Enabling radiation tolerant heterogeneous GPU-based onboard data processing in space
- PDF / 1,223,780 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 106 Downloads / 165 Views
ORIGINAL PAPER
Enabling radiation tolerant heterogeneous GPU‑based onboard data processing in space Fredrik C. Bruhn1,2,4 · Nandinbaatar Tsog2 · Fabian Kunkel1 · Oskar Flordal1 · Ian Troxel3 Received: 19 November 2019 / Revised: 31 May 2020 / Accepted: 3 June 2020 © The Author(s) 2020
Abstract The last decade has seen a dramatic increase in small satellite missions for commercial, public, and government intelligence applications. Given the rapid commercialization of constellation-driven services in Earth Observation, situational domain awareness, communications including machine-to-machine interface, exploration etc., small satellites represent an enabling technology for a large growth market generating truly Big Data. Examples of modern sensors that can generate very large amounts of data are optical sensing, hyperspectral, Synthetic Aperture Radar (SAR), and Infrared imaging. Traditional handling and downloading of Big Data from space requires a large onboard mass storage and high bandwidth downlink with a trend towards optical links. Many missions and applications can benefit significantly from onboard cloud computing similarly to Earth-based cloud services. Hence, enabling space systems to provide near real-time data and enable low latency distribution of critical and time sensitive information to users. In addition, the downlink capability can be more effectively utilized by applying more onboard processing to reduce the data and create high value information products. This paper discusses current implementations and roadmap for leveraging high performance computing tools and methods on small satellites with radiation tolerant hardware. This includes runtime analysis with benchmarks of convolutional neural networks and matrix multiplications using industry standard tools (e.g., TensorFlow and PlaidML). In addition, a ½ CubeSat volume unit (0.5U) (10 × 10 × 5 cm3) cloud computing solution, called SpaceCloud™ iX5100 based on AMD 28 nm APU technology is presented as an example of heterogeneous computer solution. An evaluation of the AMD 14 nm Ryzen APU is presented as a candidate for future advanced onboard processing for space vehicles. Keywords OBDP · Machine learning · GPU · Small satellites · Heterogeneous computing
1 Introduction * Fredrik C. Bruhn [email protected]; [email protected] Nandinbaatar Tsog [email protected] Fabian Kunkel [email protected] Oskar Flordal [email protected] Ian Troxel [email protected] 1
Unibap AB (Publ.), Kungsängsgatan 12, 753 22 Uppsala, Sweden
2
Mälardalen University, Box 883, 721 23 Västerås, Sweden
3
Troxel Aerospace Industries Inc., 2023 NE 55th Blvd., Gainesville, FL, USA
4
Bruhnspace AB, Rapphönsvägen 7B, 756 53 Uppsala, Sweden
There are numerous studies and argumentation for increased onboard autonomy and data information processing to provide more efficient use of the relatively limited communication link bandwidth on small satellites [1–3]. Expanding on the needs of intelligent processing, it is especially relevan
Data Loading...
