Search NASA⌕ Search

SEARCH · Search NASA

Results for “Fault Tolerant Algorithms”

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

A Log-Scaling Fault Tolerant Agreement Algorithm for a Fault Tolerant MPI

The lack of fault tolerance is becoming a limiting factor for application scalability in HPC systems. The MPI does not provide standardized fault tolerance interfaces and semantics. The MPI Forum's Fault Tolerance Working Group is proposing a collective fault tolerant agreement algorithm for the next MPI standard. Such algorithms play a central role in many fault tolerant applications. This paper combines a log-scaling two-phase commit agreement algorithm with a reduction operation to provide the necessary functionality for the new collective without any additional messages. Error handling mechanisms are described that preserve the fault tolerance properties while maintaining overall scalability.

99 GENERAL AND MISCELLANEOUS↗

A Test Generation Framework for Distributed Fault-Tolerant Algorithms

Heavyweight formal methods such as theorem proving have been successfully applied to the analysis of safety critical fault-tolerant systems. Typically, the models and proofs performed during such analysis do not inform the testing process of actual implementations. We propose a framework for generating test vectors from specifications written in the Prototype Verification System (PVS). The methodology uses a translator to produce a Java prototype from a PVS specification. Symbolic (Java) PathFinder is then employed to generate a collection of test cases. A small example is employed to illustrate how the framework can be used in practice.

Goodloe, Alwyn↗

Parallel reduction to hessenberg form with algorithm-based fault tolerance

This paper studies the resilience of a two-sided factorization and presents a generic algorithm-based approach capable of making two-sided factorizations resilient. We establish the theoretical proof of the correctness and the numerical stability of the approach in the context of a Hessenberg Reduction (HR) and present the scalability and performance results of a practical implementation. Our method is a hybrid algorithm combining an Algorithm Based Fault Tolerance (ABFT) technique with diskless checkpointing to fully protect the data. We protect the trailing and the initial part of the matrix with checksums, and protect finished panels in the panel scope with diskless checkpoints. Compared with the original HR (the ScaLAPACK PDGEHRD routine) our fault-tolerant algorithm introduces very little overhead, and maintains the same level of scalability. We prove that the overhead shows a decreasing trend as the size of the matrix or the size of the process grid increases.

Computer Science↗

Algorithm-Based Fault Tolerance Integrated with Replication

In a proposed approach to programming and utilization of commercial off-the-shelf computing equipment, a combination of algorithm-based fault tolerance (ABFT) and replication would be utilized to obtain high degrees of fault tolerance without incurring excessive costs. The basic idea of the proposed approach is to integrate ABFT with replication such that the algorithmic portions of computations would be protected by ABFT, and the logical portions by replication. ABFT is an extremely efficient, inexpensive, high-coverage technique for detecting and mitigating faults in computer systems used for algorithmic computations, but does not protect against errors in logical operations surrounding algorithms.

Some, Raphael↗

Algorithm-Based Fault Tolerance for Convolutional Neural Networks

Convolutional neural networks (CNNs) are becoming more and more important for solving challenging and critical problems in many fields. CNN inference applications have been deployed in safety-critical systems, which may suffer from soft errors caused by high-energy particles, high temperature, or abnormal voltage. Of critical importance is ensuring the stability of the CNN inference process against soft errors. Traditional fault tolerance methods are not suitable for CNN inference because error-correcting code is unable to protect computational components, instruction duplication techniques incur high overhead, and existing algorithm-based fault tolerance (ABFT) techniques cannot protect all convolution implementations. In this paper, we focus on how to protect the CNN inference process against soft errors as efficiently as possible, with the following three contributions. (1) We propose several systematic ABFT schemes based on checksum techniques and analyze their fault protection ability and runtime thoroughly. Unlike traditional ABFT based on matrix-matrix multiplication, our schemes support any convolution implementations. (2) We design a novel workflow integrating all the proposed schemes to obtain a high detection/correction ability with limited total runtime overhead. (3) We perform our evaluation using ImageNet with well-known CNN models including AlexNet, VGG-19, ResNet-18, and YOLOv2. Here, experimental results demonstrate that our implementation can handle soft errors with very limited runtime overhead (4%~8% in both error-free and error-injected situations).

97 MATHEMATICS AND COMPUTING↗

Algorithm-Based Fault Tolerance for Numerical Subroutines

A software library implements a new methodology of detecting faults in numerical subroutines, thus enabling application programs that contain the subroutines to recover transparently from single-event upsets. The software library in question is fault-detecting middleware that is wrapped around the numericalsubroutines. Conventional serial versions (based on LAPACK and FFTW) and a parallel version (based on ScaLAPACK) exist. The source code of the application program that contains the numerical subroutines is not modified, and the middleware is transparent to the user. The methodology used is a type of algorithm- based fault tolerance (ABFT). In ABFT, a checksum is computed before a computation and compared with the checksum of the computational result; an error is declared if the difference between the checksums exceeds some threshold. Novel normalization methods are used in the checksum comparison to ensure correct fault detections independent of algorithm inputs. In tests of this software reported in the peer-reviewed literature, this library was shown to enable detection of 99.9 percent of significant faults while generating no false alarms.

Tumon, Michael↗

An analysis of redundancy management algorithms for asynchronous fault tolerant control systems

Redundancy management algorithms, commonly referred to as voters, are algorithms used in fault-tolerant control systems to vote on incoming redundant data, isolate bad signals, and output a single good value. In a synchronous environment, this algorithm is a straightforward signal-to-signal comparison with relatively low complexity. The technology of asynchronous control systems, recently realized in the Ultrareliable Fault Tolerant Control System research program at NASA Ames Research Center, requires more complex algorithms for fault detection and signal selection. A variety of algorithms used for this process, a means of testing them, and their basic performance under a simulated environment of the ultrareliable fault-tolerant control system are presented.

Davis, Gloria J.↗

Fault-tolerant processing system

A fault-tolerant, fiber optic interconnect, or backplane, which serves as a via for data transfer between modules. Fault tolerance algorithms are embedded in the backplane by dividing the backplane into a read bus and a write bus and placing a redundancy management unit (RMU) between the read bus and the write bus so that all data transmitted by the write bus is subjected to the fault tolerance algorithms before the data is passed for distribution to the read bus. The RMU provides both backplane control and fault tolerance.

Palumbo, Daniel L.↗

Leveraging Qubit Loss Detection in Fault-Tolerant Quantum Algorithms

Qubit loss errors constitute a dominant source of noise in many quantum hardware systems, particularly in neutral-atom quantum computers. We develop a theoretical framework to effectively detect and correct loss errors in logical algorithms and leverage such loss information in decoding. Considering general quantum error correction codes and logical circuits, we introduce a delayed-erasure decoder for experimentally motivated error models which leverages information from delayed loss detection to accurately correct loss errors, even when the precise moment of the error is unknown. Using this decoder, we identify strategies for detecting and correcting loss errors based on the logical circuit structure. For deep circuits prior to logical measurement, we explore methods to integrate loss detection into syndrome extraction with minimal overhead, identifying optimal strategies depending on the qubit loss fraction in the noise and hardware capabilities. In contrast, we find that many key algorithmic subroutines involve frequent gate teleportation, shortening the circuit depth before logical measurement and naturally replacing qubits with no additional experimental overhead. We simulate this setting using a toy model algorithm for small-angle synthesis and find a significant performance improvement as the loss fraction increases. These results provide a path forward for advancing large-scale fault-tolerant quantum computation in systems with loss error detection.

atoms↗

Using Rollback Avoidance to Mitigate Failures in Next-Generation Extreme-Scale Systems

High-performance computing (HPC) systems enable scientists to numerically model complex phenomena in many important physical systems. The next major milestone in the development of HPC systems is the construction of the rst supercomputer capable executing more than an exa op, 10 18 oating point operations per second. On systems of this scale, failures will occur much more frequently than on current systems. As a result, resilience is a key obstacle to building next-generation extremescale systems. Coordinated checkpointing is currently the most widely-used mechanism for handling failures on HPC systems. Although coordinated checkpointing remains e ective on current systems, increasing the scale of today's systems to build next-generation systems will increase the cost of fault tolerance as more and more time is taken away from the application to protect against or recover from failure. Rollback avoidance techniques seek to mitigate the cost of checkpoint/restart by allowing an application to continue its execution rather than rolling back to an earlier checkpoint when failures occur. These techniqes include failure prediction and preventive migration, replicated computation, fault-tolerant algorithms, and softwarebased memory fault correction. In this thesis, we examine how rollback avoidance techniques can be used to address failures on extreme-scale systems. Using a combination of analytic modeling and simulation, we evaluate the potential impact of rollback avoidance on these systems. We then present a novel rollback avoidance technique that exploits similarities in application memory. Finally, we examine the feasibility of using this technique to protect against memory faults in kernel memory.

97 MATHEMATICS AND COMPUTING↗

Formal verification of algorithms for critical systems

We describe our experience with formal, machine-checked verification of algorithms for critical applications, concentrating on a Byzantine fault-tolerant algorithm for synchronizing the clocks in the replicated computers of a digital flight control system. First, we explain the problems encountered in unsynchronized systems and the necessity, and criticality, of fault-tolerant synchronization. We give an overview of one such algorithm, and of the arguments for its correctness. Next, we describe a verification of the algorithm that we performed using our EHDM system for formal specification and verification. We indicate the errors we found in the published analysis of the algorithm, and other benefits that we derived from the verification. Based on our experience, we derive some key requirements for a formal specification and verification system adequate to the task of verifying algorithms of the type considered. Finally, we summarize our conclusions regarding the benefits of formal verification in this domain, and the capabilities required of verification systems in order to realize those benefits.

Rushby, John M.↗

A Self-Stabilizing Hybrid Fault-Tolerant Synchronization Protocol

This paper presents a strategy for solving the Byzantine general problem for self-stabilizing a fully connected network from an arbitrary state and in the presence of any number of faults with various severities including any number of arbitrary (Byzantine) faulty nodes. The strategy consists of two parts: first, converting Byzantine faults into symmetric faults, and second, using a proven symmetric-fault tolerant algorithm to solve the general case of the problem. A protocol (algorithm) is also present that tolerates symmetric faults, provided that there are more good nodes than faulty ones. The solution applies to realizable systems, while allowing for differences in the network elements, provided that the number of arbitrary faults is not more than a third of the network size. The only constraint on the behavior of a node is that the interactions with other nodes are restricted to defined links and interfaces. The solution does not rely on assumptions about the initial state of the system and no central clock nor centrally generated signal, pulse, or message is used. Nodes are anonymous, i.e., they do not have unique identities. A mechanical verification of a proposed protocol is also present. A bounded model of the protocol is verified using the Symbolic Model Verifier (SMV). The model checking effort is focused on verifying correctness of the bounded model of the protocol as well as confirming claims of determinism and linear convergence with respect to the self-stabilization period.

Malekpour, Mahyar R.↗