paper-with-me

홈 › Papers

From Prompts to Performance: Evaluating LLMs for Task-based Parallel Code Generation

2026-02-24 · Linus Bantel, Moritz Strack, Alexander Strack, Dirk Pflüger arxiv

Large Language Models (LLM) show strong abilities in code generation, but their skill in creating efficient parallel programs is less studied. This paper explores how LLMs generate task-based parallel code from three kinds of input prompts: natural language problem descriptions, sequential reference implementations, and parallel pseudo code. We focus on three programming frameworks: OpenMP Tasking, C++ standard parallelism, and the asynchronous many-task runtime HPX. Each framework offers different levels of abstraction and control for task execution. We evaluate LLM-generated solutions for correctness and scalability. Our results reveal both strengths and weaknesses of LLMs with regard to problem complexity and framework. Finally, we discuss what these findings mean for future LLM-assisted development in high-performance and scientific computing.

📄 PDF Abstract BibTeX arXiv:2602.22240

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

Social Bias Evaluation for Large Language Models Requires Prompt Variations

2024-07-03 · Rem Hida, Masahiro Kaneko, Naoaki Okazaki

Warning: This paper contains examples of stereotypes and biases. Large Language Models (LLMs) exhibit considerable social biases, and various studies have tried to evaluate and mitigate these biases accurately. Previous …

Sensitivity

Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning

2023-05-26 · Ruixiang Tang, Dehan Kong, Longtao Huang, Hui Xue

Large language models (LLMs) have recently shown great potential for in-context learning, where LLMs learn a new task simply by conditioning on a few input-label pairs (prompts). Despite their potential, our understandin…

In-Context Learning

RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models

2023-08-21 · Yasuto Hoshi, Daisuke Miyashita, Youyang Ng, Kento Tatsuno 외

Retrieval-augmented large language models (R-LLMs) combine pre-trained large language models (LLMs) with information retrieval systems to improve the accuracy of factual question-answering. However, current libraries for…

Information RetrievalQuestion AnsweringRetrieval

Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts

2025-08-08 · Zhaomin Wu, Mingzhe Du, See-Kiong Ng, Bingsheng He arxiv

Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks, making their trustworthiness critical. A significant and underexplored risk is intentional deception, where an LLM delib…

HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization

2024-02-26 · Qiwei Peng, Yekun Chai, Xuhong LI

Large language models (LLMs) have made significant progress in generating codes from textual prompts. However, existing benchmarks have mainly concentrated on translating English prompts to multilingual codes or have bee…

Code GenerationHumanEval