In spaceborne synthetic aperture radar, the sliding spotlight mode can acquire high resolution and large azimuth scene size simultaneously. However, when the resolution is very high and the azimuth scene size is large, the traditional hyperbolic range model (HRM) is inaccurate and the variation of the equivalent velocity in azimuth dimension cannot be ignored. Thus, the traditional imaging algorithms based on HRM are no longer available. For this problem, this paper proposes an equivalent acceleration range model, which can precisely take into account the spaceborne curved orbit. Then, velocity scaling algorithm based on this new range model is proposed to meet the needs of very high resolution and large azimuth scene size. The results of the simulation validate the effectiveness of the new range model and the imaging algorithm.

Processing of Very High Resolution Spaceborne Sliding Spotlight SAR Data Using Velocity Scaling

We propose an algorithm for synthetic-aperture-radar image formation with a curved flight path based on the polar-format algorithm that corrects for defocus and distortion observed in images via the polar-format algorithm. Our correction permits application of a single quadratic phase-error correction to an entire range gate before the azimuth fast Fourier transform in the polar format algorithm. Experimental results demonstrate corrections to distortion and defocus with simulated and measured imagery, greatly increasing scene size with few additional computations.

Fast corrections for polar format algorithm with a curved flight path

Radiation-tolerant computing is of great importance to the aerospace community because future missions demand more computational power. Of special interest to the aerospace community are flight computers implemented on static random-access-memory-based field-programmable gate arrays. Such computer systems allow the in-flight reconfiguration of hardware that enables the practical deployment of truly reconfigurable computers. However, commercial static random-access-memory-based field-programmable gate arrays are uniquely susceptible to ionizing radiation. This paper introduces a computer architecture for static random-access-memory-based field-programmable gate arrays that resists failures caused by ionizing radiation. The approach extends the widely accepted fault mitigation practice of triple modular redundancy and configuration memory scrubbing by adding spare circuitry and environmental awareness through an ionizing radiation sensor. This paper describes the design of the system in addition to a theore...

Increasing Radiation Tolerance of Field-Programmable- Gate-Array-Based Computers Through Redundancy and Environmental Awareness

Survey and future directions of fault-tolerant distributed computing on board spacecraft

In this paper, we propose an active real-time capable 3D graph based simultaneous localization and mapping (Graph SLAM) approach, which actively estimates the state of an autonomous spacecraft relative to a simultaneously established map estimate. The graph is constructed in a tightly-coupled fashion, where an Extended Kalman Filter estimates the relative offset between two of its vertices. An additional relative measurement is derived by matching point clouds obtained by a light detection and ranging (LiDAR) system. In order to yield a significant speed-up, scan matching is implemented on the GPU. To reduce the uncertainty of either the state or the map estimate, we present an approach to actively control the system resting on an extended representation of uncertainty in the map. Furthermore, it adapts its behavior depending on the current uncertainty distribution in order to find a dynamic trade-off between exploitation (improve localization performance) and exploration (improve knowledge about the environment). Finally, we present a post-processing approach to discover landing sites in the map estimate without prior knowledge. The evaluation is conducted in a numerical simulation, where the spacecraft explores the real 3D model of Itokawa in its actual dynamic environment. Within that simulation, we use a shader-based GPU implementation for simulating LiDAR measurements. We evaluate the performance of the active SLAM approach and demonstrate that the use of the adaptive approach improves navigation and exploration performance at the same time.

Active Asteroid-SLAM

Taking into consideration space applications' demands for higher bandwidth and processing power, we propose to efficiently apply upcoming many-core processors and other Commercial-Off-The-Shelf (COTS) products to improve the on-board processing power.1 2 A combination of traditional hardware and software-implemented fault-tolerant techniques, addresses the reliability of the system. We first describe common requirements and design challenges presented by future space applications like the High Resolution Wide Swath Synthetic Aperture Radar (HRWS SAR). After proposing the High Performance Computing (HPC) architecture, we compare between most suitable hardware technologies and give some rough performance estimations based on their features. For benchmarking purposes we have manually converted the Scalable Synthetic Compact Application (SSCA#3) from Matlab to C and parallelized it using OpenMP. It turns out that this application scales very well on many-core processors especially on a distributed Shared Memory Architecture (SMA).

Using many-core processors to improve the performance of space computing platforms

Future space applications will demand for architectures with High Performance Computing (HPC) capabilities. In this scope, on-board computer designers will have to select between different technologies and designs, the most reliable and most efficient ones in terms of performance and power consumption. In this paper, we investigate the behavior of an Image Reconstruction Algorithm on high performance multi-core CPUs and many-core GPUs. It turns out that SAR applications can profit much more from the architecture and the capabilities of many-core GPUs than from modern multi-core CPUs. We give some remarks on how these types of HPC components can be integrated on future space-based on-board computing platforms. Throughout the paper, we illustrate by comparison the advantages and disadvantages of using GPUs over CPUs for SAR Applications. Other than this, we explain the programming and parallelization paradigms applied to the SAR application to increase its performance and efficiency on CPUs and GPUs respectively.

Performance evaluation of SAR image reconstruction on CPUs and GPUs

Recent developments in space applications have indicated that future spacecraft computing platforms will demand for high performance computing (HPC) capabilities. In order to face this challenge, HPC technologies have to be introduced in the design process of such platforms. This paper summarizes some efforts taken to achieve this. A theoretical design for future spacecraft computing platforms is proposed. This design combines traditional reliability techniques and novel HPC solutions for efficient high performance. System components are not specified in terms of type and quantity, but only a logical representation of the system is given. Benchmarking results are obtained on different parallel computing systems to help platform designers in further system specifications. A real space application that reconstructs a synthetic aperture radar (SAR) image is used to benchmark shared memory, distributed memory, and heterogeneous CPU/GPU systems. It turns out that distributed memory systems are a necessity for performance improvements, whereas heterogeneous CPU/GPU systems offer much more efficiency in terms of performance per power consumption, size, and heat dissipation.

Designing Spacecraft High Performance Computing Architectures

Future space application will require High Performance Computing (HPC) capabilities to be available on board of future spacecrafts. To cope with this requirement, multi and many-core processor technologies have to be integrated in the computing platforms of the spacecraft. One of the most important requirements, coming from the nature of space applications, is the efficiency in terms of performance per Watt. In order to improve the efficiency of such systems, algorithms and applications have to be optimized and scaled to the number of cores available in the computing platform. In this paper we describe the parallelization techniques applied to a Synthetic Aperture Radar (SAR) application based on the 2-Dimentional Fourier Matched Filtering and Interpolation (2DFMFI) Algorithm. Other than sequential optimizations, we applied parallelization techniques for shared memory, distributed shared memory and distributed memory environments, using parallel programming models like OpenMP and MPI. It turns out that parallelizing this type of algorithms is not an easy and straightforward task to do, but with a little bit of effort, one can improve performance and scalability, increasing the level of efficiency.

Parallelization techniques for the 2D Fourier Matched Filtering and Interpolation SAR algorithm

Spacecraft on-board platforms will soon contain high performance off-the-shelf computing components, as the only way to deal with applications which require High Performance Computing (HPC) capabilities. Heterogeneous architectures, give the possibility to profit from specific features of such components, by combining them on the same computing platform. Such architectures integrate different multicore CPUs with many-core accelerators (GPGPUs) so that parts of the same application can efficiently execute on the CPU while other parts can profit more from the GPU features. The problem stands in the way how to program these heterogeneous architectures. In this paper we introduce the OmpSs Programming Model as a framework to program heterogeneous architectures. For benchmarking purposes, we use a Synthetic Aperture Radar (SAR) application, which we parallelized with OmpSs for Symmetric Multi-Processor (SMP) architectures and for hybrid SMP/GPU environments. We also compare the results obtained with OmpSs with the ones obtained with OpenMP in SMP environments and it turns out that OmpSs outperforms OpenMP. When applying OmpSs to the SAR code for hybrid architectures, OmpSs does not offer better performance than CUDA, but it offers support for heterogeneous architectures and it also increases programmer's productivity.

Fisnik Kraja

Papers

Using many-core processors to improve the performance of space computing platforms

Performance evaluation of SAR image reconstruction on CPUs and GPUs

Designing Spacecraft High Performance Computing Architectures

Parallelization techniques for the 2D Fourier Matched Filtering and Interpolation SAR algorithm

2D-FMFI SAR application on HPC architectures with OmpSs parallel programming model