMs, Less Cost through Collaborative Reasoning for Compiler Optimizations
Feb 2, 2026Annabelle Sujun Tang, Christopher Priebe, Lianhui Qin +1Large Language Model-Guided Optimization Compiler Optimization
Alternative Computing Technologies (ACT) Lab, University of California San Diego
GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2
Sep 17, 2025Savini Kashmira, Jayanaka Dantanarayana, Thamirawaran Sathiyalogeswaran +3Efficient Neural Network Inference Compiler Optimization
University of Michigan USA · Jaseci Labs USA

Oct 18, 2026J/K move · Enter open · S save

Conjugate Compilation: Self-Improving Agentic Co-Compilation for Speculative Decoding

Annabelle Sujun Tang, Rohan Mahapatra, Christopher Priebe, Hanyang Xu+3

University of California, San Diego · Massachusetts Institute of Technology · Systalyze+2

LLM Inference Acceleration Speculative Decoding Compiler Optimization GPU Kernel Optimization Large Language Model-Guided Optimization

Open paper AskPDF arXiv

As LLM adoption surges, scaling model serving requires unlocking stranded GPU capacity alongside deploying more GPUs. Speculative decoding brings two models into the serving process: a small draft model proposes tokens that a larger target model verifies. Yet compiling these models individually leaves their shared execution outside the compiler's optimization boundary. We introduce CONJUGATE COMPILATION, which reframes speculative decoding as a cross-model compilation problem and jointly optimizes the draft and target models within their shared execution rather than treating each in isolation. Our key insight is that cross-model compilation should be informed by the measured performance of the co-located shared execution it produces: an optimization that improves a kernel in isolation need not improve the models when they execute together. To expand cross-model opportunities, we devise operand layouts that interleave blocks from both models within common tiles, co-locating GEMM and non-GEMM work while preserving their mathematics. We realize CONJUGATE COMPILATION through a self-improving agentic search system in which an LLM edits cross-model optimization plans using the compiler and GPU execution as its environment. Each proposed plan is compiled and evaluated through its co-located shared execution, whose measured score, together with kernel-level verdicts and compiler feedback, informs subsequent proposals, while Monte Carlo tree search accumulates rewards to guide exploration. Across six single-GPU speculative-decoding configurations on NVIDIA B300 and RTX 5090 GPUs, CONJUGATE COMPILATION achieves a geometric-mean per-round speedup of 1.37x over conventional execution. Interleaved kernels raise this speedup to 1.45x, reaching 1.59x in the best case. CONJUGATE COMPILATION also improves GPU utilization on average by 1.46x on RTX 5090 and 1.50x on B300.