Collaborative Research: Elements: Bifrost - A CPU/GPU Pipeline Framework for High Throughput Data Acquisition and Analysis

现代电脑，包括手机和平板电脑，都有复杂的图形处理单元（gpu），可以在游戏中呈现美丽的图形显示。我们正在开发软件，利用这些相同的gpu来捕获和处理天文望远镜的数据。这使我们能够从多年来开发这些强大的计算工具的努力中受益。这款名为Bifrost的软件目前正在长波阵列（LWA）上使用，这是一款用于探索广泛科学组合的射电望远镜，从研究宇宙黎明（即第一批恒星和星系照亮宇宙的时刻）到了解地球电离层的特性。我们正在积极开发Bifrost，使它更强大，更容易用于其他望远镜。最终，我们的目标是让Bifrost成为一个更通用的框架，可以应用于天文学以外的研究项目。大约5年前，我们为第二个LWA站（LWA- sv）采用了一种商用设备设计，它利用带有gpu的计算服务器来处理站级的数据捕获、波束形成和相关。以前，这些功能是由专用硬件承担的，称为数字处理器。然而，这种定制硬件设计的建造和维护费用昂贵，缺乏灵活性，并且不容易复制到未来的LWA站。相比之下，商品方法更容易维持，更灵活和可扩展，可以很容易地适应新的低空电波站。我们正在集中精力改进Bifrost的基础。这包括提高Bifrost能够处理的数据速率，改进应用程序编程接口，并提供工具，使用户更容易开发和测试新的管道。通过这个奖项，我们正在与合作者合作，将Bifrost集成到目前正在开发的望远镜和仪器中。Bifrost的可用性不仅将增加射电天文学的科学回报，而且还将增加其他需要高通量数据处理的领域的科学回报。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Modern computers, including cell phones and tablets, have sophisticated Graphics Processing Units (GPUs) that render the beautiful graphic displays in games. We are developing software that takes advantage of these same GPUs for capturing and processing data from astronomical telescopes. This allows us to benefit from all the years of effort spent developing these powerful computational tools. This software, known as Bifrost, is currently in use at the Long Wavelength Array (LWA), a radio telescope for exploration of a broad scientific portfolio ranging from the study of Cosmic Dawn when the first stars and galaxies lit up the Universe, to understanding the properties of the Earth's ionosphere. We are actively developing Bifrost to make it both more powerful and easier to use for other telescopes. Eventually we aim for Bifrost to be available as a more general purpose framework that can be applied to research projects beyond astronomy. About 5 years ago we adopted a commodity equipment design for the second LWA station (LWA-SV) which makes use of computing servers with GPUs to handle the data capture, beamforming, and correlation at the station level. Previously these functions were taken on by dedicated hardware referred to as the Digital Processor. However, this custom-hardware design was expensive to build and maintain, lacks flexibility, and cannot be easily replicated for future LWA stations. In contrast the commodity approach is easier to maintain, much more flexible and expandable, and can be readily adapted to new LWA stations. We are engaged in a concentrated effort to improve the underpinnings of Bifrost. This involves increasing the data rates that Bifrost is capable of handling, improving the application programming interface, and providing tools to make it easier for users to develop and test new pipelines. Through this award we are working with collaborators to incorporate Bifrost in telescopes and instruments currently under development. The availability of Bifrost will increase the scientific return of not only radio astronomy but also other areas where high throughput data processing is needed.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.