Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computer hardware”

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 793 records · Page 44

Automated Software for Manned Spacecraft - Bridging the Gap from Sci Fi to Reality

With a voice command or a few taps on the console, the spacecraft pivots on a dime at high velocity and gently docks to an orbiting space platform. This is the image most people have of the complex software computations and integrated hardware performance necessary for a spacecraft to successfully perform an automated launch, rendezvous, and docking. Today’s reality is that while computer operations are advancing rapidly, science fiction over-simplifies and over-sells current capabilities. This paper discusses the integration of spacecraft computer automation into the operation of one of the United States’ new Commercial Crew vehicles - the Boeing CST-100 Starliner. Lessons learned by the Boeing Mission Operations team, a private-public partnership with NASA, from conceptual design through real-time operation of the first test flight will be discussed. Focus will center on how operations has learned to use the automated software to their advantage while also knowing how to adjust the automation in response to spacecraft or mission anomalies. One goal of advanced spacecraft automation is the ability to reduce both the crew workload and the ground control footprint while at the same time increasing spacecraft and mission flexibility. Historically, crewed spacecraft required a large number of operators on the ground to use a plethora of tools to compute nominal and contingency mission trajectories. Moving those sophisticated software tools to being onboard the vehicle can reduce the need for such complex ground support. Given that today’s spacecraft software is not yet as capable or as flexible in all circumstances as the computers depicted in movies, there is usually a trade-off between software automation cost and the flexibility of that software resulting in a trade-off between what is performed on the spacecraft and what is left to onboard crew or ground control. For missions that go beyond the Moon, software that autonomously controls nearly every aspect of a crewed mission will become a necessity given the long time delays between the spacecraft and Earth’s ground control teams. The lessons learned by Boeing and its Mission Operations team, through the design and implementation of Starliner’s hardware and software automation, will be able to inform future public and private spacecraft design. As the technologies and capabilities evolve, incorporating lessons learned in successful low Earth orbit commercial crew vehicle missions, spacecraft designs will continue to improve and be able to better enable safe execution of human missions to the Moon and beyond.

Robert C Dempsey↗

Automated Software for Manned Spacecraft - Bridging the Gap from Sci Fi to Reality

With a voice command or a few taps on the console, the spacecraft pivots on a dime at high velocity and gently docks to an orbiting space platform. This is the image most people have of the complex software computations and integrated hardware performance necessary for a spacecraft to successfully perform an automated launch, rendezvous, and docking. Today’s reality is that while computer operations are advancing rapidly, science fiction over-simplifies and over-sells current capabilities. This paper discusses the integration of spacecraft computer automation into the operation of one of the United States’ new Commercial Crew vehicles - the Boeing CST-100 Starliner. Lessons learned by the Boeing Mission Operations team, a private-public partnership with NASA, from conceptual design through real-time operation of the first test flight will be discussed. Focus will center on how operations has learned to use the automated software to their advantage while also knowing how to adjust the automation in response to spacecraft or mission anomalies. One goal of advanced spacecraft automation is the ability to reduce both the crew workload and the ground control footprint while at the same time increasing spacecraft and mission flexibility. Historically, crewed spacecraft required a large number of operators on the ground to use a plethora of tools to compute nominal and contingency mission trajectories. Moving those sophisticated software tools to being onboard the vehicle can reduce the need for such complex ground support. Given that today’s spacecraft software is not yet as capable or as flexible in all circumstances as the computers depicted in movies, there is usually a trade-off between software automation cost and the flexibility of that software resulting in a trade-off between what is performed on the spacecraft and what is left to onboard crew or ground control. For missions that go beyond the Moon, software that autonomously controls nearly every aspect of a crewed mission will become a necessity given the long time delays between the spacecraft and Earth’s ground control teams. The lessons learned by Boeing and its Mission Operations team, through the design and implementation of Starliner’s hardware and software automation, will be able to inform future public and private spacecraft design. As the technologies and capabilities evolve, incorporating lessons learned in successful low Earth orbit commercial crew vehicle missions, spacecraft designs will continue to improve and be able to better enable safe execution of human missions to the Moon and beyond.

Robert C. Dempsey↗

Automated Software for Crewed Spacecraft - Bridging the Gap from Sci Fi to Reality

With a voice command or a few taps on the console, the spacecraft pivots on a dime at high velocity and gently docks to an orbiting space platform. This is the image most people have of the complex software computations and integrated hardware performance necessary for a spacecraft to successfully perform an automated launch, rendezvous, and docking. Today’s reality is that while computer operations are advancing rapidly, science fiction over-simplifies and over-sells current capabilities. This paper discusses the integration of spacecraft computer automation into the operation of one of the United States’ new Commercial Crew vehicles - the Boeing CST-100 Starliner. Lessons learned by the Boeing Mission Operations team, a private-public partnership with NASA, from conceptual design through real-time operation of the first test flight will be discussed. Focus will center on how operations has learned to use the automated software to their advantage while also knowing how to adjust the automation in response to spacecraft or mission anomalies. One goal of advanced spacecraft automation is the ability to reduce both the crew workload and the ground control footprint while at the same time increasing spacecraft and mission flexibility. Historically, crewed spacecraft required a large number of operators on the ground to use a plethora of tools to compute nominal and contingency mission trajectories. Moving those sophisticated software tools to being onboard the vehicle can reduce the need for such complex ground support. Given that today’s spacecraft software is not yet as capable or as flexible in all circumstances as the computers depicted in movies, there is usually a trade-off between software automation cost and the flexibility of that software resulting in a trade-off between what is performed on the spacecraft and what is left to onboard crew or ground control. For missions that go beyond the Moon, software that autonomously controls nearly every aspect of a crewed mission will become a necessity given the long time delays between the spacecraft and Earth’s ground control teams. The lessons learned by Boeing and its Mission Operations team, through the design and implementation of Starliner’s hardware and software automation, will be able to inform future public and private spacecraft design. As the technologies and capabilities evolve, incorporating lessons learned in successful low Earth orbit commercial crew vehicle missions, spacecraft designs will continue to improve and be able to better enable safe execution of human missions to the Moon and beyond.

Robert C Dempsey↗

Comparative Study of Variations in Quantum Approximate Optimization Algorithms for the Traveling Salesman Problem

The traveling salesman problem (TSP) is one of the most often-used NP-hard problems in computer science to study the effectiveness of computing models and hardware platforms. In this regard, it is also heavily used as a vehicle to study the feasibility of the quantum computing paradigm for this class of problems. In this paper, we tackle the TSP using the quantum approximate optimization algorithm (QAOA) approach by formulating it as an optimization problem. By adopting an improved qubit encoding strategy and a layer-wise learning optimization protocol, we present numerical results obtained from the gate-based digital quantum simulator, specifically targeting TSP instances with 3, 4, and 5 cities. We focus on the evaluations of three distinctive QAOA mixer designs, considering their performances in terms of numerical accuracy and optimization cost. Notably, we find that a well-balanced QAOA mixer design exhibits more promising potential for gate-based simulators and realistic quantum devices in the long run, an observation further supported by our noise model simulations. Furthermore, we investigate the sensitivity of the simulations to the TSP graph. Overall, our simulation results show that the digital quantum simulation of problem-inspired ansatz is a successful candidate for finding optimal TSP solutions.

97 MATHEMATICS AND COMPUTING↗

Applications of Modeling and Simulation for Flight Hardware Processing at Kennedy Space Center

The Boeing Design Visualization Group (DVG) is responsible for the creation of highly-detailed representations of both on-site facilities and flight hardware using computer-aided design (CAD) software, with a focus on the ground support equipment (GSE) used to process and prepare the hardware for space. Throughout my ten weeks at this center, I have had the opportunity to work on several projects: the modification of the Multi-Payload Processing Facility (MPPF) High Bay, weekly mapping of the Space Station Processing Facility (SSPF) floor layout, kinematics applications for the Orion Command Module (CM) hatches, and the design modification of the Ares I Upper Stage hatch for maintenance purposes. The main goal of each of these projects was to generate an authentic simulation or representation using DELMIA V5 software. This allowed for evaluation of facility layouts, support equipment placement, and greater process understanding once it was used to demonstrate future processes to customers and other partners. As such, I have had the opportunity to contribute to a skilled team working on diverse projects with a central goal of providing essential planning resources for future center operations.

Marshall, Jennifer L.↗

Global Benefits: the LBNF/DUNE Project

LBNF/DUNE is an international mega-science project hosted by the Department of Energy’s Fermilab. http://www.fnal.gov/dune It will send a beam of tiny particles called neutrinos 1,300 kilometers straight through the earth from Fermilab to the Sanford Underground Research Facility. It will help solve some of the deepest mysteries of the universe and boost innovation while training young people around the world in science, engineering and computing. Scientists and engineers at universities and laboratories are working hand-in-hand with companies to design electronics, build hardware and develop computer programs for the project. LBNF and DUNE will create jobs as well as demand for materials, products and services. Students in dozens of countries around the world will start their careers in science and engineering with this project, and then transfer their knowledge into industry, medicine, computer science and many other fields.

43 PARTICLE ACCELERATORS↗

Evaluation of Portable Acceleration Solutions for LArTPC Simulation Using Wire-Cell Toolkit

The Liquid Argon Time Projection Chamber (LArTPC) technology plays an essential role in many current and future neutrino experiments. Accurate and fast simulation is critical to developing efficient analysis algorithms and precise physics model projections. The speed of simulation becomes more important as Deep Learning algorithms are getting more widely used in LArTPC analysis and their training requires a large simulated dataset. Heterogeneous computing is an efficient way to delegate computationally intensive tasks to specialized hardware. However, as the landscape of compute accelerators quickly evolves, it becomes increasingly difficult to manually adapt the code to the latest hardware or software environments. A solution which is portable to multiple hardware architectures without substantially compromising performance would thus be very beneficial, especially for long-term projects such as the LArTPC simulations. In search of a portable, scalable and maintainable software solution for LArTPC simulations, we have started to explore high-level portable programming frameworks that support several hardware backends. In this paper, we present our experience porting the LArTPC simulation code in the Wire-Cell Toolkit to NVIDIA GPUs, first with the CUDA programming model and then with a portable library called Kokkos. Preliminary performance results on NVIDIA V100 GPUs and multi-core CPUs are presented, followed by a discussion of the factors affiecting the performance and plans for future improvements.

Yu, Haiwang↗

Distributed computing environments for future space control systems

The aim of this paper is to present the results of a CNES research project on distributed computing systems. The purpose of this research was to study the impact of the use of new computer technologies in the design and development of future space applications. The first part of this study was a state-of-the-art review of distributed computing systems. One of the interesting ideas arising from this review is the concept of a 'virtual computer' allowing the distributed hardware architecture to be hidden from a software application. The 'virtual computer' can improve system performance by adapting the best architecture (addition of computers) to the software application without having to modify its source code. This concept can also decrease the cost and obsolescence of the hardware architecture. In order to verify the feasibility of the 'virtual computer' concept, a prototype representative of a distributed space application is being developed independently of the hardware architecture.

Viallefont, Pierre↗

Automated Software for Crewed Spacecraft - Bridging the Gap from Sci Fi to Reality

With a voice command or a few taps on the console, the spacecraft pivots on a dime at high velocity and gently docks to an orbiting space platform. This is the image most people have of the complex software computations and integrated hardware performance necessary for a spacecraft to successfully perform an automated launch, rendezvous, and docking. Today’s reality is that while computer operations are advancing rapidly, science fiction over-simplifies and over-sells current capabilities. This paper discusses the integration of spacecraft computer automation into the operation of one of the United States’ new Commercial Crew vehicles - the Boeing CST-100 Starliner. Lessons learned by the Boeing Mission Operations team, a unique private-public partnership with NASA, from conceptual design through real-time operation of the first test flight will be discussed along with evolution of the system in preparation for the second uncrewed test flight. Focus will center on how operations has learned to use the automated software to their advantage while also knowing how to adjust the automation in response to spacecraft or mission anomalies.

Robert C. Dempsey↗

Parallel Rendering of Large Time-Varying Volume Data

Interactive visualization of large time-varying 3D volume datasets has been and still is a great challenge to the modem computational world. It stretches the limits of the memory capacity, the disk space, the network bandwidth and the CPU speed of a conventional computer. In this SURF project, we propose to develop a parallel volume rendering program on SGI's Prism, a cluster computer equipped with state-of-the-art graphic hardware. The proposed program combines both parallel computing and hardware rendering in order to achieve an interactive rendering rate. We use 3D texture mapping and a hardware shader to implement 3D volume rendering on each workstation. We use SGI's VisServer to enable remote rendering using Prism's graphic hardware. And last, we will integrate this new program with ParVox, a parallel distributed visualization system developed at JPL. At the end of the project, we Will demonstrate remote interactive visualization using this new hardware volume renderer on JPL's Prism System using a time-varying dataset from selected JPL applications.

Garbutt, Alexander E.↗

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗

Job Management with mpi_jm

About this book: This book constitutes the refereed post-conference proceedings of 13 workshops held at the 33rd International ISC High Performance 2018 Conference, in Frankfurt, Germany, in June 2018: HPC I/O in the Data Center, HPC-IODC 2018; Workshop on Performance and Scalability of Storage Systems, WOPSSS 2018; 13th Workshop on Virtualization in High­-Performance Cloud Computing, VHPC 2018; Third International Workshop on In Situ Visualization, WOIV 2018; 4th International Workshop on Communication Architectures for HPC, Big Data, Deep Learning and Clouds at Extreme Scale, ExaComm 2018; International Workshop on OpenPOWER for HPC, IWOPH 2018; IXPUG Workshop: Many-Core Computing on Intel Processors; Workshop on Sustainable Ultrascale Computing Systems; Approximate and Transprecision Computing on Emerging Technologies, ATCET 2018; First Workshop on the Convergence of Large-Scale Simulation and Artificial Intelligence; Third Workshop for Open Source Supercomputing, OpenSuCo 2018; First Workshop on Interactive High-Performance Computing; Workshop on Performance Portable Programming Models for Accelerators, P^3MA 2018. The 53 full papers included in this volume were carefully reviewed and selected from 80 submissions. They cover all aspects of research, development, and application of large-scale, high performance experimental and commercial systems. Topics include HPC computer architecture and hardware; programming models, system software, and applications; solutions for heterogeneity, reliability, power efficiency of systems; virtualization and containerized environments; big data and cloud computing; and artificial intelligence.

Berkowitz, Evan↗

Apollo experience report: Apollo lunar surface experiments package data processing system

Apollo Program experience in the processing of scientific data from the Apollo lunar surface experiments package, in which computers and associated hardware and software were used, is summarized. The facility developed for the preprocessing of the lunar science data is described, as are several computer facilities and programs used by the Principal Investigators. The handling, processing, and analyzing of lunar science data and the interface with the Principal Investigators are discussed. Pertinent problems that arose in the development of the data processing schemes are discussed so that future programs may benefit from the solutions to the problems. The evolution of the data processing techniques for lunar science data related to recommendations for future programs of this type.

Eason, R. L.↗

Integration of Ag-CBRAM crossbars and Mott ReLU neurons for efficient implementation of deep neural networks in hardware

In-memory computing with emerging non-volatile memory devices (eNVMs) has shown promising results in accelerating matrix-vector multiplications. However, activation function calculations are still being implemented with general processors or large and complex neuron peripheral circuits. Here, we present the integration of Ag-based conductive bridge random access memory (Ag-CBRAM) crossbar arrays with Mott rectified linear unit (ReLU) activation neurons for scalable, energy and area-efficient hardware (HW) implementation of deep neural networks. We develop Ag-CBRAM devices that can achieve a high ON/OFF ratio and multi-level programmability. Compact and energy-efficient Mott ReLU neuron devices implementing ReLU activation function are directly connected to the columns of Ag-CBRAM crossbars to compute the output from the weighted sum current. We implement convolution filters and activations for VGG-16 using our integrated HW and demonstrate the successful generation of feature maps for CIFAR-10 images in HW. Our approach paves a new way toward building a highly compact and energy-efficient eNVMs-based in-memory computing system.

Mott insulators↗

GPU-BASED MONTE CARLO DUST RADIATIVE TRANSFER SCHEME APPLIED TO ACTIVE GALACTIC NUCLEI

A three-dimensional parallel Monte Carlo (MC) dust radiative transfer code is presented. To overcome the huge computing-time requirements of MC treatments, the computational power of vectorized hardware is used, utilizing either multi-core computer power or graphics processing units. The approach is a self-consistent way to solve the radiative transfer equation in arbitrary dust configurations. The code calculates the equilibrium temperatures of two populations of large grains and stochastic heated polycyclic aromatic hydrocarbons. Anisotropic scattering is treated applying the Heney-Greenstein phase function. The spectral energy distribution (SED) of the object is derived at low spatial resolution by a photon counting procedure and at high spatial resolution by a vectorized ray tracer. The latter allows computation of high signal-to-noise images of the objects at any frequencies and arbitrary viewing angles. We test the robustness of our approach against other radiative transfer codes. The SED and dust temperatures of one- and two-dimensional benchmarks are reproduced at high precision. The parallelization capability of various MC algorithms is analyzed and included in our treatment. We utilize the Lucy algorithm for the optical thin case where the Poisson noise is high, the iteration-free Bjorkman and Wood method to reduce the calculation time, and the Fleck and Canfield diffusion approximation for extreme optical thick cells. The code is applied to model the appearance of active galactic nuclei (AGNs) at optical and infrared wavelengths. The AGN torus is clumpy and includes fluffy composite grains of various sizes made up of silicates and carbon. The dependence of the SED on the number of clumps in the torus and the viewing angle is studied. The appearance of the 10 {mu}m silicate features in absorption or emission is discussed. The SED of the radio-loud quasar 3C 249.1 is fit by the AGN model and a cirrus component to account for the far-infrared emission.

79 ASTRONOMY AND ASTROPHYSICS↗

Design of a microprocessor-based Control, Interface and Monitoring (CIM unit for turbine engine controls research

High speed minicomputers were used in the past to implement advanced digital control algorithms for turbine engines. These minicomputers are typically large and expensive. It is desirable for a number of reasons to use microprocessor-based systems for future controls research. They are relatively compact, inexpensive, and are representative of the hardware that would be used for actual engine-mounted controls. The Control, Interface, and Monitoring Unit (CIM) contains a microprocessor-based controls computer, necessary interface hardware and a system to monitor while it is running an engine. It is presently being used to evaluate an advanced turbofan engine control algorithm.

Delaat, J. C.↗

Using Likwid and Byfl to Benchmark Hardware Performance

This paper outlines a benchmarking study conducted during my internship at LANL, focusing on CPU (Computer Processing Unit) and program performance assessment. The primary goal was to gather memory access data using three methods across five polybench kernels The data gathered would then be used to compare and contrast to one another and calculate operational intensity for performance comparisons. Benchmarking tools like Byfl and Likwid were employed, with Byfl offering hardware-independent data through LLVM compiler communication and Likwid directly interacting with computer hardware. The study considered various benchmarking factors, including optimization levels, Big O notation ((n)), CPU diversity and specific kernel equations. Big O notation was utilized to simplify code complexity, with detailed breakdwons of operations and memory components for each polybench application. Specific O(n) equations enabled nuanced kernel compariosns, facilitating the identification of performance variations. CPU efficiency assessments were conducted using Likwid tests on two CPUs. The central focus on code optimization aimed at achieving higher speeds and reduced memory usage through streamlined code. Future work propsoes creating a roofline model, synthesizing benchmarking data into a comprehensive data graph to assist in optimizing code and improving hardware performance. The potential impact on the laboratory or national mission was underscored, emphasizing the importance of optimizing applications and hardware to conserve resources and accelerate program execution. The specific relevance to LANL’s operations in math-intensive fields such as Nuclear Fission, Space Exploration, and Nanotechnology highlights the necessity of efficient benchmarking for resource conservation and proram speed. Overall, this study contributes to the understanding of CPU and program performance, providing insights for future optimization efforts in a laboratory setting

97 MATHEMATICS AND COMPUTING↗

FPGA-Based, Self-Checking, Fault-Tolerant Computers

A proposed computer architecture would exploit the capabilities of commercially available field-programmable gate arrays (FPGAs) to enable computers to detect and recover from bit errors. The main purpose of the proposed architecture is to enable fault-tolerant computing in the presence of single-event upsets (SEUs). [An SEU is a spurious bit flip (also called a soft error) caused by a single impact of ionizing radiation.] The architecture would also enable recovery from some soft errors caused by electrical transients and, to some extent, from intermittent and permanent (hard) errors caused by aging of electronic components. A typical FPGA of the current generation contains one or more complete processor cores, memories, and highspeed serial input/output (I/O) channels, making it possible to shrink a board-level processor node to a single integrated-circuit chip. Custom, highly efficient microcontrollers, general-purpose computers, custom I/O processors, and signal processors can be rapidly and efficiently implemented by use of FPGAs. Unfortunately, FPGAs are susceptible to SEUs. Prior efforts to mitigate the effects of SEUs have yielded solutions that degrade performance of the system and require support from external hardware and software. In comparison with other fault-tolerant- computing architectures (e.g., triple modular redundancy), the proposed architecture could be implemented with less circuitry and lower power demand. Moreover, the fault-tolerant computing functions would require only minimal support from circuitry outside the central processing units (CPUs) of computers, would not require any software support, and would be largely transparent to software and to other computer hardware. There would be two types of modules: a self-checking processor module and a memory system (see figure). The self-checking processor module would be implemented on a single FPGA and would be capable of detecting its own internal errors. It would contain two CPUs executing identical programs in lock step, with comparison of their outputs to detect errors. It would also contain various cache local memory circuits, communication circuits, and configurable special-purpose processors that would use self-checking checkers. (The basic principle of the self-checking checker method is to utilize logic circuitry that generates error signals whenever there is an error in either the checker or the circuit being checked.) The memory system would comprise a main memory and a hardware-controlled check-pointing system (CPS) based on a buffer memory denoted the recovery cache. The main memory would contain random-access memory (RAM) chips and FPGAs that would, in addition to everything else, implement double-error-detecting and single-error-correcting memory functions to enable recovery from single-bit errors.

Some, Raphael↗