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 829 records · Page 46

Machine Learning and Understanding for Intelligent Extreme Scale Scientific Computing and Discovery. DOE Workshop Report, January 7–9, 2015, Rockville, MD

Large-scale parallel simulations and data analysis drive scientific discovery across many disciplines. To drive larger and more detailed simulations, and deal with larger data volumes, exascale machines capable of 1018 operations per second are expected within the next five to ten years. However, the complexity of developing and adapting modern simulation codes for these architectures is increasing rapidly. Workloads on exascale machines will be billion-way parallel. Exploiting the full capability of the machine will require carefully assigning application tasks to cores, accelerators, deep memories, and other heterogeneous compute resources, while simultaneously optimizing for time to solution, data movement, power, and resilience. Optimizations that improve performance on one machine may slow down another. Worse, applications themselves are dauntingly complex. Production simulations comprise millions of lines of code and use sophisticated, adaptive algorithms whose performance is input-dependent. Complex workflows can couple multi-physics simulation with data preprocessing and post-processing modules.

97 MATHEMATICS AND COMPUTING↗

OpenMP in VASP: Threading and SIMD

Abstract The Vienna Ab initio Simulation Package (VASP) is a widely used electronic structure code that originally exploits process‐level parallelism through the Message Passing Interface (MPI) for work distribution within and across nodes. Architectural changes of modern parallel processors urge programmers to address thread‐ and data‐level parallelism as well to benefit most from the available compute resources within a node. We describe for VASP how to approach for an MPI + OpenMP parallelization including data‐level parallelism through OpenMP SIMD constructs together with a generic high‐level vector coding scheme. We can demonstrate an improved scalability of VASP and more than 20% gain over the MPI‐only version as well as a 2× increased performance of collective operations using the multiple‐endpoint MPI feature. The high‐level vector coding scheme applied to VASP's general gradient approximation routine gives up 9× performance gain on AVX512 platforms with the Intel compiler.

Wende, Florian↗

Distributed Training and Optimization of Neural Networks

Deep learning models are yielding increasingly better performances thanks to multiple factors. To be successful, model may have large number of parameters or complex architectures and be trained on large dataset. This leads to large requirements on computing resource and turn around time, even more so when hyperparameter optimization is done (e.g. search over model architectures). While this is a challenge that goes beyond particle physics, we review the various ways to do the necessary computations in parallel, and put it in the context of high-energy physics.

Vlimant, Jean-Roch↗

Machine and Application Aware Partitioning for Adaptive Mesh Refinement Applications. In: HPDC '17 Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing

Load balancing and partitioning are critical when it comes to parallel computations. Popular partitioning strategies based on space filling curves focus on equally dividing work. The partitions produced are independent of the architecture or the application. Given the ever-increasing relative cost of data movement and increasing heterogeneity of our architectures, it is no longer sufficient to only consider an equal partitioning of work. Minimizing communication costs are equally if not more important. Our hypothesis is that an unequal partitioning that minimizes communication costs significantly can scale and perform better than conventional equal-work partitioning schemes. This tradeoff is dependent on the architecture as well as the application. We validate our hypothesis in the context of a finite-element computation utilizing adaptive mesh-refinement. Our central contribution is a new partitioning scheme that minimizes the overall runtime of subsequent computations by performing architecture and application-aware non-uniform work assignment in order to decrease time to solution, primarily by minimizing data-movement. We evaluate our algorithm by comparing it against standard space-filling curve based partitioning algorithms and observing time-to-solution as well as energy-to-solution for solving Finite Element computations on adaptively refined meshes. We demonstrate excellent scalability of our new partition algorithm up to $262,144$ cores on ORNL's Titan and demonstrate that the proposed partitioning scheme reduces overall energy as well as time-to-solution for application codes by up to 22.0%.

Fernando, Milinda↗

Parallel-Processing CMOS Circuitry for M-QAM and 8PSK TCM

There has been some additional development of parts reported in "Multi-Modulator for Bandwidth-Efficient Communication" (NPO-40807), NASA Tech Briefs, Vol. 32, No. 6 (June 2009), page 34. The focus was on 1) The generation of M-order quadrature amplitude modulation (M-QAM) and octonary-phase-shift-keying, trellis-coded modulation (8PSK TCM), 2) The use of square-root raised-cosine pulse-shaping filters, 3) A parallel-processing architecture that enables low-speed [complementary metal oxide/semiconductor (CMOS)] circuitry to perform the coding, modulation, and pulse-shaping computations at a high rate; and 4) Implementation of the architecture in a CMOS field-programmable gate array.

Gray, Andrew↗

Parallelizing the Unpacking and Clustering of Detector Data for Reconstruction of Charged Particle Tracks on Multi-core CPUs and Many-core GPUs

We present results from parallelizing the unpacking and clustering steps of the raw data from the silicon strip modules for reconstruction of charged particle tracks. Throughput is further improved by concurrently processing multiple events using nested OpenMP parallelism on CPU or CUDA streams on GPU. The new implementation along with earlier work in developing a parallelized and vectorized implementation of the combinatoric Kalman filter algorithm has enabled efficient global reconstruction of the entire event on modern computer architectures. We demonstrate the performance of the new implementation on Intel Xeon and NVIDIA GPU architectures.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Efficient Probabilistic Computing with Stochastic Perovskite Nickelates

Probabilistic computing has emerged as a viable approach to solve hard optimization problems. Devices with inherent stochasticity can greatly simplify their implementation in electronic hardware. In this report we demonstrate intrinsic stochastic resistance switching controlled via electric fields in perovskite nickelates doped with hydrogen. The ability of hydrogen ions to reside in various metastable configurations in the lattice leads to a distribution of transport gaps. With experimentally characterized p-bits, a shared-synapse p-bit architecture demonstrates highly parallelized and energy-efficient solutions to optimization problems such as integer factorization and Boolean satisfiability. The results introduce perovskite nickelates as scalable potential candidates for probabilistic computing and showcase the potential of light-element dopants in next-generation correlated semiconductors.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

PISCES: An environment for parallel scientific computation

The parallel implementation of scientific computing environment (PISCES) is a project to provide high-level programming environments for parallel MIMD computers. Pisces 1, the first of these environments, is a FORTRAN 77 based environment which runs under the UNIX operating system. The Pisces 1 user programs in Pisces FORTRAN, an extension of FORTRAN 77 for parallel processing. The major emphasis in the Pisces 1 design is in providing a carefully specified virtual machine that defines the run-time environment within which Pisces FORTRAN programs are executed. Each implementation then provides the same virtual machine, regardless of differences in the underlying architecture. The design is intended to be portable to a variety of architectures. Currently Pisces 1 is implemented on a network of Apollo workstations and on a DEC VAX uniprocessor via simulation of the task level parallelism. An implementation for the Flexible Computing Corp. FLEX/32 is under construction. An introduction to the Pisces 1 virtual computer and the FORTRAN 77 extensions is presented. An example of an algorithm for the iterative solution of a system of equations is given. The most notable features of the design are the provision for several granularities of parallelism in programs and the provision of a window mechanism for distributed access to large arrays of data.

Pratt, T. W.↗

Scalability of high-performance PDE solvers

Performance tests and analyses are critical to effective high-performance computing software development and are central components in the design and implementation of computational algorithms for achieving faster simulations on existing and future computing architectures for large-scale application problems. In this article, we explore performance and space-time trade-offs for important compute-intensive kernels of large-scale numerical solvers for partial differential equations (PDEs) that govern a wide range of physical applications. We consider a sequence of PDE-motivated bake-off problems designed to establish best practices for efficient high-order simulations across a variety of codes and platforms. We measure peak performance (degrees of freedom per second) on a fixed number of nodes and identify effective code optimization strategies for each architecture. In addition to peak performance, we identify the minimum time to solution at 80% parallel efficiency. The performance analysis is based on spectral and p-type finite elements but is equally applicable to a broad spectrum of numerical PDE discretizations, including finite difference, finite volume, and h-type finite elements.

97 MATHEMATICS AND COMPUTING↗

Computer Sciences and Data Systems, volume 2

Topics addressed include: data storage; information network architecture; VHSIC technology; fiber optics; laser applications; distributed processing; spaceborne optical disk controller; massively parallel processors; and advanced digital SAR processors.

Source record↗

Massively parallel and linear-scaling algorithm for second-order Moller–Plesset perturbation theory applied to the study of supramolecular wires

Here, we present a scalable cross-platform hybrid MPI/OpenMP/OpenACC implementation of the Divide–Expand–Consolidate (DEC) formalism with portable performance on heterogeneous HPC architectures. The Divide–Expand–Consolidate formalism is designed to reduce the steep computational scaling of conventional many-body methods employed in electronic structure theory to linear scaling, while providing a simple mechanism for controlling the error introduced by this approximation. Our massively parallel implementation of this general scheme has three levels of parallelism, being a hybrid of the loosely coupled task-based parallelization approach and the conventional MPI +X programming model, where X is either OpenMP or OpenACC. We demonstrate strong and weak scalability of this implementation on heterogeneous HPC systems, namely on the GPU-based Cray XK7 Titan supercomputer at the Oak Ridge National Laboratory. Using the “resolution of the identity second-order Moller–Plesset perturbation theory” (RI-MP2) as the physical model for simulating correlated electron motion, the linear-scaling DEC implementation is applied to 1-aza-adamantane-trione (AAT) supramolecular wires containing up to 40 monomers (2440 atoms, 6800 correlated electrons, 24 440 basis functions and 91 280 auxiliary functions). This represents the largest molecular system treated at the MP2 level of theory, demonstrating an efficient removal of the scaling wall pertinent to conventional quantum many-body methods.

97 MATHEMATICS AND COMPUTING↗

Parthenon—a performance portable block-structured adaptive mesh refinement framework

On the path to exascale the landscape of computer device architectures and corresponding programming models has become much more diverse. While various low-level performance portable programming models are available, support at the application level lacks behind. To address this issue, we present the performance portable block-structured adaptive mesh refinement (AMR) framework Parthenon, derived from the well-tested and widely used Athena++ astrophysical magnetohydrodynamics code, but generalized to serve as the foundation for a variety of downstream multi-physics codes. Parthenon adopts the Kokkos programming model, and provides various levels of abstractions from multidimensional variables, to packages defining and separating components, to launching of parallel compute kernels. Parthenon allocates all data in device memory to reduce data movement, supports the logical packing of variables and mesh blocks to reduce kernel launch overhead, and employs one-sided, asynchronous MPI calls to reduce communication overhead in multi-node simulations. Using a hydrodynamics miniapp, we demonstrate weak and strong scaling on various architectures including AMD and NVIDIA GPUs, Intel and AMD x86 CPUs, IBM Power9 CPUs, as well as Fujitsu A64FX CPUs. At the largest scale on Frontier (the first TOP500 exascale machine), the miniapp reaches a total of 1.7 × 10 13 zone-cycles/s on 9216 nodes (73,728 logical GPUs) at [Formula: see text] weak scaling parallel efficiency (starting from a single node). In combination with being an open, collaborative project, this makes Parthenon an ideal framework to target exascale simulations in which the downstream developers can focus on their specific application rather than on the complexity of handling massively-parallel, device-accelerated AMR.

97 MATHEMATICS AND COMPUTING↗

Fit Fly: A Case Study of Interconnect Innovation through Parallel Simulation

To meet the demand for exascale-level performance from high-performance computing (HPC) interconnects, many system architects are turning to simulation results for accurate and reliable predictions of the performance of prospective technologies. Testing full-scale networks with a variety of benchmarking tools, including synthetic workloads and application traces, can give crucial insight into what ideas are most promising without needing to physically construct a test network. While flexible, however, this approach is extremely compute time intensive. We address this time complexity challenge through the use of large-scale, optimistic parallel simulation that ultimately leads to faster HPC network architecture innovations. In this paper we demonstrate this innovation capability through a real-world network design case study. Specifically, we have simulated and compared four extreme-scale interconnects: Dragonfly, Megafly, Slim Fly, and a new dual-rail-dual-plane variation of the Slim Fly network topology. We present this new variant of Slim Fly, dubbed Fit Fly, to show how interconnect innovation and evaluation-beyond what is possible through analytic methods-can be achieved through parallel simulation. We validate and compare the model with various network designs using the CODES interconnect simulation framework. By running large-scale simulations in a parallel environment, we are able to quickly generate reliable performance results that can help network designers break ground on the next generation of high-performance network designs.

High Performance Computing↗

Global Data Re-allocation via Communication Aggregation in Chapel

Chapel is a parallel programming language designed to improve the productivity and ease of use of conventional and parallel computers. This language currently delivers sub optimal performance when executing codes that perform global data re-allocation operations on distributed memory architectures. This is mainly due to data communication that is done without aggregation (one message for each remote array element). In this work, we analyze Chapel's standard Block and Cyclic distribution modules and optimize the communication routines for array assignments by performing aggregation. Thanks to the expressive power of Chapel, the compiler and runtime have enough information to do communication aggregation without user intervention. The runtime relies on the low-level GAS Net networking layer, whose versions of one-sided bulk put/get routines that support strides are particularly useful for us. Experimental results conducted on Hector (a Cray XE6) and Jaguar (Cray XK6)reveal that the implemented techniques can lead to significant reductions in communication time.

Sanz, Alberto↗

ICASE Computer Science Program

The Institute for Computer Applications in Science and Engineering computer science program is discussed in outline form. Information is given on such topics as problem decomposition, algorithm development, programming languages, and parallel architectures.

Source record↗

Scan line graphics generation on the massively parallel processor

Described here is how researchers implemented a scan line graphics generation algorithm on the Massively Parallel Processor (MPP). Pixels are computed in parallel and their results are applied to the Z buffer in large groups. To perform pixel value calculations, facilitate load balancing across the processors and apply the results to the Z buffer efficiently in parallel requires special virtual routing (sort computation) techniques developed by the author especially for use on single-instruction multiple-data (SIMD) architectures.

Dorband, John E.↗