Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “PROCESSORS”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,711 records · Page 95

The Scalable HeterOgeneous Computing (SHOC) Benchmark Suite

Scalable heterogeneous computing systems, which are composed of a mix of compute devices, such as commodity multicore processors, graphics processors, reconfigurable processors, and others, are gaining attention as one approach to continuing performance improvement while managing the new challenge of energy efficiency. As these systems become more common, it is important to be able to compare and contrast architectural designs and programming systems in a fair and open forum. To this end, we have designed the Scalable HeterOgeneous Computing benchmark suite (SHOC). SHOC's initial focus is on systems containing graphics processing units (GPUs) and multi-core processors, and on the new OpenCL programming standard. SHOC is a spectrum of programs that test the performance and stability of these scalable heterogeneous computing systems. At the lowest level, SHOC uses microbenchmarks to assess architectural features of the system. At higher levels, SHOC uses application kernels to determine system-wide performance including many system features such as intranode and internode communication among devices. SHOC includes benchmark implementations in both OpenCL and CUDA in order to provide a comparison of these programming models.

99 GENERAL AND MISCELLANEOUS↗

A Framework to Analyze the Performance of Load Balancing Schemes for Ensembles of Stochastic Simulations

Ensembles of simulations are employed to estimate the statistics of possible future states of a system, and are widely used in important applications such as climate change and biological modeling. Ensembles of runs can naturally be executed in parallel. However, when the CPU times of individual simulations vary considerably, a simple strategy of assigning an equal number of tasks per processor can lead to serious work imbalances and low parallel efficiency. This paper presents a new probabilistic framework to analyze the performance of dynamic load balancing algorithms for ensembles of simulations where many tasks are mapped onto each processor, and where the individual compute times vary considerably among tasks. Four load balancing strategies are discussed: most-dividing, all-redistribution, random-polling, and neighbor-redistribution. Simulation results with a stochastic budding yeast cell cycle model are consistent with the theoretical analysis. It is especially significant that there is a provable global decrease in load imbalance for the local rebalancing algorithms due to scalability concerns for the global rebalancing algorithms. The overall simulation time is reduced by up to 25 %, and the total processor idle time by 85 %.

ALGORITHMS↗

Remote Objects Message Exchange (ROME)

The performance of a single program running on a single processor is limited by the character of the processor. Moreover, the cost and difficulty of developing and sustaining programs tend to increase as their size and complexity increase. Clearly there ought to be some advantage in partitioning powerful application software in relatively small and simple components that can run in parallel on multiple processors; the software should run faster and it should be cheaper and easier to deploy. Remote Objects Message Exchange (ROME) is an attempt to provide a single relatively simple, universally available abstraction for data communication among C++ objects. It aims to enable the C++ application developer to specify objects' interactions with other objects wholly in terms of the application domain, without concern for details of interprocess communication. Every ROME-compliant object is conceptually a network peer of every other, as if each one were (for example) a separate UNIX process.

processors application software data communication↗

High-Performance Spaceflight Computing (HPSC) Project Overview

The High Performance Spaceflight Computing (HPSC) multi-core processor Chiplet will provide a nearly two orders-of-magnitude improvement above the current state of the art for spaceflight processors, while also providing an unprecedented flexibility to tailor performance, power consumption, and fault tolerance to meet widely varying mission needs. These advancements will provide game changing improvements in computing performance, power efficiency, and flexibility, which will significantly improve the onboard processing capabilities of future NASA and Air Force space missions. HPSC is funded by NASA's Space Technology Mission Directorate (STMD), Science Mission Directorate (SMD), and the United States Air Force. The HPSC project is managed by Jet Propulsion Laboratory, and the HPSC contract is managed by NASA Goddard Space Flight Center (GSFC). Within the HPSC project, Boeing is under contract to NASA to develop prototype Chiplets, system software, and evaluation boards. As another development within the project, NASA Goddard Space Flight Center (GSFC) and the Jet Propulsion Laboratory (JPL) are developing middleware that will simplify application development for HPSC-based onboard processors.

multi-core processor↗

Enabling power measurement and control on Astra: The first petascale Arm supercomputer

Astra, deployed in 2018, was the first petascale supercomputer to utilize processors based on the ARM instruction set. The system was also the first under Sandia's Vanguard program which seeks to provide an evaluation vehicle for novel technologies that with refinement could be utilized in demanding, large-scale HPC environments. In addition to ARM, several other important first-of-a-kind developments were used in the machine, including new approaches to cooling the datacenter and machine. Here we document our experiences building a power measurement and control infrastructure for Astra. While this is often beyond the control of users today, the accurate measurement, cataloging, and evaluation of power, as our experiences show, is critical to the successful deployment of a large-scale platform. While such systems exist in part for other architectures, Astra required new development to support the novel Marvell ThunderX2 processor used in compute nodes. In addition to documenting the measurement of power during system bring up and for subsequent on-going routine use, we present results associated with controlling the power usage of the processor, an area which is becoming of progressively greater interest as data centers and supercomputing sites look to improve compute/energy efficiency and find additional sources for full system optimization.

97 MATHEMATICS AND COMPUTING↗

Data Movement in Data-Intensive High Performance Computing.

The cost of executing a floating point operation has been decreasing for decades at a much higher rate than that of moving data. Bandwidth and latency, two key metrics that determine the cost of moving data, have degraded significantly relative to processor cycle time and execution rate. Despite the limitation of sub-micron processor technology and the end of Dennard scaling, this trend will continue in the short-term making data movement a performance-limiting factor and an energy/power efficiency concern. Even more so in the context of large-scale and data-intensive systems and workloads. This chapter gives an overview of the aspects of moving data across a system, from the storage system to the computing system down to the node and processor level, with case study and contributions from researchers at the San Diego Supercomputer Center, the Oak Ridge National Laboratory, the Pacific Northwest National Laboratory, and the University of Delaware.

Data Movement↗

Mesh-based super-resolution of fluid flows with multiscale graph neural networks

A graph neural network (GNN) approach is introduced in this work which enables mesh-based three-dimensional super-resolution of fluid flows. In this framework, the GNN is designed to operate not on the full mesh-based field at once, but on localized meshes of elements (or cells) directly. To facilitate mesh-based GNN representations in a manner similar to spectral (or finite) element discretizations, a baseline GNN layer (termed a message passing layer, which updates local node properties) is modified to account for synchronization of coincident graph nodes, rendering compatibility with commonly used element-based mesh connectivities. Furthermore, the architecture is multiscale in nature, and is comprised of a combination of coarse-scale and fine-scale message passing layer sequences (termed processors) separated by a graph unpooling layer. The coarse-scale processor embeds a query element (alongside a set number of neighboring coarse elements) into a single latent graph representation using coarse-scale synchronized message passing over the element neighborhood, and the fine-scale processor leverages additional message passing operations on this latent graph to correct for interpolation errors. Demonstration studies are performed using hexahedral mesh-based data from Taylor–Green Vortex and backward-facing step flow simulations at Reynolds numbers of 1600 and 3200. Through analysis of both global and local errors, the results ultimately show how the GNN is able to produce accurate super-resolved fields compared to targets in both coarse-scale and multiscale model configurations. Reconstruction errors for fixed architectures were found to increase in proportion to the Reynolds number. Geometry extrapolation studies on a separate cavity flow configuration show promising cross-mesh capabilities of the super-resolution strategy.

Backward-facing step↗

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↗

Alternating Anderson–Richardson method: An efficient alternative to preconditioned Krylov methods for large, sparse linear systems

Here, we present the Alternating Anderson–Richardson (AAR) method: an efficient and scalable alternative to preconditioned Krylov solvers for the solution of large, sparse linear systems on high performance computing platforms. Specifically, we generalize the recently proposed Alternating Anderson–Jacobi (AAJ) method (Pratapa et al., 2016) to include preconditioning, discuss efficient parallel implementation, and provide serial MATLAB and parallel C/C++ implementations. In serial applications to nonsymmetric systems, we find that AAR is comparably robust to GMRES, using the same preconditioning, while often outperforming it in time to solution; and find AAR to be more robust than Bi-CGSTAB for the problems considered. In parallel applications to the Helmholtz and Poisson equations, we find that AAR shows superior strong and weak scaling to GMRES, Bi-CGSTAB, and Conjugate Gradient (CG) methods, using the same preconditioning, with consistently shorter times to solution at larger processor counts. Finally, in massively parallel applications to the Poisson equation, on up to 110,592 processors, we find that AAR shows superior strong and weak scaling to CG, with shorter minimum time to solution. We thus find that AAR offers a robust and efficient alternative to current state-of-the-art solvers, with increasing advantages as the number of processors grows.

97 MATHEMATICS AND COMPUTING↗

A generalized massively parallel ultra-high order FFT-based Maxwell solver

Dispersion-free ultra-high order FFT-based Maxwell solvers have recently proven to be paramount to a large range of applications, including the high-fidelity modeling of high-intensity laser–matter interactions with Particle-In-Cell (PIC) codes. To enable a massively parallel scaling of these solvers, a novel parallelization technique was recently proposed, which consists in splitting the simulation domain into several processor sub-domains, with guard regions appended at each sub-domain boundary. Maxwell's equations are advanced independently on each sub-domain using local shared-memory FFTs (instead of a single distributed global FFT). This implies small truncation errors at sub-domain boundaries, the amplitude of which depends on guard regions sizes and order of the Maxwell solver. For moderate guard region sizes, this ’local’ technique proved to be highly scalable on up to a million cores and notably enabled the 3D modeling of so-called plasma mirrors, for which 8 guard cells only were enough to prevent truncation error growth. Yet, for other applications, the required number of guard cells might be much higher, which would severely limit the parallel efficiency of this technique due to the large volume of guard cells to be exchanged between sub-domains. In this context, we propose a novel parallelization technique that ensures very good scaling of FFT-based solvers with an arbitrarily high number of guard cells. Our ’hybrid’ technique consists in performing distributed FFTs on local groups of processors with guard regions now appended to boundaries of each group of processors. It uses a dual domain decomposition method for the Maxwell solver and other parts of the PIC cycle to keep the simulation load-balanced. This ’hybrid’ technique was implemented in the open source exascale library PICSAR. Benchmarks show that for a large number of guard cells (>16), the ’hybrid’ technique offers up to ×3 speed-up and ×8 memory savings compared to the ’local’ one.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Parallel adaptation of general three-dimensional hybrid meshes

A new parallel dynamic mesh adaptation and load balancing algorithm for general hybrid grids has been developed. The meshes considered in this work are composed of four kinds of elements; tetrahedra, prisms, hexahedra and pyramids, which poses a challenge to parallel mesh adaptation. Additional complexity imposed by the presence of multiple types of elements affects especially data migration, updates of local data structures and interpartition data structures. Efficient partition of hybrid meshes has been accomplished by transforming them to suitable graphs and using serial graph partitioning algorithms. Communication among processors is based on the faces of the interpartition boundary and the termination detection algorithm of Dijkstra is employed to ensure proper flagging of edges for refinement. An inexpensive dynamic load balancing strategy is introduced to redistribute work load among processors after adaptation. In particular, only the initial coarse mesh, with proper weighting, is balanced which yields savings in computation time and relatively simple implementation of mesh quality preservation rules, while facilitating coarsening of refined elements. Special algorithms are employed for (i) data migration and dynamic updates of the local data structures, (ii) determination of the resulting interpartition boundary and (iii) identification of the communication pattern of processors. Several representative applications are included to evaluate the method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

An efficient parallel implementation of explicit multirate Runge–Kutta schemes for discontinuous Galerkin computations

Although explicit time integration schemes require small computational efforts per time step, their efficiency is severely restricted by their stability limits. Indeed, the multi-scale nature of some physical processes combined with highly unstructured meshes can lead some elements to impose a severely small stable time step for a global problem. Multirate methods offer a way to increase the global efficiency by gathering grid cells in appropriate groups under local stability conditions. These methods are well suited to the discontinuous Galerkin framework. The parallelization of the multirate strategy is challenging because grid cells have different workloads. The computational cost is different for each sub-time step depending on the elements involved and a classical partitioning strategy is not adequate any more. In this paper, we propose a solution that makes use of multi-constraint mesh partitioning. It tends to minimize the inter-processor communications, while ensuring that the workload is almost equally shared by every computer core at every stage of the algorithm. Particular attention is given to the simplicity of the parallel multirate algorithm while minimizing computational and communication overheads. Our implementation makes use of the MeTiS library for mesh partitioning and the Message Passing Interface for inter-processor communication. Performance analyses for two and three-dimensional practical applications confirm that multirate methods preserve important computational advantages of explicit methods up to a significant number of processors.

97 MATHEMATICS AND COMPUTING↗

The use of imprecise processing to improve accuracy in weather and climate prediction

The use of stochastic processing hardware and low precision arithmetic in atmospheric models is investigated. Stochastic processors allow hardware-induced faults in calculations, sacrificing bit-reproducibility and precision in exchange for improvements in performance and potentially accuracy of forecasts, due to a reduction in power consumption that could allow higher resolution. A similar trade-off is achieved using low precision arithmetic, with improvements in computation and communication speed and savings in storage and memory requirements. As high-performance computing becomes more massively parallel and power intensive, these two approaches may be important stepping stones in the pursuit of global cloud-resolving atmospheric modelling. The impact of both hardware induced faults and low precision arithmetic is tested using the Lorenz '96 model and the dynamical core of a global atmosphere model. In the Lorenz '96 model there is a natural scale separation; the spectral discretisation used in the dynamical core also allows large and small scale dynamics to be treated separately within the code. Such scale separation allows the impact of lower-accuracy arithmetic to be restricted to components close to the truncation scales and hence close to the necessarily inexact parametrised representations of unresolved processes. By contrast, the larger scales are calculated using high precision deterministic arithmetic. Hardware faults from stochastic processors are emulated using a bit-flip model with different fault rates. Our simulations show that both approaches to inexact calculations do not substantially affect the large scale behaviour, provided they are restricted to act only on smaller scales. By contrast, results from the Lorenz '96 simulations are superior when small scales are calculated on an emulated stochastic processor than when those small scales are parametrised. This suggests that inexact calculations at the small scale could reduce computation and power costs without adversely affecting the quality of the simulations. This would allow higher resolution models to be run at the same computational cost.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

An incentive-based distributed mechanism for scheduling divisible loads in tree networks

The underlying assumption of Divisible Load Scheduling (DLS) theory is that the pro-cessors composing the network are obedient, i.e., they do not “cheat” the scheduling algorithm. This assumption is unrealistic if the processors are owned by autonomous, self-interested organizations that have no a priori motivation for cooperation and they will manipulate the algorithm if it is beneficial to do so. In this paper, we address this issue by designing a distributed mechanism for scheduling divisible loads in tree net-works, called DLS-T, which provides incentives to processors for reporting their true processing capacity and executing their assigned load at full processing capacity. We prove that the DLS-T mechanism computes the optimal allocation in an ex post Nash equilibrium. Finally, we simulate and study the mechanism under various network structures and processor parameters.

Algorithmic mechanism design↗

Parallelizing heavyweight debugging tools with mpiecho

Idioms created for debugging execution on single processors and multicore systems have been successfully scaled to thousands of processors, but there is little hope that this class of techniques can continue to be scaled out to tens of millions of cores. In order to allow development of more scalable debugging idioms we introduce mpiecho, a novel runtime platform that enables cloning of MPI ranks. Given identical execution on each clone, we then show how heavyweight debugging approaches can be parallelized, reducing their overhead to a fraction of the serialized case. We also show how this platform can be useful in isolating the source of hardware-based nondeterministic behavior and provide a case study based on a recent processor bug at LLNL.

97 MATHEMATICS AND COMPUTING↗

Parallel implementation of multireference coupled-cluster theories based on the reference-level parallelism

A novel algorithm for implementing general type of multireference coupled-cluster (MRCC) theory based on the Jeziorski-Monkhorst exponential Ansatz [B. Jeziorski, H.J. Monkhorst, Phys. Rev. A 24, 1668 (1981)] is introduced. The proposed algorithm utilizes processor groups to calculate the equations for the MRCC amplitudes. In the basic formulation each processor group constructs the equations related to a specific subset of references. By flexible choice of processor groups and subset of reference-specific sufficiency conditions designated to a given group one can assure optimum utilization of available computing resources. The performance of this algorithm is illustrated on the examples of the Brillouin-Wigner and Mukherjee MRCC methods with singles and doubles (BW-MRCCSD and Mk-MRCCSD). A significant improvement in scalability and in reduction of time to solution is reported with respect to recently reported parallel implementation of the BW-MRCCSD formalism [J.Brabec, H.J.J. van Dam, K. Kowalski, J. Pittner, Chem. Phys. Lett. 514, 347 (2011)].

99 GENERAL AND MISCELLANEOUS↗

Towards single-chip radiofrequency signal processing via acoustoelectric electron–phonon interactions

Abstract The addition of active, nonlinear, and nonreciprocal functionalities to passive piezoelectric acoustic wave technologies could enable all-acoustic and therefore ultra-compact radiofrequency signal processors. Toward this goal, we present a heterogeneously integrated acoustoelectric material platform consisting of a 50 nm indium gallium arsenide epitaxial semiconductor film in direct contact with a 41° YX lithium niobate piezoelectric substrate. We then demonstrate three of the main components of an all-acoustic radiofrequency signal processor: passive delay line filters, amplifiers, and circulators. Heterogeneous integration allows for simultaneous, independent optimization of the piezoelectric-acoustic and electronic properties, leading to the highest performing surface acoustic wave amplifiers ever developed in terms of gain per unit length and DC power dissipation, as well as the first-ever demonstrated acoustoelectric circulator with an isolation of 46 dB with a pulsed DC bias. Finally, we describe how the remaining components of an all-acoustic radiofrequency signal processor are an extension of this work.

36 MATERIALS SCIENCE↗

Benchmarking quantum logic operations relative to thresholds for fault tolerance

Contemporary methods for benchmarking noisy quantum processors typically measure average error rates or process infidelities. However, thresholds for fault-tolerant quantum error correction are given in terms of worst-case error rates—defined via the diamond norm—which can differ from average error rates by orders of magnitude. One method for resolving this discrepancy is to randomize the physical implementation of quantum gates, using techniques like randomized compiling (RC). In this work, we use gate set tomography to perform precision characterization of a set of two-qubit logic gates to study RC on a superconducting quantum processor. We find that, under RC, gate errors are accurately described by a stochastic Pauli noise model without coherent errors, and that spatially correlated coherent errors and non-Markovian errors are strongly suppressed. We further show that the average and worst-case error rates are equal for randomly compiled gates, and measure a maximum worst-case error of 0.0197(3) for our gate set. Our results show that randomized benchmarks are a viable route to both verifying that a quantum processor’s error rates are below a fault-tolerance threshold, and to bounding the failure rates of near-term algorithms, if—and only if—gates are implemented via randomization methods which tailor noise.

97 MATHEMATICS AND COMPUTING↗