mlsanityData to 7 Oct 2026

Supersonic: Learning to Generate Source Code Optimizations in C/C++

arXiv 2309.14846 ↗First posted 26 Sep 2023cs.SE cs.AI cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Software optimization refines programs for resource efficiency while preserving functionality. Traditionally, it is a process done by developers and compilers. This paper introduces a third option, automated optimization at the source code level. We present Supersonic, a neural approach targeting minor source code modifications for optimization. Using a seq2seq model, Supersonic is trained on C/C++ program pairs (xt, xt+1), where xt+1 is an optimized version of xt, and outputs a diff. Supersonic's performance is benchmarked against OpenAI's GPT-3.5-Turbo and GPT-4 on competitive programming tasks. The experiments show that Supersonic not only outperforms both models on the code optimization task but also minimizes the extent of the change with a model more than 600x smaller than GPT-3.5-Turbo and 3700x smaller than GPT-4.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 36 of its 61 references that are in the map. First posted on arXiv 26 Sep 2023.

Builds on

36 of 61 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2022Training language models to follow instructions with human feedbackcited by 15,712
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  7. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  8. 2020Scaling Laws for Neural Language Modelscited by 6,411
  9. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  10. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  11. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  12. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
24 more
  1. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  2. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  3. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  4. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  5. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  6. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 327
  7. 2022Exploring Length Generalization in Large Language Modelscited by 204
  8. 2021CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Taskscited by 199
  9. 2018Learning to Optimize Tensor Programscited by 138
  10. 2023An Analysis of the Automatic Bug Fixing Performance of ChatGPTcited by 108
  11. 2023Learning Performance-Improving Code Editscited by 103
  12. 2023CodeBERTScore: Evaluating Code Generation with Pretrained Models of Codecited by 101
  13. 2023Is ChatGPT the Ultimate Programming Assistant -- How far is it?cited by 72
  14. 2023AI-assisted coding: Experiments with GPT-4cited by 43
  15. 2018A Survey on Compiler Autotuning using Machine Learningcited by 40
  16. 2021A Deep Learning Based Cost Model for Automatic Code Optimizationcited by 33
  17. 2020Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilationcited by 29
  18. 2023Improving ChatGPT Prompt for Code Generationcited by 28
  19. 2020ProGraML: Graph-based Deep Learning for Program Optimization and Analysiscited by 23
  20. 2023RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shotcited by 14
  21. 2017Improving Spark Application Throughput Via Memory Aware Task Co-location: A Mixture of Experts Approachcited by 5
  22. 2021Learning to Make Compiler Optimizations More Effectivecited by 4
  23. 2022Learning to Improve Code Efficiencycited by 4
  24. 2021Profile Guided Optimization without Profiles: A Machine Learning Approachcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 7; 2026: 2.

15 papers.

Sort:

By area:

  1. 2024A Performance Study of LLM-Generated Code on Leetcodecited by 48
  2. 2024Mercury: A Code Efficiency Benchmark for Code Large Language Modelscited by 34
  3. 2024Search-Based LLMs for Code Optimizationcited by 27
  4. 2024Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agentscited by 25
  5. 2026EffiSkill: Agent Skill Based Automated Code Efficiency Optimizationcited by 9
  6. 2024Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMscited by 8
  7. 2024DCA-Bench: A Benchmark for Dataset Curation Agentscited by 6
  8. 2025Rethinking Autonomy: Preventing Failures in AI-Driven Software Engineeringcited by 4
  9. 2025PerfCoder: Large Language Models for Interpretable Code Performance Optimizationcited by 3
  10. 2025FasterPy: An LLM-based Code Execution Efficiency Optimization Frameworkcited by 3
  11. 2025Investigating Execution-Aware Language Models for Code Optimizationcited by 1
  12. 2025Can We Make Code Green? Understanding Trade-Offs in LLMs vs. Human Code Optimizationscited by 1
3 more
  1. 2025ECO: Enhanced Code Optimization via Performance-Aware Prompting for Code-LLMscited by 1
  2. 2025LOOPRAG: Enhancing Loop Transformation Optimization with Retrieval-Augmented Large Language Modelscited by 1
  3. 2026Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learningcited by 0