paper-with-me

홈 › Papers

Creating a Dataset for High-Performance Computing Code Translation using LLMs: A Bridge Between OpenMP Fortran and C++

2023-07-15 · Bin Lei, Caiwen Ding, Le Chen, Pei-Hung Lin, Chunhua Liao

In this study, we present a novel dataset for training machine learning models translating between OpenMP Fortran and C++ code. To ensure reliability and applicability, the dataset is created from a range of representative open-source OpenMP benchmarks. It is also refined using a meticulous code similarity test. The effectiveness of our dataset is assessed using both quantitative (CodeBLEU) and qualitative (human evaluation) methods. We showcase how this dataset significantly elevates the translation competencies of large language models (LLMs). Specifically, models without prior coding knowledge experienced a boost of $\mathbf{\times~5.1}$ in their CodeBLEU scores, while models with some coding familiarity saw an impressive $\mathbf{\times~9.9}$-fold increase. The best fine-tuned model using our dataset outperforms GPT-4. It is also reaching human-level accuracy. This work underscores the immense potential of our dataset in propelling advancements in the domain of code translation for high-performance computing. The dataset is accessible at \href{https://github.com/bin123apple/Fortran-CPP-HPC-code-translation-dataset}{OpenMP-Fortran-CPP-Translation}.

📄 PDF Abstract BibTeX arXiv:2307.07686

Code (1)

bin123apple/fortran-cpp-hpc-code-translation-dataset 공식 구현 pytorch

Tasks

C++ codeCode TranslationTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

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 kin…

Code Generation

A recipe for creating ideal hybrid memristive-CMOS neuromorphic computing systems

2019-12-11 · Elisabetta Chicca, Giacomo Indiveri

The development of memristive device technologies has reached a level of maturity to enable the design of complex and large-scale hybrid memristive-CMOS neural processing systems. These systems offer promising solutions …

Edge-computing

Nonlinear Optical Data Transformer for Machine Learning

2022-08-19 · Mustafa Yıldırım, Ilker Oguz, Fabian Kaufmann, Marc Reig Escale 외

Modern machine learning models use an ever-increasing number of parameters to train (175 billion parameters for GPT-3) with large datasets to obtain better performance. Bigger is better has been the norm. Optical computi…

From Neurons to Computation: Biological Reservoir Computing for Pattern Recognition

2025-05-06 · Ludovico Iannello, Luca Ciampi, Gabriele Lagani, Fabrizio Tonelli 외

In this paper, we introduce a novel paradigm for reservoir computing (RC) that leverages a pool of cultured biological neurons as the reservoir substrate, creating a biological reservoir computing (BRC). This system oper…

HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages

2024-12-19 · Aman Chaturvedi, Daniel Nichols, Siddharth Singh, Abhinav Bhatele

Large Language Model (LLM) based coding tools have been tremendously successful as software development assistants, yet they are often designed for general purpose programming tasks and perform poorly for more specialize…

Code GenerationLanguage ModelingLanguage ModellingLarge Language Model