SEARCH · Engineering Papers
Results for “scalable computing”
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.
Towards Scalable Parallel Training of Deep Neural Networks
Abstract not provided
Architecture-Aware Algorithms for Scalable Performance and Resilience on Heterogeneous Architectures
This is the final report for grant, DE-SC0003959.
MarFS: A Scalable Near-POSIX Name Space over Cloud Objects – New Features
No abstract provided.
A computationally efficient P 1 radiation model for modern combustion systems utilizing pre-conditioned conjugate gradient methods
The iterative convergence of the P 1 radiation model can be slow in optically thin scenarios when employing classical iterative methods. In order to remedy this shortcoming, an in-house P 1 radiation model was interfaced with high performance, scalable, linear solver libraries. Next, the accuracies of P 1 radiation model calculations was assessed by comparing its predictions against discrete ordinates (DO) model calculations for prototypical problems representative of modern combustion systems. Corresponding benchmark results were also included for comparison. Utilizing Pre-Conditioners (PC) to the Conjugate Gradients (CG) method, the convergence time of the P 1 radiation model reduced by a factor of 30 for modest problem sizes and a factor of 70 for larger sized problems when compared against classical Gauss Seidel sweeps. Additionally, PC provided 50% computational savings compared to employing CG in a standalone mode. The P 1 model calculation times were about 25–30% of the DO model calculation time. The time to solution also scaled linearly with an increase in problem size. The weighted sum of gray gases model employed in this study in conjunction with the P 1 model provided good agreement against benchmark data with L 2 error norms (defined relative to corresponding DO calculations) improving when isotropic intensities were prevalent.
Parallel Heuristics for Scalable Community Detection
Community detection has become a fundamental operation in numerous graph-theoretic applications. It is used to reveal natural divisions that exist within real world networks without imposing prior size or cardinality constraints on the set of communities. Despite its potential for application, there is only limited support for community detection on large-scale parallel computers, largely owing to the irregular and inherently sequential nature of the underlying heuristics. In this paper, we present parallelization heuristics for fast community detection using the Louvain method as the serial template. The Louvain method is an iterative heuristic for modularity optimization. Originally developed by Blondel et al. in 2008, the method has become increasingly popular owing to its ability to detect high modularity community partitions in a fast and memory-efficient manner. However, the method is also inherently sequential, thereby limiting its scalability to problems that can be solved on desktops. Here, we observe certain key properties of this method that present challenges for its parallelization, and consequently propose multiple heuristics that are designed to break the sequential barrier. Our heuristics are agnostic to the underlying parallel architecture. For evaluation purposes, we implemented our heuristics on shared memory (OpenMP) and distributed memory (MapReduce-MPI) machines, and tested them over real world graphs derived from multiple application domains (internet, biological, natural language processing). Experimental results demonstrate the ability of our heuristics to converge to high modularity solutions comparable to those output by the serial algorithm in nearly the same number of iterations, while also drastically reducing time to solution.
Scalable Techniques for Stochastic Power Flow Problems (Final Report)
The proposed research focuses on developing scalable algorithms for two-stage security-constrained OPF problems with AC power flow constraints, a class of problems complicated by (i) scale arising from a scenario representation; and (ii) the presence of nonlinearity, nonconvexity, and possibly second-stage discreteness or complementarity. Unfortunately, most existing solvers cannot contend with both challenges simultaneously; accordingly, the proposed research focuses on developing solution techniques that can both scale with the number of scenarios and contend with nonconvexity and second-stage complementarity. We consider three avenues for addressing such problems: (i) Variable sample-size SQP (VS-SQP) methods that combine sparse Quasi-Newton updates with a scalable variance-reduced stochastic gradient scheme for stochastic QP subproblems, allowing for contending with second-stage complementarity via regularization; (ii) Variable sample-size stochastic Interior-point (VS-sIP) schemes that propose a sampling-based regularized (to allow for contending with complementarity) interior-point schemes in which a Schur-complement technique is employed for decomposing the Newton direction computation step; (iii) Variable sample-size tractable ADMM (VS-tADMM) schemes combine variable sample-sizes with carefully designed techniques for resolving each of the nonconvex updates (by leveraging the QCQP structures). We intend to compare the three schemes using performance profiles in terms of solution quality, scalability, etc. and then select one scheme which will then be developed and further refined in Python for purposes of the GO competition.
Stochastic evaluation of four-component relativistic second-order many-body perturbation energies: A potentially quadratic-scaling correlation method
A second-order many-body perturbation correction to the relativistic Dirac-Hartree-Fock energy is evaluated stochastically by integrating 13-dimensional products of four-component spinors and Coulomb potentials. The integration in the real space of electron coordinates is carried out by the Monte Carlo (MC) method with the Metropolis sampling, whereas the MC integration in the imaginary-time domain is performed by the inverse-CDF (cumulative distribution function) method. The computational cost to reach a given relative statistical error for spatially compact but heavy molecules is observed to be no worse than cubic and possibly quadratic with the number of electrons or basis functions. This is a vast improvement over the quintic scaling of the conventional, deterministic second-order many-body perturbation method. The algorithm is also easily and efficiently parallelized with demonstrated 92% strong scalability going from 64 to 4096 processors for a fixed job size.
End-to-end deep learning pipeline for real-time Bragg peak segmentation: from training to large-scale deployment
X-ray crystallography reconstruction, which transforms discrete X-ray diffraction patterns into three-dimensional molecular structures, relies critically on accurate Bragg peak finding for structure determination. As X-ray free electron laser (XFEL) facilities advance toward MHz data rates (1 million images per second), traditional peak finding algorithms that require manual parameter tuning or exhaustive grid searches across multiple experiments become increasingly impractical. While deep learning approaches offer promising solutions, their deployment in high-throughput environments presents significant challenges in automated dataset labeling, model scalability, edge deployment efficiency, and distributed inference capabilities. We present an end-to-end deep learning pipeline with three key components: (1) a data engine that combines traditional algorithms with our peak matching algorithm to generate high-quality training data at scale, (2) a modular architecture that scales from a few million to hundreds of million parameters, enabling us to train large expert-level models offline while deploying smaller, distilled models at the edge, and (3) a decoupled producer-consumer architecture that separates specialized data source layer from model inference, enabling flexible deployment across diverse computing environments. Using this integrated approach, our pipeline achieves accuracy comparable to traditional methods tuned by human experts while eliminating the need for experiment-specific parameter tuning. Although current throughput requires optimization for MHz facilities, our system's scalable architecture and demonstrated model compression capabilities provide a foundation for future high-throughput XFEL deployments.
Use Computer-Aided Tools to Parallelize Large CFD Applications
Porting applications to high performance parallel computers is always a challenging task. It is time consuming and costly. With rapid progressing in hardware architectures and increasing complexity of real applications in recent years, the problem becomes even more sever. Today, scalability and high performance are mostly involving handwritten parallel programs using message-passing libraries (e.g. MPI). However, this process is very difficult and often error-prone. The recent reemergence of shared memory parallel (SMP) architectures, such as the cache coherent Non-Uniform Memory Access (ccNUMA) architecture used in the SGI Origin 2000, show good prospects for scaling beyond hundreds of processors. Programming on an SMP is simplified by working in a globally accessible address space. The user can supply compiler directives, such as OpenMP, to parallelize the code. As an industry standard for portable implementation of parallel programs for SMPs, OpenMP is a set of compiler directives and callable runtime library routines that extend Fortran, C and C++ to express shared memory parallelism. It promises an incremental path for parallel conversion of existing software, as well as scalability and performance for a complete rewrite or an entirely new development. Perhaps the main disadvantage of programming with directives is that inserted directives may not necessarily enhance performance. In the worst cases, it can create erroneous results. While vendors have provided tools to perform error-checking and profiling, automation in directive insertion is very limited and often failed on large programs, primarily due to the lack of a thorough enough data dependence analysis. To overcome the deficiency, we have developed a toolkit, CAPO, to automatically insert OpenMP directives in Fortran programs and apply certain degrees of optimization. CAPO is aimed at taking advantage of detailed inter-procedural dependence analysis provided by CAPTools, developed by the University of Greenwich, to reduce potential errors made by users. Earlier tests on NAS Benchmarks and ARC3D have demonstrated good success of this tool. In this study, we have applied CAPO to parallelize three large applications in the area of computational fluid dynamics (CFD): OVERFLOW, TLNS3D and INS3D. These codes are widely used for solving Navier-Stokes equations with complicated boundary conditions and turbulence model in multiple zones. Each one comprises of from 50K to 1,00k lines of FORTRAN77. As an example, CAPO took 77 hours to complete the data dependence analysis of OVERFLOW on a workstation (SGI, 175MHz, R10K processor). A fair amount of effort was spent on correcting false dependencies due to lack of necessary knowledge during the analysis. Even so, CAPO provides an easy way for user to interact with the parallelization process. The OpenMP version was generated within a day after the analysis was completed. Due to sequential algorithms involved, code sections in TLNS3D and INS3D need to be restructured by hand to produce more efficient parallel codes. An included figure shows preliminary test results of the generated OVERFLOW with several test cases in single zone. The MPI data points for the small test case were taken from a handcoded MPI version. As we can see, CAPO's version has achieved 18 fold speed up on 32 nodes of the SGI O2K. For the small test case, it outperformed the MPI version. These results are very encouraging, but further work is needed. For example, although CAPO attempts to place directives on the outer- most parallel loops in an interprocedural framework, it does not insert directives based on the best manual strategy. In particular, it lacks the support of parallelization at the multi-zone level. Future work will emphasize on the development of methodology to work in a multi-zone level and with a hybrid approach. Development of tools to perform more complicated code transformation is also needed.
Runtime performance of a GAMESS quantum chemistry application offloaded to GPUs
Summary Computational chemistry is at the forefront of solving urgent societal problems, such as polymer upcycling and carbon capture. The complexity of modeling these processes at appropriate length and time scales is mainly manifested in the number and types of chemical species involved in the reactions and may require models of several thousand atoms and large basis sets to accurately capture the chemical complexity and heterogeneity in the physical and chemical processes. The quantum chemistry package General Atomic and Molecular Electronic Structure System (GAMESS) has a wide array of methods that can efficiently and accurately treat complex chemical systems. In this work, we have used the GAMESS Effective Fragment Molecule Orbital (EFMO) method for electronic structure calculation of a challenging mesoporous silica nanoparticle (MSN) model surrounded by about 4700 water molecules to investigate the strong scaling and GPU offloading on hybrid CPU‐GPU nodes. Experiments were performed on the Perlmutter platform at the National Energy Research Scientific Computing Center. Good strong scaling and load balancing have been observed on up to 88 hybrid nodes for different settings of the execution parameters for the calculation considered here. When GPUs are oversubscribed by offloading work from multiple CPU processes, using the NVIDIA multi‐process service (MPS) has consistently reduced time to solution and energy consumed. Additionally, for some configuration parameter settings, oversubscription with MPS improved performance by up to 5.8% over the case without oversubscription.
Low synchronization Gram–Schmidt and generalized minimal residual algorithms
The Gram–Schmidt process uses orthogonal projection to construct the A = QR factorization of a matrix. When Q has linearly independent columns, the operator P = I - Q(QTQ)-1QT defines an orthogonal projection onto Q⊥. In finite precision, Q loses orthogonality as the factorization progresses. A family of approximate projections is derived with the form P = I - QTQT, with correction matrix T. When T = (QTQ)-1, and T is triangular, it is postulated that the best achievable orthogonality is $\mathcal{O}(ε)\mathcal{K}(A)$. We present new variants of modified (MGS) and classical Gram–Schmidt algorithms that require one global reduction step. An interesting form of the projector leads to a compact WY representation for MGS. In particular, the inverse compact WY MGS algorithm is equivalent to a lower triangular solve. Our main contribution is to introduce a backward normalization lag into the compact WY representation, resulting in a $\mathcal{O}(ε)\mathcal{K}[r_0, AV_m])$ stable Generalized Minimal Residual Method (GMRES) algorithm that requires only one global reduce per iteration. Finally, further improvements in performance are achieved by accelerating GMRES on GPUs.
Lessons Learned and Scalability Achieved When Porting Uintah to DOE Exascale Systems
A key challenge faced when preparing codes for Department of Energy (DOE) exascale systems was designing scalable applications for systems featuring hardware and software not yet available at leadership-class scale. With such systems now available, it is important to evaluate scalability of the resulting software solutions on these target systems. One such code designed with the exascale DOE Aurora and DOE Frontier systems in mind is the Uintah Computational Framework, an open-source asynchronous many-task (AMT) runtime system. To prepare for exascale, Uintah adopted a portable MPI+X hybrid parallelism approach using the Kokkos performance portability library (i.e., MPI+Kokkos). This paper complements recent work with additional details and an evaluation of the resulting approach on Aurora and Frontier. Results are shown for a challenging benchmark demonstrating interoperability of 3 portable codes essential to Uintah-related combustion research. These results demonstrate single-source portability across Aurora and Frontier with scaling characteristics shown to 3,072 Aurora nodes and 9,216 Frontier nodes. In addition to showing results run to new scales on new systems, this paper also discusses lessons learned through efforts preparing Uintah for exascale systems.
ROOT RNTuple and EOS: The Next Generation of Event Data I/O
For several years, the ROOT team is developing the new RNTuple I/O subsystem in preparation of the next generation of collider experiments. Both HL-LHC and DUNE are expected to start data taking by the end of this decade. They pose unprecedented challenges to event data I/O in terms of data rates, event sizes, and event complexity. At the same time, the I/O landscape is becoming more diverse. HPC cluster file systems and object stores, NVMe disk cache layers in analysis facilities, and S3 storage on cloud resources are mixing with traditional XRootD-managed spinning disk pools.The ROOT team will finalize a first production version of the RNTuple binary format by the end of 2024. After this point, ROOT will provide backward compatibility for RNTuple data. This contribution provides an overview of the RNTuple feature set, the related R&D activities and the long-term vision for RNTuple. We report on performance, interface design, tooling, robustness, integration with experiment frameworks, and validation results, as well as recent R&D on parallel reading and writing and exploitation of modern hardware and storage systems. We will give an outlook on possible future features after a first production release.Collaboratively, the IT and EP departments at CERN have launched a formal project within the Research and Computing sector to evaluate the novel data format for physics analysis data utilized in LHC experiments and other fields. This part of the project focuses on validating the scalability of the EOS storage backend during the transition from the over 25 years old TTree production format to the newly developed RNTuple format, using both replicated and erasure-coded storage profiles.
(Bi 0.2 Sb 0.8 ) 2 Te 3 based dynamic synapses with programmable spatio-temporal dynamics
Neuromorphic computing has recently emerged as a promising paradigm to overcome the von-Neumann bottleneck and enable orders of magnitude improvement in bandwidth and energy efficiency. However, existing complementary metal-oxide-semiconductor (CMOS) digital devices, the building block of our computing system, are fundamentally different from the analog synapses, the building block of the biological neural network—rendering the hardware implementation of the artificial neural networks (ANNs) not scalable in terms of area and power, with existing CMOS devices. In addition, the spatiotemporal dynamic, a crucial component for cognitive functions in the neural network, has been difficult to replicate with CMOS devices. Here, we present the first topological insulator (TI) based electrochemical synapse with programmable spatiotemporal dynamics, where long-term and short-term plasticity in the TI synapse are achieved through the charge transfer doping and ionic gating effects, respectively. We also demonstrate basic neuronal functions such as potentiation/depression and paired-pulse facilitation with high precision (>500 states per device), as well as a linear and symmetric weight update. We envision that the dynamic TI synapse, which shows promising scaling potential in terms of energy and speed, can lead to the hardware acceleration of truly neurorealistic ANNs with superior cognitive capabilities and excellent energy efficiency.
An autoencoder compression approach for accelerating large-scale inverse problems
Abstract Partial differential equation (PDE)-constrained inverse problems are some of the most challenging and computationally demanding problems in computational science today. Fine meshes required to accurately compute the PDE solution introduce an enormous number of parameters and require large-scale computing resources such as more processors and more memory to solve such systems in a reasonable time. For inverse problems constrained by time-dependent PDEs, the adjoint method often employed to compute gradients and higher order derivatives efficiently requires solving a time-reversed, so-called adjoint PDE that depends on the forward PDE solution at each timestep. This necessitates the storage of a high-dimensional forward solution vector at every timestep. Such a procedure quickly exhausts the available memory resources. Several approaches that trade additional computation for reduced memory footprint have been proposed to mitigate the memory bottleneck, including checkpointing and compression strategies. In this work, we propose a close-to-ideal scalable compression approach using autoencoders to eliminate the need for checkpointing and substantial memory storage, thereby reducing the time-to-solution and memory requirements. We compare our approach with checkpointing and an off-the-shelf compression approach on an earth-scale ill-posed seismic inverse problem. The results verify the expected close-to-ideal speedup for the gradient and Hessian-vector product using the proposed autoencoder compression approach. To highlight the usefulness of the proposed approach, we combine the autoencoder compression with the data-informed active subspace (DIAS) prior showing how the DIAS method can be affordably extended to large-scale problems without the need for checkpointing and large memory.
Deffe: A Data-efficient Framework for Performance Characterization in Domain-Specific Computing
Predicting workload performance is a crucial task for many architecture and system research. In this paper we present Dee, a framework to estimate the workload performances under varying architectural configurations. The infrastructure component of Deffe is based on scalable and easy-to-use open-source software components. By casting the performance modeling as transfer learning tasks, the modeling component of Deffe can leverage the learned knowledge on one workload, and “transfer” it to a new workload. Extensive experimental results show that the method can achieve superior testing accuracy with an effective reduction of 32-80x in terms of the amount of required training data.
Enabling Scalable VQE Simulation on Leading HPC Systems
Large-scale simulations of quantum circuits pose significant challenges, especially in the context of quantum chemistry, due to the number of qubits, circuit depth, and the number of circuits needed per problem. High-performance computing (HPC) systems offer massive computational capabilities that could help overcome these obstacles. We developed a high-performance quantum circuit simulator, called NWQ-Sim, and demonstrate its capability to simulate large quantum chemistry problems on NERSC's Perlmutter supercomputer. Integrating NWQ-Sim with XACC, we have executed QPE and VQE algorithms for downfolded quantum chemistry systems at unprecedented scales. Our work demonstrates the potential of leveraging HPC resources to advance quantum chemistry and other applications of near-term quantum devices.