English
Related papers

Related papers: Magellan: Autonomous Discovery of Novel Compiler O…

200 papers

Auto-vectorization is a fundamental optimization for modern compilers to exploit SIMD parallelism. However, state-of-the-art approaches still struggle to handle intricate code patterns, often requiring manual hints or domain-specific…

Software Engineering · Computer Science 2025-06-05 Zhongchun Zheng , Kan Wu , Long Cheng , Lu Li , Rodrigo C. O. Rocha , Tianyi Liu , Wei Wei , Jianjiang Zeng , Xianwei Zhang , Yaoqing Gao

Sparse linear algebra is central to many scientific programs, yet compilers fail to optimize it well. High-performance libraries are available, but adoption costs are significant. Moreover, libraries tie programs into vendor-specific…

Performance · Computer Science 2020-01-29 Philip Ginsbach , Bruce Collie , Michael F. P. O'Boyle

Large Language Models (LLMs) have recently demonstrated impressive capabilities across various real-world applications. However, due to the current text-in-text-out paradigm, it remains challenging for LLMs to handle dynamic and complex…

Artificial Intelligence · Computer Science 2024-10-25 Timothy Wei , Annabelle Miin , Anastasia Miin

Large language models hold promise as scientific assistants, yet existing agents either rely solely on algorithm evolution or on deep research in isolation, both of which face critical limitations. Pure algorithm evolution, as in…

Artificial Intelligence · Computer Science 2025-10-08 Gang Liu , Yihan Zhu , Jie Chen , Meng Jiang

While recent research increasingly emphasizes the value of human-LLM collaboration in competitive programming and proposes numerous empirical methods, a comprehensive understanding remains elusive due to the fragmented nature of existing…

Artificial Intelligence · Computer Science 2025-05-23 Xinwei Yang , Zhaofeng Liu , Chen Huang , Jiashuai Zhang , Tong Zhang , Yifan Zhang , Wenqiang Lei

The emergence of large language models (LLMs) has significantly pushed the frontiers of program synthesis. Advancement of LLM-based program synthesis calls for a thorough evaluation of LLM-generated code. Most evaluation frameworks focus on…

Software Engineering · Computer Science 2025-02-20 Ruizhong Qiu , Weiliang Will Zeng , James Ezick , Christopher Lott , Hanghang Tong

Compiler architects increasingly look to machine learning when building heuristics for compiler optimization. The promise of automatic heuristic design, freeing the compiler engineer from the complex interactions of program, architecture,…

Programming Languages · Computer Science 2020-12-04 Chris Cummins , Hugh Leather , Zacharias Fisches , Tal Ben-Nun , Torsten Hoefler , Michael O'Boyle

We present ensmallen, a fast and flexible C++ library for mathematical optimization of arbitrary user-supplied functions, which can be applied to many machine learning problems. Several types of optimizations are supported, including…

Mathematical Software · Computer Science 2018-12-11 Shikhar Bhardwaj , Ryan R. Curtin , Marcus Edel , Yannis Mentekidis , Conrad Sanderson

LLM-based coding agents can generate functionally correct GPU kernels, yet their performance remains far below hand-optimized libraries on critical computations such as matrix multiplication, attention, and Mixture-of-Experts (MoE). Peak…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-22 Haohui Mai , Xiaoyan Guo , Xiangyun Ding , Daifeng Li , Qiuchu Yu , Chenzhun Guo , Cong Wang , Jiacheng Zhao , Christos Kozyrakis , Binhang Yuan

LLM-powered coding agents are reshaping the development paradigm. However, existing evaluation systems, neither traditional tests for humans nor benchmarks for LLMs, fail to capture this shift, excluding problems that require both human…

The key to performance optimization of a program is to decide correctly when a certain transformation should be applied by a compiler. This is an ideal opportunity to apply machine-learning models to speed up the tuning process; while this…

Large Language Models (LLMs) have advanced the field of Combinatorial Optimization through automated heuristic generation. Instead of relying on manual design, this LLM-Driven Heuristic Design (LHD) process leverages LLMs to iteratively…

Machine Learning · Computer Science 2026-04-17 Rongzheng Wang , Yihong Huang , Muquan Li , Jiakai Li , Di Liang , Bob Simons , Pei Ke , Shuang Liang , Ke Qin

Topology optimization is a widely used design method that produces optimized material distributions for prescribed objectives and constraints through well-established numerical algorithms. Throughout the workflow, engineers make a series of…

Multiagent Systems · Computer Science 2026-05-25 Hyunjee Park , Hayoung Chung

How to align large language models (LLMs) with user preferences from a static general dataset has been frequently studied. However, user preferences are usually personalized, changing, and diverse regarding culture, values, or time. This…

Computation and Language · Computer Science 2025-06-13 Zhaowei Zhang , Fengshuo Bai , Qizhi Chen , Chengdong Ma , Mingzhi Wang , Haoran Sun , Zilong Zheng , Yaodong Yang

Can a single LLM-based optimization system match specialized tools across fundamentally different domains? We show that when optimization problems are formulated as improving a text artifact evaluated by a scoring function, a single…

Optimizing CUDA code across multiple generations of GPU architectures is challenging, as achieving peak performance requires an extensive exploration of an increasingly complex, hardware-specific optimization space. Traditional compilers…

Producing high-quality code across multiple programming languages is increasingly important as today's software systems are built on heterogeneous stacks. Large language models (LLMs) have advanced the state of automated programming, yet…

As program workloads (e.g., AI) increase in size and algorithmic complexity, the primary challenge lies in their high dimensionality, encompassing computing cores, array sizes, and memory hierarchies. To overcome these obstacles, innovative…

Hardware Architecture · Computer Science 2025-10-10 Jinwei Tang , Jiayin Qin , Nuo Xu , Pragnya Sudershan Nalla , Yu Cao , Yang , Zhao , Caiwen Ding

Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrained by a Generate-Execute-Feedback paradigm. Previous approaches suffer from a severe Execution Bottleneck, as hypothesis evaluation relies…

Computation and Language · Computer Science 2026-04-08 Jingsheng Zheng , Jintian Zhang , Yujie Luo , Yuren Mao , Yunjun Gao , Lun Du , Huajun Chen , Ningyu Zhang

Medical decision-making is a critical task, where errors can result in serious, potentially life-threatening consequences. While full automation remains challenging, hybrid frameworks that combine machine intelligence with human oversight…

Artificial Intelligence · Computer Science 2025-09-10 Debodeep Banerjee , Burcu Sayin , Stefano Teso , Andrea Passerini