Search NASA⌕ Search

SEARCH · Search NASA

Results for “hardware performance”

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 937 records · Page 52

Experimental Design and Comparative Testing of a Hybrid-Cooled Computer Cluster [Thesis}

With water cooling becoming an affordable option both at home and at scale, it is important to consider the possible benefits over air cooling. There are several methods of liquid cooling, notables include: immersion, cold water cooling, and warm water cooling. The total cost of ownership is difficult to determine with these options as each has a different impact on the data center. Considering retrofit, over a new data center, introduces unforeseen variables that make cost analysis a challenge. Besides the added costs of additional infrastructure, and the cost to remove old, the upfront costs could be daunting. Therefore a cost analysis would be a study of its won. This study however hopes to reveal the resulting tradeoffs in temperature, performance, and power usage presented in the case between classical airflow based heat sink mechanisms to water provided directly at the heatsink. Having control over a discrete chiller will provide answers to the CPU temperatures, power usage, and performance at various inlet water temperatures. To water or to air?

97 MATHEMATICS AND COMPUTING↗

Hybrid Quantum-Classical Neural Networks

Deep learning is one of the most successful and far-reaching strategies used in machine learning today. However, the scale and utility of neural networks is still greatly limited by the current hardware used to train them. These concerns have become increasingly pressing as conventional computers are soon expected to approach the physical limitations that will slow their performance improvements in the near future. For these reasons, scientists have begun to explore alternative computing platforms, like quantum computers, for training neural networks. In recent years, variational quantum circuits have emerged as one of the most successful approaches to quantum deep learning on noisy intermediate scale quantum devices. We propose a hybrid quantum-classical neural network architecture where each neuron is a variational quantum circuit. We empirically analyze the performance of this hybrid neural network on a series of binary classification data sets using a simulated IBM universal quantum computer and a state-of-the-art IBM universal quantum computer. On the simulated hardware, we observe that the hybrid neural network achieves around 10% higher classification accuracy and 20% better minimization of the cost function than an individual variational quantum circuit. On the quantum hardware, we observe that each model only performs well when the qubit and gate count is sufficiently small.

Arthur, Davis↗

Dynamic Performance Comparison and Prediction based on Distribution-level Phasor Measurement Units

This paper introduces a new distribution level Phasor Measurement Unit (PMU) which adopts advanced hardware components and structure. The hardware parameters from the new PMU and the existing PMU are used to build a simulation model to predict the PMU performance. Therefore, a real-world testbench is built and four distribution level PMUs are tested under the steady-state and dynamic tests. The quantitative experiment result confirms the prediction model which could guide future PMU design, and also verifies the accuracy of the new PMU on the synchrophasor and frequency measurements in multiple scenarios.

Wu, Yuru↗

Hardware Acceleration of Adaptive Neural Algorithms.

As tradit ional numerical computing has faced challenges, researchers have turned towards alternative computing approaches to reduce power - per - computation metrics and improve algorithm performance. Here, we describe an approach towards non - conventional computing that strengthens the connection between machine learning and neuroscience concepts. The Hardware Acceleration of Adaptive Neural Algorithms (HAANA) project ha s develop ed neural machine learning algorithms and hardware for applications in image processing and cybersecurity. While machine learning methods are effective at extracting relevant features from many types of data, the effectiveness of these algorithms degrades when subjected to real - world conditions. Our team has generated novel neural - inspired approa ches to improve the resiliency and adaptability of machine learning algorithms. In addition, we have also designed and fabricated hardware architectures and microelectronic devices specifically tuned towards the training and inference operations of neural - inspired algorithms. Finally, our multi - scale simulation framework allows us to assess the impact of microelectronic device properties on algorithm performance.

97 MATHEMATICS AND COMPUTING↗

Simulation of Large-Scale HPC Architectures

The Extreme-scale Simulator (xSim) is a recently developed performance investigation toolkit that permits running high-performance computing (HPC) applications in a controlled environment with millions of concurrent execution threads. It allows observing parallel application performance properties in a simulated extreme-scale HPC system to further assist in HPC hardware and application software co-design on the road toward multi-petascale and exascale computing. This paper presents a newly implemented network model for the xSim performance investigation toolkit that is capable of providing simulation support for a variety of HPC network architectures with the appropriate trade-off between simulation scalability and accuracy. The taken approach focuses on a scalable distributed solution with latency and bandwidth restrictions for the simulated network. Different network architectures, such as star, ring, mesh, torus, twisted torus and tree, as well as hierarchical combinations, such as to simulate network-on-chip and network-on-node, are supported. Network traffic congestion modeling is omitted to gain simulation scalability by reducing simulation accuracy.

99 GENERAL AND MISCELLANEOUS↗

Critical Path-Based Thread Placement for NUMA Systems

Multicore multiprocessors use Non Uniform Memory Architecture (NUMA) to improve their scalability. However,NUMA introduces performance penalties due to remote memory accesses. Without efficiently managing data layout and thread mapping to cores, scientific applications, even if they are optimized for NUMA, may suffer performance loss. In this paper, we present an algorithm that optimizes the placement of OpenMP threads on NUMA processors. By collecting information from hardware counters and defining new metrics to capture the effects of thread placement, the algorithm reduces NUMA performance penalty by minimizing the critical path of OpenMP parallel regions and by avoiding local memory resource contention. We evaluate our algorithm with NPB benchmarks and achieve performance improvement between 8.13% and 25.68%, compared to the OS default scheduling.

99 GENERAL AND MISCELLANEOUS↗

A high performance DAC /DDS daughter module for the RHIC LLRF platform

The RHIC LLRF upgrade is a flexible, modular system. Output signals are generated by a custom designed XMC card with 4 high speed digital to analog (DAC) converters interfaced to a high performance field programmable gate array (FPGA). This paper discusses the hardware details of the XMC DAC board as well as the implementation of a low noise rf synthesizer with digital IQ modulation. This synthesizer also provides injection phase cogging and frequency hop rebucketing capabilities. A new modular RHIC LLRF system was recently designed and commissioned based on custom designed XMC cards. As part of that effort a high speed, four channel DAC board was designed. The board uses Maxim MAX5891 16 bit DACs with a maximum update rate of 600 Msps. Since this module is intended to be used for many different systems throughout the Collider Accelerator complex, it was designed to be as generic as possible. One major application of this DAC card is to implement digital synthesizers to provide drive signals to the various cavities at RHIC. Since RHIC is a storage ring with stores that typically last many hours, extremely low RF noise is a critical requirement. Synchrotron frequencies at RHIC range from a few hertz to several hundred hertz depending on the species and point in the acceleration cycle so close in phase noise is a major concern. The RHIC LLRF system uses the Update Link, a deterministic, high speed data link that broadcasts the revolution frequency and the synchronous phase angle. The digital synthesizers use this data to generate a properly phased analog drive signal. The synthesizers must also provide smooth phase shifts for cogging and support frequency shift rebucketing. One additional feature implemented in the FPGA is a digital waveform generator (WFG) that generates I and Q data pairs based on a user selected amplitude and phase profile as a function of time.

43 PARTICLE ACCELERATORS↗

Experimental Analysis of Distribution Network Voltage Regulation Using Smart Inverters: Preprint

Smart inverters (SI) have huge potential in providing grid services which has not been fully realized yet. One of these grid services, distribution network voltage regulation by SI, can improve the network voltage by regulating the SI reactive and active power output. Voltage regulation by SI is much faster compared to traditional voltage regulating devices, e.g. tap changing transformer, capacitor banks. However, there is gap in available published literature on the characteristics of SIs when the SI is controlled by local controller or external control signal. This paper presents the experimental study to characterize SI reactive power regulation response to two different control methods: autonomous control method and remote dispatch method. It was found that IS reactive power regulation response could be significantly different in terms of delay, and ramp rate for these two methods. Finally, Power-Hardware-in-The-Loop (PHIL) tests were conducted to evaluate the performance of these two methods. The PHIL tests results show that SI response characteristics for autonomous control method and remote dispatch method need to be considered during planning for distribution network voltage regulation using SI.

autonomous control↗

A Comparison of the Perceptual Benefits of Linear Perspective and Physically-Based Illumination for Display of Dense 3D Streamtubes

Large datasets typically contain coarse features comprised of finer sub-features. Even if the shapes of the small structures are evident in a 3D display, the aggregate shapes they suggest may not be easily inferred. From previous studies in shape perception, the evidence has not been clear whether physically-based illumination confers any advantage over local illumination for understanding scenes that arise in visualization of large data sets that contain features at two distinct scales. In this paper we show that physically- based illumination can improve the perception for some static scenes of complex 3D geometry from flow fields. We perform human- subjects experiments to quantify the effect of physically-based illumination on participant performance for two tasks: selecting the closer of two streamtubes from a field of tubes, and identifying the shape of the domain of a flow field over different densities of tubes. We find that physically-based illumination influences participant performance as strongly as perspective projection, suggesting that physically-based illumination is indeed a strong cue to the layout of complex scenes. We also find that increasing the density of tubes for the shape identification task improved participant performance under physically-based illumination but not under the traditional hardware-accelerated illumination model.

3D shape perception↗

Memory Errors in Modern Systems: The Good, The Bad, and The Ugly

Several recent publications have shown that hardware faults in the memory subsystem are commonplace. These faults are predicted to become more frequent in future systems that contain orders of magnitude more DRAM and SRAM than found in current memory subsystems. These memory subsystems will need to provide resilience techniques to tolerate these faults when deployed in high-performance computing systems and data centers containing tens of thousands of nodes. Therefore, it is critical to understand the efficacy of current hardware resilience techniques to determine whether they will be suitable for future systems. In this paper, we present a study of DRAM and SRAM faults and errors from the field. We use data from two leadership-class high-performance computer systems to analyze the reliability impact of hardware resilience schemes that are deployed in current systems. Our study has several key findings about the efficacy of many currently deployed reliability techniques such as DRAM ECC, DDR address/command parity, and SRAM ECC and parity. We also perform a methodological study, and find that counting errors instead of faults, a common practice among researchers and data center operators, can lead to incorrect conclusions about system reliability. Lastly, we use our data to project the needs of future large-scale systems. We find that SRAM faults are unlikely to pose a significantly larger reliability threat in the future, while DRAM faults will be a major concern and stronger DRAM resilience schemes will be needed to maintain acceptable failure rates similar to those found on today's systems.

97 MATHEMATICS AND COMPUTING↗

Final Report for CCS Cross-Layer Reliability Visioning Study

The geometric rate of improvement of transistor size and integrated circuit performance known as Moore's Law has been an engine of growth for our economy, enabling new products and services, creating new value and wealth, increasing safety, and removing menial tasks from our daily lives. Affordable, highly integrated components have enabled both life-saving technologies and rich entertainment applications. Anti-lock brakes, insulin monitors, and GPS-enabled emergency response systems save lives. Cell phones, internet appliances, virtual worlds, realistic video games, and mp3 players enrich our lives and connect us together. Over the past 40 years of silicon scaling, the increasing capabilities of inexpensive computation have transformed our society through automation and ubiquitous communications. Looking forward, increasing unpredictability threatens our ability to continue scaling integrated circuits at Moore's Law rates. As the transistors and wires that make up integrated circuits become smaller, they display both greater differences in behavior among devices designed to be identical and greater vulnerability to transient and permanent faults. Conventional design techniques expend energy to tolerate this unpredictability by adding safety margins to a circuit's operating voltage, clock frequency or charge stored per bit. However, the rising energy costs needed to compensate for increasing unpredictability are rapidly becoming unacceptable in today's environment where power consumption is often the limiting factor on integrated circuit performance and energy efficiency is a national concern. Reliability and energy consumption are both reaching key inflection points that, together, threaten to reduce or end the benefits of feature size reduction. To continue beneficial scaling, we must use a cross-layer, Jull-system-design approach to reliability. Unlike current systems, which charge every device a substantial energy tax in order to guarantee correct operation in spite of rare events, such as one high-threshold transistor in a billion or one erroneous gate evaluation in an hour of computation, cross-layer reliability schemes make reliability management a cooperative effort across the system stack, sharing information across layers so that they only expend energy on reliability when an error actually occurs. Figure 1 illustrates an example of such a system that uses a combination of information from the application and cheap architecture-level techniques to detect errors. When an error occurs, mechanisms at higher levels in the stack correct the error, efficiently delivering correct operation to the user in spite of errors at the device or circuit levels. In the realms of memory and communication, engineers have a long history of success in tolerating unpredictable effects such as fabrication variability, transient upsets, and lifetime wear using information sharing, limited redundancy, and cross-layer approaches that anticipate, accommodate, and suppress errors. Networks use a combination of hardware and software to guarantee end-toend correctness. Error-detection and correction codes use additional information to correct the most common errors, single-bit transmission errors. When errors occur that cannot be corrected by these codes, the network protocol requests re-transmission of one or more packets until the correct data is received. Similarly, computer memory systems exploit a cross-layer division of labor to achieve high performance with modest hardware. Rather than demanding that hardware alone provide the virtual memory abstraction, software page-fault and TLB-miss handlers allow a modest piece of hardware, the TLB, to handle the common-case operations on a cyc1e-by-cycle basis while infrequent misses are handled in system software. Unfortunately, mitigating logic errors is not as simple or as well researched as memory or communication systems. This lack of understanding has led to very expensive solutions. For example, triple-modular redundancy masks errors by triplicating computations in either time or area. This mitigation methods imposes a 200% increase in energy consumption for every operation, not just the uncommon failure cases. At a time when computation is rapidly becoming part of our critical civilian and military infrastructure and decreasing costsfor computation are fueling our economy and our well being, we cannot afford increasingly unreliable electronics or a stagnation in capabilities per dollar, watt, or cubic meter. If researchers are able to develop techniques that tolerate the growing unpredictability of silicon devices, Moore's Law scaling should continue until at least 2022. During this 12-year time period, transistors, which are the building blocks of electronic devices, will scale their dimensions (feature sizes) from 45nm to 4.5nm.

99 GENERAL AND MISCELLANEOUS↗

Development of Real-Time High-Density Pulsar Data Transmission and Processing for Grid Synchronization

Taking advantage of the extreme stability of the pulsar period, it can serve as the timing source for grid synchronization to compensate for the timing drift instigated by the loss of GPS signal. Nevertheless, the real-time transmission and processing of the pulsar data suffer from its high-frequency data rate, varying from megahertz to gigahertz, resulting in reduced computing speed and increased time delay. To mitigate this issue, the hardware and software frameworks are implemented for the high-density pulsar data transmission and processing for grid synchronization in this research. Initially, the high-density pulsar data is transferred using open-source software. The complementary duty cycle timing module is designed to coordinate the operation of the dual-channel high-speed interface and software. Subsequently, the multiple-threading is applied to the receiving, parsing, and splicing pulsar data. Next, the pulsar signal extraction method is implemented based on the polyphase filterbank and time of arrival estimation. Ultimately, real-time performance verification experiments are carried out for different components under two hardware platforms. Finally, the results demonstrate that only 0.482 s is required for processing 4 Gigabyte data through multiple-threading, which is 3.8 times faster than the single thread. The pulsar signal extraction can also be executed within 707 ms for 4.8 seconds of data, thereby indicating that real-time requirements can be met.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Fast DRR generation for 2D to 3D registration on GPUs

Purpose: The generation of digitally reconstructed radiographs (DRRs) is the most time consuming step on the CPU in intensity based two-dimensional x-ray to three-dimensional (CT or 3D rotational x-ray) medical image registration, which has application in several image guided interventions. This work presents optimized DRR rendering on graphical processor units (GPUs) and compares performance achievable on four commercially available devices. Methods: A ray-cast based DRR rendering was implemented for a 512 Multiplication-Sign 512 Multiplication-Sign 72 CT volume. The block size parameter was optimized for four different GPUs for a region of interest (ROI) of 400 Multiplication-Sign 225 pixels with different sampling ratios (1.1%-9.1% and 100%). Performance was statistically evaluated and compared for the four GPUs. The method and the block size dependence were validated on the latest GPU for several parameter settings with a public gold standard dataset (512 Multiplication-Sign 512 Multiplication-Sign 825 CT) for registration purposes. Results: Depending on the GPU, the full ROI is rendered in 2.7-5.2 ms. If sampling ratio of 1.1%-9.1% is applied, execution time is in the range of 0.3-7.3 ms. On all GPUs, the mean of the execution time increased linearly with respect to the number of pixels if sampling was used. Conclusions: The presented results outperform other results from the literature. This indicates that automatic 2D to 3D registration, which typically requires a couple of hundred DRR renderings to converge, can be performed quasi on-line, in less than a second or depending on the application and hardware in less than a couple of seconds. Accordingly, a whole new field of applications is opened for image guided interventions, where the registration is continuously performed to match the real-time x-ray.

07 ISOTOPE AND RADIATION SOURCES↗

Dynamic Configuration of the CMS Data Acquisition Cluster

The CMS Data Acquisition cluster, which runs around 10000 applications, is configured dynamically at run time. XML configuration documents determine what applications are executed on each node and over what networks these applications communicate. Through this mechanism the DAQ System may be adapted to the required performance, partitioned in order to perform (test-) runs in parallel, or re-structured in case of hardware faults. This paper presents the configuration procedure and the CMS DAQ Confi gurator tool, which is used to generate comprehensive configurations of the CMS DAQ system based on a high-level description given by the user. Using a database of configuration templates and a database containing a detailed model of hardware modules, dat a and control links, nodes and the network topology, the tool automatically determines which applications are needed, on which nodes they should run, and over which networks the event traffic will flow. The tool computes application parameters and generat es the XML configuration documents and the configuration of the run-control system. The performance of the configuration procedure and the tool as well as operational experience during CMS commissioning and the first LHC runs are discussed.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Inventory Management Improvement Project

The Lawrence Livermore National Laboratory (LLNL) conducts research and development for the National Nuclear Security Agency (NNSA) and its affiliates. The Polymer AM team at LLNL conducts research and development in 3D printing, specifically direct-ink-write, in accordance with LLNL and NNSA missions. The team is composed of machine operators, chemists, testing engineers, and project engineers across multiple lab spaces with one shared storage area at LLNL. The operations use a variety of different consumables and hardware to conduct research applications for LLNL and NNSA. These items are critical to performing operation tasks; if an item is out of stock, operations associated with the respective item could be suspended for weeks. As such, the Polymer AM team manages an inventory of spare consumables and hardware to ensure these items are always available. However, the current management system, an excel sheet managed by the project engineer group, is not intuitive in providing inventory information despite the high labor utilization needed to maintain the system. As such, the team is looking to improve their inventory management that can send notifications regarding inventory needs, accessible to other team members, provide all relevant information to a specific item, and store historical information for budget and operation planning. The proposed solution is a Computer Maintenance Management System (CMMS): a web-based management software that stores inventory information and provides automated notifications. The system will store information on each item including quantity in stock, technical information, supplier information, costs, lead times, and expiration date. The system has a notifications function that can send notifications to the respective team member’s when an item needs to be counted, item inventory is low, or an item is approaching their expiration date. Information for each item can be tracked over time creating data to be used for budget planning and process improvement purposes. Due to its web-based source, the system can be accessed by the respective team member viewing technical information, quantity, and purchasing information.

42 ENGINEERING↗

Performance limits for maritime Inverse Synthetic Aperture Radar (ISAR)

The performance of an Inverse Synthetic Aperture Radar (ISAR) system depends on a variety of factors, many which are interdependent in some manner. In this report we specifically examine ISAR as applied to maritime targets (e.g. ships). It is often difficult to get your arms around the problem of ascertaining achievable performance limits, and yet those limits exist and are dictated by physics. This report identifies and explores those limits, and how they depend on hardware system parameters and environmental conditions. Ultimately, this leads to a characterization of parameters that offer optimum performance for the overall ISAR system. While the information herein is not new to the literature, its collection into a single report hopes to offer some value in reducing the seek time .

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Performance limits for exo-clutter Ground Moving Target Indicator (GMTI) radar.

The performance of a Ground Moving Target Indicator (GMTI) radar system depends on a variety of factors, many which are interdependent in some manner. It is often difficult to 'get your arms around' the problem of ascertaining achievable performance limits, and yet those limits exist and are dictated by physics. This report identifies and explores those limits, and how they depend on hardware system parameters and environmental conditions. Ultimately, this leads to a characterization of parameters that offer optimum performance for the overall GMTI radar system. While the information herein is not new to the literature, its collection into a single report hopes to offer some value in reducing the 'seek time'.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

A Synthesis Methodology for Intelligent Memory Interfaces in Accelerator Systems

Domain-specific systems improve the performance of a specific set of applications compared to general-purpose processing systems by deploying custom hardware accelerators. These hardware accelerators are generated using high-level synthesis (HLS) tools. The HLS tools enable a comprehensive design space exploration to optimize the compute performance of the generated accelerators. However, they often ignore the challenges of implementing the accelerators in a system-on-chip, particularly how the accelerators access memory. Our work introduces a buffering system design that improves accelerators' memory accesses by intelligently employing burst transactions to prefetch useful data from external memory to on-chip local buffers. Our design is dynamic, parametric, and transparent to the accelerators generated by HLS tools. We derive the buffering system parameters using appropriate compiler-based analysis passes and memory channel latency constraints. The proposed buffering system design results in, on average, 8.8x performance improvements while lowering memory channel utilization on average by 53.2% for a set of PolyBench kernels.

Limaye, Ankur M. (ORCID:0000000194062584)↗