Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel 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 1,369 records · Page 76

On the memory attribution problem: A solution and case study using MPI

As parallel applications running on large–scale computing systems become increasingly memory constrained, the ability to attribute memory usage to the various components of the application is becoming increasingly important. We present the design and implementation of memnesia, a novel memory usage profiler for parallel and distributed message–passing applications. Our approach captures both application– and message–passing library–specific memory usage statistics from unmodified binaries dynamically linked to a message–passing communication library. Using microbenchmarks and proxy applications, we evaluated our profiler across three Message Passing Interface (MPI) implementations and two hardware platforms. Furthermore, the results show that our approach and the corresponding implementation can accurately quantify memory resource usage as a function of time, scale, communication workload, and software or hardware system architecture, clearly distinguishing between application and MPI library memory usage at a per–process level. With this new capability, we show that job size, communication workload, and hardware/software architecture influence peak runtime memory usage. In practice, this tool provides a potentially valuable source of information for application developers seeking to measure and optimize memory usage.

97 MATHEMATICS AND COMPUTING↗

Critical Path-Based Thread Placement for NUMA Systems

Multicore multiprocessors use a Non Uniform Memory Architecture (NUMA) to improve their scalability. However, NUMA introduces performance penalties due to remote memory accesses. Without efficiently managing data layout and thread mapping to cores, scientific applications, even if they are optimized for NUMA, may suffer performance loss. In this paper, we present algorithms and a runtime system that optimize the execution of OpenMP applications on NUMA architectures. By collecting information from hardware counters, the runtime system directs thread placement and reduces performance penalties by minimizing the critical path of OpenMP parallel regions. The runtime system uses a scalable algorithm that derives placement decisions with negligible overhead. We evaluate our algorithms and runtime system with four NPB applications implemented in OpenMP. On average the algorithms achieve between 8.13% and 25.68% performance improvement compared to the default Linux thread placement scheme. The algorithms miss the optimal thread placement in only 8.9% of the cases.

97 MATHEMATICS AND COMPUTING↗

Energy Usage in an Embedded Space Vision Application on a Tiled Architecture

The need for greater autonomy in platforms such as planetary rovers is driving rapidly to codes that far overwhelm the capabilities of conventional space-qualified single core processors to run them in real-time. However, a new generation of potentially space-qualified 2D "tiled" multi-core microprocessor chips is emerging with significant performance potential. Leveraging such inherently parallel hardware for space platforms requires consideration of both time and power limitations - the latter of which is not normally done in conventional parallel computing. This paper takes one such application, Rockster, and analyzes it for energy usage when ported to a multi-core tiled chip such as may come from the Maestro program. The results demonstrate not only the criticality of memory and interconnect in the energy of real-time parallel codes, but also the effects of possible "energy-aware" changes in partitioning and algorithm design.

multi-core processors↗

Multiprocessor architecture: Synthesis and evaluation

Multiprocessor computed architecture evaluation for structural computations is the focus of the research effort described. Results obtained are expected to lead to more efficient use of existing architectures and to suggest designs for new, application specific, architectures. The brief descriptions given outline a number of related efforts directed toward this purpose. The difficulty is analyzing an existing architecture or in designing a new computer architecture lies in the fact that the performance of a particular architecture, within the context of a given application, is determined by a number of factors. These include, but are not limited to, the efficiency of the computation algorithm, the programming language and support environment, the quality of the program written in the programming language, the multiplicity of the processing elements, the characteristics of the individual processing elements, the interconnection network connecting processors and non-local memories, and the shared memory organization covering the spectrum from no shared memory (all local memory) to one global access memory. These performance determiners may be loosely classified as being software or hardware related. This distinction is not clear or even appropriate in many cases. The effect of the choice of algorithm is ignored by assuming that the algorithm is specified as given. Effort directed toward the removal of the effect of the programming language and program resulted in the design of a high-level parallel programming language. Two characteristics of the fundamental structure of the architecture (memory organization and interconnection network) are examined.

Standley, Hilda M.↗

Distributed Stochastic Optimization of a Neural Representation Network for Time-Space Tomography Reconstruction

4D time-space reconstruction of dynamic events or deforming objects using X-ray computed tomography (CT) is an important inverse problem in non-destructive evaluation. Conventional back-projection based reconstruction methods assume that the object remains static for the duration of several tens or hundreds of X-ray projection measurement images (reconstruction of consecutive limited-angle CT scans). However, this is an unrealistic assumption for many in-situ experiments that causes spurious artifacts and inaccurate morphological reconstructions of the object. To solve this problem, we propose to perform a 4D time-space reconstruction using a distributed implicit neural representation (DINR) network that is trained using a novel distributed stochastic training algorithm. Our DINR network learns to reconstruct the object at its output by iterative optimization of its network parameters such that the measured projection images best match the output of the CT forward measurement model. Here, we use a forward measurement model that is a function of the DINR outputs at a sparsely sampled set of continuous valued 4D object coordinates. Unlike previous neural representation architectures that forward and back propagate through dense voxel grids that sample the object's entire time-space coordinates, we only propagate through the DINR at a small subset of object coordinates in each iteration resulting in an order-of-magnitude reduction in memory and compute for training. DINR leverages distributed computation across several compute nodes and GPUs to produce high-fidelity 4D time-space reconstructions. We use both simulated parallel-beam and experimental cone-beam X-ray CT datasets to demonstrate the superior performance of our approach.

36 MATERIALS SCIENCE↗

An open, parallel I/O computer as the platform for high-performance, high-capacity mass storage systems

APTEC Computer Systems is a Portland, Oregon based manufacturer of I/O computers. APTEC's work in the context of high density storage media is on programs requiring real-time data capture with low latency processing and storage requirements. An example of APTEC's work in this area is the Loral/Space Telescope-Data Archival and Distribution System. This is an existing Loral AeroSys designed system, which utilizes an APTEC I/O computer. The key attributes of a system architecture that is suitable for this environment are as follows: (1) data acquisition alternatives; (2) a wide range of supported mass storage devices; (3) data processing options; (4) data availability through standard network connections; and (5) an overall system architecture (hardware and software designed for high bandwidth and low latency). APTEC's approach is outlined in this document.

Abineri, Adrian↗

Evaluation of Graph Analytics Frameworks Using the GAP Benchmark Suite

The analysis of connected data is an increasingly important application in high-performance computing. Such analyses can reveal fraudulent patterns in financial transactions, optimize telecommunications networks, predict information flow in social networks, etc. However, the landscape of graph analytics is highly diverse. Graph algorithms stress processor architectures differently, and no one graph can represent all topologies. Consequently, no single approach or framework is expected to be optimal for all graph analytics problems. To help make sense of this diverse landscape, we evaluated four approaches to graph analytics: GraphBLAS, Galois, BGL17, GraphIt; and compare them against hand-tuned implementations that take advantage of hardware features on our test platform. Graph- BLAS formulates graph analytics as sparse linear algebra. Galois provides syntactic constructs for data parallelism over irregular data structures. BGL17 is a generic C++ template library for implementing graph algorithms. GraphIt provides a domain- specific language to describe and optimize graph algorithms. We use the GAP Benchmark Suite to establish baseline performance and guide the side-by-side evaluation of each framework. GAP consists of 30 tests: six graph analytics algorithms (breadth- first search, single-source shortest path, PageRank, betweenness centrality, connected components, and triangle counting) run on five graphs, each with different topological characteristics (e.g., high diameter, skewed degree distribution, high average degree). High-performance reference implementations are included for each benchmark algorithm. Because a graph can be loaded into memory a number of ways (e.g., flat file on disk, compressed sparse format, data frames, retrieved from SQL or NoSQL databases), our evaluation focused on computational performance rather than I/O. Our results show the relative strengths of each framework.

Graph algorithms, Benchmarking, shared-memory prog↗

Fast tree-based algorithms for DBSCAN for low-dimensional data on GPUs

DBSCAN is a well-known density-based clustering algorithm to discover arbitrary shape clusters. While conceptually simple in serial, the algorithm is challenging to efficiently parallelize on manycore GPU architectures. Common pitfalls, such as asynchronous range query calls, result in high thread execution divergence in many implementations. In this paper, we propose a new framework for GPU-accelerated DBSCAN, and describe two tree-based algorithms within that framework. Both algorithms fuse the search for neighbors with updating cluster information, but differ in their treatment of dense regions of the data. We show that the time taken to compute clusters is at most twice that of determination of the neighbors. We compare the proposed algorithms with existing CPU and GPU implementations, and demonstrate their competitiveness and performance using a fast traversal structure (bounding volume hierarchy) for low dimensional data. We also show that the memory usage can be reduced by processing object neighbors dynamically without storing them.

Prokopenko, Andrey↗

Optoelectronic analogs of self-programming neural nets - Architecture and methodologies for implementing fast stochastic learning by simulated annealing

Self-organization and learning is a distinctive feature of neural nets and processors that sets them apart from conventional approaches to signal processing. It leads to self-programmability which alleviates the problem of programming complexity in artificial neural nets. In this paper architectures for partitioning an optoelectronic analog of a neural net into distinct layers with prescribed interconnectivity pattern to enable stochastic learning by simulated annealing in the context of a Boltzmann machine are presented. Stochastic learning is of interest because of its relevance to the role of noise in biological neural nets. Practical considerations and methodologies for appreciably accelerating stochastic learning in such a multilayered net are described. These include the use of parallel optical computing of the global energy of the net, the use of fast nonvolatile programmable spatial light modulators to realize fast plasticity, optical generation of random number arrays, and an adaptive noisy thresholding scheme that also makes stochastic learning more biologically plausible. The findings reported predict optoelectronic chips that can be used in the realization of optical learning machines.

Farhat, Nabil H.↗

Computational Modeling to Limit the Impact Displays and Indicator Lights Have on Habitable Volume Operational Lighting Constraints

The goal of this investigation is to determine design limitations and architectural solutions that limit the impact light from displays and indicator lamps have on the operational environment task lighting and lighting countermeasure spectrum constraints. It is concerning that this innovative architectural lighting system, could be compromised by spectrums from display systems, architectural materials, and structures that are not considered as part a full system design implementation. The introduction of many Commercial Off the Shelf (COTS) products to the spacecraft volume that contain LEDs, without consideration to the human factors and biological constraints, is another problem. Displays and indicators are a necessary part of the spacecraft and it is the goal of this research project to determine constraints and solutions that allow these systems to be integrated while minimizing how the lighting environment is modified by them. Due to the potentially broad scope of this endeavor, the project team developed constraints for the evaluation. The evaluation will be on a set of tasks that required significant exposure in the same environment while having a large chance of impacting the light spectrum the crew is expected to receive from the architectural lighting system. The team plans to use recent HRP research on "Net Habitable Volume" [1] to provide the boundary conditions for volume size. A Zemax ® lighting model was developed of a small enclosure that had high intensity overhead lighting and a standard intensity display with LED indicator arrays. The computer model demonstrated a work surface illuminated at a high level by the overhead light source compared to displays and indicators whose light is parallel to the work plane. The overhead lighting oversaturated spectral contributions from the display and indicator at the task work surface. Interestingly, when the observer looked at the displays and LEDs within the small enclosure, their spectral contribution was significant but could be reduced by reflecting overhead light from the wall(s) to the observer. Direct observation of displays and LEDs are an issue because the user's viewing area is a display, not an illuminated work surface. Since avionics command centers consume significant crew time, the tasks that seemed at higher risk for unwanted spectral contributions as an operational volume with significant quantity of displays and indicators that were either under direct observation of the crew or impacting a volume the crew may be required to sleep in.

Clark, T. E.↗

Leaky Buddies: Cross-Component Covert Channels on Integrated CPU-GPU Systems

Graphics Processing Units (GPUs) are ubiquitous components used across the range of today’s computing plat- forms, from phones and tablets, through personal computers, to high-end server class platforms. With the increasing importance of graphics and video workloads, recent processors are shipped with GPU devices that are integrated on the same chip. Integrated GPUs share some resources with the CPU and as a result, there is a potential for microarchitectural attacks from the GPU to the CPU or vice versa. We consider the potential for covert channel attacks that arise either from shared microarchitectural components (such as caches) or through shared contention domains (e.g., shared buses). We illustrate these two types of channels by developing two reliable covert channel attacks. The first covert channel uses the shared LLC cache in Intel’s integrated GPU architectures. The second is a contention based channel targeting the ring bus connecting the CPU and GPU to the LLC. This is the first demonstrated microarchitectural attack crossing the component boundary (GPU to CPU or vice versa). Cross-component channels introduce a number of new challenges that we had to overcome since they occur across heterogeneous components that use different computation models and are interconnected using asymmetric memory hierarchies. We also exploit GPU parallelism to increase the bandwidth of the communication, even without relying on a common clock. The LLC based channel achieves a bandwidth of 120 kbps with a low error rate of 2%, while the contention based channel delivers up to 400 kbps with a 0.8% error rate. We also demonstrate a proof- of-concept prime-and-probe side channel attack that probes the full LLC from the GPU.

Cyber secruity, high performance comptuing, Hetero↗

A Simple GPU-Accelerated Two-Dimensional MUSCL-Hancock Solver for Ideal Magnetohydrodynamics

We describe our experience using NVIDIA's CUDA (Compute Unified Device Architecture) C programming environment to implement a two-dimensional second-order MUSCL-Hancock ideal magnetohydrodynamics (MHD) solver on a GTX 480 Graphics Processing Unit (GPU). Taking a simple approach in which the MHD variables are stored exclusively in the global memory of the GTX 480 and accessed in a cache-friendly manner (without further optimizing memory access by, for example, staging data in the GPU's faster shared memory), we achieved a maximum speed-up of approx. = 126 for a sq 1024 grid relative to the sequential C code running on a single Intel Nehalem (2.8 GHz) core. This speedup is consistent with simple estimates based on the known floating point performance, memory throughput and parallel processing capacity of the GTX 480.

graphics processing units↗

SpF: Enabling Petascale Performance for Pseudospectral Dynamo Models

Pseudospectral (PS) methods possess a number of characteristics (e.g., efficiency, accuracy, natural boundary conditions) that are extremely desirable for dynamo models. Unfortunately, dynamo models based upon PS methods face a number of daunting challenges, which include exposing additional parallelism, leveraging hardware accelerators, exploiting hybrid parallelism, and improving the scalability of global memory transposes. Although these issues are a concern for most models, solutions for PS methods tend to require far more pervasive changes to underlying data and control structures. Further, improvements in performance in one model are difficult to transfer to other models, resulting in significant duplication of effort across the research community.We have developed an extensible software framework for pseudospectral methods called SpF that is intended to enable extreme scalability and optimal performance. High-level abstractions provided by SpF unburden applications of the responsibility of managing domain decomposition and load balance while reducing the changes in code required to adapt to new computing architectures. The key design concept in SpF is that each phase of the numerical calculation is partitioned into disjoint numerical kernels that can be performed entirely in-processor. The granularity of domain-decomposition provided by SpF is only constrained by the data-locality requirements of these kernels. SpF builds on top of optimized vendor libraries for common numerical operations such as transforms, matrix solvers, etc., but can also be configured to use open source alternatives for portability. SpF includes several alternative schemes for global data redistribution and is expected to serve as an ideal testbed for further research into optimal approaches for different network architectures.In this presentation, we will describe the basic architecture of SpF as well as preliminary performance data and experience with adapting legacy dynamo codes. We will conclude with a discussion of planned extensions to SpF that will provide pseudospectral applications with additional flexibility with regard to time integration, linear solvers, and discretization in the radial direction.

Pseudospectral (PS)↗

Collective I/O Tuning Using Analytical and Machine-Learning Models

The ever larger demand of scientific applications for computation and data is currently driving a continuous increase in scale of parallel computers. The inherent complexity of scaling up a computing systems in terms of both hardware and software stack exposes an increasing number of factors impacting the performance and complicating the process of optimization. In particular, the optimization of parallel I/O has become increasingly challenging due to increasing storage hierarchy and well known performance variability of shared storage systems. This paper focuses on model-based autotuning of the two-phase collective I/O algorithm from a popular MPI distribution on the Blue Gene/Q architecture. We propose a novel hybrid model, constructed as a composition of analytical models for communication and storage operations and black-box models for the performance of the individual operations. We perform an in-depth study of the complexity involved in performance modeling including architecture, software stack and noise. In particular we address this challenges of modeling the performance of shared storage systems by building a benchmark that helps synthesizing factors such as topology, file caching, and noise. The experimental results show that the hybrid approach produces significantly better results than state-of-the-art machine learning approaches and shows a higher robustness to noise, at the cost of a higher modeling complexity

I/O performance modeling↗

Towards exascale for wind energy simulations

We examine large-eddy-simulation modeling approaches and computational performance of two open-source computational fluid dynamics codes for the simulation of atmospheric boundary layer flows that are of direct relevance to wind energy production. The first code, NekRS, is a high-order, unstructured-grid, spectral element code. The second code, AMR-Wind, is a second-order, block-structured, finite-volume code with adaptive mesh refinement capabilities. The objective of this study is to co-develop these codes in order to improve model fidelity and performance for each. These features will be critical for running ABL-based applications such as wind farm analysis on advanced computing architectures. To this end, we investigate the performance of NekRS and AMR-Wind on the Oak Ridge Leadership Facility supercomputers Summit, using 4 to 800 nodes (24 to 4,800 NVIDIA V100 GPUs), and Crusher, the testbed for the Frontier exascale system, using 18 to 384 Graphics Compute Dies on AMD MI250X GPUs. We compare strong- and weak-scaling capabilities, linear solver performance, and time to solution. We also identify leading inhibitors to parallel scaling.

17 WIND ENERGY↗

Multidisciplinary High-Fidelity Analysis and Optimization of Aerospace Vehicles: Formulation - Part 1

An objective of the High Performance Computing and Communication Program at the NASA Langley Research Center is to demonstrate multidisciplinary shape and sizing optimization of a complete aerospace vehicle configuration by using high-fidelity, finite element structural analysis and computational fluid dynamics aerodynamic analysis in a distributed, heterogeneous computing environment that includes high performance parallel computing. A software system has been designed and implemented to integrate a set of existing discipline analysis codes, some of them computationally intensive, into a distributed computational environment for the design of a highspeed civil transport configuration. The paper describes the engineering aspects of formulating the optimization by integrating these analysis codes and associated interface codes into the system. The discipline codes are integrated by using the Java programming language and a Common Object Request Broker Architecture (CORBA) compliant software product. A companion paper presents currently available results.

Walsh, J. L.↗

Profiling and Improving I/O Performance of a Large-Scale Climate Scientific Application

Exascale computing systems are soon to emerge, which will pose great challenges on the huge gap between computing and I/O performance. Many large-scale scientific applications play an important role in our daily life. The huge amounts of data generated by such applications require highly parallel and efficient I/O management policies. In this paper, we adopt a mission-critical scientific application, GEOS-5, as a case to profile and analyze the communication and I/O issues that are preventing applications from fully utilizing the underlying parallel storage systems. Through in-detail architectural and experimental characterization, we observe that current legacy I/O schemes incur significant network communication overheads and are unable to fully parallelize the data access, thus degrading applications' I/O performance and scalability. To address these inefficiencies, we redesign its I/O framework along with a set of parallel I/O techniques to achieve high scalability and performance. Evaluation results on the NASA discover cluster show that our optimization of GEOS-5 with ADIOS has led to significant performance improvements compared to the original GEOS-5 implementation.

Exascale↗

Computational mechanics for geosystems management to support the energy and natural resources mission.

U.S. energy needs - minimizing climate change, mining and extraction technologies, safe waste disposal - require the ability to simulate, model, and predict the behavior of subsurface systems. They propose development of a coupled thermal, hydrological, mechanical, chemistry (THMC) modeling capability for massively parallel applications that can address these critical needs. The goal and expected outcome of this research is a state-of-the-art, extensible, simulation capability, based upon SIERRA Mechanics, to address multiphase, multicomponent reactive transport coupled to nonlinear geomechanics in heterogeneous (geologic) porous materials. The THMC code provides a platform for integrating research in numerical mathematics and algorithms for chemically reactive multiphase systems with computer science research in adaptive coupled solution control and framework architecture.

54 ENVIRONMENTAL SCIENCES↗