| 1. |
|
|
| 2. |
- Navas, Byron, 1969-
(författare)
-
Cognitive and Self-Adaptive SoCs with Self-Healing Run-Time-Reconfigurable RecoBlocks
- 2015
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- In contrast to classical Field-Programmable Gate Arrays (FPGAs), partial and run-time reconfigurable (RTR) FPGAs can selectively reconfigure partitions of its hardware almost immediately while it is still powered and operative. In this way, RTR FPGAs combine the flexibility of software with the high efficiency of hardware. However, their potential cannot be fully exploited due to the increased complexity of the design process, and the intricacy to generate partial reconfigurations. FPGAs are often seen as a single auxiliary area to accelerate algorithms for specific problems. However, when several RTR partitions are implemented and combined with a processor system, new opportunities and challenges appear due to the creation of a heterogeneous RTR embedded system-on-chip (SoC).The aim of this thesis is to investigate how the flexibility, reusability, and productivity in the design process of partial and RTR embedded SoCs can be improved to enable research and development of novel applications in areas such as hardware acceleration, dynamic fault-tolerance, self-healing, self-awareness, and self-adaptation. To address this question, this thesis proposes a solution based on modular reconfigurable IP-cores and design-and-reuse principles to reduce the design complexity and maximize the productivity of such FPGA-based SoCs. The research presented in this thesis found inspiration in several related topics and sciences such as reconfigurable computing, dependability and fault-tolerance, complex adaptive systems, bio-inspired hardware, organic and autonomic computing, psychology, and machine learning.The outcome of this thesis demonstrates that the proposed solution addressed the research question and enabled investigation in initially unexpected fields. The particular contributions of this thesis are: (1) the RecoBlock SoC concept and platform with its flexible and reusable array of RTR IP-cores, (2) a simplified method to transform complex algorithms modeled in Matlab into relocatable partial reconfigurations adapted to an improved RecoBlock IP-core architecture, (3) the self-healing RTR fault-tolerant (FT) schemes, especially the Upset-Fault-Observer (UFO) that reuse available RTR IP-cores to self-assemble hardware redundancy during runtime, (4) the concept of Cognitive Reconfigurable Hardware (CRH) that defines a development path to achieve self-adaptation and cognitive development, (5) an adaptive self-aware and fault-tolerant RTR SoC that learns to adapt the RTR FT schemes to performance goals under uncertainty using rule-based decision making, (6) a method based on online and model-free reinforcement learning that uses a Q-algorithm to self-optimize the activation of dynamic FT schemes in performance-aware RecoBlock SoCs.The vision of this thesis proposes a new class of self-adaptive and cognitive hardware systems consisting of arrays of modular RTR IP-cores. Such a system becomes self-aware of its internal performance and learns to self-optimize the decisions that trigger the adequate self-organization of these RTR cores, i.e., to create dynamic hardware redundancy and self-healing, particularly while working in uncertain environments.
|
|
| 3. |
- Rosvall, Kathrin, et al.
(författare)
-
Exploring Power and Throughput for Dataflow Applications on Predictable NoC Multiprocessors
- 2018
-
Konferensbidrag (refereegranskat)abstract
- System level optimization for multiple mixed-criticality applications on shared networked multiprocessor platforms is extremely challenging. Substantial complexity arises from the interdependence between the multiple subproblems of mapping, scheduling and platform configuration under the consideration of several, potentially orthogonal, performance metrics and constraints. Instead of using heuristic algorithms and problem decomposition, novel unified design space exploration (DSE) approaches based on Constraint Programming (CP) have in the recent years shown promising results. The work in this paper takes advantage of the modularity of CP models, in order to support heterogeneous multiprocessor Network-on-Chip (NoC) with Temporally Disjoint Networks (TDNs) aware message injection. The DSE supports a range of design criteria, in particular the optimization and satisfaction of power and throughput. In addition, the DSE now provides a valid configuration for the TDNs that guarantees the performance required to fulfil the design goals. The experiments show the capability of the approach to find low-power and high-throughput designs, and validate a resulting design on a physical TDN-based NoC implementation.
|
|
| 4. |
|
|
| 5. |
- Navas, Byron, et al.
(författare)
-
On providing scalable self-healing adaptive fault-tolerance to RTR SoCs
- 2014
-
Ingår i: Proceedings of ReConFigurable Computing and FPGAs (ReConFig), 2014 International Conference on. - 9781479959440 ; , s. 1-6
-
Konferensbidrag (refereegranskat)abstract
- The dependability of heterogeneous many-core FPGA based systems are threatened by higher failure rates caused by disruptive scales of integration, increased design complexity, and radiation sensitivity. Triple-modular redundancy (TMR) and run-time reconfiguration (RTR) are traditional fault-tolerant (FT) techniques used to increase dependability. However, hardware redundancy is expensive and most approaches have poor scalability, flexibility, and programmability. Therefore, innovative solutions are needed to reduce the redundancy cost but still preserve acceptable levels of dependability. In this context, this paper presents the implementation of a self-healing adaptive fault-tolerant SoC that reuses RTR IP-cores in order to self-assemble different TMR schemes during run-time. The presented system demonstrates the feasibility of the Upset-Fault-Observer concept, which provides a run-time self-test and recovery strategy that delivers fault-tolerance over functions accelerated in RTR cores, at the same time reducing the redundancy scalability cost by running periodic reconfigurable TMR scan-cycles. In addition, this paper experimentally evaluates the trade-off of the implemented reconfigurable TMR schemes by characterizing important fault tolerant metrics i.e., recovery time (self-repair and self-replicate), detection latency, self-assembly latency, throughput reduction, and increase of physical resources.
|
|
| 6. |
- Navas, Byron, et al.
(författare)
-
Reinforcement Learning Based Self-Optimization of Dynamic Fault-Tolerant Schemes in Performance-Aware RecoBlock SoCs
- 2015
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Partial and run-time reconfiguration (RTR) technology has increased the range of opportunities and applications in the design of systems-on-chip (SoCs) based on Field-Programmable Gate Arrays (FPGAs). Nevertheless, RTR adds another complexity to the design process, particularly when embedded FPGAs have to deal with power and performance constraints uncertain environments. Embedded systems will need to make autonomous decisions, develop cognitive properties such as self-awareness and finally become self-adaptive to be deployed in the real world. Classico-line modeling and programming methods are inadequate to cope with unpredictable environments. Reinforcement learning (RL) methods have been successfully explored to solve these complex optimization problems mainly in workstation computers, yet they are rarely implemented in embedded systems. Disruptive integration technologies reaching atomic-scales will increase the probability of fabrication errors and the sensitivity to electromagnetic radiation that can generate single-event upsets (SEUs) in the configuration memory of FPGAs. Dynamic FT schemes are promising RTR hardware redundancy structures that improve dependability, but on the other hand, they increase memory system traffic. This article presents an FPGA-based SoC that is self-aware of its monitored hardware and utilizes an online RL method to self-optimize the decisions that maintain the desired system performance, particularly when triggering hardware acceleration and dynamic FT schemes on RTR IP-cores. Moreover, this article describes the main features of the RecoBlock SoC concept, overviews the RL theory, shows the Q-learning algorithm adapted for the dynamic fault-tolerance optimization problem, and presents its simulation in Matlab. Based on this investigation, the Q-learning algorithm will be implemented and verified in the RecoBlock SoC platform.
|
|
| 7. |
- Navas, Byron, et al.
(författare)
-
Towards cognitive reconfigurable hardware : Self-aware learning in RTR fault-tolerant SoCs
- 2015
-
Ingår i: Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC), 2015. - : Institute of Electrical and Electronics Engineers (IEEE). - 9781467379427
-
Konferensbidrag (refereegranskat)abstract
- Traditional embedded systems are evolving into power-and-performance-domain self-aware intelligent systems in order to overcome complexity and uncertainty. Without human control, they need to keep operative states in applications such as drone-based delivery or robotic space landing. Nowadays, the partial and run-time reconfiguration (RTR) of FPGA-based Systems-on-chip (SoC) can enable dynamic hardware acceleration or self-healing structures, but this conversely increases system-memory traffic. This paper introduces the basis of cognitive reconfigurable hardware and presents the design of an FPGA-based RTR SoC that becomes conscious of its monitored hardware and learns to make decisions that maintain a desired system performance, particularly when triggering hardware acceleration and dynamic fault-tolerant (FT) schemes on RTR cores. Self-awareness is achieved by evaluating monitored metrics in critical AXI-cores, supported by hardware performance counters. We suggest a reinforcement-learning algorithm that helps the system to search out when and which reconfigurable FT-scheme can be triggered. Executing random sequences of an embedded benchmark suite simulates unpredictability and bus traffic. The evaluation shows the effectiveness and implications of our approach.
|
|
| 8. |
- Navas, Byron, et al.
(författare)
-
Towards the generic reconfigurable accelerator : Algorithm development, core design, and performance analysis
- 2013
-
Konferensbidrag (refereegranskat)abstract
- Adoption of reconfigurable computing is limited in part by the lack of simplified, economic, and reusable solutions. The significant speedup and energy saving can increase performance but also design complexity; in particular for heterogeneous SoCs blending several CPUs, GPUs, and FPGA-Accelerator Cores. On the other hand, implementing complex algorithms in hardware requires modeling and verification, not only HDL generation. Most approaches are too specific without looking for reusability. Therefore, we present a solution based on: (1) a design methodology to develop algorithms accelerated in reconfigurable/non-reconfigurable IP-Cores, using common access tools, and contemplating verification from model to embedded software stages; (2) a generic accelerator core design that enables relocation and reuse almost independently of the algorithm, and data-flow driven execution models; and (3) a performance analysis of the acceleration mechanisms included in our system (i.e., accelerator core, burst I/O transfers, and reconfiguration pre-fetch). In consequence, the implemented system accelerates algorithms (e.g., FIR and Kalman filters) with speedups up to 3 orders of magnitude, compared to processor implementations.
|
|
| 9. |
- Vasile, Massimiliano, et al.
(författare)
-
The Suaineadh Project : a Stepping Stone Towards the Deployment of Large Flexible Structures in Space
- 2010
-
Ingår i: Proceedings of the 61<sup>st</sup> International Astronautical Congress. - : the International Astronautical Federation. ; , s. IAC-10-C3.4-
-
Konferensbidrag (refereegranskat)abstract
- The Suaineadh project aims at testing the controlled deployment and stabilization of space web. The deployment system is based on a simple yet ingenious control of the centrifugal force that will pull each of the four daughters sections apart. The four daughters are attached onto the four corners of a square web, and will be released from their initial stowed configuration attached to a central hub. Enclosed in the central hub is a specifically designed spinning reaction wheel that controls the rotational speed with a closed loop control fed by measurements from an onboard inertial measurement sensor. Five other such sensors located within the web and central hub provide information on the surface curvature of the web, and progression of the deployment. Suaineadh is currently at an advanced stage of development: all the components are manufactured with the subsystems integrated and are presently awaiting full integration and testing. This paper will present the current status of the Suaineadh project and the results of the most recent set of tests. In particular, the paper will cover the overall mechanical design of the system, the electrical and sensor assemblies, the communication and power systems and the spinning wheel with its control system.
|
|
| 10. |
|
|
