Large Language Models (LLMs), including the LLaMA model, have exhibited their efficacy across various general-domain natural language processing (NLP) tasks. However, their performance in high-performance computing (HPC) domain tasks has been less than optimal due to the specialized expertise required to interpret the model’s responses. In response to this challenge, we propose HPC-GPT, a novel LLaMA-based model that has been supervised fine-tuning using generated QA (Question-Answer) instances for the HPC domain. To evaluate its effectiveness, we concentrate on two HPC tasks: managing AI models and datasets for HPC, and data race detection. By employing HPC-GPT, we demonstrate comparable performance with existing methods on both tasks, exemplifying its excellence in HPC-related scenarios. Our experiments on open-source benchmarks yield extensive results, underscoring HPC-GPT’s potential to bridge the performance gap between LLMs and HPC-specific tasks. With HPC-GPT, we aim to pave the way for LLMs to excel in HPC domains, simplifying the utilization of language models in complex computing applications.

Current wind farm layout optimization research assumes a continuous piece of land is readily available and focuses on advancing optimization methods. In reality, projects rely on landowners’ permission for success. When a viable site is identified, local residents are approached for permission to build turbines on their land, typically in exchange for monetary compensation. Landowners play a crucial role in the development process, and some land parcels are more important to the success of project than others. This paper relaxes the assumption that a continuous piece of land is available, developing a novel approach that includes a model of landowner participation rates. A genetic algorithm (GA) is adopted to solve the nonlinear constrained optimization problem, minimizing cost and maximizing power output. The optimization results show that, given a projected participation rate, we can identify the most crucial plots prior to the negotiation process with landowners. This will ultimately increase the efficiency of wind farm development.

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 x 5.1 in their CodeBLEU scores, while models with some coding familiarity saw an impressive x 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 https://github.com/bin123apple/Fortran-CPP-HPC-code-translation-dataset.