Configuration Memory Of Field Programmable Gate Arrays Research Articles

Comparative study: AutoDPR-SEM for enhancing CNN reliability in SRAM-based FPGAs through autonomous reconfiguration

Convolutional neural networks (CNNs) are widely adopted in safety-critical systems, including space applications and autonomous vehicles. Field-programmable gate arrays (FPGAs) based on SRAM are preferred for accelerating CNN computations due to their unique characteristics. However, the configuration memory of FPGAs is susceptible to single event effects (SEEs), which can corrupt computations and lead to misclassification of CNN outputs. In this study, we investigated the impact of SEEs on SRAM-based FPGAs with Two-Photon Absorption (TPA) laser fault injections through a comparative analysis of two popular CNN acceleration architectures: streaming architecture (SA) and single compute engine (SCE). Experimental results show that SA-based CNNs require more hardware resources but exhibit superior resilience against single event upsets (SEUs). Without any Radiation Hardened by Design (RHBD) protection, SCE has an error rate approximately twice as high as SA. To mitigate errors, the Xilinx IP core - Soft Error Mitigation (SEM) is used for error detection and correction, leading to error rate reductions of up to 50 % in both architectures. Importantly, we propose the AutoDPR-SEM (Autonomous Dynamic Partial Reconfiguration for Soft Error Mitigation) approach, which automatically reconfigures the SEM IP core when it remains idle due to uncorrectable errors. AutoDPR-SEM significantly improves CNN error rates, reducing errors by approximately 17.8 times in SCE and 14.8 times in SA. We also applied software level simulation to validate the TPA experiment, showing similar trends of the testing results across all models. In conclusion, the study confirms the feasibility of AutoDPR-SEM in both architectures, showcasing its potential to improve CNN error rates in safety-critical systems.

Low-Cost Strategy to Detect Faults Affecting Scrubbers in SRAM-Based FPGAs

SRAM-based Field Programmable Gate Arrays (FPGAs) are vulnerable to SEUs. For applications demanding high reliability this problem is often solved by integrating in the system a scrubber, a circuit that periodically scans the FPGA configuration memory and reconfigures it if an error is detected. Since the scrubber is usually implemented in the same FPGA device, it is also vulnerable to SEUs, thus the scrubber reliability is increased by adopting standard fault tolerance techniques. These solutions guarantee the scrubber reliability, but generally require a large area overhead.In this paper, we present a novel low-cost strategy capable to detect faults in the FPGA configuration memory implementing the scrubber. The proposed technique is based on time redundancy, forcing the scrubber output to produce an error indication for each word read from the FPGA memory, in order to detect the faults affecting the portion of FPGA memory implementing the scrubber. The implementation of our proposed strategy presents a negligible impact in terms of area overhead (4.17%) and a limited increase in power consumption (22.9%) over the original (unprotected) scrubber. As for the impact on system performance introduced by our strategy, it is of approximately the 38.2% over the unprotected scrubber, but it can be significantly lowered by reducing the frequency at which the scrubber is applied to test the FPGA.

Identifying Radiation-Induced Micro-SEFIs in SRAM FPGAs

Field-programmable gate arrays (FPGAs) are susceptible to radiation-induced effects that can affect more than one memory cell. Radiation-induced microsingle event functional interrupts (micro-SEFIs) are one of such events that can upset several bits at a time. These events need to be studied because they can overcome protection from techniques such as triple modular redundancy (TMR) and error correction codes (ECCs). Extracting these events from radiation data helps to understand if specific resources of the FPGA are more vulnerable and the extent of this vulnerability. This article presents a method based on statistics and fault injection to identify micro-SEFIs from beam-test data in the configuration memory and block RAM (BRAM) of SRAM-based FPGAs. The results show the cross section of these events for the configuration RAM (CRAM) and BRAM for three families of Xilinx SRAM FPGAs gathered throughout three neutron tests. This article also contains data from a fault injection campaign to uncover the possible CRAM source bits causing micro-SEFIs in memory look-up tables (LUTs) of Xilinx 7-series and Ultrascale devices.

A Radiation-Tolerant, Multigigabit Serial Link Based on FPGAs

Multigigabit serial links implemented by means of static random access memory (SRAM)-based field-programmable gate arrays (FPGAs) are extensively used in trigger and data acquisition systems of high-energy physics experiments. Their usage is mostly in areas without radiation, due to the sensitivity of FPGA configuration memory to single-event upsets. In order to use these links in radiation environments, some mitigation techniques can be used. In this article, we present a bidirectional link running at 6.25 Gbps implemented in Xilinx Kintex-7 FPGAs. Transferred data are protected against radiation effects by means of a Reed-Solomon (RS) code and symbol interleaving. Logic features triple modular redundancy in critical blocks. The design includes a custom scrubber based on majority voting of configuration frames. Our custom protocol can vary the protection level of the RS code to cope with different rates of radiation-induced transmission errors, trading off the available bandwidth for reliability. We present the test results carried out using fault injection and a 62-MeV proton beam at the Istituto Nazionale di Fisica Nucleare (INFN) Laboratori Nazionali del Sud (Catania, Italy). We show the performance of the link in terms of mean time between failures and mean time between losses of lock.

Understanding the Impact of Quantization, Accuracy, and Radiation on the Reliability of Convolutional Neural Networks on FPGAs

Convolutional neural networks are quickly becoming viable solutions for self-driving vehicles, military, and aerospace applications. At the same time, due to their high level of design flexibility, reprogrammable capability, low power consumption, and relatively low cost, the field-programmable gate arrays (FPGAs) are very good candidates to implement the neural networks. Unfortunately, the radiation-induced errors are known to be an issue in static random-access memory (SRAM)-based FPGAs. More specifically, we have seen that particles can change the content of the FPGA's configuration memory, consequently corrupting the implemented circuit and generating the observable errors at the output. Through extensive fault injection, we determine the reliability impact of applying binary quantization to the convolutional layers of neural networks on FPGAs, by analyzing the relationships between model accuracy, resource utilization, performance, error criticality, and radiation cross section. We were able to find that a design with quantized convolutional layers can be 39% less sensitive to radiation, whereas the portion of errors that are considered critical (misclassifications) in the network is increased by 12%. Moreover, we also derive generic equations that consider both accuracy and radiation in order to model the overall failure rate of neural networks.

Understanding radiation effects in SRAM-based field programmable gate arrays for implementing instrumentation and control systems of nuclear power plants

Abstract Field programmable gate arrays (FPGAs) are getting more attention in safety-related and safety-critical application development of nuclear power plant instrumentation and control systems. The high logic density and advancements in architectural features make static random access memory (SRAM)-based FPGAs suitable for complex design implementations. Devices deployed in the nuclear environment face radiation particle strike that causes transient and permanent failures. The major reasons for failures are total ionization dose effects, displacement damage dose effects, and single event effects. Different from the case of space applications, soft errors are the major concern in terrestrial applications. In this article, a review of radiation effects on FPGAs is presented, especially soft errors in SRAM-based FPGAs. Single event upset (SEU) shows a high probability of error in the dependable application development in FPGAs. This survey covers the main sources of radiation and its effects on FPGAs, with emphasis on SEUs as well as on the measurement of radiation upset sensitivity and irradiation experimental results at various facilities. This article also presents a comparison between the major SEU mitigation techniques in the configuration memory and user logics of SRAM-based FPGAs.

SEU mitigation exploratory tests in a ITER related FPGA

Data acquisition hardware of ITER diagnostics if located in the port cells of the tokamak, as an example, will be irradiated with neutrons during the fusion reactor operation. Due to this reason the majority of the hardware containing Field Programmable Gate Arrays (FPGA) will be placed after the ITER bio-shield, such as the cubicles instrumentation room. Nevertheless, it is worth to explore real-time mitigation of soft-errors caused by neutrons radiation in ITER related FPGAs. A Virtex-6 FPGA from Xilinx (XC6VLX365T-1FFG1156C) is used on the ATCA-IO-PROCESSOR board, included in the ITER Catalog of Instrumentation & Control (I & C) products – Fast Controllers. The Virtex-6 is a re-programmable logic device where the configuration is stored in Static RAM (SRAM), the functional data is stored in dedicated Block RAM (BRAM) and the functional state logic in Flip-Flops. Single Event Upsets (SEU) due to the ionizing radiation of neutrons cause soft errors, unintended changes (bit-flips) of the logic values stored in the state elements of the FPGA. Real-time SEU monitoring and soft errors repairing, when possible, were explored in this work. An FPGA built-in Soft Error Mitigation (SEM) controller detects and corrects soft errors in the FPGA Configuration Memory (CM). BRAM based SEU sensors with Error Correction Code (ECC) detect and repair the respective BRAM contents. Real-time mitigation of SEU can increase reliability and availability of data acquisition hardware for nuclear applications. The results of the tests performed using the SEM controller and the SEU sensors are presented for a Virtex-6 FPGA (XC6VLX240T-1FFG1156C) when irradiated with neutrons from the Portuguese Research Reactor (RPI), a 1MW nuclear fission reactor, operated by IST in the neighborhood of Lisbon. Results show that the proposed SEU mitigation technique is able to repair the majority of the detected SEU soft-errors in the FPGA memory.

An FPGA-Based High-Speed Error Resilient Data Aggregation and Control for High Energy Physics Experiment

Due to the dramatic increase of data volume in modern high energy physics (HEP) experiments, a robust high-speed data acquisition (DAQ) system is very much needed to gather the data generated during different nuclear interactions. As the DAQ works under harsh radiation environment, there is a fair chance of data corruption due to various energetic particles like alpha, beta, or neutron. Hence, a major challenge in the development of DAQ in the HEP experiment is to establish an error resilient communication system between front-end sensors or detectors and back-end data processing computing nodes. Here, we have implemented the DAQ using field-programmable gate array (FPGA) due to some of its inherent advantages over the application-specific integrated circuit. A novel orthogonal concatenated code and cyclic redundancy check (CRC) have been used to mitigate the effects of data corruption in the user data. Scrubbing with a 32-b CRC has been used against error in the configuration memory of FPGA. Data from front-end sensors will reach to the back-end processing nodes through multiple stages that may add an uncertain amount of delay to the different data packets. We have also proposed a novel memory management algorithm that helps to process the data at the back-end computing nodes removing the added path delays. To the best of our knowledge, the proposed FPGA-based DAQ utilizing optical link with channel coding and efficient memory management modules can be considered as first of its kind. Performance estimation of the implemented DAQ system is done based on resource utilization, bit error rate, efficiency, and robustness to radiation.

Efficient dynamic priority based soft error mitigation techniques for configuration memory of FPGA hardware

Radiation-induced single bit upsets (SBUs) and multi-bit upsets (MBUs) are more prominent in Field Programmable Gate Arrays (FPGAs) due to the presence of a large number of latches in the configuration memory (CM) of FPGAs. At the same time, SBUs and MBUs in the CM can permanently or temporarily affect the hardware circuit implemented on FPGA. Hence, error mitigation and recovery techniques are necessary to protect the FPGA hardware from permanent faults arising due to such SBUs and MBUs. Different existing techniques used to mitigate the effect of soft errors in FPGA have high overhead and their implementations are also quite complex. In this paper, we have proposed efficient single bit as well as multi-bit error correcting methods to correct errors in the CM of FPGAs using simple parity equations and Erasure code. These codes are easy to implement, and the needed decoding circuits are also simple. Use of Dynamic Partial Reconfiguration (DPR) along with a simple hardware scheduling algorithm based download manager helps to perform the error correction in the CM without suspending the operations of the other hardware blocks. We propose a first of its kind methodology for novel transient fault correction using efficient error correcting codes with hardware scheduling for FPGAs. To validate the design we have tested the proposed methodology with Kintex FPGA. We have also measured different parameters like fault recovery time, power consumption, resource overhead and error correction efficiency to estimate the performance of our proposed methods.

Architecture design for reliable and reconfigurable FPGA-based GNC computer for deep space exploration

SRAM (static random access memory)-based FPGA (field programmable gate array), owing to its large capacity, high performance, and dynamical reconfiguration, has become an attractive platform for SoPC (system on programmable chip) development. However, as the configuration memory and logic memory of the SRAM-based FPGA are highly susceptible to SEUs (single-event upsets) in deep space, it is a challenge to design and implement a highly reliable FPGA-based system for spacecraft, and no practical architecture has been proposed. In this paper, a new architecture for a reliable and reconfigurable FPGAbased computer in a highly critical GNC (guidance navigation and control) system is proposed. To mitigate the effect of an SEU on the system, multi-layer reconfiguration and multi-layer TMR (triple module redundancy) techniques are proposed, with a reliable reconfigurable real-time operating system (SpaceOS) managing the system level fault tolerance of the computer in the architecture. The proposed architecture for the reconfigurable FPGA-based computer has been implemented with COTS (commercial off the shelf) FPGA and has firstly been applied to the GNC system of a circumlunar return and reentry flight vehicle. The in-orbit results show that the proposed architecture is capable of meeting the requirements of high reliability and high availability, and can provide the expressive varying functionality and runtime flexibility for an FPGA-based GNC computer in deep space.

A New Partial Reconfiguration-Based Fault-Injection System to Evaluate SEU Effects in SRAM-Based FPGAs

Modern SRAM-based field programmable gate array (FPGA) devices offer high capability in implementing complex system. Unfortunately, SRAM-based FPGAs are extremely sensitive to single event upsets (SEUs) induced by radiation particles. In order to successfully deploy safety- or mission-critical applications, designer need to validate the correctness of the obtained designs. In this paper we describe a system based on partial-reconfiguration for running fault-injection experiments within the configuration memory of SRAM-based FPGAs. The proposed fault-injection system uses the internal configuration capabilities that modern FPGAs offer in order to inject SEU within the configuration memory. Detailed experimental results show that the technique is orders of magnitude faster than previously proposed ones.

A new reliability-oriented place and route algorithm for SRAM-based FPGAs

The very high integration levels reached by VLSI technologies for SRAM-based field programmable gate arrays (FPGAs) lead to high occurrence-rate of transient faults induced by single event upsets (SEUs) in FPGAs' configuration memory. Since the configuration memory defines which circuit an SRAM-based FPGA implements, any modification induced by SEUs may dramatically change the implemented circuit. When such devices are used in safety-critical applications, fault-tolerant techniques are needed to mitigate the effects of SEUs in FPGAs' configuration memory. In this paper, we analyze the effects induced by the SEUs in the configuration memory of SRAM-based FPGAs. The reported analysis outlines that SEUs in the FPGA's configuration memory are particularly critical since they are able to escape well-known fault masking techniques such as triple modular redundancy (TMR). We then present a reliability-oriented place and route algorithm that, coupled with TMR, is able to effectively mitigate the effects of the considered faults. The effectiveness of the new reliability-oriented place and route algorithm is demonstrated by extensive fault injection experiments showing that the capability of tolerating SEU effects in the FPGA's configuration memory increases up to 85 times with respect to a standard TMR design technique

Analysis of the robustness of the TMR architecture in SRAM-based FPGAs

Non radiation-hardened SRAM-based Field Programmable Gate Arrays (FPGAs) are very sensitive to Single Event Upsets (SEUs) affecting their configuration memory and thus suitable hardening techniques are needed when they are intended to be deployed in critical applications. Triple Module Redundancy is a known solution for hardening digital logic against SEUs that is widely adopted for traditional techniques (like ASICs). In this paper we present an analysis of the SEU effects in circuits hardened according to the Triple Module Redundancy to investigate the possibilities of successfully applying TMR to designs mapped on commercial-off-the-shelf SRAM-based FPGAs, which are not radiation hardened. We performed different fault-injection experiments in the FPGA configuration memory implementing TMR designs and we observed that the percentage of SEUs escaping TMR could reach 13%. In this paper we report detailed evaluations of the effects of the observed failure rates, and we proposed a first step toward an improved TMR implementation.

Simulation-based analysis of SEU effects in SRAM-based FPGAs

SRAM-based field programmable gate arrays (FPGAs) are particularly sensitive to single event upsets (SEUs) that, by changing the FPGA's configuration memory, may affect dramatically the functions implemented by the device. In This work we describe a new approach for predicting SEU effects in circuits mapped on SRAM-based FPGAs that combines radiation testing with simulation. The former is used to characterize (in terms of device cross section) the technology on which the FPGA device is based, no matter which circuit it implements. The latter is used to predict the probability for a SEU to alter the expect behavior of a given circuit. By combining the two figures, we then compute the cross section of the circuit mapped on the pre-characterized device. Experimental results are presented that compare the approach we developed with a traditional one based on radiation testing only, to measure the cross section of a circuit mapped on an FPGA. The figures here reported confirm the accuracy of our approach.

Errata to “Identification and Classification of Single-Event Upsets in the Configuration Memory of SRAM-Based FPGAs”

This paper presents the radiation testing of a commercial-off-the-shelf SRAM-based field-programmable gate arrays (FPGAs) with heavy ions. Test experiments have been conducted to identify and to classify the single-event upsets (SEUs) in the configuration memory that induce single-event functional interrupt for the user-implemented circuit. Moreover the paper presents a new approach for assessing the effects of SEUs based on the combination of radiation testing and simulation-based fault injection tool. First experimental results show the FPGA look-up table (LUT) resources (used to implement combinatorial logic) are the most sensitive to SEUs, whereas interconnect resources are the most critical for the device cross section because they use the largest number of configuration bits. The analysis of experimental data underlines that the most probable error affecting interconnections is the shorting of two nets. This observation indicates that new fault models should be considered along with the classic stuck-at one model designing fault-tolerant architectures, which are intended for implementation in FPGA devices.

Identification and classification of single-event upsets in the configuration memory of SRAM-based FPGAs

This paper presents the radiation testing of a commercial-off-the-shelf SRAM-based field-programmable gate arrays (FPGAs) with heavy ions. Test experiments have been conducted to identify and to classify the single-event upsets (SEUs) in the configuration memory that induce single-event functional interrupt for the user-implemented circuit. Moreover the paper presents a new approach for assessing the effects of SEUs based on the combination of radiation testing and simulation-based fault injection tool. First experimental results show the FPGA look-up table (LUT) resources (used to implement combinatorial logic) are the most sensitive to SEUs, whereas interconnect resources are the most critical for the device cross section because they use the largest number of configuration bits. The analysis of experimental data underlines that the most probable error affecting interconnections is the shorting of two nets. This observation indicates that new fault models should be considered along with the classic stuck-at one model designing fault-tolerant architectures, which are intended for implementation in FPGA devices.