Copertina

Learning Performance-Improving Code Edits

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shypula, Alexander, Madaan, Aman, Zeng, Yimeng, Alon, Uri, Gardner, Jacob, Hashemi, Milad, Neubig, Graham, Ranganathan, Parthasarathy, Bastani, Osbert, Yazdanbakhsh, Amir
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Software Engineering Artificial Intelligence Machine Learning Performance
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
di: Ma, Jeffrey Jian, et al.
Pubblicazione: (2025)

Decaf: Improving Neural Decompilation with Automatic Feedback and Search
di: Shypula, Alexander, et al.
Pubblicazione: (2026)

A Magnified View into Heterogeneous-ISA Thread Migration Performance without State Transformation
di: Mavrogeorgis, Nikolaos, et al.
Pubblicazione: (2025)

CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
di: TehraniJamsaz, Ali, et al.
Pubblicazione: (2024)

An Empirical Study on the Performance and Energy Usage of Compiled Python Code
di: Stoico, Vincenzo, et al.
Pubblicazione: (2025)

Improving Structural Diversity of Blackbox LLMs via Chain-of-Specification Prompting
di: Young, Halley, et al.
Pubblicazione: (2024)

Tracing Optimization for Performance Modeling and Regression Detection
di: Shahedi, Kaveh, et al.
Pubblicazione: (2024)

Performance of Genetic Algorithms in the Context of Software Model Refactoring
di: Cortellessa, Vittorio, et al.
Pubblicazione: (2023)

gigiProfiler: Diagnosing Performance Issues by Uncovering Application Resource Bottlenecks
di: Hu, Yigong, et al.
Pubblicazione: (2025)

Optimas: An Intelligent Analytics-Informed Generative AI Framework for Performance Optimization
di: Zaeed, Mohammad, et al.
Pubblicazione: (2026)

Employing Software Diversity in Cloud Microservices to Engineer Reliable and Performant Systems
di: Akhtarian, Nazanin, et al.
Pubblicazione: (2024)

An Empirical Study on Method-Level Performance Evolution in Open-Source Java Projects
di: Shahedi, Kaveh, et al.
Pubblicazione: (2025)

A Model-driven Approach for Continuous Performance Engineering in Microservice-based Systems
di: Cortellessa, Vittorio, et al.
Pubblicazione: (2023)

An Empirical Study on How Architectural Topology Affects Microservice Performance and Energy Usage
di: Ristova, Irena, et al.
Pubblicazione: (2026)

Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software
di: Yi, Lirong, et al.
Pubblicazione: (2025)

On the Compression of Language Models for Code: An Empirical Study on CodeBERT
di: d'Aloisio, Giordano, et al.
Pubblicazione: (2024)

Can We Make Code Green? Understanding Trade-Offs in LLMs vs. Human Code Optimizations
di: Rani, Pooja, et al.
Pubblicazione: (2025)

LLM Program Optimization via Retrieval Augmented Search
di: Anupam, Sagnik, et al.
Pubblicazione: (2025)

ECO: An LLM-Driven Efficient Code Optimizer for Warehouse Scale Computers
di: Lin, Hannah, et al.
Pubblicazione: (2025)

Concorde: Fast and Accurate CPU Performance Modeling with Compositional Analytical-ML Fusion
di: Nasr-Esfahany, Arash, et al.
Pubblicazione: (2025)

Predicting Software Performance with Divide-and-Learn
di: Gong, Jingzhi, et al.
Pubblicazione: (2023)

Interpreting Performance Profiles with Deep Learning
di: Liu, Zhuoran
Pubblicazione: (2025)

LibProf: A Python Profiler for Improving Cold Start Performance in Serverless Applications
di: Tariq, Syed Salauddin Mohammad, et al.
Pubblicazione: (2024)

Stencil-Lifting: Hierarchical Recursive Lifting System for Extracting Summary of Stencil Kernel in Legacy Codes
di: Li, Mingyi, et al.
Pubblicazione: (2025)

Prompting for Performance: Exploring LLMs for Configuring Software
di: Spieker, Helge, et al.
Pubblicazione: (2025)

Risk-Aware Batch Testing for Performance Regression Detection
di: Sayedsalehi, Ali, et al.
Pubblicazione: (2026)

Should AI Optimize Your Code? A Comparative Study of Classical Optimizing Compilers Versus Current Large Language Models
di: Rosas, Miguel Romero, et al.
Pubblicazione: (2024)

PerfBench: Can Agents Resolve Real-World Performance Bugs?
di: Garg, Spandan, et al.
Pubblicazione: (2025)

VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations
di: Zheng, Zhongchun, et al.
Pubblicazione: (2025)

Estimating the Energy Footprint of Software Systems: a Primer
di: Castor, Fernando
Pubblicazione: (2024)

FaaSter Troubleshooting -- Evaluating Distributed Tracing Approaches for Serverless Applications
di: Borges, Maria C., et al.
Pubblicazione: (2021)

On the Role of Search Budgets in Model-Based Software Refactoring Optimization
di: Diaz-Pace, J. Andres, et al.
Pubblicazione: (2023)

What Is the Cost of Energy Monitoring? An Empirical Study on the Overhead of RAPL-Based Tools
di: Diamond, Jeremy, et al.
Pubblicazione: (2026)

Towards Assessing Spread in Sets of Software Architecture Designs
di: Cortellessa, Vittorio, et al.
Pubblicazione: (2024)

Scalable Software as a Service Architecture
di: Dedase, Ardy
Pubblicazione: (2024)

RAO-SS: A Prototype of Run-time Auto-tuning Facility for Sparse Direct Solvers
di: Katagiri, Takahiro, et al.
Pubblicazione: (2024)

A Test for FLOPs as a Discriminant for Linear Algebra Algorithms
di: Sankaran, Aravind, et al.
Pubblicazione: (2022)

MLKAPS: Machine Learning and Adaptive Sampling for HPC Kernel Auto-tuning
di: Jam, Mathys, et al.
Pubblicazione: (2025)

Towards a Higher Roofline for Matrix-Vector Multiplication in Matrix-Free HOSFEM
di: Cao, Zijian, et al.
Pubblicazione: (2025)

Formal Analysis of Metastable Failures in Software Systems
di: Alvaro, Peter, et al.
Pubblicazione: (2025)