Efficient incremental rerouting for fault reconfiguration in field programmable gate arrays

This paper presents a hardware implementation of morphological operations based on dynamic and partial reconfiguration (DPR) technique. This technique allows reconfiguring a part of the FPGA area with different functionalities at runtime. It is a promising solution toincrease performance in the system. Our design allows todesigner to choose the adequate morphological operation (erosion or dilation) according the image constraints. We use xilinx tools and Virtex-5 FPGA board. To evaluate our implementation, we measure the performance in terms of area occupation and time reconfiguration. The results show the implementation of morphological operations on FPGA (Field Programmable Gate Array) using DPR can improve the performance and saving at least 11% of area.

Debugging of Field-Programmable Gate Arrays (FPGAs) is a difficult task due to the limited access to the internal signals of the design. Embedded logic analyzers enhance the signal observability for FPGAs. These analyzers are implemented on the FPGA resources and they use the embedded memory blocks as trace buffers, so a limited number of signals can be observed using these analyzers due to resources constraints. Changing the traced set of signals requires re-synthesis, placement and routing of the whole design. In this paper, we propose a new methodology for FPGA debugging to change dynamically the set of signals to be observed at runtime, and consequently minimize the time required for debugging. The proposed methodology utilizes the Dynamic Partial Reconfiguration (DPR) technique to dynamically switch between different sets of signals. DPR creates a reconfigurable module (RM) to route each set of signals to an embedded logic analyzer. We demonstrate the proposed approach using Xilinx FPGA tools, finding that changing the set of signals to be observed requires only few milli-seconds to re-program the reconfigurable region (RR). The area overhead of the proposed methodology is lower than other traditional methods of using multiplexers as the DPR allows the routing module to only use buffers to connect a set of signals to the embedded logic analyzer.

A popular research topic as of late has been dynamic partial FPGA (Field Programmable Gate Array) reconfiguration. This concept allows on-the-fly reconfiguration of digital systems where only parts of the circuit change, providing application acceleration and allowing static modules to continue processing unaffected by the dynamic elements. Design characteristics which benefit from this progressive approach include increased system flexibility, increased performance, and a reduction in circuit complexity. One characteristic receiving limited focus thus far has been the increased security that could result from these changing circuits. This benefit is innate to the design and makes reverse engineering of the system a much more ambitious task. In an effort to further enhance this passive security feature, a new partial reconfiguration technique has been proposed that changes connectivity between generic modules. This extended abstract introduces the method, model, and design flow for this dynamic partial FPGA reconfiguration technique and addresses the security implications of such a design.

A multi-mode circuit implements the functionality of a limited number of circuits, called modes, of which at any given time only one needs to be realised. Using dynamic partial reconfiguration of an FPGA, all the modes can be implemented on the same reconfigurable region, requiring only an area that can contain the biggest mode. This can save considerable chip area. Conventional dynamic partial reconfiguration techniques generate a configuration for every mode separately. As a result, to switch between modes the complete reconfigurable region is rewritten, which often leads to long reconfiguration times. In this paper we give an overview of research we conducted to reduce this overhead of dynamic partial reconfiguration for multi-mode circuits. In this research we explored several joint optimization strategies at different stages of the tool flow.

K-nearest neighbour (KNN) is a supervised classification technique that is widely used in many fields of study to classify unknown queries based on some known information about the dataset. KNN is known to be robust and simple to implement when dealing with data of small size. However it performs slowly when data are large and have high dimensions. Therefore, KNN classifiers can benefit from the parallelism offered by Field Programmable Gate Arrays (FPGAs) to accelerate the algorithm. In addition, the KNN classifier is sensitive to the user defined parameter (K) which is the number of nearest neighbours. This parameter is known to affect the performance of the classifier; thus users would want the classifier to be easily adaptable to different values of K. In this work, we propose two adaptive FPGA architectures of the KNN classifier, and compare the implementations of each one of them with an equivalent implementation running on a general purpose processor (GPP). The proposed hardware implementations outperformed GPP by 76× for the first architecture and 68× for the second. In addition, we propose a novel dynamic partial reconfiguration (DPR) architecture of the KNN classifier, which allows for an efficient dynamic partial reconfiguration of a classifier implementation on FPGA for different K's. This DPR implementation offers 5× speed-up in the reconfiguration time of a KNN classifier on FPGA.

Reconfiguration technique has been considered as one of the most promising electronic design automation (EDA) technologies in MPSoC design paradigms. However, due to the unavoidable latency in the reconfiguration procedure, it still poses a significant challenge to efficiently analyze the trade-offs for the software/hardware execution, static reconfiguration and dynamic reconfiguration. In this paper we first present a heterogeneous MPSoC middleware to support state-of-the-art dynamic partial reconfigurable technologies. Furthermore, we evaluate the reconfiguration latency and analyze the trade-off for the dynamic partial reconfiguration technologies.

Business-to-Business (B2B) applications are developed predominantly based on service-oriented architectural style which is generally realized using a set of loosely coupled web services. These web services can be selected statically during design-time or dynamically during run-time. The functional and non-functional QoS requirements are typically captured in the Service Level Agreement (SLA) that is mutually agreed between the service provider and the service consumer. Whenever an SLA violation happens, the service provider incurs a penalty. In order to minimize such penalties, the application that is built through a design-time composition of web services needs to be monitored. Whenever a violation of SLA is predicted, those statically composed web services are dynamically reconfigured. This is called as dynamic reconfiguration in SOA. In this case, even the alternate service selection happens at design-time itself. On the other hand, whenever the web services needed for an SOA application development are selected and composed dynamically at run-time, it is called as dynamic composition. The turnaround time involved in both these approaches for mission-critical applications with stringent SLA requirements is compared. It has been inferred that the dynamic reconfiguration approach not only maintained the turnaround time always within the accepted limits, it also incurred only less overhead when compared to dynamic composition approach.

Recent research has shown that field programmable gate arrays (FPGAs) have a large potential for accelerating demanding applications, such as high performance digital signal process applications with low-volume market. The loss of generality in the architecture is one disadvantage of using FPGAs, however, the reconfigurability of FPGAs allow reprogramming for other applications. Therefore, a uniform FPGA-based architecture, an efficient programming model, and a simple mapping method are paramount for the wide acceptance of FPGA technology. This paper presents MASALA, a dynamically reconfigurable FPGA-based accelerator for parallel programs written in thread-intensive and explicit memory management (TEMM) programming models. Our system uses a TEMM programming model to parallelize demanding applications, including application decomposition into separate thread blocks and compute and data load/store decoupling. Hardware engines are included into MASALA using partial dynamic reconfiguration modules, each of which encapsulates a thread process engine that implements the hardware's thread functionality. A data dispatching scheme is also included in MASALA to enable the explicit communication of multiple memory hierarchies such as interhardware engines, host processors, and hardware engines. Finally, this paper illustrates a multi-FPGA prototype system of the presented architecture: MASALA-SX. A large synthetic aperture radar image formatting experiment shows that MASALA's architecture facilitates the construction of a TEMM program accelerator by providing greater performance and less power consumption than current CPU platforms, without sacrificing programmability, flexibility, and scalability.

Dynamic reconfiguration techniques can greatly improve the flexibility and reliability of manufacturing systems. However, different from static reconfigurable systems, system behavior during dynamic reconfiguration processes is quite complex due to possible concurrence of system structure changes and events inside unaltered components. This increases the difficulty in designing and developing dynamic reconfigurable systems. The current paper deals with the analysis and control of dynamic reconfiguration process of manufacturing systems from the perspective of discrete event systems. To this end, the authors improve the reconfigurable timed net condition/event systems formalism by assigning reconfiguration functions with extra permeating time, action ranges, and concurrent decision functions. As a consequence, nondeterministic behavior of a dynamic reconfigurable system during dynamic reconfigurations can be specified, while the system correctness, coherence, and safety during reconfigurations can be guaranteed. A reconfigurable manufacturing plant is used as a running example to illustrate the contribution of this paper.

An optically differential reconfigurable gate array (ODRGA) is a type of field programmable gate array (FPGA), but its gate array can be reconfigured optically in less than 6 ns. We have fabricated a 68 gate-count ODRGA. However, optical differential reconfiguration circuits, which are capable of optical detection of configuration contexts and which can support reconfiguration of an arbitrary part of its gate array bit-by-bit, occupy up to 47% of the implementation area of ODRGA-VLSI chip and prevent realization of a high gate-count ODRGA. Therefore, a dynamic optical differential reconfiguration circuit was developed to reduce the implementation area of optical reconfiguration circuits. It has been evaluated separately. This paper presents the first 476 gate count ODRGA-VLSI chip with a standard 0.35 /spl mu/m 3-metal CMOS process technology using an improved dynamic optical differential reconfiguration circuit. In addition, the dynamic reconfiguration frequency and performance of logic blocks are shown using HSPICE simulation results. Finally, this paper presents an estimation of the use of a standard 0.35 /spl mu/m 3-metal 14.2/spl times/74.2 mm chip.

Field Programmable Gate Array (FPGA) has been widely adopted as modern reconfigurable computing platforms. Traditionally, the storage elements in FPGAs are static RAM (SRAM), which has large leakage power and limited scalability. Recently, non-volatile memory (NVM) is proposed to replace the SRAM in FPGA systems for static power and density considerations, at the cost of inducing larger dynamic power. Hybrid FPGAs combine the advantages of SRAM and NVM by employing both SRAM and NVM as logic storage elements. Although the feasibility of hybrid FPGA has been confirmed, the design flow has not fully explored the hybrid features yet, resulting in inferior system performance. Besides, traditional design flow does not consider the reconfiguration cost, which may prolong the reconfiguration procedures and thus degrade the system performance in dynamically reconfigurable FPGA systems. This work proposes a runtime and reconfiguration dual aware placement strategy for dynamically reconfigurable hybrid architecture. The proposed scheme considers the tradeoff between runtime and dynamic reconfiguration latency and optimizes the overall performance of the reconfigurable system. Evaluation shows that the proposed scheme improves the system performance by 14.6% for SRAM-MRAM hybrid FPGAs compared with the default placement strategy.

Field Programmable Gate Arrays (FPGAs) have proven their potential in accelerating High Performance Computing (HPC) Applications. Conventionally such accelerators predominantly use, FPGAs that contain fine-grained elements such as LookUp Tables (LUTs), Switch Blocks (SB) and Connection Blocks (CB) as basic programmable logic blocks.\nHowever, the conventional implementation suffers from high reconfiguration and development costs. In order to solve this problem, programmable logic components are defined at a virtual higher abstraction level. These components are called Processing Elements (PEs) and the group of PEs along with the inter-connection network form an architecture called a Virtual Coarse-Grained Reconfigurable Array (VCGRA). The abstraction helps to reconfigure the PEs faster at the intermediate level than at the lower-level of an FPGA.\nConventional VCGRA implementations (built on top of the lower levels of the FPGA) use functional resources such as LUTs to establish required connections (intra-connect) within a PE. In this paper, we propose to use the parameterized reconfiguration technique to implement the intra-connections of each PE with the aim to reduce the FPGA resource utilization (LUTs). The technique is used to parameterize the intra-connections with parameters that only change their value infrequently (whenever a new VCGRA function has to be reconfigured) and that are implemented as constants. Since the design is optimized for these constants at every moment in time, this reduces the resource utilization. Further, interconnections (network between the multiple PEs) of the VCGRA grid can also be parameterized so that both the inter- and intraconnect network of the VCGRA grid can be mapped onto the physical switch blocks of the FPGA. For every change in parameter values a specialized bitstream is generated on the fly and the FPGA is reconfigured using the parameterized run-time reconfiguration technique. Our results show a drastic reduction in FPGA LUT resource utilization in the PE by at least 30% and in the intra-network of the PE by 31% when implementing an HPC application.

Performance of Field Programmable Gate Arrays (FPGAs) used for floating-point applications is poor due to the complexity of floating-point arithmetic. Implementing floating-point units on FPGAs consume a large amount of resources. This makes FPGAs less attractive for use in floating-point intensive applications. Therefore, there is a need for embedded floating-point units (FPUs) in FPGAs. However, if unutilized, embedded FPUs waste space on the FPGA die. To overcome this issue, we propose a flexible multi-mode embedded FPU for FPGAs that can be configured to perform a wide range of operations. The floating-point adder and multiplier in our embedded FPU can each be configured to perform one double-precision operation or two single-precision operations in parallel. To increase flexibility further, access to the large integer multiplier, adder and shifters in the FPU is provided. Benchmark circuits were implemented on both a standard Xilinx Virtex-II FPGA and on our FPGA with embedded FPU blocks. The results using our embedded FPUs showed a mean area improvement of 5.2 times and a mean delay improvement of 5.8 times for the double-precision benchmarks, and a mean area improvement of 4.4 times and a mean delay improvement of 4.2 times for the single-precision benchmarks.

Industrial designers and educators who plan to design microelectronic systems (e.g. hardware accelerators, co-processors, etc.) are increasingly capturing their designs using hardware description languages such as VHDL and Verilog. The designs are then most often synthesized into programmable logic components such as field-programmable gate arrays (FPGAs) offered by Xilinx, Altera, Actel and others. This approach places the emphasis on high-level design which reduces time to market by relying on synthesis software and programmable logic to produce working prototypes rapidly. These prototypes may then be altered as requirements change or converted into high-volume mask gate arrays or other application-specific integrated circuits (ASICs) when the demand is known to be sufficient. These ASICs, however, must be designed to be testable to screen out those with manufacturing defects. Hence, scan logic must be inserted, test vectors generated and fault grading performed to ensure a high level of testability. These efforts complicate and delay the conversion of FPGA designs to ASICs but must be considered by designers of microelectronic systems. Topics covered include: design flow; system partitioning; hardware description languages (HDLs); specifying behavioral control; specifying structural components; critical paths; placement and routing; technology choices; FPGA applications; rapid prototyping; retargeting; manufacturing defects; scan chain insertion; test vector generation; fault grading, and ASIC production

With the development of digital integrate circuit system which is based on Field Programmable Gate Arrays (FPGA), the request on FPGA test technique is becoming higher and higher. The Boundary Scan Technique and Built-In Self-Test (BIST) technique appear in succession, however, these techniques dont implement Configurable Logic Block (CLB) fault diagnose and fault orientation. Arrays-based technique was advanced, which also have some problems about masking of faults and too many reconfiguration times. According to these problems, A Novel Shift Register-based technique for Fault Orientation of FPGA Configurable Logic Blocks was advanced. The paper analyses the design theory about core circuit configure, and has important significance impact on Fault Orientation of FPGA Configurable Logic Blocks.