Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “parallel machines”

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 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Characterizing Output Bottlenecks of a Production Supercomputer: Analysis and Implications

This article studies the I/O write behaviors of the Titan supercomputer and its Lustre parallel file stores under production load. The results can inform the design, deployment, and configuration of file systems along with the design of I/O software in the application, operating system, and adaptive I/O libraries.We propose a statistical benchmarking methodology to measure write performance across I/O configurations, hardware settings, and system conditions. Moreover, we introduce two relative measures to quantify the write-performance behaviors of hardware components under production load. In addition to designing experiments and benchmarking on Titan, we verify the experimental results on one real application and one real application I/O kernel, XGC and HACC IO, respectively. These two are representative and widely used to address the typical I/O behaviors of applications.In summary, we find that Titan’s I/O system is variable across the machine at fine time scales. This variability has two major implications. First, stragglers lessen the benefit of coupled I/O parallelism (striping). Peak median output bandwidths are obtained with parallel writes to many independent files, with no striping or write sharing of files across clients (compute nodes). I/O parallelism is most effective when the application—or its I/O libraries—distributes the I/O load so that each target stores files for multiple clients and each client writes files on multiple targets in a balanced way with minimal contention. Second, our results suggest that the potential benefit of dynamic adaptation is limited. In particular, it is not fruitful to attempt to identify “good locations” in the machine or in the file system: component performance is driven by transient load conditions and past performance is not a useful predictor of future performance. For example, we do not observe diurnal load patterns that are predictable.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Scalable Graph Analytics and HPC Operational Enhancement: Parallel Computing and ML/DL Innovations

Parallel computing plays a pivotal role in the efficient processing of large-scale graphs. Complex network analysis stands as a capti- vating research frontier, holding promise across diverse scientific domains such as sociology, biology, online media, and recommenda- tion systems. In this era, Machine Learning (ML) and Deep Learning (DL) have emerged as indispensable tools, underpinning remarkable technological achievements. Within this dynamic landscape, my research revolves around advancing parallel algorithms tailored for large-scale graph operations. To achieve this, I harness the power of cutting-edge technologies including OpenMP, MPI, HIP, and CUDA, on the High-Performance Computing (HPC) platforms to unlock optimal performance. I also apply ML/DL techniques to HPC operational data, to streamline the monitoring and maintenance of supercomputers, alleviating the complexities associated with their upkeep and enhancing user support. My research echoes the syn- ergy between parallel computing, large-scale graph analysis, and ML/DL, improving computational efficiency and user experience.

Sattar, Naw Safrin↗
DOE OSTI2020

Visualizing group II intron dynamics between the first and second steps of splicing

Group II introns are ubiquitous self-splicing ribozymes and retrotransposable elements evolutionarily and chemically related to the eukaryotic spliceosome, with potential applications as gene-editing tools. Recent biochemical and structural data have captured the intron in multiple conformations at different stages of catalysis. Here, we employ enzymatic assays, X-ray crystallography, and molecular simulations to resolve the spatiotemporal location and function of conformational changes occurring between the first and the second step of splicing. We show that the first residue of the highly-conserved catalytic triad is protonated upon 5’-splice-site scission, promoting a reversible structural rearrangement of the active site (toggling). Protonation and active site dynamics induced by the first step of splicing facilitate the progression to the second step. Our insights into the mechanism of group II intron splicing parallels functional data on the spliceosome, thus reinforcing the notion that these evolutionarily-related molecular machines share the same enzymatic strategy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

TuckerMPI: A Parallel C++/MPI Software Package for Large-scale Data Compression via the Tucker Tensor Decomposition

With this study, our goal is compression of massive-scale grid-structured data, such as the multi-terabyte output of a high-fidelity computational simulation. For such data sets, we have developed a new software package called TuckerMPI, a parallel C++/MPI software package for compressing distributed data. The approach is based on treating the data as a tensor, i.e., a multidimensional array, and computing its truncated Tucker decomposition, a higher-order analogue to the truncated singular value decomposition of a matrix. The result is a low-rank approximation of the original tensor-structured data. Compression efficiency is achieved by detecting latent global structure within the data, which we contrast to most compression methods that are focused on local structure. In this work, we describe TuckerMPI, our implementation of the truncated Tucker decomposition, including details of the data distribution and in-memory layouts, the parallel and serial implementations of the key kernels, and analysis of the storage, communication, and computational costs. We test the software on 4.5 and 6.7 terabyte data sets distributed across 100 s of nodes (1,000 s of MPI processes), achieving compression ratios between 100 and 200,000×, which equates to 99--99.999% compression (depending on the desired accuracy) in substantially less time than it would take to even read the same dataset from a parallel file system. Moreover, we show that our method also allows for reconstruction of partial or down-sampled data on a single node, without a parallel computer so long as the reconstructed portion is small enough to fit on a single machine, e.g., in the instance of reconstructing/visualizing a single down-sampled time step or computing summary statistics. The code is available at https://gitlab.com/tensors/TuckerMPI.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Real-Time Bayesian Inference at Extreme Scale: A Digital Twin for Tsunami Early Warning Applied to the Cascadia Subduction Zone

We present a Bayesian inversion-based digital twin that employs acoustic pressure data from seafloor sensors, along with 3D coupled acoustic–gravity wave equations, to infer earthquake-induced spatiotemporal seafloor motion in real time and forecast tsunami propagation toward coastlines for early warning with quantified uncertainties. Our target is the Cascadia subduction zone, with one billion parameters. Computing the posterior mean alone would require 50 years on a 512 GPU machine. Instead, exploiting the shift invariance of the parameter-to-observable map and devising novel parallel algorithms, we induce a fast offline–online decomposition. The offline component requires just one adjoint wave propagation per sensor; using MFEM, we scale this part of the computation to the full El Capitan system (43,520 GPUs) with 92% weak parallel efficiency. Moreover, given real-time data, the online component exactly solves the Bayesian inverse and forecasting problems in 0.2 seconds on a modest GPU system, a ten-billion-fold speedup.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models

We improved the quality and reduced the time to produce machine learned models for use in small molecule antiviral design. Our globally asynchronous multi-level parallel training approach strong scales to all of Sierra with up to 97.7% efficiency. We trained a novel, character-based Wasserstein autoencoder that produces a higher quality model trained on 1.613 billion compounds in 23 minutes while the previous state of the art takes a day on 1 million compounds. Reducing training time from a day to minutes shifts the model creation bottleneck from computer job turnaround time to human innovation time. Our implementation achieves 318 PFLOPs for 17.1% of half-precision peak. We will incorporate this model into our molecular design loop enabling the generation of more diverse compounds; searching for novel, candidate antiviral drugs improves and reduces the time to synthesize compounds to be tested in the lab.

Jacobs, Sam Ade↗
DOE OSTI2025

String Data 2023 (Conference)

The annual String Data conferences have become the flagship annual meeting for the subfield at the interface of formal high energy theory, pure mathematics, and machine learning. String Data 2023 featured invited plenary talks by leading researchers in addition to a parallel session. The funds helped mitigate conference planning and provided support to young researchers.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS1981

A simple atmospheric model on the sphere with 100% parallelism

A simple shallow water equations model used to test numerical weather prediction schemes is presented. The spherical geometry is transformed into a formally doubly periodic configuration which can be implemented on a massively parallel computer at 100% parallelism. A nonstaggered grid with all variables defined at the grid points (circles) is used. The parallel structure was simulated by performing step 1 in a FORTRAN array, on an Amdahl serial machine, changing the signs of the winds on the dark side.

Kalnay, E.↗
NASA NTRS1983

The TEKLIB graphic library

TEKLIB is a library of procedures written in TI PASCAL to perform basic graphic tasks. TEKLIB was written to provide an interface between a graphics terminal and the TI 990. The TI 990 is used as a controller for the Finite Element Machine which is an array of microprocessors designed to solve problems by finite element methods in parallel. The use of TEKLIB provides a means of inputting data graphically and displaying output.

Bostic, S. W.↗
NASA NTRS1987

Simulation of an array-based neural net model

Research in cognitive science suggests that much of cognition involves the rapid manipulation of complex data structures. However, it is very unclear how this could be realized in neural networks or connectionist systems. A core question is: how could the interconnectivity of items in an abstract-level data structure be neurally encoded? The answer appeals mainly to positional relationships between activity patterns within neural arrays, rather than directly to neural connections in the traditional way. The new method was initially devised to account for abstract symbolic data structures, but it also supports cognitively useful spatial analogue, image-like representations. As the neural model is based on massive, uniform, parallel computations over 2D arrays, the massively parallel processor is a convenient tool for simulation work, although there are complications in using the machine to the fullest advantage. An MPP Pascal simulation program for a small pilot version of the model is running.

Barnden, John A.↗
NASA NTRS1995

Multiphase complete exchange on Paragon, SP2 and CS-2

The overhead of interprocessor communication is a major factor in limiting the performance of parallel computer systems. The complete exchange is the severest communication pattern in that it requires each processor to send a distinct message to every other processor. This pattern is at the heart of many important parallel applications. On hypercubes, multiphase complete exchange has been developed and shown to provide optimal performance over varying message sizes. Most commercial multicomputer systems do not have a hypercube interconnect. However, they use special purpose hardware and dedicated communication processors to achieve very high performance communication and can be made to emulate the hypercube quite well. Multiphase complete exchange has been implemented on three contemporary parallel architectures: the Intel Paragon, IBM SP2 and Meiko CS-2. The essential features of these machines are described and their basic interprocessor communication overheads are discussed. The performance of multiphase complete exchange is evaluated on each machine. It is shown that the theoretical ideas developed for hypercubes are also applicable in practice to these machines and that multiphase complete exchange can lead to major savings in execution time over traditional solutions.

Bokhari, Shahid H.↗
NASA NTRS1999

3D Multistage Simulation of Each Component of the GE90 Turbofan Engine

A 3D multistage simulation of each component of the GE90 Turbofan engine has been made. This includes 49 blade rows. A coupled simulation of all blade rows will be made very soon. The simulation is running using two levels of parallelism. The first level is on a blade row basis with information shared using files. The second level is using a grid domain decomposition with information shared using MPI. Timings will be shown for running on the SP2, an SGI Origin and a distributed system of HP workstations. On the HP workstations, the CHIMP version of MPI is used, with queuing supplied by LSF (Load Sharing Facility). A script-based control system is used to ensure reliability. An MPEG movie illustrating the flow simulation of the engine has been created using PV3, a parallel visualization library created by Bob Haimes of MIT. PVM is used to create a virtual machine from 10 HP workstations and display on an SGI workstation. A representative component simulation will be compared to rig data to demonstrate its usefulness in turbomachinery design and analysis.

Turner, Mark↗
NASA NTRS2002

An Analysis of Performance Enhancement Techniques for Overset Grid Applications

The overset grid methodology has significantly reduced time-to-solution of high-fidelity computational fluid dynamics (CFD) simulations about complex aerospace configurations. The solution process resolves the geometrical complexity of the problem domain by using separately generated but overlapping structured discretization grids that periodically exchange information through interpolation. However, high performance computations of such large-scale realistic applications must be handled efficiently on state-of-the-art parallel supercomputers. This paper analyzes the effects of various performance enhancement techniques on the parallel efficiency of an overset grid Navier-Stokes CFD application running on an SGI Origin2000 machine. Specifically, the role of asynchronous communication, grid splitting, and grid grouping strategies are presented and discussed. Results indicate that performance depends critically on the level of latency hiding and the quality of load balancing across the processors.

Djomehri, J. J.↗
NASA NTRS2019

Accelerated Simulation of Air Pollution Using NVIDIA RAPIDS

Atmospheric chemistry models are a central tool to study and forecast the impact of air pollution on the environment, vegetation, and human health. However, the numerical simulation of chemical kinetics is computationally expensive due to the stiffness of the system of ordinary differential equations that describes atmospheric chemistry. Here we present an alternative approach to the computation of atmospheric chemistry based on machine learning. Our training data set is produced using the NASA Goddard Earth Observing System (GEOS) model with GEOS-Chem chemistry, run on the NASA Center for Climate Simulation (NCCS) Discover supercomputing cluster on 384 Intel Xeon Haswell cores. This model spends more than 50% of total run time on solving atmospheric chemistry. The data set contains as input features the air pollution concentrations before solving the differential equations, together with some key physical parameters such as temperature and sun intensity. As target variables we define the air pollution concentrations after solving the differential equations. Using Dask-cuDF and Dask-XGBoost on the NVIDIA RAPIDS platform on 8 Tesla V100 GPUs, we generate from this training set gradient boosted decision tree models that can reproduce the simulation of chemical kinetics. We do this on the NCCS Advanced Data Analytics Platform (ADAPT) science cloud environment. Our application takes full advantage of recent advances in Dask-XGBoost, such as multi-node and multi-GPU scaling for distributed training with large data sets. The increase in training data size enabled by this is critical to capture the full range of chemical environments encountered across the globe and all annual seasons.The boosted tree models offer good predictability and show many of the features of the full chemistry reference simulation. Further improvements can be achieved through mass balance considerations and by accounting for error correlations. We incorporate the boosted tree models into the GEOS reference model using XGBoost's C API. This enables a seamless integration of the GPU trained models into GEOS-Chem, which is written in Fortran and optimized for use in a massively parallel CPU environment. We show the benefits of this approach and discuss the potential speedup of this machine learning accelerated atmospheric chemistry model.

Keller, Christoph A.↗
NASA NTRS1998

Automated Generation of Message-Passing Programs: An Evaluation of CAPTools using NAS Benchmarks

Scientists at NASA Ames Research Center have been developing computational aeroscience applications on highly parallel architectures over the past ten years. During the same time period, a steady transition of hardware and system software also occurred, forcing us to expand great efforts into migrating and receding our applications. As applications and machine architectures continue to become increasingly complex, the cost and time required for this process will become prohibitive. Various attempts to exploit software tools to assist and automate the parallelization process have not produced favorable results. In this paper, we evaluate an interactive parallelization tool, CAPTools, for parallelizing serial versions of the NAB Parallel Benchmarks. Finally, we compare the performance of the resulting CAPTools generated code to the hand-coded benchmarks on the Origin 2000 and IBM SP2. Based on these results, a discussion on the feasibility of automated parallelization of aerospace applications is presented along with suggestions for future work.

Hribar, Michelle R.↗
NASA NTRS1995

Communication overhead on the Intel Paragon, IBM SP2 and Meiko CS-2

Interprocessor communication overhead is a crucial measure of the power of parallel computing systems-its impact can severely limit the performance of parallel programs. This report presents measurements of communication overhead on three contemporary commercial multicomputer systems: the Intel Paragon, the IBM SP2 and the Meiko CS-2. In each case the time to communicate between processors is presented as a function of message length. The time for global synchronization and memory access is discussed. The performance of these machines in emulating hypercubes and executing random pairwise exchanges is also investigated. It is shown that the interprocessor communication time depends heavily on the specific communication pattern required. These observations contradict the commonly held belief that communication overhead on contemporary machines is independent of the placement of tasks on processors. The information presented in this report permits the evaluation of the efficiency of parallel algorithm implementations against standard baselines.

Bokhari, Shahid H.↗
DOE OSTI2023

Adrastea: An Efficient FPGA Design Environment for Heterogeneous Scientific Computing and Machine Learning

We present Adrastea, an efficient FPGA design environment for developing scientific machine learning applications. FPGA development is challenging, from deployment, proper toolchain setup, programming methods, interfacing FPGA kernels, and more importantly, the need to explore design space choices to get the best performance and area usage from the FPGA kernel design. Adrastea provides an automated and scalable design flow to parameterize, implement, and optimize complex FPGA kernels and associated interfaces. We show how virtualization of the development environment via virtual machines is leveraged to simplify the setup of the FPGA toolchain while deploying the FPGA boards and while scaling up the automated design space exploration to leverage multiple machines concurrently. Adrastea provides an automated build and test environment of FPGA kernels. By exposing design space hyper-parameters, Adrastea can automatically search the design space in parallel to optimize the FPGA design for a given metric, usually performance or area. Adrastea simplifies the task of interfacing with the FPGA kernels with a simplified interface API. To demonstrate the capabilities of Adrastea, we implement a complex random forest machine learning kernel with 10,000 input features while achieving extremely low computing latency without loss of prediction accuracy, which is required by a scientific edge application at SNS. We also demonstrate Adrastea using an FFT kernel and show that for both applications Adrastea is able to systematically and efficiently evaluate different design options, which reduced the time and effort required to develop the kernel from months of manual work to days of automatic builds.

Young, Aaron↗
DOE OSTI2021

Theoretically and practically efficient parallel nucleus decomposition

This paper studies the nucleus decomposition problem, which has been shown to be useful in finding dense substructures in graphs. We present a novel parallel algorithm that is efficient both in theory and in practice. Our algorithm achieves a work complexity matching the best sequential algorithm while also having low depth (parallel running time), which significantly improves upon the only existing parallel nucleus decomposition algorithm (Sariyüce et al. , PVLDB 2018). The key to the theoretical efficiency of our algorithm is a new lemma that bounds the amount of work done when peeling cliques from the graph, combined with the use of a theoretically-efficient parallel algorithms for clique listing and bucketing. We introduce several new practical optimizations, including a new multi-level hash table structure to store information on cliques space-efficiently and a technique for traversing this structure cache-efficiently. On a 30-core machine with two-way hyper-threading on real-world graphs, we achieve up to a 55x speedup over the state-of-the-art parallel nucleus decomposition algorithm by Sariyüce et al. , and up to a 40x self-relative parallel speedup. We are able to efficiently compute larger nucleus decompositions than prior work on several million-scale graphs for the first time.

Computer Science↗