Search NASA⌕ Search

SEARCH · Search NASA

Results for “modular redundancy”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

Localized Triple Modular Redundancy vs. Distributed Triple Modular Redundancy on a ProASIC3E Reprogrammable FPGA

Field programmable gate arrays (FPGA) are used in every space application. Currently, most space flight applications use radiation hardened (RH) FPGAs, which are very expensive. There is a desire to use cheaper, commercial off the shelf reprogrammable FPGAs, which are more susceptible to radiation effects known as single-event effects (SEE). The RH parts have SEE and total ionizing dose (TID) hardened elements pre-integrated into the part. This means that the designer does not need to implement any hardening techniques while configuring the device. The COTS parts on the other hand must be mitigated by design in order to insure any form of mitigation. The design techniques this project examines concern the use of localized triple modular redundancy (LTMR) and distributed triple modular redundancy (DTMR). LTMR triples every flip flop in the device architecture while DTMR triples everything except for the global routes (clocks, resets, and enables). The testing was performed on a ProASIC3E FPGA at the Texas A&M cyclotron facility. Two design architectures were used: shift registers and counters, both with LTMR and DTMR mitigation techniques. The test results prove that DTMR is more effective at reducing SEE than LTMR. We also determined that there was not a significant difference between the use of shift registers and counters for test purposes. More testing is required to obtain additional linear energy transfer values for each architecture and mitigation technique in order to determine the most cost-effective method of SEE mitigation.

McGuffey, Alex↗

Reducing the cost of n modular redundancy for neural networks

An N modular redundancy method, system, and computer program product include a computer-implemented N modular redundancy method for neural networks, the method including selectively replicating the neural network by employing one of checker neural networks and selective N modular redundancy (N-MR) applied only to critical computations.

97 MATHEMATICS AND COMPUTING↗

The Case for Modular Redundancy in Large-Scale High Performance Computing Systems

Recent investigations into resilience of large-scale high-performance computing (HPC) systems showed a continuous trend of decreasing reliability and availability. Newly installed systems have a lower mean-time to failure (MTTF) and a higher mean-time to recover (MTTR) than their predecessors. Modular redundancy is being used in many mission critical systems today to provide for resilience, such as for aerospace and command \& control systems. The primary argument against modular redundancy for resilience in HPC has always been that the capability of a HPC system, and respective return on investment, would be significantly reduced. We argue that modular redundancy can significantly increase compute node availability as it removes the impact of scale from single compute node MTTR. We further argue that single compute nodes can be much less reliable, and therefore less expensive, and still be highly available, if their MTTR/MTTF ratio is maintained.

99 GENERAL AND MISCELLANEOUS↗

Verification of Triple Modular Redundancy Insertion for Reliable and Trusted Systems

If a system is required to be protected using triple modular redundancy (TMR), improper insertion can jeopardize the reliability and security of the system. Due to the complexity of the verification process and the complexity of digital designs, there are currently no available techniques that can provide complete and reliable confirmation of TMR insertion. We propose a method for TMR insertion verification that satisfies the process for reliable and trusted systems.

Verification↗

Links between N-modular redundancy and the theory of error-correcting codes

N-Modular Redundancy (NMR) is one of the best known fault tolerance techniques. Replication of a module to achieve fault tolerance is in some ways analogous to the use of a repetition code where an information symbol is replicated as parity symbols in a codeword. Linear Error-Correcting Codes (ECC) use linear combinations of information symbols as parity symbols which are used to generate syndromes for error patterns. These observations indicate links between the theory of ECC and the use of hardware redundancy for fault tolerance. In this paper, we explore some of these links and show examples of NMR systems where identification of good and failed elements is accomplished in a manner similar to error correction using linear ECC's.

Bobin, V.↗

Embedding triple-modular redundancy into a hypercube architecture

This paper describes an embedding of Triple Modular Redundancy (TMR) into a binary hypercube. The goal is to improve fault tolerance by masking any single-point faults. Each module of an application task is triplicated and executed in parallel on three nodes of a 2-dimensional subcube (Q2) of the hypercube. Each of these nodes also executes a voter process. The remaining node is used for message passing only. All outputs from the triplicated modules are voted on, and the voting results are transmitted to the appropriate destination. Thus, all interunit messages are also triplicated. We propose an embedding of TMR into a hypercube which can be implemented in a manner transparent to the application program. Subcubes are allocated so that the address space for the TMR units is also a hypercube. Hence, the subcube allocation and intermodule communication schemes are defined to be analogous to the schemes used in the nonredundant system. The embedded system is proven to mask all single-point faults.

Kiskis, Daniel L.↗

Single Event Test Methodologies and System Error Rate Analysis for Triple Modular Redundant Field Programmable Gate Arrays

We present a test methodology for estimating system error rates of Field Programmable Gate Arrays (FPGAs) mitigated with Triple Modular Redundancy (TMR). The test methodology is founded in a mathematical model, which is also presented. Accelerator data from 90 nm Xilins Military/Aerospace grade FPGA are shown to fit the model. Fault injection (FI) results are discussed and related to the test data. Design implementation and the corresponding impact of multiple bit upset (MBU) are also discussed.

error rate calculations↗

Verification of Triple Modular Redundancy (TMR) Insertion for Reliable and Trusted Systems

We propose a method for TMR insertion verification that satisfies the process for reliable and trusted systems. If a system is expected to be protected using TMR, improper insertion can jeopardize the reliability and security of the system. Due to the complexity of the verification process, there are currently no available techniques that can provide complete and reliable confirmation of TMR insertion. This manuscript addresses the challenge of confirming that TMR has been inserted without corruption of functionality and with correct application of the expected TMR topology. The proposed verification method combines the usage of existing formal analysis tools with a novel search-detect-and-verify tool. Field programmable gate array (FPGA),Triple Modular Redundancy (TMR),Verification, Trust, Reliability,

Trust↗

Hardware for Accelerating N-Modular Redundant Systems for High-Reliability Computing

A hardware unit has been designed that reduces the cost, in terms of performance and power consumption, for implementing N-modular redundancy (NMR) in a multiprocessor device. The innovation monitors transactions to memory, and calculates a form of sumcheck on-the-fly, thereby relieving the processors of calculating the sumcheck in software

Dobbs, Carl, Sr.↗

Using Classical Reliability Models and Single Event Upset (SEU) Data to Determine Optimum Implementation Schemes for Triple Modular Redundancy (TMR) in SRAM-Based Field Programmable Gate Array (FPGA) Devices

Space applications are complex systems that require intricate trade analyses for optimum implementations. We focus on a subset of the trade process, using classical reliability theory and SEU data, to illustrate appropriate TMR scheme selection.

Field Programmable Gate Array (FPGA)↗

Characterization of Soft Error Rate Against Memory Elements Spacing and Clock Skew in a Logic with Triple Modular Redundancy in a 65nm Process

Single Event Effects introduce soft errors in ASICs. Design methodologies like Triple ModularRedundancy (TMR) with clock skew insertion, a system level redundancy technique is a commonpractice by designers to mitigate soft errors. However, the optimal spacing between memoryelements in a TMR in 65nm process hasn't been addressed so far. RD53SEU is a mini ASICdevelopment under the framework of the CERN RD53 collaboration to characterize the soft errorrates against the separation spacing and clock skew between memory elements in a TMR. Thisarticle describes the architecture and design aspects of the various test structures on the RD53SEUtest chip.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗