Search NASA⌕ Search

SEARCH · Search NASA

Results for “Writing”

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 721 records · Page 40

Chameleon: An Adaptive Wear Balancer for Flash Clusters

NAND flash-based Solid State Devices (SSDs) offer the desirable features of high performance, energy efficiency, and fast growing capacity. Thus, the use of SSDs is increasing in distributed storage systems. A key obstacle in this context is that the natural unbalance in distributed I/O workloads can result in wear imbalance across the SSDs in a distributed setting. This, in turn can have significant impact on the reliability, performance, and lifetime of the storage deployment. Extant load balancers for storage systems do not consider SSD wear imbalance when placing data, as the main design goal of such balancers is to extract higher performance. Consequently, data migration is the only common technique for tackling wear imbalance, where existing data is moved from highly loaded servers to the least loaded ones. In this paper, we explore an innovative holistic approach, Chameleon, that employs data redundancy techniques such as replication and erasure-coding, coupled with endurance-aware write offloading, to mitigate wear level imbalance in distributed SSD-based storage. Chameleon aims to balance the wear among different flash servers while meeting desirable objectives of: extending life of flash servers; improving I/O performance; and avoiding bottlenecks. Evaluation with a 50 node SSD cluster shows that Chameleon reduces the wear distribution deviation by 81% while improving the write performance by up to 33%.

Zhao, Nannan↗

Adaptive Spatially Aware I/O for Multiresolution Particle Data Layouts

Large-scale simulations on nonuniform particle distributions that evolve over time are widely used in cosmology, molecular dynamics, and engineering. Such data are often saved in an unstructured format that neither preserves spatial locality nor provides metadata for accelerating spatial or attribute subset queries, leading to poor performance of visualization tasks. Furthermore, the parallel I/O strategy used typically writes a file per process or a single shared file, neither of which is portable or scalable across different HPC systems. We present a portable technique for scalable, spatially aware adaptive aggregation that preserves spatial locality in the output. We evaluate our approach on two supercomputers, Stampede2 and Summit, and demonstrate that it outperforms prior approaches at scale, achieving up to 2.5× faster writes and reads for nonuniform distributions. Furthermore, the layout written by our method is directly suitable for visual analytics, supporting low-latency reads and attribute-based filtering with little overhead.

Usher, Will↗

The SENSEI Generic In Situ Interface

The SENSEI generic in situ interface is an API that promotes code portability and reusability. From the simulation view, a developer can instrument their code with the SENSEI API and then make make use of any number of in situ infrastructures. From the method view, a developer can write an in situ method using the SENSEI API, then expect it to run in any number of in situ infrastructures, or be invoked directly from a simulation code, with little or no modification. This paper presents the design principles underlying the SENSEI generic interface, along with some simplified coding examples.

Ayachit, Utkarsh↗

SEAS Communication Engine: An Extensible, Flexible Wrapper for Co-Simulation Agents

When modeling and analyzing the power grid and other large scale systems, researchers often express scenarios as optimization problems and feed them into advanced software solvers. In order to allow multiple solvers to communicate with each other and share data from different domains, the National Renewable Energy Laboratory (NREL) and associated Department of Energy (DOE) labs have developed a software framework called the Hierarchical Engine for Large-scale Infrastructure Co-Simulation (HELICS). HELICS allows cosimulation via a collection of client libraries for different languages that can be called from the appropriate optimization software. However, these client libraries do not provide a higher level of abstraction beyond reading and writing data off of the shared HELICS bus. In this paper, we describe a new software library called the SEAS Communication Engine that exposes a higher-level API for running cosimulation problems. The SEAS Engine provides a class-based abstraction on top of the Python HELICS client, in order to allow users to implement their domain-specific cosimulations without needing to interact with core HELICS primitives. This will make adoption of HELICS and cosimulation in general easier, by exposing a simpler API. In the second part of the paper, we validate our library on a collection of different simulation examples, including the canonical IEEE 13 Bus Feeder. Lastly, we demonstrate using the SEAS Engine to directly call domain-specific code written in the Julia programming language. Our hope is that this will serve as a template for easily calling software in different programming languages via the SEAS Engine, thereby avoiding code duplication and complexity.

co-simulation↗

Architecture for Hard Disk Drives

Magnetic data storage has made rapid progress in terms of areal density over the past few decades. Current products have areal density levels that exceed 10(12) bits per square inch, about 1000 times greater than areal densities of the mid-1990s. Five component technologies have become hard-disk-drive industry standards over the past two decades: read heads based on giant magnetoresistance or tunneling magnetoresistance, perpendicular write heads, perpendicular recording media, heaters, and contact detection sensors. At the recording system level, shingled magnetic recording has been implemented by all disk-drive companies, but it has not become a new standard due to the additional penalty in access time (or latency). Here, interlaced magnetic recording and blocked magnetic recording are introduced and compared with conventional and shingled magnetic recording.

97 MATHEMATICS AND COMPUTING↗

PyOMP: Multithreaded Parallel Programming in Python

We know that Python is a widely used language in scientific computing. When the goal is high performance, however, Python lags far behind low-level languages such as C and Fortran. To support applications that stress performance, Python needs to access the full capabilities of modern CPUs. That means support for parallel multithreading. In this paper, we describe PyOMP, a system that enables OpenMP in Python. Programmers write code in Python with OpenMP, Numba generates code that compiles to LLVM, and the resulting programs run with performance that approaches that from code written with C and OpenMP. In this paper we provide an update on the PyOMP project and explain how to install it and use it to write parallel multithreaded code in Python.

97 MATHEMATICS AND COMPUTING↗

Can I/O Variability Be Reduced on QoS-Less HPC Storage Systems?

For a production high-performance computing (HPC) system, where storage devices are shared between multiple applications and managed in a best effort manner, I/O contention is often a major problem. In this paper, we propose a balanced messaging-based re-routing in conjunction with throttling at the middleware level. This work tackles two key challenges that have not been fully resolved in the past: whether I/O variability can be reduced on a QoS-less HPC storage system, and how to design a runtime scheduling system that can scale up to a large amount of cores. The proposed scheme uses a two-level messaging system to re-route I/O requests to a less congested storage location so that write performance is improved, while limiting the impact on read by throttling re-routing. An analytical model is derived to guide the setup of optimal throttling factor. We thoroughly analyze the virtual messaging layer overhead and explore whether the in-transit buffering is effective in managing I/O variability. Contrary to the intuition, in-transit buffer cannot completely solve the problem. It can reduce the absolute variability but not the relative variability. The proposed scheme is verified against a synthetic benchmark as well as being used by production applications.

Huang, Dan↗

PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy-Efficient ReRAM

The wide adoption of deep neural networks has been accompanied by ever-increasing energy and performance demands due to the expensive nature of training them. Additionally, numerous special-purpose architectures have been proposed to accelerate training: both digital and hybrid digital-analog using resistive RAM (ReRAM) crossbars. ReRAM-based accelerators have demonstrated the effectiveness of ReRAM crossbars at performing matrix-vector multiplication operations that are prevalent in training. However, they still suffer from inefficiency due to the use of serial reads and writes for performing the weight gradient and update step. A few works have demonstrated the possibility of performing outer products in crossbars, which can be used to realize the weight gradient and update step without the use of serial reads and writes. However, these works have been limited to low precision operations which are not sufficient for typical training workloads. Moreover, they have been confined to a limited set of training algorithms for fully-connected layers only. To address these limitations, we propose a bit-slicing technique for enhancing the precision of ReRAM-based outer products, which is substantially different from bit-slicing for matrix-vector multiplication only. We incorporate this technique into a crossbar architecture with three variants catered to different training algorithms. To evaluate our design on different types of layers in neural networks (fully-connected, convolutional, etc.) and training algorithms, we develop PANTHER, an ISA-programmable training accelerator with compiler support. Our design can also be integrated into other accelerators in the literature to enhance their efficiency. Our evaluation shows that PANTHER achieves up to 8.02×, 54.21×, and 103× energy reductions as well as 7.16×, 4.02×, and 16× execution time reductions compared to digital accelerators, ReRAM-based accelerators, and GPUs, respectively.

42 ENGINEERING↗

Preemptible I/O Scheduling of Garbage Collection for Solid State Drives

Unlike hard disks, flash devices use out-of-place updates operations and require a garbage collection (GC) process to reclaim invalid pages to create free blocks. This GC process is a major cause of performance degradation when running concurrently with other I/O operations as internal bandwidth is consumed to reclaim these invalid pages. The invocation of the GC process is generally governed by a low watermark on free blocks and other internal device metrics that different workloads meet at different intervals. This results in an I/O performance that is highly dependent on workload characteristics. In this paper, we examine the GC process and propose a semipreemptible GC (PGC) scheme that allows GC processing to be preempted while pending I/O requests in the queue are serviced. Moreover, we further enhance flash performance by pipelining internal GC operations and merge them with pending I/O requests whenever possible. Our experimental evaluation of this semi-PGC scheme with realistic workloads demonstrates both improved performance and reduced performance variability. Write-dominant workloads show up to a 66.56% improvement in average response time with a 83.30% reduced variance in response time compared to the non-PGC scheme. In addition, we explore opportunities of a new NAND flash device that supports suspend/resume commands for read, write, and erase operations for fully PGC (F-PGC). Our experiments with an F-PGC enabled flash device show that request response time can be improved by up to 14.57% compared to semi-PGC.

97 MATHEMATICS AND COMPUTING↗

Demonstration of Vertical 2T-nC FeRAM Hybrid Cell and Its Scalability for High-Density 3-D Ferroelectric Capacitor Memory

In this work, we present a comprehensive experimental and modeling study on the scaling of vertical 2T-nC ferroelectric random access memory (FeRAM) hybrid cells, comprising n metal-ferroelectric–metal (MFM) capacitors, to demonstrate a high-performance and high-density 3-D capacitor memory. Our contributions include: 1) successful process integration of vertical 2T-3C FeRAM cells by stacking MFM structures on top of Si CMOS transistors; 2) experimental validation of memory cell functionality, confirming the feasibility of the vertical 2T-nC FeRAM architecture; 3) an analysis of scaling effects on parasitic capacitance in densely integrated 3-D arrays, using 3-D technology computer-aided design (TCAD) simulations; 4) exploration of aggressive stacking of write bitlines (WBLs) to enhance memory density, where ferroelectric linear capacitance ( C FE ) enables self-boosted inhibition under the V W /2 scheme, but renders the V W /3 scheme ineffective due to intolerable write disturbances; and 5) assessment of horizontal scaling, revealing significant increases in read disturbances caused by interplane capacitance between adjacent WBLs ( C Z ). This work represents an early exploration into the potential of 2T-nC FeRAM as a scalable and efficient 3-D memory solution.

42 ENGINEERING↗

Charge Trap Layer Supercharging for Improved Bit Reliability in 3-D NAND Flash Under Proton Irradiation

Single-event upset (SEU) cross sections are reduced in 176-layer charge trap (CT) 3-D nand devices under proton irradiation when multiple write operations are applied sequentially without the typical erase-before-write. Here, this effect is observed for multiple data patterns and in both single-level cell (SLC) and triple-level cell (TLC) operating modes. SEU cross section calculation methodologies are discussed for highly scaled 3-D devices both with and without the application of rewrites, and potential implications for long-term endurance effects are proposed.

Breeding, Matthew Luel [Sandia National Laboratori↗

Detailed Modeling and Evaluation of a Scalable Multilevel Checkpointing System

High-performance computing (HPC) systems are growing more powerful by utilizing more components. As the system mean time before failure correspondingly drops, applications must checkpoint frequently to make progress. But, at scale, the cost of checkpointing becomes prohibitive. A solution to this problem is multilevel checkpointing, which employs multiple types of checkpoints in a single run. Moreover, lightweight checkpoints can handle the most common failure modes, while more expensive checkpoints can handle severe failures. We designed a multilevel checkpointing library, the Scalable Checkpoint/Restart (SCR) library, that writes lightweight checkpoints to node-local storage in addition to the parallel file system. We present probabilistic Markov models of SCR's performance. We show that on future large-scale systems, SCR can lead to a gain in machine efficiency of up to 35 percent, and reduce the load on the parallel file system by a factor of two. In addition, we predict that checkpoint scavenging, or only writing checkpoints to the parallel file system on application termination, can reduce the load on the parallel file system by 20 × on today's systems and still maintain high application efficiency.

97 MATHEMATICS AND COMPUTING↗

Do Programmers Prefer Predictable Expressions in Code?

Source code is a form of human communication, albeit one where the information shared between the programmers reading and writing the code is constrained by the requirement that the code executes correctly. Programming languages are more syntactically constrained than natural languages, but they are also very expressive, allowing a great many different ways to express even very simple computations. Still, code written by developers is highly predictable, and many programming tools have taken advantage of this phenomenon, relying on language model surprisal as a guiding mechanism. Additionally, while surprisal has been validated as a measure of cognitive load in natural language, its relation to human cognitive processes in code is still poorly understood. In this paper, we explore the relationship between surprisal and programmer preference at a small granularity—do programmers prefer more predictable expressions in code? Using meaning-preserving transformations, we produce equivalent alternatives to developer-written code expressions and run a corpus study on Java and Python projects. In general, language models rate the code expressions developers choose to write as more predictable than these transformed alternatives. Then, we perform two human subject studies asking participants to choose between two equivalent snippets of Java code with different surprisal scores (one original and transformed). We find that programmers do prefer more predictable variants, and that stronger language models like the transformer align more often and more consistently with these preferences.

97 MATHEMATICS AND COMPUTING↗

Cost-Effective Additive Manufacturing of Ambient Pressure-Dried Silica Aerogel

The conventional manufacturing processes for aerogel insulation materials mostly rely on the supercritical drying, which suffers from issues of massive energy consumption, high-cost equipment, and prolonged processing time. Considering the large market demand for the aerogel insulation material in the next decade, a cost-effective and scalable fabrication technique is highly desired. In this paper, a direct ink writing (DIW) method is used to three-dimensionally fabricate the silica aerogel insulation material, followed by room-temperature and ambient pressure drying. Compared with the supercritical drying and freeze-drying techniques, the reported method significantly reduces the fabrication time and costs. The cost-effective DIW technique offers the capability to print complex hollow internal structures, coupled with the porous aerogel structure, it is found to be beneficial for the thermal insulation property. In this work, the addition of fiber to the ink assures the durability of the fabricated product, without sacrificing the thermal insulation performance. The foam ink preparation methods and the printability are demonstrated in this paper, along with the printing of complex three-dimensional geometries. The thermal insulation performance of the printed objects is characterized, and the mechanical properties were also examined. The proposed approach is found to have a 56% reduction in the processing time. The printed silica aerogels exhibit a low thermal conductivity of 0.053 W m –1 K –1 .

36 MATERIALS SCIENCE↗

Multilayer on-chip stacked Fresnel zone plates: Hard x-ray fabrication and soft x-ray simulations

Fresnel zone plates are widely used as x-ray nanofocusing optics. To achieve high spatial resolution combined with good focusing efficiency, high aspect ratio nanolithography is required, and one way to achieve that is through multiple e-beam lithography writing steps to achieve on-chip stacking. A two-step writing process producing 50 nm finest zone width at a zone thickness of 1.14 µm for possible hard x-ray applications is shown here. The authors also consider in simulations the case of soft x-ray focusing where the zone thickness might exceed the depth of focus. In this case, the authors compare on-chip stacking with, and without, adjustment of zone positions and show that the offset zones lead to improved focusing efficiency. The simulations were carried out using a multislice propagation method employing Hankel transforms.

Li, Kenan↗

Detailed analysis of latencies in image-based dynamic MLC tracking

Purpose: Previous measurements of the accuracy of image-based real-time dynamic multileaf collimator (DMLC) tracking show that the major contributor to errors is latency, i.e., the delay between target motion and MLC response. Therefore the purpose of this work was to develop a method for detailed analysis of latency contributions during image-based DMLC tracking. Methods: A prototype DMLC tracking system integrated with a linear accelerator was used for tracking a phantom with an embedded fiducial marker during treatment delivery. The phantom performed a sinusoidal motion. Real-time target localization was based on x-ray images acquired either with a portal imager or a kV imager mounted orthogonal to the treatment beam. Each image was stored in a file on the imaging workstation. A marker segmentation program opened the image file, determined the marker position in the image, and transferred it to the DMLC tracking program. This program estimated the three-dimensional target position by a single-imager method and adjusted the MLC aperture to the target position. Imaging intervals {Delta}T{sub image} from 150 to 1000 ms were investigated for both kV and MV imaging. After the experiments, the recorded images were synchronized with MLC log files generated by the MLC controller and tracking log files generated by the tracking program. This synchronization allowed temporal analysis of the information flow for each individual image from acquisition to completed MLC adjustment. The synchronization also allowed investigation of the MLC adjustment dynamics on a considerably finer time scale than the 50 ms time resolution of the MLC log files. Results: For {Delta}T{sub image}=150 ms, the total time from image acquisition to completed MLC adjustment was 380{+-}9 ms for MV and 420{+-}12 ms for kV images. The main part of this time was from image acquisition to completed image file writing (272 ms for MV and 309 ms for kV). Image file opening (38 ms), marker segmentation (4 ms), MLC position calculation (16 ms), and MLC adjustment (52 ms) were considerably faster. For {Delta}T{sub image}=1000 ms, the total time from image acquisition to completed MLC adjustment increased to 1030{+-}62 ms (MV) and 1330{+-}52 ms (kV) mainly because of delayed image file writing. The MLC adjustment duration was constant 52 ms ({+-}3 ms) for MLC adjustments below 1.1 mm and increased linearly for larger MLC adjustments. Conclusions: A method for detailed time analysis of each individual real-time position signal for DMLC tracking has been developed and applied to image-based tracking. The method allows identification of the major contributors to latency and therefore a focus for reducing this latency. The method could be an important tool for the reconstruction of the delivered target dose during DMLC tracking as it provides synchronization between target motion and MLC motion.

60 APPLIED LIFE SCIENCES↗

TU-EF-304-07: Monte Carlo-Based Inverse Treatment Plan Optimization for Intensity Modulated Proton Therapy

Purpose: Intensity-modulated proton therapy (IMPT) is increasingly used in proton therapy. For IMPT optimization, Monte Carlo (MC) is desired for spots dose calculations because of its high accuracy, especially in cases with a high level of heterogeneity. It is also preferred in biological optimization problems due to the capability of computing quantities related to biological effects. However, MC simulation is typically too slow to be used for this purpose. Although GPU-based MC engines have become available, the achieved efficiency is still not ideal. The purpose of this work is to develop a new optimization scheme to include GPU-based MC into IMPT. Methods: A conventional approach using MC in IMPT simply calls the MC dose engine repeatedly for each spot dose calculations. However, this is not the optimal approach, because of the unnecessary computations on some spots that turned out to have very small weights after solving the optimization problem. GPU-memory writing conflict occurring at a small beam size also reduces computational efficiency. To solve these problems, we developed a new framework that iteratively performs MC dose calculations and plan optimizations. At each dose calculation step, the particles were sampled from different spots altogether with Metropolis algorithm, such that the particle number is proportional to the latest optimized spot intensity. Simultaneously transporting particles from multiple spots also mitigated the memory writing conflict problem. Results: We have validated the proposed MC-based optimization schemes in one prostate case. The total computation time of our method was ∼5–6 min on one NVIDIA GPU card, including both spot dose calculation and plan optimization, whereas a conventional method naively using the same GPU-based MC engine were ∼3 times slower. Conclusion: A fast GPU-based MC dose calculation method along with a novel optimization workflow is developed. The high efficiency makes it attractive for clinical usages.

60 APPLIED LIFE SCIENCES↗