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 703 records · Page 39

Investigation and Diagnosis of Faulty Data Channels in CMS Outer Tracker Module Testing

The High-Luminosity Large Hadron Collider (HL-LHC) is currently undergoing upgrades to improve its luminosity. In parallel, this requires an upgrade to the Compact Muon Solenoid (CMS)’s Outer Tracker, consisting of Pixel-Strip (PS) and Strip-Strip (2S) modules that can accurately track the path of charged particles originating from the collisions. It follows that such complex modules call for extensive testing, requiring a sophisticated Data Acquisition (DAQ) system that can perform specific tests to assess their performance. In addition, errors caused by the hardware of a given testing station, and its associated data channel, need to be accurately identified to guarantee proper testing of modules. We have developed a software extension to the Phase-II Outer Tracker Analyzer of Test Outputs (POTATO), which is a specialized software designed to analyze and grade all of the module tests through a centralized database. This extension categorizes and analyzes module test results by its station and data channel. Its analysis can be used to identify trends in grading that indicate issues in these channels’ grading process rather than in the individual modules. This poster shows our methodology and results for identifying faulty data channels. Using this extension, we can quickly diagnose and address problems in our DAQ system, ensuring proper evaluation corrections for each module.

Chen, Angus [Fermilab]↗

Investigation and Diagnosis of Faulty Data Channels in CMS Outer Tracker Module Testing

The High-Luminosity Large Hadron Collider (HL-LHC) is currently undergoing upgrades to improve its luminosity. In parallel, this requires an upgrade to the Compact Muon Solenoid (CMS)’s Outer Tracker, consisting of Pixel-Strip (PS) and Strip-Strip (2S) modules that can accurately track the path of charged particles originating from the collisions. It follows that such complex modules call for extensive testing, requiring a sophisticated Data Acquisition (DAQ) system that can perform specific tests to assess their performance. In addition, errors caused by the hardware of a given testing station, and its associated data channel, need to be accurately identified to guarantee proper testing of modules. We have developed a software extension to the Phase-II Outer Tracker Analyzer of Test Outputs (POTATO), which is a specialized software designed to analyze and grade all of the module tests through a centralized database. This extension categorizes and analyzes module test results by its station and data channel. Its analysis can be used to identify trends in grading that indicate issues in these channels’ grading process rather than in the individual modules. This poster shows our methodology and results for identifying faulty data channels. Using this extension, we can quickly diagnose and address problems in our DAQ system, ensuring proper evaluation corrections for each module.

Chen, Angus [Fermilab]↗

A Modular Multilevel Converter with Power Mismatch Control for Grid-Connected Photovoltaic Systems

A modular multilevel power converter configuration for grid connected photovoltaic (PV) systems is proposed. The converter configuration replaces the conventional bulky line frequency transformer with several high frequency transformers, potentially reducing the balance of systems cost of PV systems. The front-end converter for each port is a neutral-point diode clamped (NPC) multi-level dc-dc dual-active bridge (ML-DAB) which allows maximum power point tracking (MPPT). The integrated high frequency transformer provides the galvanic isolation between the PV and grid side and also steps up the low dc voltage from PV source. Following the ML-DAB stage, in each port, is a NPC inverter. N number of NPC inverters’ outputs are cascaded to attain the per-phase line-to-neutral voltage to connect directly to the distribution grid (i.e., 13.8 kV). The cascaded NPC (CNPC) inverters have the inherent advantage of using lower rated devices, smaller filters and low total harmonic distortion required for PV grid interconnection. The proposed converter system is modular, scalable, and serviceable with zero downtime with lower foot print and lower overall cost. A novel voltage balance control at each module based on power mismatch among N-ports, have been presented and verified in simulation. Analysis and simulation results are presented for the N-port converter. The converter performance has also been verified on a hardware prototype.

14 SOLAR ENERGY↗

Energy and Exergy Analysis of Low-Global Warming Potential Refrigerants as Replacement for R410A in Two-Speed Heat Pumps for Cold Climates

Heat pumps (HPs) are being developed with a new emphasis on cold climates. To lower the environmental impact of greenhouse gas (GHG) emissions, alternate low global warming potential (GWP) refrigerants must also replace the exclusive use of the refrigerant R410A, preferably without re-engineering the mechanical hardware. In this paper, we analyze the performance of four low-GWP alternative refrigerants (R32, R452B, R454B, and R466A) relative to the conventional R410A and draw conclusions on the relative performances for providing heating in cold climates based on the Air-Conditioning, Heating, and Refrigeration Institute (AHRI) 210/240 standard for two-speed heat pumps. The simulations are carried using the Department of Energy, Oak Ridge National Laboratory (DOE/ORNL) Heat Pump Design Model (HPDM), a well-known heating, ventilation, and air conditioning (HVAC) modeling and design tool in the public domain and the HVAC research and development community. The results of the simulation are further scrutinized using exergy analysis to identify sources of systemic inefficiency, the root cause of lost work. This rigorous approach provides an exhaustive analysis of alternate low-GWP refrigerants to replace R410A using available compressors and system components, without compromising performance.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Understanding the Impact of Interconnect Failures on System Operation

Hardware failures are inevitable on large high performance computing systems. Faults or performance degradations in the high-speed network can reduce the entire system s performance. Since the introduction of the Gemini interconnect, Cray systems have become resilient to many networking faults that were fatal in their previous generation systems. These new network reliability and resiliency features have enabled higher uptimes on Cray systems by allowing them to continue running with reduced network performance. Oak Ridge National Laboratory has developed a set of user-level diagnostics that stresses the high-speed network and searches for components that are not performing as expected. Nearest-neighbor bandwidth tests check every network chip and network link in the system. Additionally, performance counters stored on the network ASIC s memory mapped registers (MMRs) are used to better understand the state of the network. Applications have also been characterized under various suboptimal network conditions to better understand what impact network problems have on user codes.

Cray↗

Linux-Based Software Control for Xenon Systems

This paper will review software control solutions for systems requiring automated control and analysis. Written in the C++ language under the Linux operating system (OS), a client/server architecture was developed for automated systems enabling modularized processes to perform system control. In this scheme, narrowly focused clients and servers communicate with each other to perform tasks necessary for system execution. Each hardware interface, such as analog input/output modules, instrumentation, and detectors, have a server associated with it that can be accessed individually with various client interface programs. These servers also inherently support reporting all sensor values to a state-of-health server. One advantage to this software architecture is that all software servers can be accessed and altered independently without stopping the entire control system providing flexibility during development and operation. Automation is achieved using a state-machine based control program that implements the process necessary to run the system. The state-machine provides a well-defined process flow with each state defining one step in the overall control process. The state-machine framework is highly flexible. During development, states can easily be modified, added, or removed as needed.

Suarez, Reynold↗

Binary Complex Neural Network Acceleration on FPGA

Being able to learn from complex data with phase information is imperative for many signal processing applications. Today’s real-valued deep neural networks (DNNs) have shown efficiency in latent information analysis but fall short when applied to the complex domain. Deep complex networks (DCN) , in contrast, can learn from complex data, but have high computational costs; therefore, they cannot satisfy the instant decision making requirements of many deployable systems dealing with short observations or short signal bursts. Recent, Binarized Complex Neural Network (BCNN), which integrates DCNs with binarized neural networks (BNN), shows great potential in classifying complex data in real-time. In this paper, we propose a structural pruning based accelerator of BCNN, which is able to provide more than 5000 frames/s inference throughput on edge devices. The high performance comes from both the algorithm and hardware sides. On the algorithm side, we conduct structural pruning to the original BCNN models and obtain 20 × pruning rates with negligible accuracy loss; on the hardware side, we propose a novel 2D convolution operation accelerator for the binary complex neural network. Experimental results show that the proposed design works with over 90% utilization and is able to achieve the inference throughput of 5882 frames/s and 4938 frames/s for complex NIN-Net and ResNet-18 using CIFAR-10 dataset and Alveo U280 Board.

Peng, Hongwu↗

Rapid Cryogenic Electrical Characterization of Materials and Devices Using Gifford-McMahon Cryocoolers

Thin-film heterostructures are necessary building blocks for superconducting and phononic quantum computing devices. Many new generations of quantum hardware demand extensive materials research to optimize performances at cryogenic temperatures (below 10 K). Here, we demonstrate compact cryogenic measurement systems capable of reaching sub-10K temperatures in less than three hours with the ability to measure AC/DC resistance and dielectric properties of thin-film materials. Our platform utilizes Gifford-McMahon (GM) cryocoolers as effective tools for providing high throughput cooling-warming cycles. We successfully used the GM-based measurement systems to measure 1) the superconducting transition temperature for Nb thin films (T c ~7.8 K), and 2) the temperature dependence of the dielectric constant in SiO 2 thin films down to 10 K. The fast electrical characterization feedback will be critical in developing robust materials and components for cryogenic computing devices.

36 MATERIALS SCIENCE↗

Experiences on 64 and 150 FPGA Systems

Four FPGA systems were evaluated: the Cray XD1 system with 6 FPGAs at ORNL and Cray, the Cray XD1 system with 150 FPGAs at NRL* and the 64 FPGAs on Edinburgh s Maxwell . Their hardware and software architectures, programming tools and performance on scientific applications are discussed. FPGA speedup (over a 2.2 GHz Opteron) of 10X was typical for matrix equation solution, molecular dynamics and weather/climate codes and upto 100X for human genome DNA sequencing. Large genome comparisons requiring 12.5 years for an Opteron took less than 24 hours on NRL s Cray XD1 with 150 Virtex FPGAs for a 7,350X speedup. pipeline so each query and database character are compared in parallel, resulting in a table of scores. Genome Sequencing Results: FPGA timing results (for up to 150 FPGAs) were obtained and compared with up to 150 Opterons for sequences of varying size and complexity (e.g. 4GB openfpga.org human DNA benchmark and 155M human vs. 166M mouse DNA). 1 FPGA: Bacillus_anthracis DNA compare: Genomes

59 BASIC BIOLOGICAL SCIENCES↗

Scaling quantum approximate optimization on near-term hardware

The quantum approximate optimization algorithm (QAOA) is an approach for near-term quantum computers to potentially demonstrate computational advantage in solving combinatorial optimization problems. However, the viability of the QAOA depends on how its performance and resource requirements scale with problem size and complexity for realistic hardware implementations. Here, we quantify scaling of the expected resource requirements by synthesizing optimized circuits for hardware architectures with varying levels of connectivity. Assuming noisy gate operations, we estimate the number of measurements needed to sample the output of the idealized QAOA circuit with high probability. We show the number of measurements, and hence total time to solution, grows exponentially in problem size and problem graph degree as well as depth of the QAOA ansatz, gate infidelities, and inverse hardware graph degree. These problems may be alleviated by increasing hardware connectivity or by recently proposed modifications to the QAOA that achieve higher performance with fewer circuit layers.

97 MATHEMATICS AND COMPUTING↗

Application of JMP and design of experiments to security system technology testing.

JMP and design of experiments (DOE) have been successfully applied to security system technologies from sensors to communication and display systems. In all cases, the technologies have been complex enough to warrant the need for a statistical determination of significant factors and/or the generation of predictive models. For the sensors, it was the task of calibrating a fiber optic intrusion detection sensor (FOIDS) with 32 adjustable settings. In addition to the numerous settings, the FOIDS also had two software processors for detecting different types of alarms. The problem was made more complex when the different types of alarms occurred on the wrong processors, causing nuisance alarms. JMP's ability to optimize several predictive models simultaneously with JMP's Prediction Profiler flash files was an important factor in producing field solutions. For the Communications and Display testbed system, numerous hardware and software network components had been integrated to build a functional system. Although the components of the system had been tested individually, the system's performance could not be piecewise evaluated. Through the application of JMP's design of experiments and data mining capabilities, it was possible to test some of the factors affecting the system's performance and to differentiate between some of the software and hardware contributors. This paper will discuss design of experiments and the JMP tools applied to the solutions for both security systems.

47 OTHER INSTRUMENTATION↗

Dispersion-Based Fresh-Slice Scheme for Free-Electron Lasers

The fresh-slice technique improved the performance of several self-amplified spontaneous emission free-electron laser schemes by granting selective control on the temporal lasing slice without spoiling the other electron bunch slices. So far, the implementation has required a special insertion device to create the beam yaw, called a dechirper. Finally, we demonstrate a novel scheme to enable fresh-slice operation based on electron energy chirp and orbit dispersion that can be implemented at any free-electron laser facility without additional hardware.

47 OTHER INSTRUMENTATION↗

Single-node Partitioned-Memory for Huge Graph Analytics: Cost and Performance Trade-offs

Nonvolatile memory NVDIMMs, available as Intel Optane, are less expensive than DRAM and bring large byte-addressable storage within reach to many applications. Evaluations on graph analytics have shown promising performance only when DRAM is used as a hardware cache (Memory mode). An open question is whether graph applications can exploit Optane and DRAM directly (AppDirect mode) and achieving better-than-DRAM average bandwidth and run times. We evaluate Optane as a volatile pool on two large-scale graph applications with very different computational patterns, Grappolo and Ripples. We show that AppDirect mode can deliver better-than-DRAM performance, by allocating data structures to Optane and DRAM according to their access characteristics, resulting in higher average memory bandwidth and lower average latency. Memory mode provides DRAM-competitive performance with capacity equal to persistent memory. We demonstrate occasional 4x improvement using the latest AppDirect option and frequently observe competitive performance between Optane AppDirect Memory modes and DRAM.

Ghosh, Sayan↗

Modular Platforms for Advanced Inspection, Locomotion, and Manipulation - 17150

Robots can provide remote access, manipulation, and inspection capabilities to augment human workers and improve safety in potentially dangerous decommissioning, radioactive waste management, and emergency response operations. However, such activities may require navigating challenging and unstructured environments, such as those with uneven terrain, obstacles, or loose debris. This remains a difficult task, even for modern robots. What's more, a robot's physical design can inhibit it from accessing hard-to-reach areas such as the tight spaces around, underneath, or inside piping and equipment. To address these challenges, we have developed a series of physically robust hardware modules that can be configured into a variety of robot morphologies, specialized to support different operational needs. Each hardware module consists of a number of onboard sensors and a high performance actuator with a series elastic element to sense and control interaction forces for improved locomotion and manipulation. Using this hardware, we have designed several robotic platforms that support the access, manipulation, and inspection requirements of decommissioning and radioactive waste management. To highlight current capabilities and potential opportunities for technological improvement, we present the outcomes from field demonstrations of our modular platforms at the Office of Environmental Management's Science of Safety Portsmouth Gaseous Diffusion Plant Robotics Challenge. Specifically, results include a serpentine robot climbing vertical structures such as pipes, posts, and supports to demonstrate advanced inspection. Additionally, we discuss field trials of a similar modular configuration that yields a highly dexterous manipulator arm and camera system capable of adding manipulation and inspection functionality to existing structures. Results are presented from inspection tasks in which the manipulator is installed on another mobile robotic platform. Finally, we show our hardware modules can be reconfigured into platforms capable of withstanding significant impacts and of alternative means of locomotion, as may be required to cross terrain too challenging for traditional wheeled robots. Results describe the performance of a hexapod robot that uses proprioceptive feedback to locomote in outdoor trials reminiscent of emergency response conditions. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

RanCompute: Computational Security in Embedded Devices via Random Input and Output Encodings

An embedded device in an insecure environment is subject to additional security risk through capture and reverse-engineering by a capable adversary. If this device contains a microchip performing sensitive computations, capture of the chip may leak functionality to an adversary. In this paper we propose a novel method in which we randomly encode the input operands and the outputs of a computation, thus not revealing the arithmetic operations being performed. The operations are sequenced in a graph representing the overall application. Once the initialization values are overwritten and lost, the results of these computations are indecipherable by the device performing the calculations as well as by any adversary. The result is transmitted back to a secure server which has stored the initialization values and so can decode the results which appear random to the adversary.

Embedded computing↗

Design and Implementation of a Radiation Portal Monitor Multi-Lane Simulator

Abstract - Deploying radiation portal monitors (RPMs) at U.S. ports of entry requires an understanding of an RPM system’s performance at sites with a large number of RPMs. This paper describes an RPM Multi-Lane Simulator that has been designed and implemented to simulate vehicle traffic at these sites. The Simulator’s flexible architecture simulates vehicle traffic with its associated radiation profiles and emulates each RPM’s radiation sensor panels. The RPM vendor’s embedded control computer firmware and supervisory software are left unchanged, thereby enabling hardware-in-the-loop testing of RPM system performance in configurations that exceed what is experienced in the field. The Simulator has proven to be a valuable and cost effective performance testing tool used by both Pacific Northwest National Laboratory and U.S. Customs and Border Protection systems integration and testing staff.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

HPC Interconnection Networks: The Key to Exascale Computing

Scientists from many domains desire to address problems within the next decade that, by all estimates, require computer systems that can achieve sustained exaflop computing rates (i.e., 1 x 10{sup 18} floating point operations per second) with real-world applications. Simply scaling existing designs is insufficient: analysis of current technological trends suggests that only a few architectural components are on track to reach the performance levels needed for exascale computing. The network connecting computer system nodes presents a particularly difficult challenge because of the prevalence of a wide variety of communication patterns and collective communication operations in algorithms used in scientific applications and their tendency to be the most significant limit to application scalability. Researchers at Oak Ridge National Laboratory and elsewhere are actively working to overcome these network-related scalability barriers using advanced hardware and software design, alternative network topologies, and performance prediction using modeling and simulation.

97 MATHEMATICS AND COMPUTING↗

Understanding the I/O Performance Gap Between Cori KNL and Haswell

The Cori system at NERSC has two compute partitions with different CPU architectures: a 2,004 node Haswell partition and a 9,688 node KNL partition, which ranked as the 5th most powerful and fastest supercomputer on the November 2016 Top 500 list. The compute partitions share a common storage configuration, and understanding the IO performance gap between them is important, impacting not only to NERSC/LBNL users and other national labs, but also to the relevant hardware vendors and software developers. In this paper, we have analyzed performance of single core and single node IO comprehensively on the Haswell and KNL partitions, and have discovered the major bottlenecks, which include CPU frequencies and memory copy performance. We have also extended our performance tests to multi-node IO and revealed the IO cost difference caused by network latency, buffer size, and communication cost. Overall, we have developed a strong understanding of the IO gap between Haswell and KNL nodes and the lessons learned from this exploration will guide us in designing optimal IO solutions in many-core era.

97 MATHEMATICS AND COMPUTING↗