Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Multiple processors”

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 361 records · Page 20

Method and apparatus for evaluating superconducting tunnel junction detector noise versus bias voltage

A technique for characterizing the noise behavior of a superconducting tunnel junction (STJ) detector as a function of its applied bias voltage Vb by stepping the STJ's bias voltage across a predetermined range and, at each applied bias, making multiple measurements of the detector's current, calculating their mean and their standard deviation from their mean, and using this standard deviation as a measure of the STJ detector's noise at that applied bias. Because the method is readily executed under computer control, it is particularly useful when large numbers of STJ detectors require biasing, as in STJ detector arrays In a preferred implementation, the STJ is measured under computer control by attaching it to a digital spectrometer comprising a digital x-ray processor (DXP) coupled to a preamplifier that can set the STJ's bias voltage Vb using a digital-to-analog converter (DAC) controlled by the DXP.

Warburton, William K.↗

Improving MPI Collective I/O for High Volume Non-Contiguous Requests With Intra-Node Aggregation

Two-phase I/O is a well-known strategy for implementing collective MPI-IO functions. It redistributes I/O requests among the calling processes into a form that minimizes the file access costs. As modern parallel computers continue to grow into the exascale era, the communication cost of such request redistribution can quickly overwhelm collective I/O performance. In this study, this effect has been observed from parallel jobs that run on multiple compute nodes with a high count of MPI processes on each node. Furthermore, to reduce the communication cost, we present a new design for collective I/O by adding an extra communication layer that performs request aggregation among processes within the same compute nodes. This approach can significantly reduce inter-node communication contention when redistributing the I/O requests. We evaluate the performance and compare it with the original two-phase I/O on Cray XC40 parallel computers (Theta and Cori) with Intel KNL and Haswell processors. Using I/O patterns from two large-scale production applications and an I/O benchmark, we show our proposed method effectively reduces the communication cost and hence maintains the scalability for a large number of processes.

97 MATHEMATICS AND COMPUTING↗

Modeling UV Radiation Feedback from Massive Stars. I. Implementation of Adaptive Ray-tracing Method and Tests [Modeling UV Radiation Feedback from Massive Stars: I. Implementation of Adaptive Ray Tracing Algorithm]

Here, we present an implementation of an adaptive ray-tracing (ART) module in the Athena hydrodynamics code that accurately and efficiently handles the radiative transfer involving multiple point sources on a three-dimensional Cartesian grid. We adopt a recently proposed parallel algorithm that uses nonblocking, asynchronous MPI communications to accelerate transport of rays across the computational domain. We validate our implementation through several standard test problems, including the propagation of radiation in vacuum and the expansions of various types of H II regions. Additionally, scaling tests show that the cost of a full ray trace per source remains comparable to that of the hydrodynamics update on up to $\sim {10}^{3}$ processors. To demonstrate application of our ART implementation, we perform a simulation of star cluster formation in a marginally bound, turbulent cloud, finding that its star formation efficiency is 12% when both radiation pressure forces and photoionization by UV radiation are treated. We directly compare the radiation forces computed from the ART scheme with those from the M 1 closure relation. Although the ART and M 1 schemes yield similar results on large scales, the latter is unable to resolve the radiation field accurately near individual point sources.

79 ASTRONOMY AND ASTROPHYSICS↗

Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence

With the advent of faster computer processors and especially graphics processing units (GPUs) over the last few decades, the use of data-intensive machine learning (ML) and artificial intelligence (AI) has increased greatly, and the study of crystal nucleation has been one of the beneficiaries. In this study, we outline how ML and AI have been applied to address four outstanding difficulties of crystal nucleation: how to discover better reaction coordinates (RCs) for describing accurately non-classical nucleation situations; the development of more accurate force fields for describing the nucleation of multiple polymorphs or phases for a single system; more robust identification methods for determining crystal phases and structures; and as a method to yield improved course-grained models for studying nucleation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DIissolution of low enriched uranium from the experimental breeder reactor-II fuel stored at the Idaho National Laboratory

The Idaho National Laboratory (INL) is actively engaged in the development of electrochemical processing technology for the treatment of fast reactor fuels using irradiated fuel from the Experimental Breeder Reactor-II (EBR-II) as the primary test material. The research and development (R&D) activities generate a low enriched uranium (LEU) metal product from the electrorefining of the EBR-II fuel and the subsequent consolidation and removal of chloride salts by the cathode processor. The LEU metal ingots from past R&D activities are currently stored at INL awaiting disposition. One potential disposition pathway is the shipment of the ingots to the Savannah River Site (SRS) for dissolution in H-Canyon. Carbon steel cans containing the LEU metal would be loaded into reusable charging bundles in the H-Canyon Crane Maintenance Area and charged to the 6.4D or 6.1D dissolver. The LEU dissolution would be accomplished as the final charge in a dissolver batch (following the dissolution of multiple charges of spent nuclear fuel (SNF)). The solution would then be purified and the 235 U enrichment downblended to allow use of the U in commercial reactor fuel. To support this potential disposition path, the Savannah River National Laboratory (SRNL) developed a dissolution flowsheet for the LEU using samples of the material received from INL.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

CTF 4.0 User's Manual

The deck version is specified using the PPV flag on Card 1.1. In general, you should always use the latest version of the CTF input deck in order to make sure your model is treated correctly in CTF. This feature was added to retain backwards compatibility for older input decks. When an input deck is created with the CTF pre-processor, the latest version will always be used. Table 1 provides the revision history of the CTF input deck. The first column gives the version number of the deck and the second columns gives a description of what changed since the previous version of the input deck. This document describes how to make a CTF input deck. A CTF input deck is organized into Card Groups and Cards. A Card Group is a collection of Cards. A Card is defined as a line of input. Each Card may contain multiple data. A Card is terminated by making a new line. This document has been organized so that each Card Group is discussed in its own dedicated chapter. Each card is discussed in its own dedicated section. Each data in the card is discussed in its own block. The block gives information about the data, including the number of the input, the title, a description of the meaning of the data, units, data type, and so on. An example block is shown below to discuss the meaning of each entry in the block.

97 MATHEMATICS AND COMPUTING↗

A performance study of the time-varying cache behavior: a study on APEX, Mantevo, NAS, and PARSEC

Cache has long been used to minimize the latency of main memory accesses by storing frequently used data near the processor. Processor performance depends on the underlying cache performance. Therefore, significant research has been done to identify the most crucial metrics of cache performance. Although the majority of research focuses on measuring cache hit rates and data movement as the primary cache performance metrics, cache utilization is significantly important. We investigate the application’s locality using cache utilization metrics. In addition, we present cache utilization and traditional cache performance metrics as the program progresses providing detailed insights into the dynamic application behavior on parallel applications from four benchmark suites running on multiple cores. We explore cache utilization for APEX, Mantevo, NAS, and PARSEC, mostly scientific benchmark suites. Our results indicate that 40% of the data bytes in a cache line are accessed at least once before line eviction. Also, on average a byte is accessed two times before the cache line is evicted for these applications. Moreover, we present runtime cache utilization, as well as, conventional performance metrics that illustrate a holistic understanding of cache behavior. To facilitate this research, we build a memory simulator incorporated into the Structural Simulation Toolkit (Rodrigues et al. in SIGMETRICS Perform Eval Rev 38(4):37–42, 2011). Finally, our results suggest that variable cache line size can result in better performance and can also conserve power.

97 MATHEMATICS AND COMPUTING↗

Designing Next Generation Massively Multithreaded Architectures for Irregular Applications

Irregular applications, such as data mining or graph-based computations, show unpredictable memory/network access patterns and control structures. Massively multi-threaded architectures with large node count, like the Cray XMT, have been shown to address their requirements better than commodity clusters. In this paper we present the approaches that we are currently pursuing to design future generations of these architectures. First, we introduce the Cray XMT and compare it to other multithreaded architectures. We then propose an evolution of the architecture, integrating multiple cores per node and next generation network interconnect. We advocate the use of hardware support for remote memory reference aggregation to optimize network utilization. For this evaluation we developed a highly parallel, custom simulation infrastructure for multi-threaded systems. Our simulator executes unmodified XMT binaries with very large datasets, capturing effects due to contention and hot-spotting, while predicting execution times with greater than 90% accuracy. We also discuss the FPGA prototyping approach that we are employing to study efficient support for irregular applications in next generation manycore processors.

Tumeo, Antonino↗

Optimization of Forward Wave Modeling on Contemporary HPC Architectures

Reverse Time Migration (RTM) is one of the main approaches in the seismic processing industry for imaging the subsurface structure of the Earth. While RTM provides qualitative advantages over its predecessors, it has a high computational cost warranting implementation on HPC architectures. We focus on three progressively more complex kernels extracted from RTM: for isotropic (ISO), vertical transverse isotropic (VTI) and tilted transverse isotropic (TTI) media. In this work, we examine performance optimization of forward wave modeling, which describes the computational kernels used in RTM, on emerging multi- and manycore processors and introduce a novel common subexpression elimination optimization for TTI kernels. We compare attained performance and energy efficiency in both the single-node and distributed memory environments in order to satisfy industry’s demands for fidelity, performance, and energy efficiency. Moreover, we discuss the interplay between architecture (chip and system) and optimizations (both on-node computation) highlighting the importance of NUMA-aware approaches to MPI communication. Ultimately, our results show we can improve CPU energy efficiency by more than 10× on Magny Cours nodes while acceleration via multiple GPUs can surpass the energy-efficient Intel Sandy Bridge by as much as 3.6×.

97 MATHEMATICS AND COMPUTING↗

Performance Models for Split-execution Computing Systems

Split-execution computing leverages the capabilities of multiple computational models to solve problems, but splitting program execution across different computational models incurs costs associated with the translation between domains. We analyze the performance of a split-execution computing system developed from conventional and quantum processing units (QPUs) by using behavioral models that track resource usage. We focus on asymmetric processing models built using conventional CPUs and a family of special-purpose QPUs that employ quantum computing principles. Our performance models account for the translation of a classical optimization problem into the physical representation required by the quantum processor while also accounting for hardware limitations and conventional processor speed and memory. We conclude that the bottleneck in this split-execution computing system lies at the quantum-classical interface and that the primary time cost is independent of quantum processor behavior.

multiprocessor↗

Multiple Component Multiple Data Programming in Subsurface Simulations: The CCA Approach

The dynamic nature and the encapsulation provided by the component approach maps quite naturally to the concepts of multiple-program multiple-data (MPMD) programming. In this paper, we will introduce a new programming model called multiple component multiple data (MCMD). The MCMD model provides a high-level infrastructure in the common component architecture (CCA) environment to exploit hardware parallelism in emerging petascale and exascale systems. We demonstrate the effectiveness of CCA MCMD programming in context of subsurface simulations to express and manage many-task parallelism. Our target application is STOMP, a large scale (~800K lines of code) subsurface simulation code. The performance results for a 3D saturated flow problem with the STOMP CCA framework show that the MCMD programming model is very effective to achieve scalability on thousands of processors with high efficiency. For example, to simulate the saturated flow problem containing ~1.2 million nodes on 2048 processors, the CCA MCMD version of STOMP is an order of magnitude faster than the original parallel version of STOMP.

99 GENERAL AND MISCELLANEOUS↗

Modular Countermine Payload for Small Robots

Payloads for small robotic platforms have historically been designed and implemented as platform and task specific solutions. A consequence of this approach is that payloads cannot be deployed on different robotic platforms without substantial re-engineering efforts. To address this issue, we developed a modular countermine payload that is designed from the ground-up to be platform agnostic. The payload consists of the multi-mission payload controller unit (PCU) coupled with the configurable mission specific threat detection, navigation and marking payloads. The multi-mission PCU has all the common electronics to control and interface to all the payloads. It also contains the embedded processor that can be used to run the navigational and control software. The PCU has a very flexible robot interface which can be configured to interface to various robot platforms. The threat detection payload consists of a two axis sweeping arm and the detector. The navigation payload consists of several perception sensors that are used for terrain mapping, obstacle detection and navigation. Finally, the marking payload consists of a dual-color paint marking system. Through the multi-mission PCU, all these payloads are packaged in a platform agnostic way to allow deployment on multiple robotic platforms, including Talon and Packbot.

42 ENGINEERING↗

Exploiting first-class arrays in Fortran for accelerator programming

Emerging architectures for high performance computing often are well suited to a data parallel programming model. This paper presents a simple programming methodology based on existing languages and compiler tools that allows programmers to take advantage of these systems. We will work with the array features of Fortran 90 to show how this infrequently exploited, standardized language feature is easily transformed to lower level accelerator code. Our transformations are based on a mapping from Fortran 90 to C++ code with OpenCL extensions. The sheer complexity of programming for clusters of many or multi-core processors with tens of millions threads of execution make the simplicity of the data parallel model attractive. Furthermore, the increasing complexity of todays applications (especially when convolved with the increasing complexity of the hardware) and the need for portability across hardware architectures make a higher-level and simpler programming model like data parallel attractive. The goal of this work has been to exploit source-to-source transformations that allow programmers to develop and maintain programs at a high-level of abstraction, without coding to a specific hardware architecture. Furthermore these transformations allow multiple hardware architectures to be targeted without changing the high-level source. It also removes the necessity for application programmers to understand details of the accelerator architecture or to know OpenCL.

43 PARTICLE ACCELERATORS↗

Performance Evaluation of an Intelligent Sensor Platform for Radiation Monitoring Applications

Accurate, rugged, and reliable radiation detection systems are important for area and environmental monitoring applications. The desire for spectroscopic capability has increased in monitoring aspects of the nuclear fuel cycle to provide fast characterization of the radiation profile of a situation, such as the planned or unplanned release of material. The reduction or elimination of having to conduct sampling for laboratory analysis can result in significant cost savings for an industry, government agency, or regulatory body. A new system, comprised of a NaI:Tl scintillator and a G-M tube, has been designed and tested, taking into account the following end-user requirements: ease-of-use, capability to network and supervise multiple units, compact form factor, low power consumption, versatility, and stability. The detector sizes were selected to accommodate a dose rate up to 1 Sv/hr. Several algorithms and analysis routines have been developed to incorporate these key needs without sacrificing on accuracy, dynamic range, nuclide identification, and sensitivity. This presentation will introduce the major hardware and software components of the platform, as well as the user interface and data analysis workflow. Key features of the hardware include an environmentally robust housing, low power signal processing electronics, patented LED-based gain stabilization, and an embedded processor for unattended instrument management and data analysis. New and improved algorithms for determining scintillator gamma dose rates, total integrated dose, and nuclide identification will be introduced. The two detector elements were modeled with MCNP and validated experimentally. The results of the radiological testing shall be presented including energy resolution, throughput, dose response, and minimum detectable activities. The dose response has been evaluated in simulations and with measurements to ensure accurate response with respect to energy spectrum of the dose field and direction of the incident radiation. Spectroscopy evaluations, such as nuclide detection probability and false alarm rates, were performed and comparisons to existing algorithms shall also be presented. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Numerical gate synthesis for quantum heuristics on bosonic quantum processors

There is a recent surge of interest and insights regarding the interplay of quantum optimal control and variational quantum algorithms. We study the framework in the context of qudits which are, for instance, definable as controllable electromagnetic modes of a superconducting cavity system coupled to a transmon. By employing recent quantum optimal control approaches described in (Petersson and Garcia, 2021), we showcase control of single-qudit operations up to eight states, and two-qutrit operations, mapped respectively onto a single mode and two modes of the resonator. We discuss the results of numerical pulse engineering on the closed system for parametrized gates useful to implement Quantum Approximate Optimization Algorithm (QAOA) for qudits. The results show that high fidelity ( > 0.99) is achievable with sufficient computational effort for most cases under study, and extensions to multiple modes and open, noisy systems are possible. The tailored pulses can be stored and used as calibrated primitives for a future compiler in circuit quantum electrodynamics (cQED) systems.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Refactoring the elastic–viscous–plastic solver from the sea ice model CICE v6.5.1 for improved performance

This study focuses on the performance of the elastic–viscous–plastic (EVP) dynamical solver within the sea ice model, CICE v6.5.1. The study has been conducted in two steps. First, the standard EVP solver was extracted from CICE for experiments with refactored versions, which are used for performance testing. Second, one refactored version was integrated and tested in the full CICE model to demonstrate that the new algorithms do not significantly impact the physical results. The study reveals two dominant bottlenecks, namely (1) the number of Message Parsing Interface (MPI) and Open Multi-Processing (OpenMP) synchronization points required for halo exchanges during each time step combined with the irregular domain of active sea ice points and (2) the lack of single-instruction, multiple-data (SIMD) code generation. The standard EVP solver has been refactored based on two generic patterns. The first pattern exposes how general finite differences on masked multi-dimensional arrays can be expressed in order to produce significantly better code generation by changing the memory access pattern from random access to direct access. The second pattern takes an alternative approach to handle static grid properties. The measured single-core performance improvement is more than a factor of 5 compared to the standard implementation. The refactored implementation of strong scales on the Intel® Xeon® Scalable Processors series node until the available bandwidth of the node is used. For the Intel® Xeon® CPU Max series, there is sufficient bandwidth to allow the strong scaling to continue for all the cores on the node, resulting in a single-node improvement factor of 35 over the standard implementation. This study also demonstrates improved performance on GPU processors.

58 GEOSCIENCES↗

CUDA Computation of the Feynman Distribution

In 2006, NVIDIA Corporation introduced the Computer Unified Device Architecture (CUDA) for C, C++, and Fortran programming languages. The CUDA parallel computing platform uses the Graphics Processing Unit (GPU) of NVIDIA graphics card, and it is designed for parallel computations. In these computations, the same algorithms are executed on the data in parallel. The GPU contains many Streaming Multiprocessors (SM) that can independently execute blocks of threads. A thread is a sequence of serial programmed instructions. The SM executes threads in groups of 32 and a group of 32 threads is called warp. The threads within a block can be synchronized and have access to a shared memory that is visible only to them. Conversely, blocks of threads cannot be synchronized and have access only to the global memory of the graphics card. This memory is called device memory and is independent of the host memory controlled by the Central Processing Unit (CPU). A single thread has access to a local memory (register) that is not visible to any other thread. The part of the program that is executed on the graphics card is called kernel. Each thread of the kernel has a unique identification index that is accessible by the in-built variable threadIdx; the latter is a 3-component vector. A threads block can contain up to 1024 threads. Blocks of threads have a unique identification index that is accessible by the in-built variable blockIdx; the latter is a 3-component vector. The in-built variable blockDim contains the number of threads per block; this variable is a 3-component vector. Threads and blocks represent different levels of parallelism; a kernel is executed as a grid of blocks of threads. Figure 1 illustrates a grid of thread blocks for a GPU with 2 SM. A SM can execute multiple blocks of threads in parallel; a block of threads is executed on a single SM. A GPU can execute multiple kernels concurrently. This work has used the Quadro M5000 graphics card with the following technical specifications: - 2048 cores with 861 MHz frequency, - 16 streaming multiprocessors, - 5.2 trillion transistors, - 8.2 Gb device memory, - 64 kb register memory (per thread), - 48 kb shared memory (per block) - 211.6 GB/s memory bandwidth, and - 3.5 GFLOPS floating point performance.

97 MATHEMATICS AND COMPUTING↗

High-performance computing with quantum processing units

The prospects of quantum computing have driven efforts to realize fully functional quantum processing units (QPUs). Recent success in developing proof-of-principle QPUs has prompted the question of how to integrate these emerging processors into modern high-performance computing (HPC) systems. We examine how QPUs can be integrated into current and future HPC system architectures by accounting for func- tional and physical design requirements. We identify two integration pathways that are differentiated by infrastructure constraints on the QPU and the use cases expected for the HPC system. This includes a tight integration that assumes infrastructure bottlenecks can be overcome as well as a loose integration that as- sumes they cannot. We find that the performance of both approaches is likely to depend on the quantum interconnect that serves to entangle multiple QPUs. As a result, we also identify several challenges in assessing QPU performance for HPC, and we consider new metrics that capture the interplay between system architecture and the quantum parallelism underlying computational performance.

97 MATHEMATICS AND COMPUTING↗