Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Parallel Supercomputers”

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 361 records · Page 20

Towards reversible basic linear algebra subprograms: A performance study

Problems such as fault tolerance and scalable synchronization can be efficiently solved using reversibility of applications. Making applications reversible by relying on computation rather than on memory is ideal for large scale parallel computing, especially for the next generation of supercomputers in which memory is expensive in terms of latency, energy, and price. In this direction, a case study is presented here in reversing a computational core, namely, Basic Linear Algebra Subprograms, which is widely used in scientific applications. A new Reversible BLAS (RBLAS) library interface has been designed, and a prototype has been implemented with two modes: (1) a memory-mode in which reversibility is obtained by checkpointing to memory in forward and restoring from memory in reverse, and (2) a computational-mode in which nothing is saved in the forward, but restoration is done entirely via inverse computation in reverse. The article is focused on detailed performance benchmarking to evaluate the runtime dynamics and performance effects, comparing reversible computation with checkpointing on both traditional CPU platforms and recent GPU accelerator platforms. For BLAS Level-1 subprograms, data indicates over an order of magnitude better speed of reversible computation compared to checkpointing. For BLAS Level-2 and Level-3, a more complex tradeoff is observed between reversible computation and checkpointing, depending on computational and memory complexities of the subprograms.

97 MATHEMATICS AND COMPUTING↗

Development of mpi_EPIC model for global agroecosystem modeling

Models that address policy-maker concerns about multi-scale effects of food and bioenergy production systems are computationally demanding. We integrated the message passing interface algorithm into the process-based EPIC model to accelerate computation of ecosystem effects. Simulation performance was further enhanced by applying the Vampir framework. When this enhanced mpi_EPIC model was tested, total execution time for a global 30-year simulation of a switchgrass cropping system was shortened to less than 0.5 hours on a supercomputer. The results illustrate that mpi_EPIC using parallel design can balance simulation workloads and facilitate large-scale, high-resolution analysis of agricultural production systems, management alternatives and environmental effects.

54 ENVIRONMENTAL SCIENCES↗

Porting Ordinary Applications to Blue Gene/Q Supercomputers

Efficiently porting ordinary applications to Blue Gene/Q supercomputers is a significant challenge. Codes are often originally developed without considering advanced architectures and related tool chains. Science needs frequently lead users to want to run large numbers of relatively small jobs (often called many-task computing, an ensemble, or a workflow), which can conflict with supercomputer configurations. In this paper, we discuss techniques developed to execute ordinary applications over leadership class supercomputers. We use the high-performance Swift parallel scripting framework and build two workflow execution techniques-sub-jobs and main-wrap. The sub-jobs technique, built on top of the IBM Blue Gene/Q resource manager Cobalt's sub-block jobs, lets users submit multiple, independent, repeated smaller jobs within a single larger resource block. The main-wrap technique is a scheme that enables C/C++ programs to be defined as functions that are wrapped by a high-performance Swift wrapper and that are invoked as a Swift script. We discuss the needs, benefits, technicalities, and current limitations of these techniques. We further discuss the real-world science enabled by these techniques and the results obtained.

Maheshwari, Ketan C.↗

Community Detection on the GPU

We present and evaluate a new GPU algorithm based on the Louvain method for community detection. Our algorithm is the first for this problem that parallelizes the access to individual edges. In this way we can fine tune the load balance when processing networks with nodes of highly varying degrees. This is achieved by scaling the number of threads assigned to each node according to its degree. Extensive experiments show that we obtain speedups up to a factor of 270 compared to the sequential algorithm. The algorithm consistently outperforms other recent shared memory implementations and is only one order of magnitude slower than the current fastest parallel Louvain method running on a Blue Gene/Q supercomputer using more than 500K threads.

community detection↗

Cyber Dumpster Diving: Creating New Software Systems for Less

Modern scientific software is daunting in its breadth and complexity. From massively parallel simulations running on the world’s largest supercomputers to visualizations and user support environments that manage ever-growing, complex data collections, the challenges for software engineers are plentiful indeed.

software architecture↗

ExaMPM

ExaMPM is a mini-application for the Material Point Method (MPM) for studying the application of MPM to future exascale computing systems. MPM is a general method for computational mechanics and fluids and is used in a wide variety of science and engineering disciplines to study problems with large deformations, phase change, fracture, and other phenomena. ExaMPM provides a reference implementation of MPM as described in the 1994 work of Sulsky et.al. (Sulsky, Deborah, Zhen Chen, and Howard L. Schreyer. "A particle method for history-dependent materials." Computer methods in applied mechanics and engineering 118.1-2 (1994): 179-196.). The software can solve basic MPM problems in solid mechanics using the original algorithm of Sulsky with explicit time integration, basic geometries, and free-slip and no-slip boundary conditions as described in the reference. ExaMPM is intended to be used as a starting point to design new parallel algorithms for the next generation of DOE supercomputers.

Slattery, StuartR↗

A Data Exploration Tool for Large Sets of Spectra

We present an exploration tool for very large spectrum data sets such as the SDSS (Sloan Digital Sky Survey), LAMOST (Large Sky Area Multi-Object Fiber Spectroscopic Telescope), and 4MOST (4-meter Multi-Object Spectroscopic Telescope) data sets. The tool works in two stages: the first uses batch processing and the second runs interactively. The latter employs the NASA hyperwall, a configuration of 128 workstation displays (8 by 16 array) controlled by a parallelized software suite running on NASA's Pleiades supercomputer. The stellar subset of the Sloan Digital Sky Survey, DR10, was chosen to show how the our tool may be used. In stage one, SDSS files for 569,740 stars are processed through our data pipeline. The pipeline fits each spectrum using an iterative continuum algorithm, distinguishing emission from absorption and handling molecular absorption bands correctly. It then measures 1659 discrete atomic and molecular spectral features that were carefully preselected based on their likelihood of being visible at some spectral type. The depths relative to the local continuum at each feature wavelength are determined for each spectrum: these depths, the local S/N (signal to noise ratio) level, and DR10-supplied variables such as magnitudes, colors, positions, and radial velocities are the basic measured quantities used on the hyperwall. In stage two, each hyperwall panel is used to display a 2-D scatter plot showing the depth of feature A vs the depth of feature B for all of the stars. A and B change from panel to panel. The relationships between the various (A,B) strengths and any distinctive clustering are immediately apparent when examining and inter-comparing the different panels on the hyperwall. The interactive software allows the user to select the stars in any interesting region of any 2-D plot on the hyperwall, immediately rendering the same stars on all the other 2-D plots in a unique color. The process may be repeated multiple times, each selection displaying a distinctive color on all the plots. At any time, the spectra of the selected stars may be examined in detail on a connected workstation display. We illustrate how our approach allows us to quickly isolate and examine such interesting stellar subsets as EMP (Extremely Metal‐Poor) stars, CV (Cataclymic Variable) stars and C (Carbon)-rich stars.

Data Exploration↗

One Giant Leap for Womankind: Studying NASA’s SLS Rocket With Pressure-Sensitive Paint

Combining computer vision techniques, high-speed cameras, pressure-sensitive paint and a transonic wind tunnel, NASA studies unsteady aerodynamic forces on the Space Launch System rocket with unprecedented temporal and spatial resolution. NASA’s most powerful supercomputer, Pleiades, enables real-time visualization and parallel processing to investigate buffet forces and aeroacoustic physics.

Lucy Zhonghui Tang↗

Dynamic Mode Decomposition of Unsteady Pressure-Sensitive Paint Measurements for the NASA Unitary Plan Wind Tunnel Tests

This paper describes the Dynamic Mode Decomposition (DMD) of the pressures on the scale model of the Space Launch System (SLS) Block 1 cargo vehicle with the Unsteady Pressure-Sensitive Paint (uPSP) measurements, which were collected in the Ascent Transient Aerodynamics Tests with the Unitary Plan Wind Tunnel 11-by-11-foot Transonic Wind Tunnel in September 2019 at NASA Ames Research Center. The work described in this paper is a part of NASA’s development of a new state-of-the-art uPSP capability in production wind tunnels. The conventional DMD algorithm is based on the Singular Value Decomposition (SVD) of the data matrix. For the matrix of the uPSP measurements of the SLS ATAT, the number of rows is equal to the number of nodes in the grid of the scale model, and the number of columns is equal to the number of frames in the videos taken with 4 Phantom high-speed cameras. In this paper, it is verified that, for the time series with zero mean value, the DMD is equivalent to the decomposition with the Discrete Fourier Transform (DFT). Considering the uPSP is mainly used in the assessment of the unsteady, aerodynamic phenomena, the DMD of the uPSP measurements can be implemented in two steps: (1) subtract the mean value from the uPSP measurement on each of the grid nodes; (2) apply the Fast Fourier Transform (FFT) on the resulting zero-mean time series. The DMD of the uPSP measurements with FFT has two advantages: (1) the computational complexity of FFT is O(N*logN), where N is the length of the time series; (2) compared to the SVD-based DMD algorithm, the DMD with FFT can be easily implemented in parallel processing. A sample matrix of uPSP measurements, at the size of 341 grid nodes and 128 frames, is generated. Figures 1 and 2 show the eigenvalues and the ratios of the eigenvectors, respectively, of the sample matrix, without and with the mean value removed on each of the grid nodes, computed with the SVD-based DMD and the FFT. The figures demonstrate the equivalence of the SVD-based DMD and the decomposition with DFT/FFT for the time series with zero mean value. The results of DMD of the uPSP measurements of the SLS ATAT in September 2019 are presented in the paper. The DMD modes at different frequencies are shown, the aerodynamic phenomena (e.g. shockwave and vortex shedding) are demonstrated and the correlation of the DMD modes with the test configuration parameter (e.g., the Mach Number) is discussed. Figure 3 shows a software tool to visualize the DMD modes. The code to implement the algorithm described in this paper was written in C, with libraries of FFTW for FFT and MPI/OpenMP for parallel processing, and executed on the NASA Pleiades supercomputer. Funding for this research was provided by the NASA Aerosciences Evaluation and Test Capabilities Project.

Pressure-Sensitive Paint↗

Integration experiments and performance studies of a COTS parallel archive system

Current and future Archive Storage Systems have been asked to (a) scale to very high bandwidths, (b) scale in metadata performance, (c) support policy-based hierarchical storage management capability, (d) scale in supporting changing needs of very large data sets, (e) support standard interface, and (f) utilize commercial-off-the-shelf (COTS) hardware. Parallel file systems have been asked to do the same thing but at one or more orders of magnitude faster in performance. Archive systems continue to move closer to file systems in their design due to the need for speed and bandwidth, especially metadata searching speeds such as more caching and less robust semantics. Currently the number of extreme highly scalable parallel archive solutions is very small especially those that will move a single large striped parallel disk file onto many tapes in parallel. We believe that a hybrid storage approach of using COTS components and innovative software technology can bring new capabilities into a production environment for the HPC community much faster than the approach of creating and maintaining a complete end-to-end unique parallel archive software solution. In this paper, we relay our experience of integrating a global parallel file system and a standard backup/archive product with a very small amount of additional code to provide a scalable, parallel archive. Our solution has a high degree of overlap with current parallel archive products including (a) doing parallel movement to/from tape for a single large parallel file, (b) hierarchical storage management, (c) ILM features, (d) high volume (non-single parallel file) archives for backup/archive/content management, and (e) leveraging all free file movement tools in Linux such as copy, move, Is, tar, etc. We have successfully applied our working COTS Parallel Archive System to the current world's first petafiop/s computing system, LANL's Roadrunner machine, and demonstrated its capability to address requirements of future archival storage systems.

99 GENERAL AND MISCELLANEOUS↗

Sisal

Sisal (Streams and Iterations in a Single Assignment Language) was a general-purpose applicative language developed for shared-memory and vector supercomputer systems. It provided an hierarchical intermediate form, parallel runtime system, optimizing compiler, and programming environment. The language was strongly typed. It supported both array and stream data structures, and had both iterative and parallel loop constructs.

Feo, John T↗

Build Less Code, Deliver More Science: An Experience Report on Composing Scientific Environments using Component-based and Commodity Software Platforms

Modern scientific software is daunting in its diversity and complexity. From massively parallel simulations running on the world’s largest supercomputers, to visualizations and user support environments that manage ever growing complex data collections, the challenges for software engineers are plentiful. While high performance simulators are necessarily specialized codes to maximize performance on specific supercomputer architectures, we argue the vast majority of supporting infrastructure, data management and analysis tools can leverage commodity open source and component-based technologies. This approach can significantly drive down the effort and costs of building complex, collaborative scientific user environments, as well as increase their reliability and extensibility. In this paper we describe our experiences in creating an initial user environment for scientists involved in modeling the detailed effects of climate change on the environment of selected geographical regions. Our approach composes the user environment using the Velo scientific knowledge management platform and the MeDICi Integration Framework for scientific workflows. These established platforms leverage component-based technologies and extend commodity open source platforms with abstractions and capabilities that make them amenable for broad use in science. Using this approach we were able to deliver an operational user environment capable of running thousands of simulations in a 7 month period, and achieve significant software reuse.

Gorton, Ian↗

ExaMPM

ExaMPM is a mini-application for the Material Point Method (MPM) for studying the application of MPM to future exascale computing systems. MPM is a general method for computational mechanics and fluids and is used in a wide variety of science and engineering disciplines to study problems with large deformations, phase change, fracture, and other phenomena. ExaMPM provides a reference implementation of MPM as described in the 1994 work of Sulsky et.al. (Sulsky, Deborah, Zhen Chen, and Howard L. Schreyer. "A particle method for history-dependent materials." Computer methods in applied mechanics and engineering 118.1-2 (1994): 179-196.). The software can solve basic MPM problems in solid mechanics using the original algorithm of Sulsky with explicit time integration, basic geometries, and free-slip and no-slip boundary conditions as described in the reference. ExaMPM is intended to be used as a starting point to design new parallel algorithms for the next generation of DOE supercomputers.

Slattery, Stuart R↗

Enabling Large-Scale Condensed-Phase Hybrid Density Functional Theory Based Ab Initio Molecular Dynamics. 1. Theory, Algorithm, and Performance

By including a fraction of exact exchange (EXX), hybrid functionals reduce the self-interaction error in semilocal density functional theory (DFT) and thereby furnish a more accurate and reliable description of the underlying electronic structure in systems throughout biology, chemistry, physics, and materials science. However, the high computational cost associated with the evaluation of all required EXX quantities has limited the applicability of hybrid DFT in the treatment of large molecules and complex condensed-phase materials. To overcome this limitation, we describe a linear-scaling approach that utilizes a local representation of the occupied orbitals (e.g., maximally localized Wannier functions (MLWFs)) to exploit the sparsity in the real-space evaluation of the quantum mechanical exchange interaction in finite-gap systems. In this work, we present a detailed description of the theoretical and algorithmic advances required to perform MLWF-based ab initio molecular dynamics (AIMD) simulations of large-scale condensed-phase systems of interest at the hybrid DFT level. We focus our theoretical discussion on the integration of this approach into the framework of Car–Parrinello AIMD, and highlight the central role played by the MLWF-product potential (i.e., the solution of Poisson’s equation for each corresponding MLWF-product density) in the evaluation of the EXX energy and wave function forces. We then provide a comprehensive description of the exx algorithm implemented in the open-source Quantum ESPRESSO program, which employs a hybrid MPI/OpenMP parallelization scheme to efficiently utilize the high-performance computing (HPC) resources available on current- and next-generation supercomputer architectures. Furthermore, this is followed by a critical assessment of the accuracy and parallel performance (e.g., strong and weak scaling) of this approach when AIMD simulations of liquid water are performed in the canonical (NVT) ensemble. With access to HPC resources, we demonstrate that exx enables hybrid DFT-based AIMD simulations of condensed-phase systems containing 500–1000 atoms (e.g., (H₂O)₂₅₆) with a wall time cost that is comparable to that of semilocal DFT. In doing so, exx takes us one step closer to routinely performing AIMD simulations of complex and large-scale condensed-phase systems for sufficiently long time scales at the hybrid DFT level of theory.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

CEAZ: Accelerating Parallel I/O Via Hardware-Algorithm Co-Designed Adaptive Lossy Compression

As supercomputers continue to grow to exa-scale, the amount of data that needs to be saved or transmitted is exploding. To this end, many previous works have studied using error-bounded lossy compressors to reduce the data size and improve the I/O performance. However, little work has been done for effectively offloading lossy compression onto FPGA-based SmartNICs to reduce the compression overhead. In this paper, we propose a hardware-algorithm co-design of efficient and adaptive lossy compressor for scientific data on FPGAs (called CEAZ) to accelerate parallel I/O. Our contribution is fourfold: (1) We propose an efficient Huffman coding approach that can adaptively update Huffman codewords online based on codewords generated offline (from a variety of representative scientific datasets). (2) We derive a theoretical analysis to support a precise control of compression ratio under an error-bounded compression mode, enabling accurate offline Huffman codewords generation. This also help us create a fixed-ratio compression mode for consistent throughput. (3) We develop an efficient compression pipeline by adopting cuSZ’s dual-quantization algorithm to our hardware use case. (4) We evaluate CEAC on five real-world datasets with both a single FPGA board and 256 nodes from Bridges2 supercomputer. Experiments show that CEAZ outperforms the second-best FPGA-based lossy compressor by 2× of throughput and 9.6× of compression ratio. It also improves MPI_File_write and MPI_Gather throughputs by up to 32.7× and 31.4×, respectively.

Zhang, Chengming↗

CFD code evaluation for internal flow modeling

Research on the computational fluid dynamics (CFD) code evaluation with emphasis on supercomputing in reacting flows is discussed. Advantages of unstructured grids, multigrids, adaptive methods, improved flow solvers, vector processing, parallel processing, and reduction of memory requirements are discussed. As examples, researchers include applications of supercomputing to reacting flow Navier-Stokes equations including shock waves and turbulence and combustion instability problems associated with solid and liquid propellants. Evaluation of codes developed by other organizations are not included. Instead, the basic criteria for accuracy and efficiency have been established, and some applications on rocket combustion have been made. Research toward an ultimate goal, the most accurate and efficient CFD code, is in progress and will continue for years to come.

Chung, T. J.↗

HPC formulations of optimization algorithms for tensor completion

Tensor completion is a powerful tool used to estimate or recover missing values in multi-way data. It has seen great success in domains such as product recommendation and healthcare. Tensor completion is most often accomplished via low-rank sparse tensor factorization, a computationally expensive non-convex optimization problem which has only recently been studied in the context of parallel computing. In this work, we study three optimization algorithms that have been successfully applied to tensor completion: alternating least squares (ALS), stochastic gradient descent (SGD), and coordinate descent (CCD++). We explore opportunities for parallelism on shared- and distributed-memory systems and address challenges such as memory- and operation-efficiency, load balance, cache locality, and communication. Among our advancements are a communication-efficient CCD++ algorithm, an ALS algorithm rich in level-3 BLAS routines, and an SGD algorithm which combines stratification with asynchronous communication. Furthermore, we show that introducing randomization during ALS and CCD++ can accelerate convergence. We evaluate our parallel formulations on a variety of real datasets on a modern supercomputer and demonstrate speedups through 16384 cores. Further, these improvements reduce time-to-solution from hours to seconds on real-world datasets. We show that after our optimizations, ALS is advantageous on parallel systems of small-to-moderate scale, while both ALS and CCD++ provide the lowest time-to-solution on large-scale distributed systems.

97 MATHEMATICS AND COMPUTING↗