“Hey CAI” - Conversational AI Enabled User Interface for HPC Tools

“Hey CAI” - Conversational AI Enabled User Interface for HPC Tools
复制标题

–Hey CAI – 适用于 HPC 工具的对话式 AI 用户界面

DOI:
10.1007/978-3-031-07312-0_5
复制
发表时间:
2022
期刊:
Proceedings International Conference on High Performance Computing
影响因子:
--
通讯作者:
Panda, DK.
Panda, DK.
中科院分区:
--
文献类型:
--
作者:
Kousha, P.;Jain, A.;Kolli, A.;Prasanna, S.;Miriyala, S.;Subramoni, H.;Shafi, A.;Panda, DK.

文献摘要

相似文献

HPC系统用户依赖于分析和分析工具来深入了解其应用程序的性能并对其进行调整。现代HPC系统的复杂性使得相关HPC工具的进步成为必要,这使得它们具有各种高级功能和复杂的用户界面。虽然这些界面是广泛和详细的,他们需要一个陡峭的学习曲线,即使是专家用户,使他们更难使用新手用户。虽然用户能够直观地表达他们在单词或文本中寻找的内容(例如,向我展示传输最大数据的过程),他们发现很难快速适应、导航和使用高级HPC工具的界面来获得所需的见解。在本文中,我们探讨了与设计一个对话(语音/文本)接口的HPC工具的挑战。我们使用最先进的语音和文本AI模型,并通过在我们创建的新HPC数据集上重新训练它们,使其适用于HPC竞技场。我们证明了我们提出的模型,用HPC特定的数据集重新训练,可以提供比现有的最先进的预训练语言模型更高的准确性。我们还创建了一个接口,将语音/文本数据转换为HPC工具的命令,并展示了用户如何利用拟议的接口更快地获得洞察力,从而提高生产力。据我们所知,这是第一次努力,旨在设计一个对话界面的HPC工具使用最先进的人工智能技术,以提高新手和高级用户的生产力。
HPC system users depend on profiling and analysis tools to obtain insights into the performance of their applications and tweak them. The complexity of modern HPC systems have necessitated advances in the associated HPC tools making them equally complex with various advanced features and complex user interfaces. While these interfaces are extensive and detailed, they require a steep learning curve even for expert users making them harder to use for novice users. While users are intuitively able to express what they are looking for in words or text (e.g., show me the process transmitting maximum data), they find it hard to quickly adapt to, navigate, and use the interface of advanced HPC tools to obtain desired insights. In this paper, we explore the challenges associated with designing a conversational (speech/text) interface for HPC tools. We use state-of-the-art AI models for speech and text and adapt it for use in the HPC arena by retraining them on a new HPC dataset we create. We demonstrate that our proposed model, retrained with an HPC specific dataset, can deliver higher accuracy than the existing state-of-the-art pre-trained language models. We also create an interface to convert speech/text data to commands for HPC tools and show how users can utilize the proposed interface to gain insights quicker leading to better productivity.To the best of our knowledge, this is the first effort aimed at designing a conversational interface for HPC tools using state-of-the-art AI techniques to enhance the productivity of novice and advanced users alike.