Search NASA⌕ Search

SEARCH · Search NASA

Results for “computer architecture”

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

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

At least 1,099 records · Page 61

On multigrid methods for the Navier-Stokes Computer

The overall architecture of the multipurpose parallel-processing Navier-Stokes Computer (NSC) being developed by Princeton and NASA Langley (Nosenchuck et al., 1986) is described and illustrated with extensive diagrams, and the NSC implementation of an elementary multigrid algorithm for simulating isotropic turbulence (based on solution of the incompressible time-dependent Navier-Stokes equations with constant viscosity) is characterized in detail. The present NSC design concept calls for 64 nodes, each with the performance of a class VI supercomputer, linked together by a fiber-optic hypercube network and joined to a front-end computer by a global bus. In this configuration, the NSC would have a storage capacity of over 32 Gword and a peak speed of over 40 Gflops. The multigrid Navier-Stokes code discussed would give sustained operation rates of about 25 Gflops.

Nosenchuck, D. M.↗

Computer-Aided Design of Organic Host Architectures for Selective Chemosensors

Selective organic hosts provide the foundation for the development of many types of sensors. The deliberate design of host molecules with predetermined selectivity, however, remains a challenge in supramolecular chemistry. To address this issue we have developed a de novo structure-based design approach for the unbiased construction of complementary host architectures. This chapter summarizes recent progress including improvements on a computer software program, HostDesigner, specifically tailored to discover host architectures for small guest molecules. HostDesigner is capable of generating and evaluating millions of candidate structures in minutes on a desktop personal computer, allowing a user to rapidly identify three-dimensional architectures that are structurally organized for binding a targeted guest species. The efficacy of this computational methodology is illustrated with a search for cation hosts containing aliphatic ether oxygen groups and anion hosts containing urea groups.

99 GENERAL AND MISCELLANEOUS↗

Active Measurement of the Impact of Network SwitchUtilization on Application Performance

Inter-node networks are a key capability of High-Performance Computing (HPC) systems that differentiates them from less capable classes of machines. However, in spite of their very high performance, the increasing computational power of HPC compute nodes and the associated rise in application communication needs make network performance a common performance bottleneck. To achieve high performance in spite of network limitations application developers require tools to measure their applications’ network utilization and inform them about how the network’s communication capacity relates to the performance of their applications. This paper presents a new performance measurement and analysis methodology based on empirical measurements of network behavior. Our approach uses two benchmarks that inject extra network communication. The first probes the fraction of the network that is utilized by a software component (an application or an individual task) to determine the existence and severity of network contention. The second aggressively injects network traffic while a software component runs to evaluate its performance on less capable networks or when it shares the network with other software components. We then combine the information from the two types of experiment to predict the performance slowdown experienced by multiple software components (e.g. multiple processes of a single MPI application) when they share a single network. Our methodology is applied to individual network switches and demonstrated on two real systems with different types of switches and compute node architectures.

97 MATHEMATICS AND COMPUTING↗

Magellan at NERSC Progress Report for June 2010

The Magellan Project was funded by the American Recovery and Reinvestment Act to investigate the applicability of cloud computing for the Department of Energy's Office of Science (DOE-SC). This report covers the progress for the Magellan Project at NERSC since it began in September 2009and focuses on the research aspects of the project.

97 MATHEMATICS AND COMPUTING↗

Time-sliced quantum circuit partitioning for modular architectures

Current quantum computer designs will not scale. To scale beyond small prototypes, quantum architectures will likely adopt a modular approach with clusters of tightly connected quantum bits and sparser connections between clusters. We exploit this clustering and the statically-known control flow of quantum programs to create tractable partitioning heuristics which map quantum circuits to modular physical machines one time slice at a time. Specifically, we create optimized mappings for each time slice, accounting for the cost to move data from the previous time slice and using a tunable lookahead scheme to reduce the cost to move to future time slices. We compare our approach to a traditional statically-mapped, owner-computes model. Our results show strict improvement over the static mapping baseline. Here, we reduce the non-local communication overhead by 89.8% in the best case and by 60.9% on average. Our techniques, unlike many exact solver methods, are computationally tractable.

Baker, Jonathan M.↗

Developing the Next Generation of Science Data System Engineers

At Goddard, engineers and scientists with a range of experience in science data systems are needed to employ new technologies and develop advances in capabilities for supporting new Earth and Space science research. Engineers with extensive experience in science data, software engineering and computer-information architectures are needed to lead and perform these activities. The increasing types and complexity of instrument data and emerging computer technologies coupled with the current shortage of computer engineers with backgrounds in science has led the need to develop a career path for science data systems engineers and architects.The current career path, in which undergraduate students studying various disciplines such as Computer Engineering or Physical Scientist, generally begins with serving on a development team in any of the disciplines where they can work in depth on existing Goddard data systems or serve with a specific NASA science team. There they begin to understand the data, infuse technologies, and begin to know the architectures of science data systems. From here the typical career involves peermentoring, on-the-job training or graduate level studies in analytics, computational science and applied science and mathematics. At the most senior level, engineers become subject matter experts and system architect experts, leading discipline-specific data centers and large software development projects. They are recognized as a subject matter expert in a science domain, they have project management expertise, lead standards efforts and lead international projects. A long career development remains necessary not only because of the breadth of knowledge required across physical sciences and engineering disciplines, but also because of the diversity of instrument data being developed today both by NASA and international partner agencies and because multidiscipline science and practitioner communities expect to have access to all types of observational data.This paper describes an approach to defining career-path guidance for college-bound high school and undergraduate engineering students, junior and senior engineers from various disciplines.

Next Generation of Science↗

Trigger Detection for Adaptive Scientific Workflows Using Percentile Sampling

The increasing complexity of both scientific simulations and high-performance computing system architectures are driving the need for adaptive workflows, in which the composition and execution of computational and data manipulation steps dynamically depend on the evolutionary state of the simulation itself. Consider, for example, the frequency of data storage. Critical phases of the simulation should be captured with high frequency and with high fidelity for postanalysis; however, we cannot afford to retain the same frequency for the full simulation due to the high cost of data movement. We can instead look for triggers, indicators that the simulation will be entering a critical phase, and adapt the workflow accordingly. In this paper, we present a methodology for detecting triggers and demonstrate its use in the context of direct numerical simulations of turbulent combustion using S3D. We show that chemical explosive mode analysis (CEMA) can be used to devise a noise-tolerant indicator for rapid increase in heat release. However, exhaustive computation of CEMA values dominates the total simulation, and thus is prohibitively expensive. To overcome this computational bottleneck, we propose a quantile sampling approach. Our sampling-based algorithm comes with provable error/confidence bounds, as a function of the number of samples. Most importantly, the number of samples is independent of the problem size, and thus our proposed sampling algorithm offers perfect scalability. Our experiments on homogeneous charge compression ignition and reactivity controlled compression ignition simulations show that the proposed method can detect rapid increases in heat release, and its computational overhead is negligible. Our results will be used to make dynamic workflow decisions regarding data storage and mesh resolution in future combustion simulations.

97 MATHEMATICS AND COMPUTING↗

A Massively Parallel Adaptive Fast-Multipole Method on Heterogeneous Architectures

We present new scalable algorithms and an implementation of the kernel-independent fast multiple method (KIFMM), employing hybrid distributed memory message passing (via MPI) and shared memory/streaming using graphics processing unit (GPU) acceleration to rapidly evaluate two-body non-oscillatory potentials. On traditional CPU-only systems, our implementation scales well up to 30 billion unknowns on 65k cores (AMD/CRAY-based Kraken system at NSF/NICS) on tree data structures with 25 levels between leaves. On GPU-enabled systems, we achieve 30 x speedup for problems of up to 256 million points on 256 GPUs (Lincoln at NSF/NCSA) over a comparable CPU-only implementation. Both of these demonstrations represent the largest and fastest of their kind of which we are aware. We achieve scalability at extreme core counts by extending the initial work of Ying et al. (ACM/IEEE SC 03) with a new approach to scalable MPI-based tree construction and partitioning. For the sub-components of KIFMM, which direct- and approximate-interactions, target evaluation, and source-to-multipole translations, we use CUDA-based GPU-acceleration to achieve excellent performance. To do so requires carefully constructed data structure transformations, which we describe, and whose cost we show is minor. Taken together, these components show promise for ultrascalable FMM in the petascale era and beyond.

99 GENERAL AND MISCELLANEOUS↗

Massively Parallel Latent Semantic Analyzes using a Graphics Processing Unit

Latent Semantic Indexing (LSA) aims to reduce the dimensions of large Term-Document datasets using Singular Value Decomposition. However, with the ever expanding size of data sets, current implementations are not fast enough to quickly and easily compute the results on a standard PC. The Graphics Processing Unit (GPU) can solve some highly parallel problems much faster than the traditional sequential processor (CPU). Thus, a deployable system using a GPU to speedup large-scale LSA processes would be a much more effective choice (in terms of cost/performance ratio) than using a computer cluster. Due to the GPU s application-specific architecture, harnessing the GPU s computational prowess for LSA is a great challenge. We present a parallel LSA implementation on the GPU, using NVIDIA Compute Unified Device Architecture and Compute Unified Basic Linear Algebra Subprograms. The performance of this implementation is compared to traditional LSA implementation on CPU using an optimized Basic Linear Algebra Subprograms library. After implementation, we discovered that the GPU version of the algorithm was twice as fast for large matrices (1000x1000 and above) that had dimensions not divisible by 16. For large matrices that did have dimensions divisible by 16, the GPU algorithm ran five to six times faster than the CPU version. The large variation is due to architectural benefits the GPU has for matrices divisible by 16. It should be noted that the overall speeds for the CPU version did not vary from relative normal when the matrix dimensions were divisible by 16. Further research is needed in order to produce a fully implementable version of LSA. With that in mind, the research we presented shows that the GPU is a viable option for increasing the speed of LSA, in terms of cost/performance ratio.

99 GENERAL AND MISCELLANEOUS↗

Deploy Nalu/Kokkos algorithmic infrastructure with performance benchmarking.

The former Nalu interior heterogeneous algorithm design, which was originally designed to manage matrix assembly operations over all elemental topology types, has been modified to operate over homogeneous collections of mesh entities. This newly templated kernel design allows for removal of workset variable resize operations that were formerly required at each loop over a Sierra ToolKit (STK) bucket (nominally, 512 entities in size). Extensive usage of the Standard Template Library (STL) std::vector has been removed in favor of intrinsic Kokkos memory views. In this milestone effort, the transition to Kokkos as the underlying infrastructure to support performance and portability on many-core architectures has been deployed for key matrix algorithmic kernels. A unit-test driven design effort has developed a homogeneous entity algorithm that employs a team-based thread parallelism construct. The STK Single Instruction Multiple Data (SIMD) infrastructure is used to interleave data for improved vectorization. The collective algorithm design, which allows for concurrent threading and SIMD management, has been deployed for the core low-Mach element- based algorithm. Several tests to ascertain SIMD performance on Intel KNL and Haswell architectures have been carried out. The performance test matrix includes evaluation of both low- and higher-order methods. The higher-order low-Mach methodology builds on polynomial promotion of the core low-order control volume nite element method (CVFEM). Performance testing of the Kokkos-view/SIMD design indicates low-order matrix assembly kernel speed-up ranging between two and four times depending on mesh loading and node count. Better speedups are observed for higher-order meshes (currently only P=2 has been tested) especially on KNL. The increased workload per element on higher-order meshes bene ts from the wide SIMD width on KNL machines. Combining multiple threads with SIMD on KNL achieves a 4.6x speedup over the baseline, with assembly timings faster than that observed on Haswell architecture. The computational workload of higher-order meshes, therefore, seems ideally suited for the many-core architecture and justi es further exploration of higher-order on NGP platforms. A Trilinos/Tpetra-based multi-threaded GMRES preconditioned by symmetric Gauss Seidel (SGS) represents the core solver infrastructure for the low-Mach advection/diffusion implicit solves. The threaded solver stack has been tested on small problems on NREL's Peregrine system using the newly developed and deployed Kokkos-view/SIMD kernels. fforts are underway to deploy the Tpetra-based solver stack on NERSC Cori system to benchmark its performance at scale on KNL machines.

97 MATHEMATICS AND COMPUTING↗

Implementing High Performance Remote Method Invocation in CCA

We report our effort in engineering a high performance remote method invocation (RMI) mechanism for the Common Component Architecture (CCA). This mechanism provides a highly efficient and easy-to-use mechanism for distributed computing in CCA, enabling CCA applications to effectively leverage parallel systems to accelerate computations. This work is built on the previous work of Babel RMI. Babel is a high performance language interoperability tool that is used in CCA for scientific application writers to share, reuse, and compose applications from software components written in different programming languages. Babel provides a transparent and flexible RMI framework for distributed computing. However, the existing Babel RMI implementation is built on top of TCP and does not provide the level of performance required to distribute fine-grained tasks. We observed that the main reason the TCP based RMI does not perform well is because it does not utilize the high performance interconnect hardware on a cluster efficiently. We have implemented a high performance RMI protocol, HPCRMI. HPCRMI achieves low latency by building on top of a low-level portable communication library, Aggregated Remote Message Copy Interface (ARMCI), and minimizing communication for each RMI call. Our design allows a RMI operation to be completed by only two RDMA operations. We also aggressively optimize our system to reduce copying. In this paper, we discuss the design and our experimental evaluation of this protocol. Our experimental results show that our protocol can improve RMI performance by an order of magnitude.

99 GENERAL AND MISCELLANEOUS↗

ARENA: Adversary-Resistant Evolving Neural Architectures

Neural networks are becoming the cornerstone for national security prediction tasks. However, designing them requires significant research and trial/error, as they have many hyperparameters, including their computation graph (“architecture”). Neural architecture search (NAS) employs secondary optimizers to search for architectures maximizing objectives like accuracy. Evolutionary algorithms (EAs) are the most used class of optimizer for NAS. However, existing Python libraries for writing EAs limit the complexity of experiments a user can design. In this project, we built ARENA, a Python framework that encodes complex, hyper-realistic EAs. ARENA collects detailed information as it runs and is flexible enough to encode non-EA search algorithms. We tested ARENA on 4 toy optimization problems by encoding 3 search algorithms for each—random search, an EA, and simulated annealing. We also designed an EA that performs NAS on the MNIST dataset. Our experiments suggest the potential for immediate mission impact through solving lab-wide optimization problems.

97 MATHEMATICS AND COMPUTING↗

The architecture of an event correlation service for adaptive middleware-based applications

Loosely coupled component communication driven by events is a key mechanism for building middleware- based applications that must achieve reliable qualities of service in an adaptive manner. In such a system, events that encapsulate state snapshots of a running system are generated by monitoring components. Hence, an event correlation service is necessary for correlating monitored events from multiple sources. The requirements for the event correlation raise two challenges: to seamlessly integrate event correlation services with other services and applications; and to provide reliable event management with minimal delay. This paper describes our experience in the design and implementation of an event correlation service. The design encompasses an event correlator and an event proxy that are integrated with an architecture for adaptive middleware components. The implementation utilizes the common-based event (CBE) specification and stateful Web service technologies to support the deployment of the event correlation service in a distributed architecture. We evaluate the performance of the overall solution in a test bed and present the results in terms of the trade-off between the flexibility and the performance overhead of the architecture

99 GENERAL AND MISCELLANEOUS↗

Power and Performance Trade-offs for Space Time Adaptive Processing

Computational efficiency – performance relative to power or energy – is one of the most important concerns when designing RADAR processing systems. This paper analyzes power and performance trade-offs for a typical Space Time Adaptive Processing (STAP) application. We study STAP implementations for CUDA and OpenMP on two computationally efficient architectures, Intel Haswell Core I7-4770TE and NVIDIA Kayla with a GK208 GPU. We analyze the power and performance of STAP’s computationally intensive kernels across the two hardware testbeds. We also show the impact and trade-offs of GPU optimization techniques. We show that data parallelism can be exploited for efficient implementation on the Haswell CPU architecture. The GPU architecture is able to process large size data sets without increase in power requirement. The use of shared memory has a significant impact on the power requirement for the GPU. A balance between the use of shared memory and main memory access leads to an improved performance in a typical STAP application.

Gawande, Nitin A.↗

Modular Spiking Neural Circuits for Mapping Long Short-Term Memory on a Neurosynaptic Processor

Due to the distributed and asynchronous nature of neural computation through low-energy spikes, brain-inspired hardware systems offer high energy efficiency and massive parallelism. One such platform is the IBM TrueNorth neurosynaptic system. Recently, TrueNorth compatible representation learning algorithms have emerged, achieving close to the state-of-the-art performance in various data sets. However, its application in temporal sequence processing models, such as recurrent neural networks (RNNs), is still only at the proof of concept level. There is an inherent difficulty in capturing temporal dynamics of an RNN using spiking neurons, which is only exasperated by the hardware constraints in connectivity and synaptic weight resolution. This paper presents a design flow that overcomes these difficulties and maps a special case of recurrent networks called long short-term memory (LSTM) onto a spike-based platform. The framework utilizes various approximation techniques, such as activation discretization, weight quantization, and scaling and rounding, spiking neural circuits that implement the complex gating mechanisms, and a store-and-release technique to enable neuron synchronization and faithful storage. While the presented techniques can be applied to map LSTM to any spiking neural network (SNN) simulator/emulator, here we choose the TrueNorth chip as the target platform by adhering to its hardware constraints. Three LSTM applications, parity check, extended Reber grammar, and question classification, are evaluated. The tradeoffs among accuracy, performance, and energy tradeoffs achieved on TrueNorth are demonstrated. Finally, this is compared with the performance on an SNN platform without hardware constraints, which represents the upper bound of the achievable accuracy.

97 MATHEMATICS AND COMPUTING↗

BDEM (Discrete-element-simulator for high-solids granular flows) [SWR-22-72]

BDEM is a discrete element method based simulation tool developed specifically for modeling high-solids granular flows that include polydispersity, heat-transfer, moving boundaries and chemistry. Our solver provides facilities for simulating spherical/non-spherical particles with modified contact and friction models in complex dynamic geometries defined using level-sets or triangulated files. The solver is developed on top of NREL's open-source performance portable library, AMReX, providing parallel execution capabilities on current and upcoming high-performance-computing (HPC) architectures. Simulations at the scale of several millions to billion particles have been performed using this software on large scale computing resources. This software can be applied to non-reacting solids dominant flows in silos, hoppers and screw conveyors as well as in high temperature reacting systems such as screw kilns and auger reactors.

Sitaraman, Hariswaran↗

Instrumented Architectural Simulation System

Simulation of systems at an architectural level can offer an effective way to study critical design choices if (1) the performance of the simulator is adequate to examine designs executing significant code bodies, not just toy problems or small application fragements, (2) the details of the simulation include the critical details of the design, (3) the view of the design presented by the simulator instrumentation leads to useful insights on the problems with the design, and (4) there is enough flexibility in the simulation system so that the asking of unplanned questions is not suppressed by the weight of the mechanics involved in making changes either in the design or its measurement. A simulation system with these goals is described together with the approach to its implementation. Its application to the study of a particular class of multiprocessor hardware system architectures is illustrated.

COMPUTERIZED SIMULATION↗