Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “COMPUTER ARCHITECTURE”

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 1,675 records · Page 93

Performance analysis of a 3D unstructured mesh hydrodynamics code on multi‐core and many‐core architectures

SUMMARY Several next generation high performance computing platforms are or will be based on the so‐called many‐core architectures, which represent a significant departure from commodity multi‐core architectures. A key issue in transitioning large‐scale simulation codes from multi‐core to many‐core systems is closing the serial performance gap, that is, overcoming the large difference in single‐core performance between multi‐core and many‐core systems. In this paper, we discuss how this problem was addressed for a 3D unstructured mesh hydrodynamics code, describe how Amdahl's law can be used to estimate performance targets and guide optimization efforts, and present timing studies performed on multi‐core and many‐core platforms. Published 2014. This article is a U.S. Government work and is in the public domain in the USA.

Waltz, J.↗

Optimizing the performance of reactive molecular dynamics simulations for many-core architectures

Reactive molecular dynamics simulations are computationally demanding. Reaching spatial and temporal scales where interesting scientific phenomena can be observed requires efficient and scalable implementations on modern hardware. In this article, we focus on optimizing the performance of the widely used LAMMPS/ReaxC package for many-core architectures. As hybrid parallelism allows better leverage of the increasing on-node parallelism, we adopt thread parallelism in the construction of bonded and nonbonded lists and in the computation of complex ReaxFF interactions. To mitigate the I/O overheads due to large volumes of trajectory data produced and to save users the burden of post-processing, we also develop a novel in situ tool for molecular species analysis. We analyze the performance of the resulting ReaxC-OMP package on two different architectures: (i) Mira, an IBM Blue Gene/Q system and (ii) Cori-II, a Cray XC-40 sytem with Knights Landing processors. For Pentaerythritol tetranitrate (PETN) systems of sizes ranging from 32 thousand to 16.6 million particles, we observe speedups in the range of 1.5-4.5x. We observe sustained performance improvements for up to 262,144 cores (1,048,576 processes) of Mira and a weak scaling efficiency of 91.5% in large simulations containing 16.6 million particles. Finally, the in situ molecular species analysis tool incurs only insignificant overheads across various system sizes and runs configurations.

97 MATHEMATICS AND COMPUTING↗

Nonvolatile “AND,” “OR,” and “NOT” Boolean logic gates based on phase-change memory

Electronic devices or circuits that can implement both logic and memory functions are regarded as the building blocks for future massive parallel computing beyond von Neumann architecture. Here we proposed phase-change memory (PCM)-based nonvolatile logic gates capable of AND, OR, and NOT Boolean logic operations verified in SPICE simulations and circuit experiments. The logic operations are parallel computing and results can be stored directly in the states of the logic gates, facilitating the combination of computing and memory in the same circuit. These results are encouraging for ultralow-power and high-speed nonvolatile logic circuit design based on novel memory devices.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Exploring code portability solutions for HEP with a particle tracking test code

Traditionally, high energy physics (HEP) experiments have relied on x86 CPUs for the majority of their significant computing needs. As the field looks ahead to the next generation of experiments such as DUNE and the High-Luminosity LHC, the computing demands are expected to increase dramatically. To cope with this increase, it will be necessary to take advantage of all available computing resources, including GPUs from different vendors. A broad landscape of code portability tools—including compiler pragma-based approaches, abstraction libraries, and other tools—allow the same source code to run efficiently on multiple architectures. In this paper, we use a test code taken from a HEP tracking algorithm to compare the performance and experience of implementing different portability solutions. While in several cases portable implementations perform close to the reference code version, we find that the performance varies significantly depending on the details of the implementation. Achieving optimal performance is not easy, even for relatively simple applications such as the test codes considered in this work. Several factors can affect the performance, such as the choice of the memory layout, the memory pinning strategy, and the compiler used. The compilers and tools are being actively developed, so future developments may be critical for their deployment in HEP experiments.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Generating and executing programs for a floating point single instruction multiple data instruction set architecture

Mechanisms for generating and executing programs for a floating point (FP) only single instruction multiple data (SIMD) instruction set architecture (ISA) are provided. A computer program product comprising a computer recordable medium having a computer readable program recorded thereon is provided. The computer readable program, when executed on a computing device, causes the computing device to receive one or more instructions and execute the one or more instructions using logic in an execution unit of the computing device. The logic implements a floating point (FP) only single instruction multiple data (SIMD) instruction set architecture (ISA), based on data stored in a vector register file of the computing device. The vector register file is configured to store both scalar and floating point values as vectors having a plurality of vector elements.

97 MATHEMATICS AND COMPUTING↗

Implementing a neural network interatomic model with performance portability for emerging exascale architectures

The two main thrusts of computational science are increasingly accurate predictions and faster calculations; to this end, the zeitgeist in molecular dynamics (MD) simulations is pursuing machine learned and data driven interatomic models, e.g. neural network potentials, and novel hardware architectures, e.g. GPUs. Current implementations of neural network potentials are orders of magnitude slower than traditional interatomic models and while looming exascale computing offers the ability to run large, accurate simulations with these models, achieving portable performance for MD with new and varied exascale hardware requires rethinking traditional algorithms, using novel data structures, and library solutions. We re-implement a neural network interatomic model in CabanaMD, an MD proxy application, built on libraries developed for performance portability. Our implementation shows significantly improved thread scaling in this complex kernel as compared to a current LAMMPS implementation, across both strong and weak scaling. Our single-source solution enables simulations up to 20 million atoms on a single CPU node and 4 million atoms with improved performance on a single GPU. Furthermore, we also explore parallelism and data layout choices (using flexible data structures called AoSoAs) and their effect on performance, seeing up to ~50% and ~5% improvements in performance on a GPU by choosing the right level of parallelism and data layout respectively.

97 MATHEMATICS AND COMPUTING↗

Architectural concepts and redundancy techniques in fault-tolerant computers

This paper presents a description of redundancy techniques employed in the design of fault-tolerant computers, and a discussion of the effects of functional requirements, technology constraints, and cost considerations which enter into the choice of these techniques. The STAR computer, developed at the Jet Propulsion Laboratory for long-duration planetary spacecraft missions, is discussed along with several later fault-tolerant computer designs. The class of computers described in this paper employs dynamic redundancy, i.e., the machine is divided into a set of submodules, each with standby spares; a special hard core monitor unit detects and diagnoses faults, and effects automated recovery by replacing failed parts.

Rennels, D. A.↗

Systolic multipliers for finite fields GF(2 exp m)

Two systolic architectures are developed for performing the product-sum computation AB + C in the finite field GF(2 exp m) of 2 exp m elements, where A, B, and C are arbitrary elements of GF(2 exp m). The first multiplier is a serial-in, serial-out one-dimensional systolic array, while the second multiplier is a parallel-in, parallel-out two-dimensional systolic array. The first multiplier requires a smaller number of basic cells than the second multiplier. The second multiplier needs less average time per computation than the first multiplier, if a number of computations are performed consecutively. To perform single computations both multipliers require the same computational time. In both cases the architectures are simple and regular and possess the properties of concurrency and modularity. As a consequence, they are well suited for use in VLSI systems.

Yeh, C.-S.↗

Formal design and verification of a reliable computing platform for real-time control. Phase 1: Results

A high-level design is presented for a reliable computing platform for real-time control applications. Design tradeoffs and analyses related to the development of the fault-tolerant computing platform are discussed. The architecture is formalized and shown to satisfy a key correctness property. The reliable computing platform uses replicated processors and majority voting to achieve fault tolerance. Under the assumption of a majority of processors working in each frame, it is shown that the replicated system computes the same results as a single processor system not subject to failures. Sufficient conditions are obtained to establish that the replicated system recovers from transient faults within a bounded amount of time. Three different voting schemes are examined and proved to satisfy the bounded recovery time conditions.

Divito, Ben L.↗

Exploring OpenSNAPI Use Cases and Evolving Requirements [Slides]

Emerging system architectures are rapidly transforming in order to meet shifting requirements. Motivated by expanding data volumes, energy efficiency concerns, and the omnipresent need to improve performance, architectures are increasingly adopting a data-centric approach. At the core of this concept is the goal of minimizing data motion and instead processing data in-situ to the greatest degree possible. Therefore, data-centric designs, in contrast to conventional CPU-centric models, typically distribute compute capabilities throughout the architecture. As part of this paradigm shift, a novel class of devices known as data processing units (DPUs), alongside CPUs and GPUs, are quickly forming a third pillar of data-centric systems. These devices, which include smart network adapters and switches, seek to offload computation on data at the network edge as well as in-flight within the network fabric. The Open Smart Network API (OpenSNAPI) project seeks to develop a unified API for DPU devices. In our previous talks, we introduced the OpenSNAPI project and detailed our investigations regarding the viability of offloading compute intensive kernels to BlueField DPUs. In contrast, in this talk we detail our efforts to offload application-level file I/O to the DPU. We also discuss plans and early efforts to explore in-network compute capabilities. Finally, we describe our observations with respect to the evolving design of OpenSNAPI.

97 MATHEMATICS AND COMPUTING↗

The physics of parallel machines

The idea is considered that architectures for massively parallel computers must be designed to go beyond supporting a particular class of algorithms to supporting the underlying physical processes being modelled. Physical processes modelled by partial differential equations (PDEs) are discussed. Also discussed is the idea that an efficient architecture must go beyond nearest neighbor mesh interconnections and support global and hierarchical communications.

Chan, Tony F.↗

Materials loss measurements using superconducting microwave resonators

The performance of superconducting circuits for quantum computing is limited by materials losses. In particular, coherence times are typically bounded by two-level system (TLS) losses at single photon powers and millikelvin temperatures. The identification of low loss fabrication techniques, materials, and thin film dielectrics is critical to achieving scalable architectures for superconducting quantum computing. Superconducting microwave resonators provide a convenient qubit proxy for assessing performance and studying TLS loss and other mechanisms relevant to superconducting circuits such as non-equilibrium quasiparticles and magnetic flux vortices. In this review article, we provide an overview of considerations for designing accurate resonator experiments to characterize loss, including applicable types of losses, cryogenic setup, device design, and methods for extracting material and interface losses, summarizing techniques that have been evolving for over two decades. Results from measurements of a wide variety of materials and processes are also summarized. Finally, we present recommendations for the reporting of loss data from superconducting microwave resonators to facilitate materials comparisons across the field.

47 OTHER INSTRUMENTATION↗

An ICAI architecture for troubleshooting in complex, dynamic systems

Ahab, an intelligent computer-aided instruction (ICAI) program, illustrates an architecture for simulator-based ICAI programs to teach troubleshooting in complex, dynamic environments. The architecture posits three elements of a computerized instructor: the task model, the student model, and the instructional module. The task model is a prescriptive model of expert performance that uses symptomatic and topographic search strategies to provide students with directed problem-solving aids. The student model is a descriptive model of student performance in the context of the task model. This student model compares the student and task models, critiques student performance, and provides interactive performance feedback. The instructional module coordinates information presented by the instructional media, the task model, and the student model so that each student receives individualized instruction. Concept and metaconcept knowledge that supports these elements is contained in frames and production rules, respectively. The results of an experimental evaluation are discussed. They support the hypothesis that training with an adaptive online system built using the Ahab architecture produces better performance than training using simulator practice alone, at least with unfamiliar problems. It is not sufficient to develop an expert strategy and present it to students using offline materials. The training is most effective if it adapts to individual student needs.

Fath, Janet L.↗

Systems and methods for architecture-independent binary code analysis

Binaries configured for execution within respective computing environments may be disassembled into architecture-specific intermediate (AIL) representations. The AIL representations may be converted into canonical intermediate language (CIL) representations. The CIL representations may comprise normalized, architecture-independent code configured to characterize functionality of respective components of a binary (e.g., respective functions or the like). Feature vectors may be extracted from the CIL representations. The feature vectors may be used to identify components of respective binaries, assign security classifications to the binaries, and/or the like.

Haile, Jedediah T.↗

On-board computers for control

On-board computers for control and sequencing from Apollo to Voyager are described along with future trends and recent design examples. Consideration is given to a high-order language for the Space Shuttle program. Emphasis is placed on the usage of modern LSI and new distributed architectural approaches. The distributed computer of the Galileo spacecraft and the data processing system for the Shuttle Orbiter are outlined.

Scull, J. R.↗

Experimental evaluation of the impact of packet capturing tools for web services.

Network measurement is a discipline that provides the techniques to collect data that are fundamental to many branches of computer science. While many capturing tools and comparisons have made available in the literature and elsewhere, the impact of these packet capturing tools on existing processes have not been thoroughly studied. While not a concern for collection methods in which dedicated servers are used, many usage scenarios of packet capturing now requires the packet capturing tool to run concurrently with operational processes. In this work we perform experimental evaluations of the performance impact that packet capturing process have on web-based services; in particular, we observe the impact on web servers. We find that packet capturing processes indeed impact the performance of web servers, but on a multi-core system the impact varies depending on whether the packet capturing and web hosting processes are co-located or not. In addition, the architecture and behavior of the web server and process scheduling is coupled with the behavior of the packet capturing process, which in turn also affect the web server's performance.

99 GENERAL AND MISCELLANEOUS↗