Experiences with implementing common mathematical operations using field programmable gate arrays

Many computationally intensive scientific applications involve repetitive floating point operations other than addition and multiplication which may present a significant performance bottleneck due to the relatively large latency or low throughput involved in executing such arithmetic primitives on commod- ity processors. A promising alternative is to execute such primitives on Field Programmable Gate Array (FPGA) hardware acting as an application-specific custom co-processor in a high performance reconfig- urable computing platform. The use of FPGAs can provide advantages such as fine-grain parallelism but issues relating to code development in a hardware description language and efficient data transfer to and from the FPGA chip can present significant application development challenges. In this paper, we discuss our practical experiences in developing a selection of floating point hardware designs to be implemented using FPGAs. Our designs include some basic mathemati cal library functions which can be implemented for user defined precisions suitable for novel applications requiring non-standard floating point represen- tation. We discuss the details of our designs along with results from performance and accuracy analysis tests.

Solving tri-diagonal linear systems using field programmable gate arrays

In this paper, we present the outcomes of a project on the exploration of the use of Field Programmable Gate Arrays(FPGAs) as co-processors for scientific computation. We designed a custom circuit for the pipelined solving of multiple tri-diagonal linear systems. The design is well suited for applications that require many independent tri diagonal system solves, such as finite difference methods for solving PDEs or applications utilising cubic spline interpolation. The selected solver algorithm was the Tri Diagonal Matrix Algorithm (TDMA or Thomas Algorithm). Our solver supports user specified precision thought the use of a custom floating point VHDL library supporting addition, subtraction, multiplication and division. The variable precision TDMA solver was tested for correctness in simulation mode. The TDMA pipeline was tested successfully in hardware using a simplified solver model. The details of implementation, the limitations, and future work are also discussed.

Solving tri-diagonal linear systems using field programmable gate arrays

In this paper, we present the outcomes of a project on the exploration of the use of Field Programmable Gate Arrays (FPGAs) as co-processors for scientific computation. We designed a custom circuit for the pipelined solving of multiple tri-diagonal linear systems. The design is well suited for applications that require many independent tri-diagonal system solves, such as finite difference methods for solving PDEs or applications utilising cubic spline interpolation. The selected solver algorithm was the Tri-Diagonal Matrix Algorithm (TDMA or Thomas Algorithm). Our solver supports user specified precision thought the use of a custom floating point VHDL library supporting addition, subtraction, multiplication and division. The variable precision TDMA solver was tested for correctness in simulation mode. The TDMA pipeline was tested successfully in hardware using a simplified solver model. The details of implementation, the limitations, and future work are also discussed.

FPGA implementation of dual-microphone delay-and-sum beamforming for in-car speech enhancement and recognition

In an automotive environment, the performance of a speech recognition system is affected by environmental noise if the speech signal is acquired directly from a microphone. Speech enhancement techniques are therefore necessary to improve the speech recognition performance. In this paper, a field-programmable gate array (FPGA) implementation of dual-microphone delay-and-sum beamforming (DASB) for speech enhancement is presented. As the first step towards a cost-effective solution, the implementation described in this paper uses a relatively high-end FPGA device to facilitate the verification of various design strategies and parameters. Experimental results show that the proposed design can produce output waveforms close to those generated by a theoretical (floating-point) model with modest usage of FPGA resources. Speech recognition experiments are also conducted on enhanced in-car speech waveforms produced by the FPGA in order to compare recognition performance with the floating-point representation running on a PC.

An FPGA-based approach to multi-objective evolutionary algorithm for multi-disciplinary design optimisation

This paper investigates the field programmable gate array (FPGA) approach for multi-objective and multi-disciplinary design optimisation (MDO) problems. One class of optimisation method that has been well-studied and established for large and complex problems, such as those inherited in MDO, is multi-objective evolutionary algorithms (MOEAs). The MOEA, nondominated sorting genetic algorithm II (NSGA-II), is hardware implemented on an FPGA chip. The NSGA-II on FPGA application to multi-objective test problem suites has verified the designed implementation effectiveness. Results show that NSGA-II on FPGA is three orders of magnitude better than the PC based counterpart.

FPGA implementation of an evolutionary algorithm for autonomous unmanned aerial vehicle on-board path planning

In this paper, a hardware-based path planning architecture for unmanned aerial vehicle (UAV) adaptation is proposed. The architecture aims to provide UAVs with higher autonomy using an application specific evolutionary algorithm (EA) implemented entirely on a field programmable gate array (FPGA) chip. The physical attributes of an FPGA chip, being compact in size and low in power consumption, compliments it to be an ideal platform for UAV applications. The design, which is implemented entirely in hardware, consists of EA modules, population storage resources, and three-dimensional terrain information necessary to the path planning process, subject to constraints accounted for separately via UAV, environment and mission profiles. The architecture has been successfully synthesised for a target Xilinx Virtex-4 FPGA platform with 32% logic slices utilisation. Results obtained from case studies for a small UAV helicopter with environment derived from LIDAR (Light Detection and Ranging) data verify the effectiveness of the proposed FPGA-based path planner, and demonstrate convergence at rates above the typical 10 Hz update frequency of an autopilot system.

Hardware design and implementation of a MAVLink interface for an FPGA-based autonomous UAV flight control system

This paper details the initial design and planning of a Field Programmable Gate Array (FPGA) implemented control system that will enable a path planner to interact with a MAVLink based flight computer. The design is aimed at small Unmanned Aircraft Vehicles (UAV) under autonomous operation which are typically subject to constraints arising from limited on-board processing capabilities, power and size. An FPGA implementation for the de- sign is chosen for its potential to address such limitations through low power and high speed in-hardware computation. The MAVLink protocol offers a low bandwidth interface for the FPGA implemented path planner to communicate with an on-board flight computer. A control system plan is presented that is capable of accepting a string of GPS waypoints generated on-board from a previously developed in- hardware Genetic Algorithm (GA) path planner and feeding them to the open source PX4 autopilot, while simultaneously respond- ing with flight status information.

Characteristic analysis for multisampled digital implementation of fixed-switching-frequency closed-loop modulation of voltage-source inverter

In this paper, a fixed-switching-frequency closed-loop modulation of a voltage-source inverter (VSI), upon the digital implementation of the modulation process, is analyzed and characterized. The sampling frequency of the digital processor is considered as an integer multiple of the modulation switching frequency. An expression for the determination of the modulation design parameter is developed for smooth modulation at a fixed switching frequency. The variation of the sampling frequency, switching frequency, and modulation index has been analyzed for the determination of the switching condition under closed loop. It is shown that the switching condition determined based on the continuous-time analysis of the closed-loop modulation will ensure smooth modulation upon the digital implementation of the modulation process. However, the stability properties need to be tested prior to digital implementation as they get deteriorated at smaller sampling frequencies. The closed-loop modulation index needs to be considered maximum while determining the design parameters for smooth modulation. In particular, a detailed analysis has been carried out by varying the control gain in the sliding-mode control of a two-level VSI. The proposed analysis of the closed-loop modulation of the VSI has been verified for the operation of a distribution static compensator. The theoretical results are validated experimentally on both single- and three-phase systems.

Vision-based topological mapping and localisation

Competent navigation in an environment is a major requirement for an autonomous mobile robot to accomplish its mission. Nowadays, many successful systems for navigating a mobile robot use an internal map which represents the environment in a detailed geometric manner. However, building, maintaining and using such environment maps for navigation is difficult because of perceptual aliasing and measurement noise. Moreover, geometric maps require the processing of huge amounts of data which is computationally expensive. This thesis addresses the problem of vision-based topological mapping and localisation for mobile robot navigation. Topological maps are concise and graphical representations of environments that are scalable and amenable to symbolic manipulation. Thus, they are well-suited for basic robot navigation applications, and also provide a representational basis for the procedural and semantic information needed for higher-level robotic tasks. In order to make vision-based topological navigation suitable for inexpensive mobile robots for the mass market we propose to characterise key places of the environment based on their visual appearance through colour histograms. The approach for representing places using visual appearance is based on the fact that colour histograms change slowly as the field of vision sweeps the scene when a robot moves through an environment. Hence, a place represents a region of the environment rather than a single position. We demonstrate in experiments using an indoor data set, that a topological map in which places are characterised using visual appearance augmented with metric clues provides sufficient information to perform continuous metric localisation which is robust to the kidnapped robot problem. Many topological mapping methods build a topological map by clustering visual observations to places. However, due to perceptual aliasing observations from different places may be mapped to the same place representative in the topological map. A main contribution of this thesis is a novel approach for dealing with the perceptual aliasing problem in topological mapping. We propose to incorporate neighbourhood relations for disambiguating places which otherwise are indistinguishable. We present a constraint based stochastic local search method which integrates the approach for place disambiguation in order to induce a topological map. Experiments show that the proposed method is capable of mapping environments with a high degree of perceptual aliasing, and that a small map is found quickly. Moreover, the method of using neighbourhood information for place disambiguation is integrated into a framework for topological off-line simultaneous localisation and mapping which does not require an initial categorisation of visual observations. Experiments on an indoor data set demonstrate the suitability of our method to reliably localise the robot while building a topological map.

A synthesizable hardware evolutionary algorithm design for unmanned aerial system real-time path planning

The main objective of this paper is to detail the development of a feasible hardware design based on Evolutionary Algorithms (EAs) to determine flight path planning for Unmanned Aerial Vehicles (UAVs) navigating terrain with obstacle boundaries. The design architecture includes the hardware implementation of Light Detection And Ranging (LiDAR) terrain and EA population memories within the hardware, as well as the EA search and evaluation algorithms used in the optimizing stage of path planning. A synthesisable Very-high-speed integrated circuit Hardware Description Language (VHDL) implementation of the design was developed, for realisation on a Field Programmable Gate Array (FPGA) platform. Simulation results show significant speedup compared with an equivalent software implementation written in C++, suggesting that the present approach is well suited for UAV real-time path planning applications.

A hardware-based multi-disciplinary design optimization method for aeronautical applications

There are many applications in aeronautics where there exist strong couplings between disciplines. One practical example is within the context of Unmanned Aerial Vehicle(UAV) automation where there exists strong coupling between operation constraints, aerodynamics, vehicle dynamics, mission and path planning. UAV path planning can be done either online or offline. The current state of path planning optimisation online UAVs with high performance computation is not at the same level as its ground-based offline optimizer's counterpart, this is mainly due to the volume, power and weight limitations on the UAV; some small UAVs do not have the computational power needed for some optimisation and path planning task. In this paper, we describe an optimisation method which can be applied to Multi-disciplinary Design Optimisation problems and UAV path planning problems. Hardware-based design optimisation techniques are used. The power and physical limitations of UAV, which may not be a problem in PC-based solutions, can be approached by utilizing a Field Programmable Gate Array (FPGA) as an algorithm accelerator. The inevitable latency produced by the iterative process of an Evolutionary Algorithm (EA) is concealed by exploiting the parallelism component within the dataflow paradigm of the EA on an FPGA architecture. Results compare software PC-based solutions and the hardware-based solutions for benchmark mathematical problems as well as a simple real world engineering problem. Results also indicate the practicality of the method which can be used for more complex single and multi objective coupled problems in aeronautical applications.

Calculation of engine parameters using reconfigurable hardware

The feasibility of real-time calculation of parameters for an internal combustion engine via reconfigurable hardware implementation is investigated as an alternative to software computation. A detailed in-hardware field programmable gate array (FPGA)-based design is developed and evaluated using input crank angle and in-cylinder pressure data from fully instrumented diesel engines in the QUT Biofuel Engine Research Facility (BERF). Results indicate the feasibility of employing a hardware-based implementation for real-time processing for speeds comparable to the data sampling rate currently used in the facility, with acceptably low level of discrepancies between hardware and software-based calculation of key engine parameters.

Implementation of parallel tridiagonal solvers for a heterogeneous computing environment

Tridiagonal diagonally dominant linear systems arise in many scientific and engineering applications. The standard Thomas algorithm for solving such systems is inherently serial forming a bottleneck in computation. Algorithms such as cyclic reduction and SPIKE reduce a single large tridiagonal system into multiple small independent systems which can be solved in parallel. We have developed portable cyclic reduction and SPIKE algorithm OpenCL implementations with the intent to target a range of co-processors in a heterogeneous computing environment including Field Programmable Gate Arrays (FPGAs), Graphics Processing Units (GPUs) and other multi-core processors. In this paper, we evaluate these designs in the context of solver performance, resource efficiency and numerical accuracy.

Pulse-coupled neural network performance for real-time identification of vegetation during forced landing

Safety concerns in the operation of autonomous aerial systems require safe-landing protocols be followed during situations where the a mission should be aborted due to mechanical or other failure. On-board cameras provide information that can be used in the determination of potential landing sites, which are continually updated and ranked to prevent injury and minimize damage. Pulse Coupled Neural Networks have been used for the detection of features in images that assist in the classification of vegetation and can be used to minimize damage to the aerial vehicle. However, a significant drawback in the use of PCNNs is that they are computationally expensive and have been more suited to off-line applications on conventional computing architectures. As heterogeneous computing architectures are becoming more common, an OpenCL implementation of a PCNN feature generator is presented and its performance is compared across OpenCL kernels designed for CPU, GPU and FPGA platforms. This comparison examines the compute times required for network convergence under a variety of images obtained during unmanned aerial vehicle trials to determine the plausibility for real-time feature detection.

Pulse-coupled neural network performance for real-time identification of vegetation during forced landing

Safety concerns in the operation of autonomous aerial systems require safe-landing protocols be followed during situations where the mission should be aborted due to mechanical or other failure. This article presents a pulse-coupled neural network (PCNN) to assist in the vegetation classification in a vision-based landing site detection system for an unmanned aircraft. We propose a heterogeneous computing architecture and an OpenCL implementation of a PCNN feature generator. Its performance is compared across OpenCL kernels designed for CPU, GPU, and FPGA platforms. This comparison examines the compute times required for network convergence under a variety of images to determine the plausibility for real-time feature detection.