Scientific Computing

The world of computing is in rapid transition, now dominated by a world of smartphones and cloud services, with profound implications for the future of advanced scientific computing. Simply put, high-performance computing (HPC) is at an important inflection point. For the last 60 years, the world's fastest supercomputers were almost exclusively produced in the United States on behalf of scientific research in the national laboratories. Change is now in the wind. While costs now stretch the limits of U.S. government funding for advanced computing, Japan and China are now leaders in the bespoke HPC systems funded by government mandates. Meanwhile, the global semiconductor shortage and political battles surrounding fabrication facilities affect everyone. However, another, perhaps even deeper, fundamental change has occurred. The major cloud vendors have invested in global networks of massive scale systems that dwarf today's HPC systems. Driven by the computing demands of AI, these cloud systems are increasingly built using custom semiconductors, reducing the financial leverage of traditional computing vendors. These cloud systems are now breaking barriers in game playing and computer vision, reshaping how we think about the nature of scientific computation. Building the next generation of leading edge HPC systems will require rethinking many fundamentals and historical approaches by embracing end-to-end co-design; custom hardware configurations and packaging; large-scale prototyping, as was common thirty years ago; and collaborative partnerships with the dominant computing ecosystem companies, smartphone, and cloud computing vendors.

Proper orthogonal decomposition (POD) allows reduced-order modeling of complex dynamical systems at a substantial level, while maintaining a high degree of accuracy in modeling the underlying dynamical systems. Advances in machine learning algorithms enable learning POD-based dynamics from data and making accurate and fast predictions of dynamical systems. In this paper, we leverage the recently proposed heavy-ball neural ODEs (HBNODEs) [Xia et al. NeurIPS, 2021] for learning data-driven reduced-order models (ROMs) in the POD context, in particular, for learning dynamics of time-varying coefficients generated by the POD analysis on training snapshots generated from solving full order models. HBNODE enjoys several practical advantages for learning POD-based ROMs with theoretical guarantees, including 1) HBNODE can learn long-term dependencies effectively from sequential observations and 2) HBNODE is computationally efficient in both training and testing. We compare HBNODE with other popular ROMs on several complex dynamical systems, including the von Kármán Street flow, the Kurganov-Petrova-Popov equation, and the one-dimensional Euler equations for fluids modeling.

A common feature of many methods in computational mechanics is that there is often a way of estimating the error in the computed solution. The situation for computational mechanics codes based upon the Material Point Method is very different in that there has been comparatively little work on computable error estimates for these methods. This work is concerned with introducing such an approach for the Material Point Method. Although it has been observed that spatial errors may dominate temporal ones at stable time steps, recent work has made more precise the sources and forms of the different MPM errors. There is then a need to estimate these errors computationally through computable estimates of the different errors in the material point method. Estimates of the different spatial errors in the Material Point Method are constructed based upon nodal derivatives of the different physical variables in MPM. These derivatives are then estimated using standard difference approximations calculated on the background mesh. The use of these estimates of the spatial error makes it possible to measure the growth of errors over time. A number of computational experiments are used to illustrate the performance of the computed error estimates. As the key feature of the approach is the calculation of derivatives on the regularly spaced background mesh, the extension to calculating derivatives and hence to error estimates for higher dimensional problems is clearly possible.

Orthogonal polynomials of several variables have a vector-valued three-term recurrence relation, much like the corresponding one-dimensional relation. This relation requires only knowledge of certain recurrence matrices, and allows simple and stable evaluation of multivariate orthogonal polynomials. In the univariate case, various algorithms can evaluate the recurrence coefficients given the ability to compute polynomial moments, but such a procedure is absent in multiple dimensions. We present a new Multivariate Stieltjes (MS) algorithm that fills this gap in the multivariate case, allowing computation of recurrence matrices assuming moments are available. The algorithm is essentially explicit in two and three dimensions, but requires the numerical solution to a non-convex problem in more than three dimensions. Compared to direct Gram-Schmidt-type orthogonalization, we demonstrate on several examples in up to three dimensions that the MS algorithm is far more stable, and allows accurate computation of orthogonal bases in the multivariate setting, in contrast to direct orthogonalization approaches.

The success of the Material Point Method (MPM) in solving many challenging problems nevertheless raises some open questions regarding the fundamental properties of the method such as time integration accuracy and energy conservation. The traditional MPM time integration methods are often based upon the symplectic Euler method or staggered central differences. This raises the question of how to best ensure energy conservation in explicit time integration for MPM. Two approaches are used here, one is to extend the Symplectic Euler method (Cromer Euler) to provide better energy conservation and the second is to use a potentially more accurate symplectic methods, namely the widely-used Stormer-Verlet Method. The Stormer-Verlet method is shown to have locally third order time accuracy of energy conservation in time, in contrast to the second order accuracy in energy conservation of the symplectic Euler methods that are used in many MPM calculations. It is shown that there is an extension to the Symplectic Euler stress-last method that provides better energy conservation that is comparable with the Stormer-Verlet method. This extension is referred to as TRGIMP and also has third order accuracy in energy conservation. When the interactions between space and time errors are studied it is seen that spatial errors may dominate in computed quantities such as displacement and velocity. This connection between the local errors in space and time is made explicit mathematically and explains the observed results that displacement and velocity errors are very similar for both methods. The observed and theoretically predicted third-order energy conservation accuracy and computational costs are demonstrated on a standard MPM test example.

Adaptive representations are increasingly indispensable for reducing the in-memory and on-disk footprints of large-scale data. Usual solutions are designed broadly along two themes: reducing data precision, e.g., through compression, or adapting data resolution, e.g., using spatial hierarchies. Recent research suggests that combining the two approaches, i.e., adapting both resolution and precision simultaneously, can offer significant gains over using them individually. However, there currently exist no practical solutions to creating and evaluating such representations at scale. In this work, we present a new resolution-precision-adaptive representation to support hybrid data reduction schemes and offer an interface to existing tools and algorithms. Through novelties in spatial hierarchy, our representation, Adaptive Multilinear Meshes (AMM), provides considerable reduction in the mesh size. AMM creates a piecewise multilinear representation of uniformly sampled scalar data and can selectively relax or enforce constraints on conformity, continuity, and coverage, delivering a flexible adaptive representation. AMM also supports representing the function using mixed-precision values to further the achievable gains in data reduction. We describe a practical approach to creating AMM incrementally using arbitrary orderings of data and demonstrate AMM on six types of resolution and precision datastreams. By interfacing with state-of-the-art rendering tools through VTK, we demonstrate the practical and computational advantages of our representation for visualization techniques. With an open-source release of our tool to create AMM, we make such evaluation of data reduction accessible to the community, which we hope will foster new opportunities and future data reduction schemes

The Scientific Computing and Imaging (SCI) Institute at the University of Utah evolved from the SCI research group, started in 1994 by Professors Chris Johnson and Rob MacLeod. Over time, research centers funded by the National Institutes of Health, Department of Energy, and State of Utah significantly spurred growth, and SCI became a permanent interdisciplinary research institute in 2000. The SCI Institute is now home to more than 150 faculty, students, and staff. The history of the SCI Institute is underpinned by a culture of multidisciplinary, collaborative research, which led to its emergence as an internationally recognized leader in the development and use of visualization, scientific computing, and image analysis research to solve important problems in a broad range of domains in biomedicine, science, and engineering. A particular hallmark of SCI Institute research is the creation of open source software systems, including the SCIRun scientific problem-solving environment, Seg3D, ImageVis3D, Uintah, ViSUS, Nektar++, VisTrails, FluoRender, and FEBio. At this point, the SCI Institute has made more than 50 software packages broadly available to the scientific community under open-source licensing and supports them through web pages, documentation, and user groups. While the vast majority of academic research software is written and maintained by graduate students, the SCI Institute employs several professional software developers to help create, maintain, and document robust, tested, well-engineered open source software. The story of how and why we worked, and often struggled, to make professional software engineers an integral part of an academic research institute is crucial to the larger story of the SCI Institute’s success in translational computer science (TCS).

In-situ processing addresses the gap between speeds of computing and I/O capabilities by processing data close to the data source, i.e., on the same system as the data source (e.g., a simulation). However, the effective implementation of in-situ processing workflows requires the optimization of several design parameters such as where on the system workflow data analysis/visualization (ana/vis) as placed and how execution as well as the interaction and data exchanges between ana/vis are coordinated. For example, in the case of hybrid in-situ processing, interacting ana/vis may be tightly or loosely coupled depending on their placement, and this can lead to very different performance and scalability. A key challenge is deciding the most appropriate ana/vis placement, which depends on dynamic applications, workflow, and system characteristics that might change at runtime. In this paper, we present a framework to support online adaptive data analysis placement during the execution of an in-situ workflow. Specifically, the paper presents a model and architecture, and explores several data analysis placement strategies. Evaluation results show that dynamically choosing appropriate data analysis placement strategies can balance the benefits and overhead of different data analysis placement patterns to reduce in-situ processing time.

The growth of the Internet of Things is resulting in an explosion of data volumes at the Edge of the Internet. To reduce costs incurred due to data movement and centralized cloud-based processing, it is becoming increasingly important to process and analyze such data closer to the data sources. Exploiting Edge computing capabilities for stream-based processing is however challenging. It requires addressing the complex characteristics and constraints imposed by all the resources along the data path, as well as the large set of heterogeneous data processing and management frameworks. Consequently, the community needs tools that can facilitate the modeling of this complexity and can integrate the various components involved. In this work, we introduce MDSC, a hierarchical approach for modeling distributed stream-based applications on Edge-to-Cloud continuum infrastructures. We demonstrate how MDSC can be applied to a concrete real-life ML-based application -early earthquake warning - to help answer questions such as: when is it worth decentralizing the classification load from the Cloud to the Edge and how?

A Gaussian process (GP) is a powerful and widely used regression technique. The main building block of a GP regression is the covariance kernel, which characterizes the relationship between pairs in the random field. The optimization to find the optimal kernel, however, requires several large-scale and often unstructured matrix inversions. We tackle this challenge by introducing a hierarchical matrix approach, named HMAT, which effectively decomposes the matrix structure, in a recursive manner, into significantly smaller matrices where a direct approach could be used for inversion. Our matrix partitioning uses a particular aggregation strategy for data points, which promotes the low-rank structure of off-diagonal blocks in the hierarchical kernel matrix. We employ a randomized linear algebra method for matrix reduction on the low-rank off-diagonal blocks without factorizing a large matrix. We provide analytical error and cost estimates for the inversion of the matrix, investigate them empirically with numerical computations, and demonstrate the application of our approach on three numerical examples involving GP regression for engineering problems and a large-scale real dataset. We provide the computer implementation of GP-HMAT, HMAT adapted for GP likelihood and derivative computations, and the implementation of the last numerical example on a real dataset. We demonstrate superior scalability of the HMAT approach compared to built-in operator in MATLAB for large-scale linear solves Ax=y via a repeatable and verifiable empirical study. An extension to hierarchical semiseparable (HSS) matrices is discussed as future research.

Developing data-driven applications requires developers and service providers to orchestrate data-to-discovery pipelines across distributed data sources and computing units. Realizing such pipelines poses two major challenges: programming analytics that reacts at runtime to unforeseen events, and adaptation of the resources and computing paths between the edge and the cloud. While these concerns are interdependent, they must be separated during the design process of the application and the deployment operations of the infrastructure. This work proposes a system stack for the adaptation of distributed analytics across the computing continuum. We implemented this software stack to evaluate its ability to continually balance the computation or data movement’s cost with the value of operations to the application objectives. Using a disaster response application, we observe that the system can select appropriate configurations while managing trade-offs between user-defined constraints, quality of results, and resource utilization. The evaluation shows that our model is able to adapt to variations in the data input size, bandwidth, and CPU capacities with minimal deadline violations (close to 10%). This constitutes encouraging results to benefit and facilitate the creation of ad-hoc computing paths for urgent science and time-critical decision-making.

In-situ processing alleviates the gap between computation and I/O capabilities by performing data analysis close to the data source. With simulation data varying in size and content during workflow execution, it becomes necessary for insitu processing to support resource elasticity, i.e., the ability to change resource configurations such as the number of computing nodes/processes during workflow execution. An elastic job may dynamically adjust resource configurations; it may use a few resources at the beginning and more resources towards the end of the job when interesting data appears. However, it is hard to predict a priori how many computing nodes/processes need to be added/removed during the workflow execution to adapt to changing workflow needs. How to efficiently guide elasticity operations, such as growing or shrinking the number of processes used for in-situ analysis during workflow execution, is an open-ended research question. In this paper, we present an adaptive elasticity policy that adopts workflow runtime information collected online to predict how to trigger the addition and removal of processes in order to minimize in-situ processing overheads. We integrate the presented elasticity policy into a staging-based elastic workflow and evaluate its efficiency in multiple elasticity scenarios. The results indicate that an adaptive elasticity policy can save overhead in finding a proper resource configuration, when compared with a static policy that uses a fixed number of processes for each rescaling operation. Finally, we discuss multiple existing research opportunities of elastic insitu processing from different aspects.

Data collected by large-scale instruments, observatories, and sensor networks are key enablers of scientific discoveries in many disciplines. However, ensuring that these data can be accessed, integrated, and analyzed in a democratized and timely manner remains a challenge. In this article, we explore how state-of-the-art techniques for data discovery and access can be adapted to facility data and develop a conceptual framework for intelligent data access and discovery.

We consider the Bayesian approach to the linear Gaussian inference problem of inferring the initial condition of a linear dynamical system from noisy output measurements taken after the initial time. In practical applications, the large dimension of the dynamical system state poses a computational obstacle to computing the exact posterior distribution. Model reduction offers a variety of computational tools that seek to reduce this computational burden. In particular, balanced truncation is a system-theoretic approach to model reduction which obtains an efficient reduced-dimension dynamical system by projecting the system operators onto state directions which trade off the reachability and observability of state directions as expressed through the associated Gramians. We introduce Gramian definitions relevant to the inference setting and propose a balanced truncation approach based on these inference Gramians that yield a reduced dynamical system that can be used to cheaply approximate the posterior mean and covariance. Our definitions exploit natural connections between (i) the reachability Gramian and the prior covariance and (ii) the observability Gramian and the Fisher information. The resulting reduced model then inherits stability properties and error bounds from system theoretic considerations, and in some settings yields an optimal posterior covariance approximation. Numerical demonstrations on two benchmark problems in model reduction show that our method can yield near-optimal posterior covariance approximations with order-of-magnitude state dimension reduction.

The choice of the time step for the Material Point Method (MPM) is often addressed by using a simple stability criterion, such as the speed of sound or a CFL condition. Recently there have been several advances in understanding the stability of MPM. These range from non-linear stability analysis, through to Von Neumann type approaches. While in many instances this works well it is important to understand how this relates to the overall errors present in the method. Although it has been observed that spatial errors may dominate temporal ones at stable time steps, recent work has made more precise the sources and forms of the different MPM errors. This now makes it possible to understand how the different errors and the stability analysis are connected. At the same time this also requires simple computable estimates of the different errors in the material point method. The use of simple estimates of these errors makes it possible to connect some of the errors introduced with the stability criteria used. A number of simple computational experiments are used to illustrate the theoretical results.

The paper gives an overview of Material Point Method and shows its evolution over the last 25 years. The Material Point Method developments followed a logical order. The article aims at identifying this order and show not only the current state of the art, but explain the drivers behind the developments and identify what is currently still missing.The paper explores modern implementations of both explicit and implicit Material Point Method. It concentrates mainly on uses of the method in engineering, but also gives a short overview of Material Point Method application in computer graphics and animation. Furthermore, the article gives overview of errors in the material point method algorithms, as well as identify gaps in knowledge, filling which would hopefully lead to a much more efficient and accurate Material Point Method. The paper also briefly discusses algorithms related to contact and boundaries, coupling the Material Point Method with other numerical methods and modeling of fractures. It also gives an overview of modeling of multi-phase continua with Material Point Method. The paper closes with numerical examples, aiming at showing the capabilities of Material Point Method in advanced simulations. Those include landslide modeling, multiphysics simulation of shaped charge explosion and simulations of granular material flow out of a silo undergoing changes from continuous to discontinuous and back to continuous behavior.The paper uniquely illustrates many of the developments not only with figures but also with videos, giving the whole extend of simulation instead of just a timestamped image

The paper gives an overview of Material Point Method and shows its evolution over the last 25 years. The Material Point Method developments followed a logical order. The article aims at identifying this order and show not only the current state of the art, but explain the drivers behind the developments and identify what is currently still missing.The paper explores modern implementations of both explicit and implicit Material Point Method. It concentrates mainly on uses of the method in engineering, but also gives a short overview of Material Point Method application in computer graphics and animation. Furthermore, the article gives overview of errors in the material point method algorithms, as well as identify gaps in knowledge, filling which would hopefully lead to a much more efficient and accurate Material Point Method. The paper also briefly discusses algorithms related to contact and boundaries, coupling the Material Point Method with other numerical methods and modeling of fractures. It also gives an overview of modeling of multi-phase continua with Material Point Method. The paper closes with numerical examples, aiming at showing the capabilities of Material Point Method in advanced simulations. Those include landslide modeling, multiphysics simulation of shaped charge explosion and simulations of granular material flow out of a silo undergoing changes from continuous to discontinuous and back to continuous behavior.The paper uniquely illustrates many of the developments not only with figures but also with videos, giving the whole extend of simulation instead of just a timestamped image

In this work, we present a reinforcement learning (RL) based approach to designing parallel prefix circuits such as adders or priority encoders that are fundamental to high-performance digital design. Unlike prior methods, our approach designs solutions tabula rasa purely through learning with synthesis in the loop. We design a grid-based state-action representation and an RL environment for constructing legal prefix circuits. Deep Convolutional RL agents trained on this environment produce prefix adder circuits that Pareto-dominate existing baselines with up to 16.0% and 30.2% lower area for the same delay in the 32b and 64b settings respectively. We observe that agents trained with open-source synthesis tools and cell library can design adder circuits that achieve lower area and delay than commercial tool adders in an industrial cell library.

The complexity of heterogeneous nodes near and at exascale has increased the need for “heroic” programming efforts. To accommodate this complexity, significant investment is required for codes not yet optimizing for low-level architecture features (e.g., wide vector units) and/or running at large-scale. This paper describes ongoing efforts to combine two codes, Hedgehog and Uintah, lying at both extremes to ease programming efforts. The end goals of this effort are (1) to combine the two codes to make an asynchronous many-task runtime system specializing in both node-level and large-scale performance and (2) to further improve the accessibility of both with portable abstractions. A prototype adopting Hedgehog in Uintah and a prototype extending Hedgehog to support MPI+X hybrid parallelism are discussed. Results achieving ∼60% of NVIDIA V100 GPU peak performance for a distributed DGEMM problem are shown for a naive MPI+Hedgehog implementation before any attempt to optimize for performance.

Authors note: This is a refereed but unpublished report that was
submitted to, reviewed for and accepted in revised form for a presentation of the same material at the Hipar Workshop at Supercomputing 21

Deep Learning has shifted the focus of traditional batch workflows to data-driven feature engineering on streaming data. In particular, the execution of Deep Learning workflows presents expectations of near-real-time results with user-defined acceptable accuracy. Meeting the objectives of such applications across heterogeneous resources located at the edge of the network, the core, and in-between requires managing trade-offs between the accuracy and the urgency of the results. However, current data analysis rarely manages the entire Deep Learning pipeline along the data path, making it complex for developers to implement strategies in real-world deployments. Driven by an object detection use case, this paper presents an architecture for time-critical Deep Learning workflows by providing a data-driven scheduling approach to distribute the pipeline across Edge to Cloud resources. Furthermore, it adopts a data management strategy that reduces the resolution of incoming data when potential trade-off optimizations are available. We illustrate the system's viability through a performance evaluation of the object detection use case on the Grid'5000 testbed. We demonstrate that in a multiuser scenario, with a standard frame rate of 25 frames per second, the system speed-up data analysis up to 54.4% compared to a Cloud-only-based scenario with an analysis accuracy higher than a fixed threshold.