Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “fault tolerant computing”

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 919 records · Page 51

Evaluating Online Global Recovery with Fenix Using Application-Aware In-Memory Checkpointing Techniques

Exascale systems promise the potential for computation at unprecedented scales and resolutions, but achieving exascale by the end of this decade presents significant challenges. A key challenge is due to the very large number of cores and components and the resulting mean time between failures (MTBF) in the order of hours or minutes. Since the typical run times of target scientific applications are longer than this MTBF, fault tolerance techniques will be essential. An important class of failures that must be addressed is process or node failures. While checkpoint/restart (C/R) is currently the most widely accepted technique for addressing processor failures, coordinated, stable-storage-based global C/R might be unfeasible at exascale when the time to checkpoint exceeds the expected MTBF. This paper explores transparent recovery via implicitly coordinated, diskless, application-driven checkpointing as a way to tolerate process failures in MPI applications at exascale. The discussed approach leverages User Level Failure Mitigation (ULFM), which is being proposed as an MPI extension to allow applications to create policies for tolerating process failures. Specifically, this paper demonstrates how different implementations of application-driven in-memory checkpoint storage and recovery compare in terms of performance and scalability. We also experimentally evaluate the effectiveness and scalability of the Fenix online global recovery framework on a production system -the Titan Cray XK7 at ORNL- and demonstrate the ability of Fenix to tolerate dynamically injected failures using the execution of four benchmarks and mini-applications with different behaviors.

97 MATHEMATICS AND COMPUTING↗

TTEthernet for Integrated Spacecraft Networks

Aerospace projects have traditionally employed federated avionics architectures, in which each computer system is designed to perform one specific function (e.g. navigation). There are obvious downsides to this approach, including excessive weight (from so much computing hardware), and inefficient processor utilization (since modern processors are capable of performing multiple tasks). There has therefore been a push for integrated modular avionics (IMA), in which common computing platforms can be leveraged for different purposes. This consolidation of multiple vehicle functions to shared computing platforms can significantly reduce spacecraft cost, weight, and design complexity. However, the application of IMA principles introduces significant challenges, as the data network must accommodate traffic of mixed criticality and performance levels - potentially all related to the same shared computer hardware. Because individual network technologies are rarely so competent, the development of truly integrated network architectures often proves unreasonable. Several different types of networks are utilized - each suited to support a specific vehicle function. Critical functions are typically driven by precise timing loops, requiring networks with strict guarantees regarding message latency (i.e. determinism) and fault-tolerance. Alternatively, non-critical systems generally employ data networks prioritizing flexibility and high performance over reliable operation. Switched Ethernet has seen widespread success filling this role in terrestrial applications. Its high speed, flexibility, and the availability of inexpensive commercial off-the-shelf (COTS) components make it desirable for inclusion in spacecraft platforms. Basic Ethernet configurations have been incorporated into several preexisting aerospace projects, including both the Space Shuttle and International Space Station (ISS). However, classical switched Ethernet cannot provide the high level of network determinism required by real-time spacecraft applications. Even with modern advancements, the uncoordinated (i.e. event-driven) nature of Ethernet communication unavoidably leads to message contention within network switches. The arbitration process used to resolve such conflicts introduces variation in the time it takes for messages to be forwarded. TTEthernet1 introduces decentralized clock synchronization to switched Ethernet, enabling message transmission according to a time-triggered (TT) paradigm. A network planning tool is used to allocate each device a finite amount of time in which it may transmit a frame. Each time slot is repeated sequentially to form a periodic communication schedule that is then loaded onto each TTEthernet device (e.g. switches and end systems). Each network participant references the synchronized time in order to dispatch messages at predetermined instances. This schedule guarantees that no contention exists between time-triggered Ethernet frames in the network switches, therefore eliminating the need for arbitration (and the timing variation it causes). Besides time-triggered messaging, TTEthernet networks may provide two additional traffic classes to support communication of different criticality levels. In the rate-constrained (RC) traffic class, the frame payload size and rate of transmission along each communication channel are limited to predetermined maximums. The network switches can therefore be configured to accommodate the known worst-case traffic pattern, and buffer overflows can be eliminated. The best-effort (BE) traffic class behaves akin to classical Ethernet. No guarantees are provided regarding transmission latency or successful message delivery. TTEthernet coordinates transmission of all three traffic classes over the same physical connections, therefore accommodating the full spectrum of traffic criticality levels required in IMA architectures. Common computing platforms (e.g. LRUs) can share networking resources in such a way that failures in non-critical systems (using BE or RC communication modes) cannot impact flight-critical functions (using TT communication). Furthermore, TTEthernet hardware (e.g. switches, cabling) can be shared by both TTEthernet and classical Ethernet traffic.

Loveless, Andrew↗

Feed-Forward Compensation for Model Predictive Control in Tri-port Current-Source Medium-Voltage String Inverters for PV-Plus-Storage Farms

The novel tri-port current-source medium-voltage string inverter (TCS-MVSI) is a promising candidate for large-scale PV-plus-storage (PVS) farms owing to its galvanic isolation, easy storage integration, soft-switching capability across entire load range, controlled low dv/dt and EMI, benign fault tolerance, etc. Due to its low inertia feature, traditional PI-based control cannot manage large transients effectively. Instead, a model-based predictive control (MPC) is proposed to achieve robust and stable operation. As is well known, the control performance of MPC is compromised by the sampling and computational delay during implementation significantly, if not well addressed. This paper analyzed and quantified these delays and then proposes feed-forward compensation (FFC) for the MPC method to compensate the delays and the large parameter variations due to the low-inertia nature. In addition, this method also compensates for the high dc-link ripple within each switching cycle, a unique issue for low-inertia converters. Here, the proposed method requires low computational effort, allowing it to be extended for multiple ports. The effectiveness of the proposed method has been validated in experiments. In 10 kW test, the proposed method decreases the average dc-link current by 17%, leading to ~20% conduction losses and ~0.5% increase in converter efficiency. In addition, the peak dc-link current also decreases by 15%, resulting in reduced transformer size. As a result, an increased power density can be achieved with the proposed method. Similar improvements have been observed across the power range from 2 kW to 10 kW.

30 DIRECT ENERGY CONVERSION↗

Proteins with Novel Structure, Function and Dynamics

Recently, a small enzyme that ligates two RNA fragments with the rate of 10(exp 6) above background was evolved in vitro (Seelig and Szostak, Nature 448:828‐831, 2007). This enzyme does not resemble any contemporary protein (Chao et al., Nature Chem. Biol. 9:81‐83, 2013). It consists of a dynamic, catalytic loop, a small, rigid core containing two zinc ions coordinated by neighboring amino acids, and two highly flexible tails that might be unimportant for protein function. In contrast to other proteins, this enzyme does not contain ordered secondary structure elements, such as alpha‐helix or beta‐sheet. The loop is kept together by just two interactions of a charged residue and a histidine with a zinc ion, which they coordinate on the opposite side of the loop. Such structure appears to be very fragile. Surprisingly, computer simulations indicate otherwise. As the coordinating, charged residue is mutated to alanine, another, nearby charged residue takes its place, thus keeping the structure nearly intact. If this residue is also substituted by alanine a salt bridge involving two other, charged residues on the opposite sides of the loop keeps the loop in place. These adjustments are facilitated by high flexibility of the protein. Computational predictions have been confirmed experimentally, as both mutants retain full activity and overall structure. These results challenge our notions about what is required for protein activity and about the relationship between protein dynamics, stability and robustness. We hypothesize that small, highly dynamic proteins could be both active and fault tolerant in ways that many other proteins are not, i.e. they can adjust to retain their structure and activity even if subjected to mutations in structurally critical regions. This opens the doors for designing proteins with novel functions, structures and dynamics that have not been yet considered.

Proteins↗

Designing and Evaluating Redundancy-Based Soft-Error Masking on a Continuum of Energy versus Robustness

Near-threshold computing is an effective strategy to reduce the power dissipation of deeply-scaled CMOS logic circuits. However, near-threshold strategies exacerbate the impact of delay variations on device performance and increase the susceptibility to soft errors due to narrow voltage margins. The objective of this work is to develop and assess design approaches that leverage tradeoffs between performance and the resilience of fault masking coverage for various soft-error mitigation techniques. The primary insight from this work is identification of redundancy-based hardening techniques that can deliver increased benefits in terms of the fault coverage energy ratio (FCER) for the leveraged tradeoffs within iso-energy constraints at near-threshold voltage (NTV). Simulation results demonstrate that temporal redundancy approaches offer favorable tradeoffs in terms of FCER. They exhibit reduced impact on performance variations and achieve extensive soft fault masking, therefore improving the system robustness within acceptable delay constraints. Meanwhile, it is shown that a hybrid redundancy approach can be used to protect a low-power system to maintain throughput while tolerating soft errors. We demonstrate how the FCER metric can be used as an optimization parameter to guide circuit synthesis to meet performance and robustness goals. Lastly, the impact of design diversity on spatial and hybrid redundancy at NTV is assessed in terms of FCER and delay variation to form overall recommendations regarding soft-error mitigation at NTV.

97 MATHEMATICS AND COMPUTING↗

Analyzing Prospects for Quantum Advantage in Topological Data Analysis

Lloyd [Nat. Commun. , 10138 (2016)] were first to demonstrate the promise of quantum algorithms for computing Betti numbers, a way to characterize topological features of data sets. Here, we propose, analyze, and optimize an improved quantum algorithm for topological data analysis (TDA) with reduced scaling, including a method for preparing Dicke states based on inequality testing, a more efficient amplitude estimation algorithm using Kaiser windows, and an optimal implementation of eigenvalue projectors based on Chebyshev polynomials. We compile our approach to a fault-tolerant gate set and estimate constant factors in the Toffoli complexity. Our analysis reveals that superquadratic quantum speedups are only possible for this problem when targeting a multiplicative error approximation and the Betti number grows asymptotically. Further, we propose a dequantization of the quantum TDA algorithm that shows that having exponentially large dimension and Betti number are necessary, but insufficient conditions, for superpolynomial advantage. We then introduce and analyze specific problem examples which have parameters in the regime where superpolynomial advantages may be achieved, and argue that quantum circuits with tens of billions of Toffoli gates can solve seemingly classically intractable instances. Published by the American Physical Society 2024

97 MATHEMATICS AND COMPUTING↗

The development and demonstration of hybrid programmable attitude control electronics

In the course of extended life attitude control system (ELACS) research sponsored by NASA a hybrid programable attitude control electronics (HYPACE) concept was developed and demonstrated. The wide variety of future planetary missions demanded a new control approach to accommodate the automatic fault tolerance and long the life requirements of such missions. HYPACE provides an adaptable, analog/digital design approach that permits preflight and in-flight accommodation of mission changes, component performance variations, and spacecraft changes, through programing. This enabled broad multimission flexibility of application in a cost effective manner. Previously, flight control computers have not been not flown on planetary missions because of weight and power problems. These problems were resolved in the design of HYPACE. The HYPACE design, which was demonstrated in breadboard form on a single-axis gas-bearing spacecraft simulation, uses a single control channel to perform the attitude control functions sequentially, thus significantly reducing the number of component parts over hard-wired designs.

Smith, L. S.↗

Specification of Fenix MPI Fault Tolerance library (V.0.9)

Fenix is a software library compatible with the Message Passing Interface (MPI) to support fault recovery without application shutdown. This specification is derived from a current implementation of Fenix that employs the User Level Fault Mitigation (ULFM) MPI fault tolerance module proposal. We only present the C library interface for Fenix; the Fortran interface will be added once the C version is complete.

97 MATHEMATICS AND COMPUTING↗

Constant-Overhead Fault-Tolerant Bell-Pair Distillation Using High-Rate Codes

We present a fault-tolerant Bell-pair distillation scheme achieving constant overhead through high-rate quantum low-density parity-check (qLDPC) codes. Our approach maintains a constant distillation rate equal to the code rate while requiring no additional overhead beyond the physical qubits of the code. Full circuit-level analysis demonstrates fault-tolerance for input Bell-pair infidelities below a threshold ∼10%, readily achievable with near-term capabilities. Unlike previous proposals, our scheme keeps the output Bell pairs encoded in qLDPC codes at each node, eliminating unencoding overhead and enabling direct use in distributed quantum applications through recent advances in qLDPC computation. These results establish qLDPC-based distillation as a practical route toward resource-efficient quantum networks and distributed quantum computing.

quantum communication, protocols & technology↗

Self-stabilizing Connected Components

For the problem of computing the connected components of a graph, this paper considers the design of algorithms that are resilient to transient hardware faults, like bit Hips. More specifically, it applies the technique of self-stabilization. A system is self-stabilizing if, when starting from a valid or invalid state, it is guaranteed to reach a valid state after a finite number of steps. Therefore on a machine subject to a transient fault, a self-stabilizing algorithm could recover if that fault caused the system to enter an invalid state. We give a comprehensive analysis of the valid and invalid states during label propagation and derive algorithms to verify and correct the invalid state. The self-stabilizing label-propagation algorithm performs O (V log V) additional computation and requires O (V) additional storage over its conventional counterpart (and, as such, does not increase asymptotic complexity over conventional label propagation). When run against a battery of simulated fault injection tests, the self-stabilizing label propagation algorithm exhibits more resilient behavior than a triple modular redundancy (TMR) based fault-tolerant algorithm in 80% of cases. From a performance perspective, it also outperforms TMR as it requires fewer iterations in total. Beyond the fault tolerance properties of self-stabilizing label-propagation, we believe, they are useful from the theoretical perspective; and may have other use-cases.

Sao, Piyush↗

Science Application Teams

This paper discusses the science application team activities. Science Application team are: (1) Represent the diversity of NASA onboard computing of the future. (2) Drive architecture and system software requirements. (3) Demonstrate the benefit of highly capable computing onboard. (4) Study the birth of the first galaxies. (5) Study formation of stars. (6) Discusses the next generation space telescope hardware/software requirement: image processing and on-board optical calibration. Also discusses gamma ray large area space telescope; orbital thermal imaging spectrometer; solar terrestrial probe program; autonomous Mars rover;fault tolerance and errors.

Source record↗

Highly reliable processor system for space application.

Description of a redundant processor organization which can be implemented with off-the-shelf processors for fault-tolerant operation. Reconfiguration can be performed automatically in a transientless manner. To support this system configuration and redundancy management concept, an operating system referred to as a synchronous executive has been designed. This system is directed at real-time closed-loop space applications where minimum response time, no degradation of software solution, and system simplicity are of importance. The system is based on a multicomputer organization with each machine solving the same problem based on a common set of inputs. Processor status is fed to a higher-level device which selects a controlling processor for controlling outputs and monitoring computers for fault detection.

Tsou, H. S. E.↗

Adaptive Client Selection in Federated Learning: A Network Anomaly Detection Use Case

Federated Learning (FL) has become a ubiquitous approach for training machine learning models on decentralized data, addressing the myriad privacy concerns inherent in traditional centralized methods. However, the efficiency of FL depends on effective client selection and robust privacy preservation mechanisms. Inadequate client selection may lead to suboptimal model performance, while insufficient privacy measures risk exposing sensitive data. This paper proposes a client selection framework for FL that integrates differential privacy and fault tolerance. Our adaptive approach dynamically adjusts the number of selected clients based on model performance and system constraints, ensuring privacy through calibrated noise addition. We evaluate our method on a network anomaly detection use case using the UNSW-NB15 and ROAD datasets. Results show up to a 7% increase in accuracy and a 25% reduction in training time compared to FedL2P. Moreover, we highlight the trade-offs between privacy budgets and model performance, with higher privacy budgets reducing noise and improving accuracy. Our fault tolerance mechanism, while causing a slight performance drop, enhances robustness to client failures. Statistical validation using Mann-Whitney U tests confirms the significance of these improvements (p < 0.05).

Marfo, William [University of Texas at El Paso,Dep↗

High performance flight computer developed for deep space applications

The development of an advanced space flight computer for real time embedded deep space applications which embodies the lessons learned on Galileo and modern computer technology is described. The requirements are listed and the design implementation that meets those requirements is described. The development of SPACE-16 (Spaceborne Advanced Computing Engine) (where 16 designates the databus width) was initiated to support the MM2 (Marine Mark 2) project. The computer is based on a radiation hardened emulation of a modern 32 bit microprocessor and its family of support devices including a high performance floating point accelerator. Additional custom devices which include a coprocessor to improve input/output capabilities, a memory interface chip, and an additional support chip that provide management of all fault tolerant features, are described. Detailed supporting analyses and rationale which justifies specific design and architectural decisions are provided. The six chip types were designed and fabricated. Testing and evaluation of a brass/board was initiated.

Bunker, Robert L.↗

Scientific Data Services -- A High-Performance I/O System with Array Semantics

As high-performance computing approaches exascale, the existing I/O system design is having trouble keeping pace in both performance and scalability. We propose to address this challenge by adopting database principles and techniques in parallel I/O systems. First, we propose to adopt an array data model because many scientific applications represent their data in arrays. This strategy follows a cardinal principle from database research, which separates the logical view from the physical layout of data. This high-level data model gives the underlying implementation more freedom to optimize the physical layout and to choose the most effective way of accessing the data. For example, knowing that a set of write operations is working on a single multi-dimensional array makes it possible to keep the subarrays in a log structure during the write operations and reassemble them later into another physical layout as resources permit. While maintaining the high-level view, the storage system could compress the user data to reduce the physical storage requirement, collocate data records that are frequently used together, or replicate data to increase availability and fault-tolerance. Additionally, the system could generate secondary data structures such as database indexes and summary statistics. We expect the proposed Scientific Data Services approach to create a “live” storage system that dynamically adjusts to user demands and evolves with the massively parallel storage hardware.

97 MATHEMATICS AND COMPUTING↗

Scattering Processes from Quantum Simulation Algorithms for Scalar Field Theories

We provide practical simulation methods for scalar field theories on a quantum computer that yield improved asymptotics as well as concrete gate estimates for the simulation and physical qubit estimates using the surface code. We achieve these improvements through two optimizations. First, we consider a finite volume approach for estimating the elements of the S-matrix. This approach is appropriate in general for 1+1D and for certain low-energy elastic collisions in higher dimensions. Second, we implement our approach using a series of different fault-tolerant simulation algorithms for Hamiltonians formulated both in the field occupation basis and field amplitude basis. Our algorithms are based on either second-order Trotterization or qubitization. The cost of Trotterization in occupation basis scales as O ( λ N 7 | Ω | 3 / ( M 5 / 2 ϵ 3 / 2 ) ) where λ is the coupling strength, N is the occupation cutoff, | Ω | is the volume of the spatial lattice, M is the mass of the particles and ϵ is the uncertainty in the energy calculation used for the S -matrix determination. Qubitization in the field basis scales as O ( | Ω | 2 ( k 2 Λ + k M 2 ) / ϵ ) , where k is the cutoff in the field and Λ is a scaled coupling constant. We find in both cases that the bounds suggest physically meaningful simulations can be performed using on the order of 4 × 10 6 physical qubits and 10 12 T -gates which corresponds to roughly one day on a superconducting quantum computer with surface code and a cycle time of 100 ns. This places the simulation of scalar field theory within striking distance of the gate counts for the best available chemistry simulation results.

Hardy, Andrew [Toronto U.] (ORCID:0000000235817382↗

The application of emulation techniques in the analysis of highly reliable, guidance and control computer systems

Emulation techniques can be a solution to a difficulty that arises in the analysis of the reliability of guidance and control computer systems for future commercial aircraft. Described here is the difficulty, the lack of credibility of reliability estimates obtained by analytical modeling techniques. The difficulty is an unavoidable consequence of the following: (1) a reliability requirement so demanding as to make system evaluation by use testing infeasible; (2) a complex system design technique, fault tolerance; (3) system reliability dominated by errors due to flaws in the system definition; and (4) elaborate analytical modeling techniques whose precision outputs are quite sensitive to errors of approximation in their input data. Use of emulation techniques for pseudo-testing systems to evaluate bounds on the parameter values needed for the analytical techniques is then discussed. Finally several examples of the application of emulation techniques are described.

Migneault, Gerard E.↗

Lessons Learned in Deploying the World s Largest Scale Lustre File System

The Spider system at the Oak Ridge National Laboratory's Leadership Computing Facility (OLCF) is the world's largest scale Lustre parallel file system. Envisioned as a shared parallel file system capable of delivering both the bandwidth and capacity requirements of the OLCF's diverse computational environment, the project had a number of ambitious goals. To support the workloads of the OLCF's diverse computational platforms, the aggregate performance and storage capacity of Spider exceed that of our previously deployed systems by a factor of 6x - 240 GB/sec, and 17x - 10 Petabytes, respectively. Furthermore, Spider supports over 26,000 clients concurrently accessing the file system, which exceeds our previously deployed systems by nearly 4x. In addition to these scalability challenges, moving to a center-wide shared file system required dramatically improved resiliency and fault-tolerance mechanisms. This paper details our efforts in designing, deploying, and operating Spider. Through a phased approach of research and development, prototyping, deployment, and transition to operations, this work has resulted in a number of insights into large-scale parallel file system architectures, from both the design and the operational perspectives. We present in this paper our solutions to issues such as network congestion, performance baselining and evaluation, file system journaling overheads, and high availability in a system with tens of thousands of components. We also discuss areas of continued challenges, such as stressed metadata performance and the need for file system quality of service alongside with our efforts to address them. Finally, operational aspects of managing a system of this scale are discussed along with real-world data and observations.

99 GENERAL AND MISCELLANEOUS↗