Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel applications”

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 631 records · Page 35

Hybrid algorithms in quantum Monte Carlo

With advances in algorithms and growing computing powers, quantum Monte Carlo (QMC) methods have become a leading contender for high accuracy calculations for the electronic structure of realistic systems. The performance gain on recent HPC systems is largely driven by increasing parallelism: the number of compute cores of a SMP and the number of SMPs have been going up, as the Top500 list attests. However, the available memory as well as the communication and memory bandwidth per element has not kept pace with the increasing parallelism. This severely limits the applicability of QMC and the problem size it can handle. OpenMP/MPI hybrid programming provides applications with simple but effective solutions to overcome efficiency and scalability bottlenecks on large-scale clusters based on multi/many-core SMPs. We discuss the design and implementation of hybrid methods in QMCPACK and analyze its performance on current HPC platforms characterized by various memory and communication hierarchies.

Esler, Kenneth P↗

Empirical Evaluation of Conservative and Optimistic Discrete Event Execution on Cloud and VM Platforms

Virtual machine (VM) technologies, especially those offered via Cloud platforms, present new dimensions with respect to performance and cost in executing parallel discrete event simulation (PDES) applications. Due to the introduction of overall cost as a metric, the choice of the highest-end computing configuration is no longer the most economical one. Moreover, runtime dynamics unique to VM platforms introduce new performance characteristics, and the variety of possible VM configurations give rise to a range of choices for hosting a PDES run. Here, an empirical study of these issues is undertaken to guide an understanding of the dynamics, trends and trade-offs in executing PDES on VM/Cloud platforms. Performance results and cost measures are obtained from actual execution of a range of scenarios in two PDES benchmark applications on the Amazon Cloud offerings and on a high-end VM host machine. The data reveals interesting insights into the new VM-PDES dynamics that come into play and also leads to counter-intuitive guidelines with respect to choosing the best and second-best configurations when overall cost of execution is considered. In particular, it is found that choosing the highest-end VM configuration guarantees neither the best runtime nor the least cost. Interestingly, choosing a (suitably scaled) low-end VM configuration provides the least overall cost without adversely affecting the total runtime.

Yoginath, Srikanth B↗

Characterization and Optimization of the Fitting of Quantum Correlation Functions

This case study presents a characterization and optimization of an application code for extracting parton distribution functions from high energy electron-proton scattering data. Profiling this application code reveals that the phase-space density computation accounts for 93% of the overall execution time for a single iteration on a single core. When executing multiple iterations in parallel on a multicore system, the application spends 78% of its overall execution time idling due to load imbalance. We address these issues by first transforming the application code from Python to C++ and then tackling the application load imbalance via a hybrid scheduling strategy that combines dynamic and static scheduling. These techniques result in a 62% reduction in CPU idle time and a 2.46x speedup in overall execution time per node. In addition, the typically enabled power-management mechanisms in supercomputers (e.g., AMD Turbo Core, Intel Turbo Boost, and RAPL) can significantly impact intra-node scalability when more than 50% of the CPU cores are used. This finding underscores the importance of understanding system interactions with power management, as they can adversely impact application performance, and highlights the necessity of intra-node scaling tests to identify performance degradation that inter-node scaling tests might otherwise overlook.

Chuang, Pi-Yueh [Virginia Tech,Dept. of Computer S↗

Lifeline-based Global Load Balancing

On shared-memory systems, Cilk-style work-stealing has been used to effectively parallelize irregular task-graph based applications such as Unbalanced Tree Search (UTS). There are two main difficulties in extending this approach to distributed memory. In the shared memory approach, thieves (nodes without work) constantly attempt to asynchronously steal work from randomly chosen victims until they find work. In distributed memory, thieves cannot autonomously steal work from a victim without disrupting its execution. When work is sparse, this results in performance degradation. In essence, a direct extension of traditional work-stealing to distributed memory violates the work-first principle underlying work-stealing. Further, thieves spend useless CPU cycles attacking victims that have no work, resulting in system inefficiencies in multi-programmed contexts. Second, it is non-trivial to detect active distributed termination (detect that programs at all nodes are looking for work, hence there is no work). This problem is well-studied and requires careful design for good performance. Unfortunately, in most existing languages/frameworks, application developers are forced to implement their own distributed termination detection. In this paper, we develop a simple set of ideas that allow work-stealing to be efficiently extended to distributed memory. First, we introduce lifeline graphs: low-degree, low diameter, fully connected directed graphs. Such graphs can be constructed from k-dimensional hypercubes. When a node is unable to find work after w unsuccessful steals, it quiesces after informing the outgoing edges in its lifeline graph. Quiescent nodes do not disturb other nodes. A quiesced node is reactivated when work arrives from a lifeline and itself shares this work with those of its incoming lifelines that are activated. Termination occurs precisely when computation at all nodes has quiesced. In a language such as X10, such passive distributed termination can be detected automatically using the finish construct -- no application code is necessary.

99 GENERAL AND MISCELLANEOUS↗

An Adaptive Memory Interface Controller for Improving Bandwidth Utilization of Hybrid and Reconfigurable Systems

Emerging applications such as data mining, bioinformatics, knowledge discovery, social network analysis are irregular. They use data structures based on pointers or linked lists, such as graphs, unbalanced trees or unstructures grids, which generates unpredictable memory accesses. These data structures usually are large, but difficult to partition. These applications mostly are memory bandwidth bounded and have high synchronization intensity. However, they also have large amounts of inherent dynamic parallelism, because they potentially perform a task for each one of the element they are exploring. Several efforts are looking at accelerating these applications on hybrid architectures, which integrate general purpose processors with reconfigurable devices. Some solutions, which demonstrated significant speedups, include custom-hand tuned accelerators or even full processor architectures on the reconfigurable logic. In this paper we present an approach for the automatic synthesis of accelerators from C, targeted at irregular applications. In contrast to typical High Level Synthesis paradigms, which construct a centralized Finite State Machine, our approach generates dynamically scheduled hardware components. While parallelism exploitation in typical HLS-generated accelerators is usually bound within a single execution flow, our solution allows concurrently running multiple execution flow, thus also exploiting the coarser grain task parallelism of irregular applications. Our approach supports multiple, multi-ported and distributed memories, and atomic memory operations. Its main objective is parallelizing as many memory operations as possible, independently from their execution time, to maximize the memory bandwidth utilization. This significantly differs from current HLS flows, which usually consider a single memory port and require precise scheduling of memory operations. A key innovation of our approach is the generation of a memory interface controller, which dynamically maps concurrent memory accesses to multiple ports. We present a case study on a typical irregular kernel, Graph Breadth First search (BFS), exploring different tradeoffs in terms of parallelism and number of memories.

BFS↗

LDRD final report : managing shared memory data distribution in hybrid HPC applications.

MPI is the dominant programming model for distributed memory parallel computers, and is often used as the intra-node programming model on multi-core compute nodes. However, application developers are increasingly turning to hybrid models that use threading within a node and MPI between nodes. In contrast to MPI, most current threaded models do not require application developers to deal explicitly with data locality. With increasing core counts and deeper NUMA hierarchies seen in the upcoming LANL/SNL 'Cielo' capability supercomputer, data distribution poses an upper boundary on intra-node scalability within threaded applications. Data locality therefore has to be identified at runtime using static memory allocation policies such as first-touch or next-touch, or specified by the application user at launch time. We evaluate several existing techniques for managing data distribution using micro-benchmarks on an AMD 'Magny-Cours' system with 24 cores among 4 NUMA domains and argue for the adoption of a dynamic runtime system implemented at the kernel level, employing a novel page table replication scheme to gather per-NUMA domain memory access traces.

99 GENERAL AND MISCELLANEOUS↗

Convergence of the multigrid reduction in time algorithm for the linear elasticity equations

This paper presents some recent advances for parallel-in-time methods applied to linear elasticity. With recent computer architecture changes leading to stagnant clock speeds, but ever increasing numbers of cores, future speedups will be available through increased concurrency. Thus, sequential algorithms, such as time stepping, will suffer a bottleneck. This paper explores multigrid reduction in time (MGRIT) for an important application area, linear elasticity. Previously, efforts at parallel-in-time for elasticity have experienced difficulties, for example, the beating phenomenon. As a result, practical parallel-in-time algorithms for this application area currently do not exist. This paper proposes some solutions made possible by MGRIT (e.g., slow temporal coarsening and FCF-relaxation) and, more importantly, a different formulation of the problem that is more amenable to parallel-in-time methods. Using a recently developed convergence theory for MGRIT and Parareal, we show that the changed formulation of the problem avoids the instability issues and allows the reduction of the error using two temporal grids. We then extend our approach to the multilevel case, where we demonstrate how slow temporal coarsening improves convergence. Finally, the paper ends with supporting numerical results showing a practical algorithm enjoying speedup benefits over the sequential algorithm.

97 MATHEMATICS AND COMPUTING↗

Discrete event performance prediction of speculatively parallel temperature-accelerated dynamics

Due to its unrivaled ability to predict the dynamical evolution of interacting atoms, molecular dynamics (MD) is a widely used computational method in theoretical chemistry, physics, biology, and engineering. Despite its success, MD is only capable of modeling time scales within several orders of magnitude of thermal vibrations, leaving out many important phenomena that occur at slower rates. The Temperature Accelerated Dynamics (TAD) method overcomes this limitation by thermally accelerating the state-to-state evolution captured by MD. Due to the algorithmically complex nature of the serial TAD procedure, implementations have yet to improve performance by parallelizing the concurrent exploration of multiple states. Here we utilize a discrete event-based application simulator to introduce and explore a new Speculatively Parallel TAD (SpecTAD) method. We investigate the SpecTAD algorithm, without a full-scale implementation, by constructing an application simulator proxy (SpecTADSim). Finally, following this method, we discover that a nontrivial relationship exists between the optimal SpecTAD parameter set and the number of CPU cores available at run-time. Furthermore, we find that a majority of the available SpecTAD boost can be achieved within an existing TAD application using relatively simple algorithm modifications.

97 MATHEMATICS AND COMPUTING↗

Multi-fuel surrogate chemical kinetic mechanisms for real world applications

The most important driving force for development of detailed chemical kinetic reaction mechanisms in combustion is the desire by researchers to simulate practical systems. Here, this article reviews the parallel evolution of kinetic reaction mechanisms and applications of those models to practical, real engines. Early, quite simple, kinetic models for small fuel molecules were extremely valuable in analyzing long-standing, poorly understood applied ignition and flame quenching problems, and later kinetic models have been applied to much more complex flame propagation, problems including autoignition in spark-ignition engines and issues related to octane numbers and knock in modern, high compression ratio and other engines. The recent emergence of very large, multi-fuel surrogate kinetic mechanisms that can address many different fuel types and real engine applications is discussed as a modern analytical tool that can be used for a wide variety of practical applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

AMReX and pyAMReX: Looking beyond the exascale computing project

AMReX is a software framework for the development of block-structured mesh applications with adaptive mesh refinement (AMR). AMReX was initially developed and supported by the AMReX Co-Design Center as part of the U.S. DOE Exascale Computing Project (ECP), and is continuing to grow post-ECP. In addition to adding new functionality and performance improvements to the core AMReX framework, we have also developed a Python binding, pyAMReX, that provides a bridge between AMReX-based application codes and the data science ecosystem. pyAMReX provides zero-copy application GPU data access for AI/ML, in situ analysis and application coupling, and enables rapid, massively parallel prototyping. In this paper we review the overall functionality of AMReX and pyAMReX, focusing on new developments, new functionality, and optimizations of key operations. We also summarize capabilities of ECP projects that used AMReX and provide an overview of new, non-ECP applications.

Myers, Andrew↗

Nontraditional tensor decompositions and applications.

This presentation will discuss two tensor decompositions that are not as well known as PARAFAC (parallel factors) and Tucker, but have proven useful in informatics applications. Three-way DEDICOM (decomposition into directional components) is an algebraic model for the analysis of 3-way arrays with nonsymmetric slices. PARAFAC2 is a related model that is less constrained than PARAFAC and allows for different objects in one mode. Applications of both models to informatics problems will be shown.

99 GENERAL AND MISCELLANEOUS↗

Parallel Optical Flow Processing of 4D Cardiac CT Data on Multicore Clusters, In: 2014 IEEE 17th International Conference on Computational Science and Engineering

Optical flow is the distribution of apparent velocities of movement of brightness patterns in a sequence of images. For large 3D image sequences, optical flow applications are time consuming and memory-bound. To cope with these problems, in this paper, we present parallel optical flow processing of 4D cardiac CT data on multicore cluster systems to significantly shorten the time for computing velocity fields of the heart in order to aid cardiologists in diagnosing heart disease such as myocardial infarction and cardiac dysrhythmia in time. First, we modify and extend two traditional 2D optical flow methods Horn-Schunck and Lucas-Kanade to three-dimensional cases to process the 4D cardiac CT data. Second, we extend Mat lab MPI to support parallel computing with Mat lab and Octave on these cluster systems. Then we develop the parallel Mat lab/Octave optical flow applications for the 4D cardiac CT data in detail. Our experimental results show that these parallel optical flow applications have good scalability with close to linear speedup, and are able to shorten the image processing time significantly from more than 5 hours on 4 cores to 1.5 minutes on 1024 cores.

Engineering↗

The development and applications of multidimensional biomolecular spectroscopy illustrated by photosynthetic light harvesting

The parallel and synergistic developments of atomic resolution structural information, new spectroscopic methods, their underpinning formalism, and the application of sophisticated theoretical methods have led to a step function change in our understanding of photosynthetic light harvesting, the process by which photosynthetic organisms collect solar energy and supply it to their reaction centers to initiate the chemistry of photosynthesis. The new spectroscopic methods, in particular multidimensional spectroscopies, have enabled a transition from recording rates of processes to focusing on mechanism. We discuss two ultrafast spectroscopies – two-dimensional electronic spectroscopy and two-dimensional electronic-vibrational spectroscopy – and illustrate their development through the lens of photosynthetic light harvesting. Both spectroscopies provide enhanced spectral resolution and, in different ways, reveal pathways of energy flow and coherent oscillations which relate to the quantum mechanical mixing of, for example, electronic excitations (excitons) and nuclear motions. The new types of information present in these spectra provoked the application of sophisticated quantum dynamical theories to describe the temporal evolution of the spectra and provide new questions for experimental investigation. While multidimensional spectroscopies have applications in many other areas of science, we feel that the investigation of photosynthetic light harvesting has had the largest influence on the development of spectroscopic and theoretical methods for the study of quantum dynamics in biology, hence the focus of this review. We conclude with key questions for the next decade of this review.

59 BASIC BIOLOGICAL SCIENCES↗

Modelling a Transition-Edge Sensor X-Ray Microcalorimeter Linear Array for Compton Profile Measurements and Energy Dispersive Diffraction

Transition-edge sensors (TES) are a type of superconducting detector that offers high energy resolution based on their sharp resistance-temperature feature in the superconducting-to-normal transition. TES X-ray microcalorimeters have typically been designed and used for spectroscopic applications. In this work, we present a design optimization for a TES X-ray microcalorimeter array for high-energy scattering and diffraction measurements. Specifically, Compton scattering provides information about the electron momentum distribution, while energy dispersive diffraction provides structural information about dense engineering materials. Compton scattering and energy dispersive diffraction experiments must be conducted in the very hard X-ray regime (~100 keV), demanding a high X-ray stopping power in the detector; therefore, an absorber with a large heat capacity is needed in conjunction with the TES. In addition, both applications would benefit from an array composed of parallel strips. We propose a design for a TES X-ray microcalorimeter optimized for such applications. In particular, we model the longitudinal position dependence due to the finite thermal diffusion time in the absorber.

47 OTHER INSTRUMENTATION↗

End-to-end data movement using MPI-IO over routed terabits infrastructures. In: NDM '13 Proceedings of the Third International Workshop on Network-Aware Data Management, Article No. 9

Scientific discovery is nowadays driven by large-scale simulations running on massively parallel high-performance computing (HPC) systems. These applications each generate a large amount of data, which then needs to be post-processed for example for data mining or visualization. Unfortunately, the computing platform used for post processing might be different from the one on which the data is initially generated, introducing the challenge of moving large amount of data between computing platforms. This is especially challenging when these two platforms are geographically separated since the data needs to be moved between computing facilities. This is even more critical when scientists tightly couple their domain specific applications with a post processing application. The paper presents a solution for the data transfer between MPI applications using a dedicated wide area network (WAN) terabit infrastructure. The proposed solution is based on parallel access to data files and the Message Passing Interface (MPI) over the Common Communication Infrastructure (CCI) for the data transfer over a routed infrastructure. In the context of this research, the Energy Sciences Network (ESnet) of the U.S. Department of Energy (DOE) is targeted for the transfer of data between DOE national laboratories.

Vallée, Geoffroy↗

End-to-End Data Movement Using MPI-IO Over Routed Terabots Infrastructures

Scientific discovery is nowadays driven by large-scale simulations running on massively parallel high-performance computing (HPC) systems. These applications each generate a large amount of data, which then needs to be post-processed for example for data mining or visualization. Unfortunately, the computing platform used for post processing might be different from the one on which the data is initially generated, introducing the challenge of moving large amount of data between computing platforms. This is especially challenging when these two platforms are geographically separated since the data needs to be moved between computing facilities. This is even more critical when scientists tightly couple their domain specific applications with a post processing application. The paper presents a solution for the data transfer between MPI applications using a dedicated wide area network (WAN) terabit infrastructure. The proposed solution is based on parallel access to data files and the Message Passing Interface (MPI) over the Common Communication Infrastructure (CCI) for the data transfer over a routed infrastructure. In the context of this research, the Energy Sciences Network (ESnet) of the U.S. Department of Energy (DOE) is targeted for the transfer of data between DOE national laboratories.

Vallee, Geoffroy R↗

A template-based approach for parallel hexahedral two-refinement

Here, we provide a template-based approach for generating locally refined all-hex meshes. We focus specifically on refinement of initially structured grids utilizing a 2-refinement approach where uniformly refined hexes are subdivided into eight child elements. The refinement algorithm consists of identifying marked nodes that are used as the basis for a set of four simple refinement templates. The target application for 2-refinement is a parallel grid-based all-hex meshing tool for high performance computing in a distributed environment. The result is a parallel consistent locally refined mesh requiring minimal communication and where minimum mesh quality is greater than scaled Jacobian 0.3 prior to smoothing.

2-refinement↗

Towards Flexible Exascale Stream Processing System Simulation

Stream processing is an important emerging computational model for performing complex operations on and across multi-source, high-volume, unpredictable dataflows. We present Flow, a platform for parallel and distributed stream processing system simulation that provides a flexible modeling environment for analyzing stream processing applications. The Flow stream processing system simulator is a high-performance, scalable simulator that automatically parallelizes chunks of the model space and incurs near-zero synchronization overhead for acyclic stream application graphs. We show promising parallel and distributed event rates exceeding 149 million events per second on a cluster with 512 processor cores.

99 GENERAL AND MISCELLANEOUS↗