Search NASA⌕ Search

SEARCH · Search NASA

Results for “memory efficiency”

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 1,045 records · Page 58

GENESPACE R Package (GENESPACE) v1.0

In short, the GENESPACE pipeline conducts analysis of orthology networks, constrained within syntenic regions. Since analyses are limited to local tests conducted within syntenic blocks, GENESPACE is agnostic to ploidy, duplicated regions, inversions or other whole-genome chromosomal complexities that are common across many evolutionary lineages. This advantage allows for evolutionary tests in polyploids (e.g. switchgrass, manuscript in review), species with ancient, but retained whole-genome duplications (e.g. pecan, manuscript in prep), high levels of tandem array proliferation (e.g. eukalypts, manuscript in review) and many other factors that can confound comparative genomic analyses. The major advances of GENESPACE are three-fold: First, this is the first R package to integrate visualization and analysis of large-scale comparative genomics. R, which offers a high-level environment for graphical and statistical exploration of data, is often speed- and memory-limited and not used for computationally intensive tasks such as comparative genomics. The highly efficient C++ scripts used in GENESPACE (via data.table) permit a much faster and computationally lightweight implementation of comparative genomics than is currently available. Second, the pipeline itself is novel. To the best of our knowledge, no other program accomplishes synteny-constrained and ploidy-agnostic comparative genomics. Since nearly all plants and many animals have a history of whole-genome duplications, this is a major and necessary advance to the field. Third, GENESPACE offers high-level and intuitive multi-genome graphical outputs. The dotplots and 'riparian' plots produced herein, which are produced entirely through original R code, are publication-ready and easily customizable.

Schmutz, Jeremy↗

Coupled Electron-Photon Monte Carlo Radiation Transport for Next-Generation Computing Systems

Traditional Monte Carlo particle transport codes are expected to run inefficiently on next-generation architectures as they are memory-intensive and highly divergent. Since electrons and photons also behave differently, the future for coupled electron-photon radiation transport looks even worse. This project describes preliminary efforts to improve the performance of Monte Carlo particle transport codes when using accelerators like the graphics processing unit (GPU). Two key issues are addressed: how to handle memory-intensive tallies, and how to reduce divergence. Tallying on the GPU can be done efficiently by post-processing particle data, or by using a feature called warp shuffle for summing scores in parallel during the simulation. Reducing divergence is possible by using an event-based algorithm for particle tracking instead of the traditional history-based one. Although performance tests presented in this work show that the history-based algorithm generally outperformed the event-based one for simple problems, this outcome will likely change as the complexity of the code increases.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Investigation of spin and magnetism in two dimensional materials with atomic-scale spatial resolution (Final Technical Report)

Spintronics is an approach to energy-efficient electronics beyond silicon CMOS that utilizes the electron’s spin degree of freedom for memory and logic. The record spin diffusion length in graphene has generated considerable interest in two dimensional (2D) materials (i.e. graphene and beyond) as a platform for spintronics. Magnetism in 2D van der Waals materials may offer additional opportunities for tunability via strain, external fields, and layer-dependent quantum effects. The inherently atomic-scale nature of exchange interactions and the inherently all-surface nature of 2D sheets motivate an integrated approach combining atomic-scale magnetic characterization, epitaxial growth, and nanodevice fabrication. The mission of the research is to develop and utilize atomic-scale imaging of spin and magnetism via spin-polarized scanning tunneling microscopy (STM) in conjunction with atom-by-atom materials growth via molecular beam epitaxy (MBE) and nanoscale device fabrication to explore new frontiers of spintronics and quantum science in 2D materials. The PIs are particularly motivated by understanding how the magnetic and spin-dependent properties at the atomic scale lead to interesting and potentially useful phenomena in spintronic devices at the macroscopic scale.

36 MATERIALS SCIENCE↗

The psychophysics of workload - A second look at the relationship between subjective measures and performance

Load estimates based upon subjective and performance indices were compared for subjects performing size matching and letter typing tasks under 6 levels of priorities, in single and dual task conditions. Each half of the group used a different task as reference in their subjective judgement. The results are interpreted to indicate that subjective measures are especially sensitive to voluntary allocation of attention and to the load on working memory. Association with performance is expected whenever these two factors are main determinants of performance efficiency, otherwise the two are likely to dissociate.

Gopher, D.↗

Implementation of a digital optical matrix-vector multiplier using a holographic look-up table and residue arithmetic

The design and implementation of a digital (numerical) optical matrix-vector multiplier are presented. The objective is to demonstrate the operation of an optical processor designed to minimize computation time in performing a practical computing application. This is done by using the large array of processing elements in a Hughes liquid crystal light valve, and relying on the residue arithmetic representation, a holographic optical memory, and position coded optical look-up tables. In the design, all operations are performed in effectively one light valve response time regardless of matrix size. The features of the design allowing fast computation include the residue arithmetic representation, the mapping approach to computation, and the holographic memory. In addition, other features of the work include a practical light valve configuration for efficient polarization control, a model for recording multiple exposures in silver halides with equal reconstruction efficiency, and using light from an optical fiber for a reference beam source in constructing the hologram. The design can be extended to implement larger matrix arrays without increasing computation time.

Habiby, Sarry F.↗

Distributed memory compiler design for sparse problems

A compiler and runtime support mechanism is described and demonstrated. The methods presented are capable of solving a wide range of sparse and unstructured problems in scientific computing. The compiler takes as input a FORTRAN 77 program enhanced with specifications for distributing data, and the compiler outputs a message passing program that runs on a distributed memory computer. The runtime support for this compiler is a library of primitives designed to efficiently support irregular patterns of distributed array accesses and irregular distributed array partitions. A variety of Intel iPSC/860 performance results obtained through the use of this compiler are presented.

Wu, Janet↗

GPU Usage in ATLAS Reconstruction and Analysis

With Graphical Processing Units (GPUs) and other kinds of accelerators becoming ever more accessible, High Performance Computing Centres all around the world using them ever more, ATLAS has to find the best way of making use of such accelerators in much of its computing. Tests with GPUs - mainly with CUDA - have been performed in the past in the experiment. At that time the conclusion was that it was not advantageous for the ATLAS offline and trigger software to invest time and money into GPUs. However as the usage of accelerators has become cheaper and simpler in recent years, their re-evaluation in ATLAS's offline software is warranted. We show new results of using GPU accelerated calculations in ATLAS's offline software environment using the ATLAS offline/analysis (xAOD) Event Data Model. We compare the performance and flexibility of a couple of the available GPU programming methods, and show how different memory management setups affect our ability to offload different types of calculations to a GPU efficiently.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Performance and Energy Usage of Workloads on KNL and Haswell Architectures. In: High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation

Manycore architectures are an energy-efficient step towards exascale computing within a constrained power budget. The Intel Knights Landing (KNL) manycore chip is a specific example of this and has seen early adoption by a number of HPC facilities. It is therefore important to understand the performance and energy usage characteristics of KNL. In this paper, we evaluate the performance and energy efficiency of KNL in contrast to the Xeon (Haswell) architecture for applications representative of the workload of users at NERSC. We consider the optimal MPI/OpenMP configuration of each application and use the results to characterize KNL in contrast to Haswell. As well as traditional DDR memory, KNL contains MCDRAM and we also evaluate its efficacy. Our results show that, averaged over our benchmarks, KNL is 1.84 × more energy efficient than Haswell and has 1.27 × greater performance.

Benchmarking↗

Parallel Finite Element Domain Decomposition for Structural/Acoustic Analysis

A domain decomposition (DD) formulation for solving sparse linear systems of equations resulting from finite element analysis is presented. The formulation incorporates mixed direct and iterative equation solving strategics and other novel algorithmic ideas that are optimized to take advantage of sparsity and exploit modern computer architecture, such as memory and parallel computing. The most time consuming part of the formulation is identified and the critical roles of direct sparse and iterative solvers within the framework of the formulation are discussed. Experiments on several computer platforms using several complex test matrices are conducted using software based on the formulation. Small-scale structural examples are used to validate thc steps in the formulation and large-scale (l,000,000+ unknowns) duct acoustic examples are used to evaluate the ORIGIN 2000 processors, and a duster of 6 PCs (running under the Windows environment). Statistics show that the formulation is efficient in both sequential and parallel computing environmental and that the formulation is significantly faster and consumes less memory than that based on one of the best available commercialized parallel sparse solvers.

Nguyen, Duc T.↗

Random access quantum information processors using multimode circuit quantum electrodynamics

Qubit connectivity is an important property of a quantum processor, with an ideal processor having random access—the ability of arbitrary qubit pairs to interact directly. This a challenge with superconducting circuits, as state-of-the-art architectures rely on only nearest-neighbor coupling. Here, we implement a random access superconducting quantum information processor, demonstrating universal operations on a nine-qubit memory, with a Josephson junction transmon circuit serving as the central processor. The quantum memory uses the eigenmodes of a linear array of coupled superconducting resonators. We selectively stimulate vacuum Rabi oscillations between the transmon and individual eigenmodes through parametric flux modulation of the transmon frequency. Utilizing these oscillations, we perform a universal set of quantum gates on 38 arbitrary pairs of modes and prepare multimode entangled states, all using only two control lines. We thus achieve hardware-efficient random access multi-qubit control in an architecture compatible with long-lived microwave cavity-based quantum memories.

97 MATHEMATICS AND COMPUTING↗

AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators

Tensor algebra operations represent an important class of algorithms used across many applications, including machine learning, scientific computing, and data analytics. As a result, the efficient generation of custom accelerators for tensor operations has received increased attention. Previous efforts have produced automated tools enabling users to prototype and explore optimized accelerators. However, little effort has been focused on the host-accelerator interaction in these tools. Efficient use of hardware accelerators requires knowledge about the accelerator's capabilities (operations, data formats, and opcode support), the host CPU microarchitecture (e.g., memory hierarchy), the host-accelerator interface, and the application's features (which code regions should be mapped onto an accelerator). Manually rewriting the original applications to facilitate improved custom accelerator mapping is an error-prone and time-consuming endeavor. To cope with this, we propose AXI4MLIR, a new framework to automatically generate and optimize the communication between the host CPU and arbitrary accelerators that implement linear algebra algorithms. AXI4MLIR extends the MLIR compiler framework to automatically generate efficient host-accelerator driver code for accelerators with AXI-based interfaces. Our compiler extensions enable automatic driver code generation while carefully considering the host's memory hierarchy and target accelerator features. To demonstrate the flexibility and utility of AXI4MLIR, we test it with diverse use cases that include different types of accelerators, tiling scenarios, and dataflow schemes. We compare our experimental results to manual implementations of host-accelerator driver code and find that our approach can reduce CPU cache references by 56% and deliver up to a 1.65x speedup.

Bohm Agostini, Nicolas↗

Design of a Variational Multiscale Method for Turbulent Compressible Flows

A spectral-element framework is presented for the simulation of subsonic compressible high-Reynolds-number flows. The focus of the work is maximizing the efficiency of the computational schemes to enable unsteady simulations with a large number of spatial and temporal degrees of freedom. A collocation scheme is combined with optimized computational kernels to provide a residual evaluation with computational cost independent of order of accuracy up to 16th order. The optimized residual routines are used to develop a low-memory implicit scheme based on a matrix-free Newton-Krylov method. A preconditioner based on the finite-difference diagonalized ADI scheme is developed which maintains the low memory of the matrix-free implicit solver, while providing improved convergence properties. Emphasis on low memory usage throughout the solver development is leveraged to implement a coupled space-time DG solver which may offer further efficiency gains through adaptivity in both space and time.

Design↗

An efficient and portable SIMD algorithm for charge/current deposition in Particle-In-Cell codes

In current computer architectures, data movement (from die to network) is by far the most energy consuming part of an algorithm (≈20pJ/word on-die to ≈10,000 pJ/word on the network). To increase memory locality at the hardware level and reduce energy consumption related to data movement, future exascale computers tend to use many-core processors on each compute nodes that will have a reduced clock speed to allow for efficient cooling. To compensate for frequency decrease, machine vendors are making use of long SIMD instruction registers that are able to process multiple data with one arithmetic operator in one clock cycle. SIMD register length is expected to double every four years. As a consequence, Particle-In-Cell (PIC) codes will have to achieve good vectorization to fully take advantage of these upcoming architectures. In this paper, we present a new algorithm that allows for efficient and portable SIMD vectorization of current/charge deposition routines that are, along with the field gathering routines, among the most time consuming parts of the PIC algorithm. Our new algorithm uses a particular data structure that takes into account memory alignment constraints and avoids gather/scat;ter instructions that can significantly affect vectorization performances on current CPUs. The new algorithm was successfully implemented in the 3D skeleton PIC code PICSAR and tested on Haswell Xeon processors (AVX2-256 bits wide data registers). Results show a factor of ×2 to ×2.5 speed-up in double precision for particle shape factor of orders 1–3. The new algorithm can be applied as is on future KNL (Knights Landing) architectures that will include AVX-512 instruction sets with 512 bits register lengths (8 doubles/16 singles). Program summary Program Title: vec_deposition Program Files doi:http://dx.doi.org/10.17632/nh77fv9k8c.1 Licensing provisions: BSD 3-Clause Programming language: Fortran 90 External routines/libraries: OpenMP > 4.0 Nature of problem: Exascale architectures will have many-core processors per node with long vector data registers capable of performing one single instruction on multiple data during one clock cycle. Data register lengths are expected to double every four years and this pushes for new portable solutions for efficiently vectorizing Particle-In-Cell codes on these future many-core architectures. One of the main hotspot routines of the PIC algorithm is the current/charge deposition for which there is no efficient and portable vector algorithm. Solution method: Here we provide an efficient and portable vector algorithm of current/charge deposition routines that uses a new data structure, which significantly reduces gather/scatter operations. Vectorization is controlled using OpenMP 4.0 compiler directives for vectorization which ensures portability across different architectures. Restrictions: Here we do not provide the full PIC algorithm with an executable but only vector routines for current/charge deposition. These scalar/vector routines can be used as library routines in your 3D Particle-In-Cell code. However, to get the best performances out of vector routines you have to satisfy the two following requirements: (1) Your code should implement particle tiling (as explained in the manuscript) to allow for maximized cache reuse and reduce memory accesses that can hinder vector performances. The routines can be used directly on each particle tile. (2) You should compile your code with a Fortran 90 compiler (e.g Intel, gnu or cray) and provide proper alignment flags and compiler alignment directives (more details in README file).

97 MATHEMATICS AND COMPUTING↗

Energy and Area Efficiency in Neuromorphic Computing for Resource Constrained Devices

Resource constrained devices are the building blocks of the internet of things (IoT) era. Since the idea behind IoT is to develop an interconnected environment where the devices are tiny enough to operate with limited resources, several control systems have been built to maintain low energy and area consumption while operating as IoT edge devices. Several researchers have begun work on implementing control systems built from resource constrained devices using machine learning. However, there are many ways such devices can achieve lower power consumption and area utilization while maximizing application efficiency. Spiky neuromorphic computing (SNC) is an emerging paradigm that can be leveraged in resource constrained devices for several emerging applications. While delivering the benefits of machine learning, SNC also helps minimize power consumption. For example, low energy memory devices (memristors) are often used to achieve low power operation and also help in reducing system area. In total, we anticipate SNC will provide computational efficiency approaching that of deep learning while using low power, resource constrained devices.

Chakma, Gangotree↗

Identification of Linear and Nonlinear Aerodynamic Impulse Responses Using Digital Filter Techniques

This paper discusses the mathematical existence and the numerically-correct identification of linear and nonlinear aerodynamic impulse response functions. Differences between continuous-time and discrete-time system theories, which permit the identification and efficient use of these functions, will be detailed. Important input/output definitions and the concept of linear and nonlinear systems with memory will also be discussed. It will be shown that indicial (step or steady) responses (such as Wagner's function), forced harmonic responses (such as Tbeodorsen's function or those from doublet lattice theory), and responses to random inputs (such as gusts) can all be obtained from an aerodynamic impulse response function. This paper establishes the aerodynamic impulse response function as the most fundamental, and, therefore, the most computationally efficient, aerodynamic function that can be extracted from any given discrete-time, aerodynamic system. The results presented in this paper help to unify the understanding of classical two-dimensional continuous-time theories with modem three-dimensional, discrete-time theories. First, the method is applied to the nonlinear viscous Burger's equation as an example. Next the method is applied to a three-dimensional aeroelastic model using the CAP-TSD (Computational Aeroelasticity Program - Transonic Small Disturbance) code and then to a two-dimensional model using the CFL3D Navier-Stokes code. Comparisons of accuracy and computational cost savings are presented. Because of its mathematical generality, an important attribute of this methodology is that it is applicable to a wide range of nonlinear, discrete-time problems.

Silva, Walter A.↗

Identification of Linear and Nonlinear Aerodynamic Impulse Responses Using Digital Filter Techniques

This paper discusses the mathematical existence and the numerically-correct identification of linear and nonlinear aerodynamic impulse response functions. Differences between continuous-time and discrete-time system theories, which permit the identification and efficient use of these functions, will be detailed. Important input/output definitions and the concept of linear and nonlinear systems with memory will also be discussed. It will be shown that indicial (step or steady) responses (such as Wagner's function), forced harmonic responses (such as Theodorsen's function or those from doublet lattice theory), and responses to random inputs (such as gusts) can all be obtained from an aerodynamic impulse response function. This paper establishes the aerodynamic impulse response function as the most fundamental, and, therefore, the most computationally efficient, aerodynamic function that can be extracted from any given discrete-time, aerodynamic system. The results presented in this paper help to unify the understanding of classical two-dimensional continuous-time theories with modern three-dimensional, discrete-time theories. First, the method is applied to the nonlinear viscous Burger's equation as an example. Next the method is applied to a three-dimensional aeroelastic model using the CAP-TSD (Computational Aeroelasticity Program - Transonic Small Disturbance) code and then to a two-dimensional model using the CFL3D Navier-Stokes code. Comparisons of accuracy and computational cost savings are presented. Because of its mathematical generality, an important attribute of this methodology is that it is applicable to a wide range of nonlinear, discrete-time problems.

Silva, Walter A.↗

Domain walls riding the wave.

Recent years have witnessed a rapid proliferation of electronic gadgets around the world. These devices are used for both communication and entertainment, and it is a fact that they account for a growing portion of household energy consumption and overall world consumption of electricity. Increasing the energy efficiency of these devices could have a far greater and immediate impact than a gradual switch to renewable energy sources. The advances in the area of spintronics are therefore very important, as gadgets are mostly comprised of memory and logic elements. Recent developments in controlled manipulation of magnetic domains in ferromagnet nanostructures have opened opportunities for novel device architectures. This new class of memories and logic gates could soon power millions of consumer electronic devices. The attractiveness of using domain-wall motion in electronics is due to its inherent reliability (no mechanical moving parts), scalability (3D scalable architectures such as in racetrack memory), and nonvolatility (retains information in the absence of power). The remaining obstacles in widespread use of 'racetrack-type' elements are the speed and the energy dissipation during the manipulation of domain walls. In their recent contribution to Physical Review Letters, Oleg Tretiakov, Yang Liu, and Artem Abanov from Texas A&M University in College Station, provide a theoretical description of domain-wall motion in nanoscale ferromagnets due to the spin-polarized currents. They find exact conditions for time-dependent resonant domain-wall movement, which could speed up the motion of domain walls while minimizing Ohmic losses. Movement of domain walls in ferromagnetic nanowires can be achieved by application of external magnetic fields or by passing a spin-polarized current through the nanowire itself. On the other hand, the readout of the domain state is done by measuring the resistance of the wire. Therefore, passing current through the ferromagnetic wire is the preferred method, as it combines manipulation and readout of the domain-wall state. The electrons that take part in the process of readout and manipulation of the domain-wall structure in the nanowire do so through the so-called spin transfer torque: When spin-polarized electrons in the ferromagnet nanowire pass through the domain wall they experience a nonuniform magnetization, and they try to align their spins with the local magnetic moments. The force that the electrons experience has a reaction force counterpart that 'pushes' the local magnetic moments, resulting in movement of the domain wall in the direction of the electron flow through the spin-transfer torque. The forces between the electrons and the local magnetic moments in the ferromagnet also create additional electrical resistance for the electrons passing through the domain wall. By measuring resistance across a segment of the nanowire, one determines if a domain wall is present; i.e., one can read the stored information. The interaction of the spin-polarized electrons with the domain wall in the ferromagnetic nanowire is not very efficient. Even for materials achieving high polarization of the free electrons, it is very difficult to move the magnetic domain wall. Several factors contribute to this problem, with imperfections of the ferromagnetic nanowire that cause domain-wall pinning being the dominant one. Permalloy nanowires, one of the best candidates for domain-wall-based memory and logic devices, require current densities of the order of 10{sup 8} A/cm{sup 2} in order to move a domain wall from a pinning well. Considering that this current has to pass through a relatively long wire, it is not very difficult to imagine that most of the energy will go to Joule heating. The efficiency of the process - the ratio of the energy converted to domain-wall motion to the total energy consumed - is comparable to that of an incandescent light bulb converting electricity to light. A step towards more efficient domain-wall-based memory devices is the advance of using alternating currents or current pulses to drive the domain walls. Injection of a spin-polarized current below the threshold value necessary to move the domain wall only causes oscillation of the domain wall inside the pinning potential. Exploiting the effect of resonance, one can apply a specific current waveform to drive the oscillations of the domain wall into resonance. Resonant amplification of domain-wall oscillations will free the domain wall from the pinning well at current levels that are a fraction of the dc threshold. Currents of an order of magnitude lower than before were shown to be sufficient to manipulate domain walls, thus reducing Joule heating 100 times. In their current paper, Tretiakov et al. provide a theoretical basis for the mechanism of resonant domain-wall motion in ferromagnetic nanowires.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Carbon Nanotube Memory Elements

Carbon nanotubes are among the most cited prototypical materials for nanoelectronics and information storage devices, a dominant position that originates from their intrinsic structural and electronic properties. In this chapter we review the developments in memory elements that directly exploit the unique properties of carbon nanotubes. Fundamental operational principles and characteristics are examined for the different types of carbon nanotube-based memory devices along with the current status of experimental fabrication and scalability. These include memory elements based on carbon nanotube field-effect transistors (CNFET), nanoelectromechanical systems (NEMS), and electromigration. Many of these devices show tremendous promise for providing enhanced densities, lower power requirements, more efficient read/write processes, and non-volatility of data.

77 NANOSCIENCE AND NANOTECHNOLOGY↗