Radiation issues and applications of floating gate memories
The radiation effects that affect various systems that comprise floating gate memories are presented.
SEARCH · Search NASA
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.
The radiation effects that affect various systems that comprise floating gate memories are presented.
The increase in the number of processors needed to build exascale systems implies that the mean time between failure will further decrease, making it increasingly important to develop scalable techniques for fault tolerance. In this paper we develop an efficient checksum-based approach to fault tolerance for data in volatile memory systems, i.e., an approach without the need to save any data on stable persistent storage. The developed scheme is applicable in multiple scenarios, including: 1) online recovery of large read-only data structures from the memory of failed nodes, with very low storage overhead 2) online recovery from soft errors in blocked data, and 3) online recovery of read/write data via in-memory check-pointing. The approach uses a logical multi-dimension view of the data to be protected. Changing the dimensionality of the data view enables a trade-off between multiple factors, including the storage overheads, the checksum generation time, the failure recovery time, and the number of faults that can be tolerated. Experimental results demonstrating effectiveness are presented on a Cray XE6 system.
The need for technology advances to accomplish the Titan probe mission was determined by defining mission conditions and requirements and evaluating the technology impact on the baseline probe configuration. Mission characteristics found to be technology drivers include (1) ten years dormant life in space vacuum; (2) unknown surface conditions, various sample materials, and a surface temperature; and (3) mission constraints of the Saturn Orbiter Dual Probe mission regarding weight allocation. The following areas were identified for further development: surface sample acquisition system; battery powered system; nonmetallic materials; magnetic bubble memory devices, and the landing system. Preentry science, reliability, and weight reduction and redundancy must also be considered.
Memory storage requirements in space systems have steadily increased, much like storage requirements in terrestrial systems. Large arrays of dynamic memories (DRAMs) have been used in solid-state recorders, relying on a combination of shielding and error-detection-and correction (EDAC) to overcome the extreme sensitivity of DRAMs to space radiation. For example, a 2-Gbit memory (with 4-Mb DRAMs) used on the Clementine mission functioned perfectly during its moon mapping mission, in spite of an average of 71 memory bit flips per day from heavy ions. Although EDAC worked well with older types of memory circuits, newer DRAMs use extremely complex internal architectures which has made it increasingly difficult to implement EDAC. Some newer DRAMs have also exhibited catastrophic latchup. Flash memories are an intriguing alternative to DRAMs because of their nonvolatile storage and extremely high storage density, particularly for applications where writing is done relatively infrequently. This paper discusses radiation effects in advanced flash memories, including general observations on scaling and architecture as well as the specific experience obtained at the Jet Propulsion Laboratory in evaluating high-density flash memories for use on the NASA mission to Europa, one of Jupiter's moons. This particular mission must pass through the Jovian radiation belts, which imposes a very demanding radiation requirement.
We analyze the depth of the memory of quantum memory channels generated by a fixed unitary transformation describing the interaction between the principal system and internal degrees of freedom of the process device. We investigate the simplest case of a qubit memory channel with a two-level memory system. In particular, we explicitly characterize all interactions for which the memory depth is finite. We show that the memory effects are either infinite, or they disappear after at most two uses of the channel. Memory channels of finite depth can be to some extent controlled and manipulated by so-called reset sequences. We show that actions separated by the sequences of inputs of the length of the memory depth are independent and constitute memoryless channels.
Holographic storage and retrieval using photorefractive media (electro-optic ferroelectric materials), particularly iron-doped lithium niobate with its enhanced sensitivity, are discussed. Refractive index changes induced by exposure to light render the materials useful for read-write memories and read-write memory simulation. Resolution, dark storage time, write and erase times, reversibility, and noise levels of the materials are examined. The laser source, deflection system, hololens, page composer, and detector array of the holographic memory system are described. High SNR and two orders of magnitude improvement in speed are reported over earlier experimental prototypes, but the system is still too slow to meet practical needs.
Techniques of combining separate but correlated measurements to form a second-order or higher order correlation function to suppress the effects of noise in the initial condition of a system capable of retaining memory of an initial state of the system with a characteristic relaxation time. At least two separate measurements are obtained from the system. The temporal separation between the two separate measurements is preferably comparable to or less than the characteristic relaxation time and is adjusted to allow for a correlation between two measurements.
Combination of two dimensional graphene and semi-conducting molybdenum disulfide (MoS{sub 2}) is of great interest for various electronic device applications. Here, we demonstrate fabrication of a hybridized structure with the chemical vapor deposited graphene and MoS{sub 2} crystals to configure a memory device. Elongated hexagonal and rhombus shaped MoS{sub 2} crystals are synthesized by sulfurization of thermally evaporated molybdenum oxide (MoO{sub 3}) thin film. Scanning transmission electron microscope studies reveal atomic level structure of the synthesized high quality MoS{sub 2} crystals. In the prospect of a memory device fabrication, poly(methyl methacrylate) (PMMA) is used as an insulating dielectric material as well as a supporting layer to transfer the MoS{sub 2} crystals. In the fabricated device, PMMA-MoS{sub 2} and graphene layers act as the functional and electrode materials, respectively. Distinctive bistable electrical switching and nonvolatile rewritable memory effect is observed in the fabricated PMMA-MoS{sub 2}/graphene heterostructure. The developed material system and demonstrated memory device fabrication can be significant for next generation data storage applications.
Twenty pilots with instrument flight ratings were asked to perform a fault-diagnosis task for which they had relevant domain knowledge. The pilots were asked to think out loud as they requested and interpreted information. Performances were then modeled as the activation and use of a frame system. Cognitive biases, memory distortions and losses, and failures to correctly diagnose the problem were studied in the context of this frame system model.
Here, the latest OpenMP standard offers automatic device offloading capabilities which facilitate GPU programming. Despite this, there remain many challenges. One of these is the unified memory feature introduced in recent GPUs. GPUs in current and future HPC systems have enhanced support for unified memory space. In such systems, CPU and GPU can access each other's memory transparently, that is, the data movement is managed automatically by the underlying system software and hardware. Memory over subscription is also possible in these systems. However, there is a significant lack of knowledge about how this mechanism will perform, and how programmers should use it. We have modified several benchmarks codes, in the Rodinia benchmark suite, to study the behavior of OpenMP accelerator extensions and have used them to explore the impact of unified memory in an OpenMP context. We moreover modified the open source LLVM compiler to allow OpenMP programs to exploit unified memory. The results of our evaluation reveal that, while the performance of unified memory is comparable with that of normal GPU offloading for benchmarks with little data reuse, it suffers from significant overhead when GPU memory is over subcribed for benchmarks with large amount of data reuse. Based on these results, we provide several guidelines for programmers to achieve better performance with unified memory.
A single-burst-error correction system is described for data stored in the UNICON laser memory. In the proposed system, a long fire code with code length n greater than 16,768 bits was used as an outer code to augment an existing inner shorter fire code for burst error corrections. The inner fire code is a (80,64) code shortened from the (630,614) code, and it is used to correct a single-burst-error on a per-word basis with burst length b less than or equal to 6. The outer code, with b less than or equal to 12, would be used to correct a single-burst-error on a per-page basis, where a page consists of 512 32-bit words. In the proposed system, the encoding and error detection processes are implemented by hardware. A minicomputer, currently used as a UNICON memory management processor, is used on a time-demanding basis for error correction. Based upon existing error statistics, this combination of an inner code and an outer code would enable the UNICON system to obtain a very low error rate in spite of flaws affecting the recorded data.
Despite state-of-the-art technologies like artificial intelligence, human judgment is critically essential in cooperative systems, such as the multi-agent system (MAS), which collect information among agents based on multiple-cue judgment. Human agents can prevent impaired situational awareness of automated agents by confirming situations under environmental uncertainty. System error caused by uncertainty can result in an unreliable system environment, and this environment affects the human agent, resulting in non-optimal decision-making in MAS. Thus, it is necessary to know how human behavior is changed to capture system reliability under uncertainty. Another issue affecting MAS is time delay, which can delay agent information transfer, resulting in low performance and instability. However, it is difficult to find studies on the influence of time delay on human agents. This study is about understanding the human decision-making process under a specific system reliability environment by uncertainty with time delay. We used concepts of expected and unexpected uncertainty to implement reliability of the system usage environment with three types of time delay conditions: no time delay, regular time delay, and irregular time delay conditions. We used electroencephalogram (EEG) for human cognitive neural mechanisms in multiple-cue judgment systems to understand human decision-making. In the reliability of system usage environment, the unreliable system environment significantly creates less memory load by less utilization of system rules for decision-making. In terms of time delay, delayed information delivery does not significantly affect memory load for decision-making.
Among the topics discussed are: access control models for a distributed CAIS-conforming system; a knowledge-based advisory system for casualty procedures; and automated interactive simulation modeling system. Consideration is also given to: reusable software concepts and software development methodologies; the electronic device aspects of neutral network memories; an expert system for automated satellite anomaly resolution; and the use of automatic programming techniques for fault-tolerant computing systems. Among additional topics discussed are: systems approaches to software fault tolerance; a Space Shuttle navigation validation system; and a vision-based road following system for an autonomous land vehicle.
Kanaerva's sparse distributed memory (SDM) is an associative memory model based on the mathematical properties of high dimensional binary address spaces. Holland's genetic algorithms are a search technique for high dimensional spaces inspired by evolutional processes of DNA. Genetic Memory is a hybrid of the above two systems, in which the memory uses a genetic algorithm to dynamically reconfigure its physical storage locations to reflect correlations between the stored addresses and data. This architecture is designed to maximize the ability of the system to scale-up to handle real world problems.
A multiprocessor system includes nodes. Each node includes a data path that includes a core, a TLB, and a first level cache implementing disambiguation. The system also includes at least one second level cache and a main memory. For thread memory access requests, the core uses an address associated with an instruction format of the core. The first level cache uses an address format related to the size of the main memory plus an offset corresponding to hardware thread meta data. The second level cache uses a physical main memory address plus software thread meta data to store the memory access request. The second level cache accesses the main memory using the physical address with neither the offset nor the thread meta data after resolving speculation. In short, this system includes mapping of a virtual address to a different physical addresses for value disambiguation for different threads.
Trace driven simulation is a well-established method of performance analysis for single processor computer systems. However, efficient and accurate memory address tracing for parallel computer systems is not well understood. In this paper we present a critical survey of recently implemented approaches to address tracing and highlight the issues specific to collection of traces for both shared and distributed memory parallel computers. These issues include potential distortion of the relative ordering of events by the address tracing activity, realistic interleaving of addresses generated by multiple processors, and I/O and storage problems associated with collecting traces for large parallel systems. The strengths and weaknesses of the parallel tracing approaches are described.
Scientific applications use collective communication operations in Message Passing Interface (MPI) for global synchronization and data exchanges. Alltoall and AlltoallV are two important collective operations. They are used by MPI jobs to exchange messages among all of MPI processes. AlltoallV is a generalization of Alltoall, supporting messages of varying sizes. However, the existing MPI AlltoallV implementation has linear complexity, i.e., each process has to send messages to all other processes in the job. Such linear complexity can result in sub optimal scalability of MPI applications when they are deployed on millions of cores. To address above challenge, in this paper, we introduce a new Scalable LOgarithmic AlltoallV algorithm, named SLOAV, for MPI AlltoallV collective operation. SLOAV aims to achieve global exchange of small messages of different sizes in a logarithmic number of rounds. Furthermore, given the prevalence of multicore systems with shared memory, we design a hierarchical AlltoallV algorithm based on SLOAV by leveraging the advantages of shared memory, which is referred to as SLOAVx. Compared to SLOAV, SLOAVx significantly reduces the inter-node communication, thus improving the entire system performance and mitigating the impact of message latency. We have implemented and embedded both algorithms in Open MPI. Our evaluation on large-scale computer systems shows that for the 8-byte and 1024-process MPI Alltoallv operation, the SLOAV can reduce the latency by as much as 86.4%, when compared to the state-of-the-art, and SLOAVx can further optimize the SLOAV by up to 83.1% in terms of message latency on multicore systems. In addition, experiments with NAS Parallel Benchmark (NPB) demonstrate that our algorithms are very effective for real-world applications.
Programmable maintenance processor (MAINT) made of commercially available integrated circuits. Autonomous one of four digital electronic processors in extended aircraft interrogation and display system (XAIDS). Developed for testing of system and application computer programs as well as for testing equipment. MAINT has independent terminal and printer interfaces and dedicated magnetic bubble memory storing system-testing sequences entered from terminal. Software for MAINT written in PLM86 programming language and broken into four separate modules.