Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “compute in memory”

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 1,189 records · Page 66
All sourcesNASA NTRSDOE OSTI
NASA NTRS2000

Dynamic Load-Balancing for Distributed Heterogeneous Computing of Parallel CFD Problems

The developed methodology is aimed at improving the efficiency of executing block-structured algorithms on parallel, distributed, heterogeneous computers. The basic approach of these algorithms is to divide the flow domain into many sub- domains called blocks, and solve the governing equations over these blocks. Dynamic load balancing problem is defined as the efficient distribution of the blocks among the available processors over a period of several hours of computations. In environments with computers of different architecture, operating systems, CPU speed, memory size, load, and network speed, balancing the loads and managing the communication between processors becomes crucial. Load balancing software tools for mutually dependent parallel processes have been created to efficiently utilize an advanced computation environment and algorithms. These tools are dynamic in nature because of the chances in the computer environment during execution time. More recently, these tools were extended to a second operating system: NT. In this paper, the problems associated with this application will be discussed. Also, the developed algorithms were combined with the load sharing capability of LSF to efficiently utilize workstation clusters for parallel computing. Finally, results will be presented on running a NASA based code ADPAC to demonstrate the developed tools for dynamic load balancing.

Ecer, A.↗
DOE OSTI2021

Xyce Parallel Electronic Simulator Users' Guide (V. 7.3)

This manual describes the use of the Xyce Parallel Electronic Simulator. Xyce has been designed as a SPICE-compatible, high-performance analog circuit simulator, and has been written to support the simulation needs of the Sandia National Laboratories electrical designers. This development has focused on improving capability over the current state-of-the-art in the following areas: Capability to solve extremely large circuit problems by supporting large-scale parallel computing platforms (up to thousands of processors). This includes support for most popular parallel and serial computers; A differential-algebraic-equation (DAE) formulation, which better isolates the device model package from solver algorithms. This allows one to develop new types of analysis without requiring the implementation of analysis-specific device models; Device models that are specifically tailored to meet Sandia's needs, including some radiation-aware devices (for Sandia users only); Object-oriented code design and implementation using modern coding practices. Xyce is a parallel code in the most general sense of the phrase—a message passing parallel implementation—which allows it to run efficiently a wide range of computing platforms. These include serial, shared-memory and distributed-memory parallel platforms. Attention has been paid to the specific nature of circuit-simulation problems to ensure that optimal parallel efficiency is achieved as the number of processors grows.

42 ENGINEERING↗
DOE OSTI2024

Xyce™ Parallel Electronic Simulator Users' Guide (V.7.9)

This manual describes the use of the Xyce Parallel Electronic Simulator. Xyce has been designed as a SPICE-compatible, high-performance analog circuit simulator, and has been written to support the simulation needs of the Sandia National Laboratories electrical designers. This development has focused on improving capability over the current state-of-the-art in the following areas: • Capability to solve extremely large circuit problems by supporting large-scale parallel computing platforms (up to thousands of processors). This includes support for most popular parallel and serial computers. • A differential-algebraic-equation (DAE) formulation, which better isolates the device model package from solver algorithms. This allows one to develop new types of analysis without requiring the implementation of analysis-specific device models. • Device models that are specifically tailored to meet Sandia’s needs, including some radiation-aware devices (for Sandia users only). • Object-oriented code design and implementation using modern coding practices. Xyce is a parallel code in the most general sense of the phrase — a message passing parallel implementation — which allows it to run efficiently a wide range of computing platforms. These include serial, shared-memory and distributed-memory parallel platforms. Attention has been paid to the specific nature of circuit-simulation problems to ensure that optimal parallel efficiency is achieved as the number of processors grows.

42 ENGINEERING↗
DOE OSTI2021

Xyce Parallel Electronic Simulator Users' Guide Version 7.4

This manual describes the use of the Xyce Parallel Electronic Simulator. Xyce has been designed as a SPICE-compatible, high-performance analog circuit simulator, and has been written to support the simulation needs of the Sandia National Laboratories electrical designers. This development has focused on improving capability over the current state-of-the-art in the following areas: • Capability to solve extremely large circuit problems by supporting large-scale parallel computing platforms (up to thousands of processors). This includes support for most popular parallel and serial computers. • A differential-algebraic-equation (DAE) formulation, which better isolates the device model package from solver algorithms. This allows one to develop new types of analysis without requiring the implementation of analysis-specific device models. • Device models that are specifically tailored to meet Sandia’s needs, including some radiation-aware devices (for Sandia users only). • Object-oriented code design and implementation using modern coding practices. Xyce is a parallel code in the most general sense of the phrase — a message passing parallel implementation — which allows it to run efficiently a wide range of computing platforms. These include serial, shared-memory and distributed-memory parallel platforms. Attention has been paid to the specific nature of circuit-simulation problems to ensure that optimal parallel efficiency is achieved as the number of processors grows.

42 ENGINEERING↗
DOE OSTI2024

GPU-enabled extreme-scale turbulence simulations: Fourier pseudo-spectral algorithms at the exascale using OpenMP offloading

Fourier pseudo-spectral methods for nonlinear partial differential equations are of wide interest in many areas of advanced computational science, including direct numerical simulation of three-dimensional (3-D) turbulence governed by the Navier-Stokes equations in fluid dynamics. This paper presents a new capability for simulating turbulence at a new record resolution up to 35 trillion grid points, on the world's first exascale computer, Frontier, comprising AMD MI250x GPUs with HPE's Slingshot interconnect and operated by the US Department of Energy's Oak Ridge Leadership Computing Facility (OLCF). Key programming strategies designed to take maximum advantage of the machine architecture involve performing almost all computations on the GPU which has the same memory capacity as the CPU, performing all-to-all communication among sets of parallel processes directly on the GPU, and targeting GPUs efficiently using OpenMP offloading for intensive number-crunching including 1-D Fast Fourier Transforms (FFT) performed using AMD ROCm library calls. With 99% of computing power on Frontier being on the GPU, leaving the CPU idle leads to a net performance gain via avoiding the overhead of data movement between host and device except when needed for some I/O purposes. Memory footprint including the size of communication buffers for MPI_ALLTOALL is managed carefully to maximize the largest problem size possible for a given node count. Detailed performance data including separate contributions from different categories of operations to the elapsed wall time per step are reported for five grid resolutions, from 2048 3 on a single node to 32768 3 on 4096 or 8192 nodes out of 9408 on the system. Both 1D and 2D domain decompositions which divide a 3D periodic domain into slabs and pencils respectively are implemented. The present code suite (labeled by the acronym GESTS, GPUs for Extreme Scale Turbulence Simulations) achieves a figure of merit (in grid points per second) exceeding goals set in the Center for Accelerated Application Readiness (CAAR) program for Frontier. The performance attained is highly favorable in both weak scaling and strong scaling, with notable departures only for 2048 3 where communication is entirely intra-node, and for 32768 3 , where a challenge due to small message sizes does arise. Communication performance is addressed further using a lightweight test code that performs all-to-all communication in a manner matching the full turbulence simulation code. Performance at large problem sizes is affected by both small message size due to high node counts as well as dragonfly network topology features on the machine, but is consistent with official expectations of sustained performance on Frontier. Overall, although not perfect, the scalability achieved at the extreme problem size of 32768 3 (and up to 8192 nodes — which corresponds to hardware rated at just under 1 exaflop/sec of theoretical peak computational performance) is arguably better than the scalability observed using prior state-of-the-art algorithms on Frontier's predecessor machine (Summit) at OLCF. New science results for the study of intermittency in turbulence enabled by this code and its extensions are to be reported separately in the near future.

3D fast Fourier transform↗
DOE OSTI2023

Photothermally Activated Artificial Neuromorphic Synapses

Biological nervous systems rely on the coordination of billions of neurons with complex, dynamic connectivity to enable the ability to process information and form memories. In turn, artificial intelligence and neuromorphic computing platforms have sought to mimic biological cognition through software-based neural networks and hardware demonstrations utilizing memristive circuitry with fixed dynamics. Here, to incorporate the advantages of tunable dynamic software implementations of neural networks into hardware, we develop a proof-of-concept artificial synapse with adaptable resistivity. This synapse leverages the photothermally induced local phase transition of VO 2 thin films by temporally modulated laser pulses. Such a process quickly modifies the conductivity of the film site-selectively by a factor of 500 to “activate” these neurons and store “memory” by applying varying bias voltages to induce self-sustained Joule heating between electrodes after activation with a laser. These synapses are demonstrated to undergo a complete heating and cooling cycle in less than 120 ns.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (distributed parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

graph algorithms, high performance comptuing↗
DOE OSTI2024

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (Distributed Parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve an optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively, the performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

Sattar, Naw Safrin↗
NASA NTRS1992

Supercomputers Of The Future

Report evaluates supercomputer needs of five key disciplines: turbulence physics, aerodynamics, aerothermodynamics, chemistry, and mathematical modeling of human vision. Predicts these fields will require computer speed greater than 10(Sup 18) floating-point operations per second (FLOP's) and memory capacity greater than 10(Sup 15) words. Also, new parallel computer architectures and new structured numerical methods will make necessary speed and capacity available.

Peterson, Victor L.↗
DOE OSTI2023

Ume: Unstructured Mesh Explorations

Ume is an open-source collection of data structures for unstructured computational meshes and some simple algorithms that operate on them. These algorithms mimic the memory access patterns of a common class of operations found in several of the computational physics simulation codes developed at Los Alamos National Laboratory. The intent is that Ume can be used by hardware vendors to understand the memory traffic created by complex codes in a simplified environment, and to explore new means of optimization for that traffic. Ume is provided as a source-code C++ library and includes several applications that demonstrate the use of that library.

Henning, Paul↗
NASA NTRS1993

A class of hybrid finite element methods for electromagnetics: A review

Integral equation methods have generally been the workhorse for antenna and scattering computations. In the case of antennas, they continue to be the prominent computational approach, but for scattering applications the requirement for large-scale computations has turned researchers' attention to near neighbor methods such as the finite element method, which has low O(N) storage requirements and is readily adaptable in modeling complex geometrical features and material inhomogeneities. In this paper, we review three hybrid finite element methods for simulating composite scatterers, conformal microstrip antennas, and finite periodic arrays. Specifically, we discuss the finite element method and its application to electromagnetic problems when combined with the boundary integral, absorbing boundary conditions, and artificial absorbers for terminating the mesh. Particular attention is given to large-scale simulations, methods, and solvers for achieving low memory requirements and code performance on parallel computing architectures.

Volakis, J. L.↗
NASA NTRS1996

Fault-Tolerant Flight Computer

In design concept for adaptive, fault-tolerant flight computer, upon detection of fault in either processor, surviving processor assumes responsibility for both equipment systems. Possible because of cross-strapping between processors, memories, and input/output units. Concept also applicable to other computing systems required to tolerate faults and in which partial loss of processing speed or functionality acceptable price to pay for continued operation in event of faults.

Chau, Savio↗
NASA NTRSDate not supplied

Controlling properties by chemistry in doped shape memory alloys

Shape memory alloys find increasing use in airspace applications. Using theoretical and computational methods, we investigate correlations between the selected properties and composition in doped NiTi-based shape memory alloys. Among the properties we consider relative energies, phase transition temperature, and hysteresis. We compare predictions to experimental data. Our theoretical guidance facilitates design of future alloys.

Nikolai A Zarkevich↗
DOE OSTI2021

Leaky Buddies: Cross-Component Covert Channels on Integrated CPU-GPU Systems

Graphics Processing Units (GPUs) are ubiquitous components used across the range of today’s computing plat- forms, from phones and tablets, through personal computers, to high-end server class platforms. With the increasing importance of graphics and video workloads, recent processors are shipped with GPU devices that are integrated on the same chip. Integrated GPUs share some resources with the CPU and as a result, there is a potential for microarchitectural attacks from the GPU to the CPU or vice versa. We consider the potential for covert channel attacks that arise either from shared microarchitectural components (such as caches) or through shared contention domains (e.g., shared buses). We illustrate these two types of channels by developing two reliable covert channel attacks. The first covert channel uses the shared LLC cache in Intel’s integrated GPU architectures. The second is a contention based channel targeting the ring bus connecting the CPU and GPU to the LLC. This is the first demonstrated microarchitectural attack crossing the component boundary (GPU to CPU or vice versa). Cross-component channels introduce a number of new challenges that we had to overcome since they occur across heterogeneous components that use different computation models and are interconnected using asymmetric memory hierarchies. We also exploit GPU parallelism to increase the bandwidth of the communication, even without relying on a common clock. The LLC based channel achieves a bandwidth of 120 kbps with a low error rate of 2%, while the contention based channel delivers up to 400 kbps with a 0.8% error rate. We also demonstrate a proof- of-concept prime-and-probe side channel attack that probes the full LLC from the GPU.

Cyber secruity, high performance comptuing, Hetero↗
NASA NTRS2003

Software for Displaying Data from Planetary Rovers

Science Activity Planner (SAP) DownlinkBrowser is a computer program that assists in the visualization of processed telemetric data [principally images, image cubes (that is, multispectral images), and spectra] that have been transmitted to Earth from exploratory robotic vehicles (rovers) on remote planets. It is undergoing adaptation to (1) the Field Integrated Design and Operations (FIDO) rover (a prototype Mars-exploration rover operated on Earth as a test bed) and (2) the Mars Exploration Rover (MER) mission. This program has evolved from its predecessor - the Web Interface for Telescience (WITS) software - and surpasses WITS in the processing, organization, and plotting of data. SAP DownlinkBrowser creates Extensible Markup Language (XML) files that organize data files, on the basis of content, into a sortable, searchable product database, without the overhead of a relational database. The data-display components of SAP DownlinkBrowser (descriptively named ImageView, 3DView, OrbitalView, PanoramaView, ImageCubeView, and SpectrumView) are designed to run in a memory footprint of at least 256MB on computers that utilize the Windows, Linux, and Solaris operating systems.

Powell, Mark↗
NASA NTRS1987

Utilization of parallel processing in solving the inviscid form of the average-passage equation system for multistage turbomachinery

A procedure is outlined which utilizes parallel processing to solve the inviscid form of the average-passage equation system for multistage turbomachinery along with a description of its implementation in a FORTRAN computer code, MSTAGE. A scheme to reduce the central memory requirements of the program is also detailed. Both the multitasking and I/O routines referred to are specific to the Cray X-MP line of computers and its associated SSD (Solid-State Disk). Results are presented for a simulation of a two-stage rocket engine fuel pump turbine.

Mulac, Richard A.↗
DOE OSTI2022

Improved Distributed-memory Triangle Counting by Exploiting the Graph Structure

Graphs are ubiquitous in modeling complex systems and representing interactions between entities to uncover structural information of the domain. Traditionally, graph analytics workloads are challenging to efficiently scale (both strong and weak cases) on distributed memory due to the irregular memory-access driven nature (with little or no computations) of the methods. The structure of graphs and their relative distribution over the processing elements poses another level of complexity, making it difficult to attain sustainable scalability across platforms. In this paper, we discuss enhancements to TriC, a distributed-memory implementation of graph triangle counting using Message Passing Interface (MPI), which was featured in the 2020 Graph Challenge competition. We have made some incremental enhancements to TriC, primarily adopting a user-defined buffering strategy to overcome the startup problem for large graphs (by fixing the memory for intermediate data), and experimenting with probabilistic data structures such as bloom filter to improve the query response time for assessing edge existence, at the expense of increasing the overall false positive rate. These adjustments have led to a modest improvements in most cases, as compared to the previous version.

Graph Analytics, HPC↗
NASA NTRS2011

Dynamical Evolution of Meteoroid Streams, Developments Over the Last 30 Years

As soon as reliable methods for observationally determining the heliocentric orbits of meteoroids and hence the mean orbit of a meteoroid stream in the 1950s and 60s, astronomers strived to investigate the evolution of the orbit under the effects of gravitational perturbations from the planets. At first, the limitations in the capabilities of computers, both in terms of speed and memory, placed severe restrictions on what was possible to do. As a consequence, secular perturbation methods, where the perturbations are averaged over one orbit became the norm. The most popular of these is the Halphen- Goryachev method which was used extensively until the early 1980s. The main disadvantage of these methods lies in the fact that close encounter can be missed, however they remain useful for performing very long-term integrations. Direct integration methods determine the effects of the perturbing forces at many points on an orbit. This give a better picture of the orbital evolution of an individual meteoroid, but many meteoroids have to be integrated in order to obtain a realistic picture of the evolution of a meteoroid stream. The notion of generating a family of hypothetical meteoroids to represent a stream and directly integrate the motion of each was probably first used by Williams Murray & Hughes (1979), to investigate the Quadrantids. Because of computing limitations, only 10 test meteoroids were used. Only two years later, Hughes et. al. (1981) had increased the number of particles 20-fold to 200 while after a further year, Fox Williams and Hughes used 500 000 test meteoroids to model the Geminid stream. With such a number of meteoroids it was possible for the first time to produce a realistic cross-section of the stream on the ecliptic. From that point on there has been a continued increase in the number of meteoroids, the length of time over which integration is carried out and the frequency with which results can be plotted so that it is now possible to produce moving images of the stream. As a consequence, over recent years, emphasis has moved to considering stream formation and the role fragmentation plays in this.

Williams, I. P.↗