Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “processor performance factors”

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 109 records · Page 6

Solving the Cauchy-Riemann equations on parallel computers

Discussed is the implementation of a single algorithm on three parallel-vector computers. The algorithm is a relaxation scheme for the solution of the Cauchy-Riemann equations; a set of coupled first order partial differential equations. The computers were chosen so as to encompass a variety of architectures. They are: the MPP, and SIMD machine with 16K bit serial processors; FLEX/32, an MIMD machine with 20 processors; and CRAY/2, an MIMD machine with four vector processors. The machine architectures are briefly described. The implementation of the algorithm is discussed in relation to these architectures and measures of the performance on each machine are given. Simple performance models are used to describe the performance. These models highlight the bottlenecks and limiting factors for this algorithm on these architectures. Conclusions are presented.

Fatoohi, Raad A.↗

Generalized hypercube structures and hyperswitch communication network

This paper discusses an ongoing study that uses a recent development in communication control technology to implement hybrid hypercube structures. These architectures are similar to binary hypercubes, but they also provide added connectivity between the processors. This added connectivity increases communication reliability while decreasing the latency of interprocessor message passing. Because these factors directly determine the speed that can be obtained by multiprocessor systems, these architectures are attractive for applications such as remote exploration and experimentation, where high performance and ultrareliability are required. This paper describes and enumerates these architectures and discusses how they can be implemented with a modified version of the hyperswitch communication network (HCN). The HCN is analyzed because it has three attractive features that enable these architectures to be effective: speed, fault tolerance, and the ability to pass multiple messages simultaneously through the same hyperswitch controller.

Young, Steven D.↗

Efficient Approximation Algorithms for Weighted $b$-Matching

We describe a half-approximation algorithm, b-Suitor, for computing a b-Matching of maximum weight in a graph with weights on the edges. b-Matching is a generalization of the well-known Matching problem in graphs, where the objective is to choose a subset of M edges in the graph such that at most a speci ed number b(v) of edges in M are incident on each vertex v. Subject to this restriction we maximize the sum of the weights of the edges in M. We prove that the b-Suitor algorithm computes the same b-Matching as the one obtained by the greedy algorithm for the problem. We implement the algorithm on serial and shared-memory parallel processors, and compare its performance against a collection of approximation algorithms that have been proposed earlier. Our results show that the b-Suitor algorithm outperforms the Greedy and Locally Dominant edge algorithms by one to two orders of magnitude on a serial processor. The b-Suitor algorithm has a high degree of concurrency, and it scales well up to 240 threads on a shared memory multiprocessor. The b-Suitor algorithm outperforms the Locally Dominant edge algorithm by a factor of fourteen on 16 cores of an Intel Xeon multiprocessor.

97 MATHEMATICS AND COMPUTING↗

Performance of a plasma fluid code on the Intel parallel computers

One approach to improving the real-time efficiency of plasma turbulence calculations is to use a parallel algorithm. A parallel algorithm for plasma turbulence calculations was tested on the Intel iPSC/860 hypercube and the Touchtone Delta machine. Using the 128 processors of the Intel iPSC/860 hypercube, a factor of 5 improvement over a single-processor CRAY-2 is obtained. For the Touchtone Delta machine, the corresponding improvement factor is 16. For plasma edge turbulence calculations, an extrapolation of the present results to the Intel (sigma) machine gives an improvement factor close to 64 over the single-processor CRAY-2.

Lynch, V. E.↗

Basker: Parallel sparse LU factorization utilizing hierarchical parallelism and data layouts

Transient simulation in circuit simulation tools, such as SPICE and Xyce, depend on scalable and robust sparse LU factorizations for efficient numerical simulation of circuits and power grids. As the need for simulations of very large circuits grow, the prevalence of multicore architectures enable us to use shared memory parallel algorithms for such simulations. A parallel factorization is a critical component of such shared memory parallel simulations. We develop a parallel sparse factorization algorithm that can solve problems from circuit simulations efficiently, and map well to architectural features. This new factorization algorithm exposes hierarchical parallelism to accommodate irregular structure that arise in our target problems. It also uses a hierarchical two-dimensional data layout which reduces synchronization costs and maps to memory hierarchy found in multicore processors. We present an OpenMP based implementation of the parallel algorithm in a new multithreaded solver called Basker in the Trilinos framework. Here, we present performance evaluations of Basker on the Intel SandyBridge and Xeon Phi platforms using circuit and power grid matrices taken from the University of Florida sparse matrix collection and from Xyce circuit simulation. Basker achieves a geometric mean speedup of 5.91× on CPU (16 cores) and 7.4× on Xeon Phi (32 cores) relative to state-of-the-art solver KLU. Basker outperforms Intel MKL Pardiso solver (PMKL) by as much as 30× on CPU (16 cores) and 7.5× on Xeon Phi (32 cores) for low fill-in circuit matrices. Furthermore, Basker provides 5.4× speedup on a challenging matrix sequence taken from an actual Xyce simulation.

97 MATHEMATICS AND COMPUTING↗

On the stability of robotic systems with random communication rates

Control problems of sampled data systems which are subject to random sample rate variations and delays are studied. Due to the rapid growth of the use of computers more and more systems are controlled digitally. Complex systems such as space telerobotic systems require the integration of a number of subsystems at different hierarchical levels. While many subsystems may run on a single processor, some subsystems require their own processor or processors. The subsystems are integrated into functioning systems through communications. Communications between processes sharing a single processor are also subject to random delays due to memory management and interrupt latency. Communications between processors involve random delays due to network access and to data collisions. Furthermore, all control processes involve delays due to casual factors in measuring devices and to signal processing. Traditionally, sampling rates are chosen to meet the worst case communication delay. Such a strategy is wasteful as the processors are then idle a great proportion of the time; sample rates are not as high as possible resulting in poor performance or in the over specification of control processors; there is the possibility of missing data no matter how low the sample rate is picked. Asymptotical stability with probability one for randomly sampled multi-dimensional linear systems is studied. A sufficient condition for the stability is obtained. This condition is so simple that it can be applied to practical systems. A design procedure is also shown.

Kobayashi, H.↗

Self-contained, automated, long-term sensor system for monitoring of soil and water nutrients in fields

An automated, fieldable ion-selective sensor system for frequent detection of nutrients in soils or water is set forth. In one aspect, an integrated small form-factor housing includes a battery, processor, a fluid manipulation unit and reservoirs, and a chemical species detection cell. A flow-through sampling head can be connected to the detection cell and a waste reservoir by flexible tubing sealingly connected at opposite ends of the tube. In one aspect, improved performance of the ion-selective sensor includes adding an ion-to-electron transfer interlayer between an ion-selective membrane and its working electrode. In one aspect, the sensor is solid-state and uses printed polymeric composite of POT-MoS$_{2}$. The use of a porous tube for a sampling head and fluid connection at opposite ends allows not only fluid to be removed from the head to the detection cell for measurement but also flow in an opposite direction and out to a waste reservoir to clean and reset for a next sample measurement.

60 APPLIED LIFE SCIENCES↗

A family of independent Variable Eddington Factor methods with efficient preconditioned iterative solvers

We present a family of discretizations for the Variable Eddington Factor (VEF) equations that have high-order accuracy on curved meshes and efficient preconditioned iterative solvers. The VEF discretizations are combined with the Discontinuous Galerkin transport discretization from to form effective high-order, linear transport methods. The VEF discretizations are derived by extending the unified analysis of Discontinuous Galerkin methods for elliptic problems presented by Arnold et al. to the VEF equations. This framework is used to define analogs of the interior penalty, second method of Bassi and Rebay, minimal dissipation local Discontinuous Galerkin, and continuous finite element methods. The analysis of subspace correction preconditioners, which use a continuous operator to iteratively precondition the discontinuous discretization, is extended to the case of the non-symmetric VEF system. Numerical results demonstrate that the VEF discretizations have arbitrary-order accuracy on curved meshes, preserve the thick diffusion limit, and are effective on a proxy problem from thermal radiative transfer in both outer transport iterations and inner preconditioned linear solver iterations. We demonstrate that the VEF solution converges to the S N transport solution as the mesh is refined on both problems with smooth and non-smooth behavior in angle. Parallel performance studies show that the interior penalty VEF discretization's linear solve weak scales out to 1024 processors and strong scales well on a single node. Particular attention is paid to the parallel performance of the VEF algorithm when used in combination with a parallel block Jacobi transport sweep.

97 MATHEMATICS AND COMPUTING↗

Implementation and design of a teleoperation system based on a VMEBUS/68020 pipelined architecture

A pipelined control design and architecture for a force-feedback teleoperation system that is being implemented at the Jet Propulsion Laboratory and which will be integrated with the autonomous portion of the testbed to achieve share control is described. At the local site, the operator sees real-time force/torque displays and moves two 6-degree of freedom (dof) force-reflecting hand-controllers as his hands feel the contact force/torques generated at the remote site where the robots interact with the environment. He also uses a graphical user menu to monitor robot states and specify system options. The teleoperation software is written in the C language and runs on MC68020-based processor boards in the VME chassis, which utilizes a real-time operating system; the hardware is configured to realize a four-stage pipeline configuration. The environment is very flexible, such that the system can easily be configured as a stand-alone facility for performing independent research in human factors, force control, and time-delayed systems.

Lee, Thomas S.↗

Preconditioned conjugate-gradient methods for low-speed flow calculations

An investigation is conducted into the viability of using a generalized Conjugate Gradient-like method as an iterative solver to obtain steady-state solutions of very low-speed fluid flow problems. Low-speed flow at Mach 0.1 over a backward-facing step is chosen as a representative test problem. The unsteady form of the two dimensional, compressible Navier-Stokes equations is integrated in time using discrete time-steps. The Navier-Stokes equations are cast in an implicit, upwind finite-volume, flux split formulation. The new iterative solver is used to solve a linear system of equations at each step of the time-integration. Preconditioning techniques are used with the new solver to enhance the stability and convergence rate of the solver and are found to be critical to the overall success of the solver. A study of various preconditioners reveals that a preconditioner based on the Lower-Upper Successive Symmetric Over-Relaxation iterative scheme is more efficient than a preconditioner based on Incomplete L-U factorizations of the iteration matrix. The performance of the new preconditioned solver is compared with a conventional Line Gauss-Seidel Relaxation (LGSR) solver. Overall speed-up factors of 28 (in terms of global time-steps required to converge to a steady-state solution) and 20 (in terms of total CPU time on one processor of a CRAY-YMP) are found in favor of the new preconditioned solver, when compared with the LGSR solver.

Ajmani, Kumud↗

Preconditioned Conjugate Gradient methods for low speed flow calculations

An investigation is conducted into the viability of using a generalized Conjugate Gradient-like method as an iterative solver to obtain steady-state solutions of very low-speed fluid flow problems. Low-speed flow at Mach 0.1 over a backward-facing step is chosen as a representative test problem. The unsteady form of the two dimensional, compressible Navier-Stokes equations are integrated in time using discrete time-steps. The Navier-Stokes equations are cast in an implicit, upwind finite-volume, flux split formulation. The new iterative solver is used to solve a linear system of equations at each step of the time-integration. Preconditioning techniques are used with the new solver to enhance the stability and the convergence rate of the solver and are found to be critical to the overall success of the solver. A study of various preconditioners reveals that a preconditioner based on the lower-upper (L-U)-successive symmetric over-relaxation iterative scheme is more efficient than a preconditioner based on incomplete L-U factorizations of the iteration matrix. The performance of the new preconditioned solver is compared with a conventional line Gauss-Seidel relaxation (LGSR) solver. Overall speed-up factors of 28 (in terms of global time-steps required to converge to a steady-state solution) and 20 (in terms of total CPU time on one processor of a CRAY-YMP) are found in favor of the new preconditioned solver, when compared with the LGSR solver.

Ajmani, Kumud↗

An intelligent allocation algorithm for parallel processing

The problem of allocating nodes of a program graph to processors in a parallel processing architecture is considered. The algorithm is based on critical path analysis, some allocation heuristics, and the execution granularity of nodes in a program graph. These factors, and the structure of interprocessor communication network, influence the allocation. To achieve realistic estimations of the executive durations of allocations, the algorithm considers the fact that nodes in a program graph have to communicate through varying numbers of tokens. Coarse and fine granularities have been implemented, with interprocessor token-communication duration, varying from zero up to values comparable to the execution durations of individual nodes. The effect on allocation of communication network structures is demonstrated by performing allocations for crossbar (non-blocking) and star (blocking) networks. The algorithm assumes the availability of as many processors as it needs for the optimal allocation of any program graph. Hence, the focus of allocation has been on varying token-communication durations rather than varying the number of processors. The algorithm always utilizes as many processors as necessary for the optimal allocation of any program graph, depending upon granularity and characteristics of the interprocessor communication network.

Carroll, Chester C.↗

The design of a digital voice data compression technique for orbiter voice channels

Voice bandwidth compression techniques were investigated to anticipate link margin difficulties in the shuttle S-band communication system. It was felt that by reducing the data rate on each voice channel from the baseline 24 (or 32) Kbps to 8 Kbps, additional margin could be obtained. The feasibility of such an alternate voice transmission system was studied. Several factors of prime importance that were addressed are: (1) achieving high quality voice at 8 Kbps; (2) performance in the presence of the anticipated shuttle cabin environmental noise; (3) performance in the presence of the anticipated channel error statistics; and (4) minimal increase in size, weight, and power over the current baseline voice processor.

Source record↗

Optimizing Communication in 2D Grid-Based MPI Applications at Exascale

The new reality of exascale computing faces many challenges in achieving optimal performance on large numbers of nodes. A key challenge is the efficient utilization of the message-passing interface (MPI), a critical component for process communication. This paper explores communication optimization strategies to harness the GPU-accelerated architectures of these supercomputers. We focus on MPI applications where processors form a two-dimensional process grid, a common arrangement in applications involving dense matrix operations. This configuration offers a unique opportunity to implement innovative strategies to improve performance and maintain effective load distribution. We study two applications— Dist-FW (Apsp:all-pair-shortest-path) and HPL-MxP (LU factorization with Mixed precision)—on two accelerated systems: Summit (IBM Power and NVIDIA V100) and Frontier (AMD EPYC and MI250X). These supercomputers are operated by the Oak Ridge Leadership Computing Facility (OLCF) and are currently ranked #1 and #5 on the Top500 list. We show how to scale up both applications to exascale levels and tackle the MPI challenges related to implementation, synchronization, and performance. We also compare the performance of several communication strategies at an unprecedented scale. Accurately predicting application performance becomes crucial for cost reduction as the computational scale grows. To address this, we suggest a hyperbolic model as a better alternative to the traditional one-sided asymptotic model for predicting future application performance at such large scales.

Lu, Hao↗

Exploration of superconducting multi-mode cavity architectures for quantum computing

Superconducting radio-frequency (SRF) cavities coupled to transmon circuits have proven to be a promising platform for building high-coherence quantum information processors. An essential aspect of this realization involves designing high quality factor three-dimensional superconducting cavities to extend the lifetime of quantum systems. To increase the computational capability of this architecture, we are exploring a multimode approach. This paper presents the design optimization process of a multi-cell SRF cavity to perform quantum computation based on an existing design developed in the scope of particle accelerator technology. We perform parametric electromagnetic simulations to evaluate and optimize the design. In particular, we focus on the analysis of the interaction between a nonlinear superconducting circuit known as the transmon and the cavity. This parametric design optimization is structured to serve as a blueprint for future studies on similar systems.

Reineri, Alessandro↗

Optimizing Performance of Combustion Chemistry Solvers on Intel's Many Integrated Core (MIC) Architectures

This work investigates novel algorithm designs and optimization techniques for restructuring chemistry integrators in zero and multidimensional combustion solvers, which can then be effectively used on the emerging generation of Intel's Many Integrated Core/Xeon Phi processors. These processors offer increased computing performance via large number of lightweight cores at relatively lower clock speeds compared to traditional processors (e.g. Intel Sandybridge/Ivybridge) used in current supercomputers. This style of processor can be productively used for chemistry integrators that form a costly part of computational combustion codes, in spite of their relatively lower clock speeds. Performance commensurate with traditional processors is achieved here through the combination of careful memory layout, exposing multiple levels of fine grain parallelism and through extensive use of vendor supported libraries (Cilk Plus and Math Kernel Libraries). Important optimization techniques for efficient memory usage and vectorization have been identified and quantified. These optimizations resulted in a factor of ~ 3 speed-up using Intel 2013 compiler and ~ 1.5 using Intel 2017 compiler for large chemical mechanisms compared to the unoptimized version on the Intel Xeon Phi. The strategies, especially with respect to memory usage and vectorization, should also be beneficial for general purpose computational fluid dynamics codes.

97 MATHEMATICS AND COMPUTING↗

The Inertial Stellar Compass (ISC): A Multifunction, Low Power, Attitude Determination Technology Breakthrough

The Inertial Stellar Compass (ISC) is a miniature, low power, stellar inertial attitude determination system with an accuracy of better than 0.1 degree (1 sigma) in three axes. The ISC consumes only 3.5 Watts of power and is contained in a 2.5 kg package. With its embedded on-board processor, the ISC provides attitude quaternion information and has Lost-in-Space (LIS) initialization capability. The attitude accuracy and LIS capability are provided by combining a wide field of view Active Pixel Sensor (APS) star camera and Micro- ElectroMechanical System (MEMS) inertial sensor information in an integrated sensor system. The performance and small form factor make the ISC a useful sensor for a wide range of missions. In particular, the ISC represents an enabling, fully integrated, micro-satellite attitude determination system. Other applications include using the ISC as a single sensor solution for attitude determination on medium performance spacecraft and as a bolt on independent safe-hold sensor or coarse acquisition sensor for many other spacecraft. NASA's New Millennium Program (NMP) has selected the ISC technology for a Space Technology 6 (ST6) flight validation experiment scheduled for 2004. NMP missions, such a s ST6, are intended to validate advanced technologies that have not flown in space in order to reduce the risk associated with their infusion into future NASA missions. This paper describes the design, operation, and performance of the ISC and outlines the technology validation plan. A number of mission applications for the ISC technology are highlighted, both for the baseline ST6 ISC configuration and more ambitious applications where ISC hardware and software modifications would be required. These applications demonstrate the wide range of Space and Earth Science missions that would benefit from infusion of the ISC technology.

Bauer, Frank H.↗

Performance of the ATLAS Level-1 topological trigger in Run 2

During LHC Run 2 (2015–2018) the ATLAS Level-1 topological trigger allowed efficient data-taking by the ATLAS experiment at luminosities up to 2.1x10 34 cm -2 s -1 , which exceeds the design value by a factor of two. The system was installed in 2016 and operated in 2017 and 2018. It uses Field Programmable Gate Array processors to select interesting events by placing kinematic and angular requirements on electromagnetic clusters, jets, τ-leptons, muons and the missing transverse energy. It allowed to significantly improve the background event rejection and signal event acceptance, in particular for Higgs and B-physics processes.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗