Programming and Performance Visualization Tools
Explore the source record for details and available documents.
SEARCH · Search NASA
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.
Explore the source record for details and available documents.
In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer paral- lelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation.
Compiling quantum algorithms for near-term quantum computers (accounting for connectivity and native gate alphabets) is a major challenge that has received significant attention both by industry and academia. Avoiding the exponential overhead of classical simulation of quantum dynamics will allow compilation of larger algorithms, and a strategy for this is to evaluate an algorithm's cost on a quantum computer. To this end, we propose a variational hybrid quantum-classical algorithm called quantum-assisted quantum compiling (QAQC). In QAQC, we use the overlap between a target unitary U and a trainable unitary V as the cost function to be evaluated on the quantum computer. More precisely, to ensure that QAQC scales well with problem size, our cost involves not only the global overlap T r ( V † U ) but also the local overlaps with respect to individual qubits. We introduce novel short-depth quantum circuits to quantify the terms in our cost function, and we prove that our cost cannot be efficiently approximated with a classical algorithm under reasonable complexity assumptions. We present both gradient-free and gradient-based approaches to minimizing this cost. As a demonstration of QAQC, we compile various one-qubit gates on IBM's and Rigetti's quantum computers into their respective native gate alphabets. Furthermore, we successfully simulate QAQC up to a problem size of 9 qubits, and these simulations highlight both the scalability of our cost function as well as the noise resilience of QAQC. Future applications of QAQC include algorithm depth compression, black-box compiling, noise mitigation, and benchmarking.
Current trends point to a future where large-scale scientific applications are tightly coupled high-performance computing/artificial intelligence (HPC/AI) hybrids. Hence, we urgently need to invest in creating a seamless, scalable framework where HPC and AI/machine learning can efficiently work together and adapt to novel hardware and vendor libraries without starting from scratch every few years. Finally, the current ecosystem and sparsely connected community are not sufficient to tackle these challenges, and we require a breakthrough catalyst for science similar to what PyTorch enabled for AI.
Scaling up new scientific technologies from laboratory to industry often involves demonstrating performance on a larger scale. Computer simulations can accelerate design and predictions in the deployment process, though traditional numerical methods are computationally intractable even for intermediate pilot plant scales. Recently, the component reduced order modeling method has been developed to tackle this challenge by combining projection reduced order modeling and discontinuous Galerkin domain decomposition. However, while many scientific or engineering applications involve nonlinear physics, this method has only been demonstrated for various linear systems. In this work, the component reduced order modeling method is extended to steady Navier–Stokes flow, with application to general nonlinear physics in view. The large‐scale, global domain is decomposed into a combination of small‐scale unit component. Linear subspaces for flow velocity and pressure are identified via proper orthogonal decomposition over sample snapshots collected from each small‐scale unit component. Velocity bases are augmented with a pressure supremizer to satisfy the inf–sup condition for stable pressure prediction. Two different nonlinear reduced order modeling methods are employed and compared for efficient evaluation of nonlinear advection: A third‐order tensor projection operator and the empirical quadrature procedure. The proposed method is demonstrated on the flow over arrays of five different unit objects, achieving a 23‐fold speedup with less than 4% relative error in domains up to 256 times larger than the unit components. Furthermore, a numerical experiment with the pressure supremizer strongly indicates the need for a supremizer for stable pressure prediction. A comparison between the tensorial approach and the empirical quadrature procedure revealed a slight advantage of the empirical quadrature procedure. The framework is compared with an alternating Schwarz‐based reduced‐order approach, demonstrating improved efficiency and robustness for the DG‐based global solver while retaining flexibility for sub‐scale iterative solvers. The method is further extended to a coupled advection–diffusion and Navier–Stokes system, illustrating its applicability to multi‐physics problems and its potential for more general, inter‐coupled nonlinear systems.
Many popular vetting tools for Android applications use static code analysis techniques. In particular, Interprocedural Data-Flow Graph (IDFG) construction is the computation at the core of Android static data-flow analysis and consumes most of the analysis time. Many analysis tools use a worklist algorithm, an iterative fixed-point approach, to construct the IDFG. In this paper, we observe that a straightforward GPU parallelization of the worklist algorithm leads to significant underutilization of the GPU resources. We identify four performance bottlenecks, namely, frequent dynamic memory allocations, high branch divergence, workload imbalance, and irregular memory access patterns. Accordingly, we propose GDroid, a GPU-based worklist algorithm implementation with multiple fine-grained optimizations tailored to common characteristics of Android applications. The optimizations considered are: matrix-based data structure, memory access-based node grouping, and worklist merging. Our experimental evaluation, performed on 1000 Android applications, shows that the proposed optimizations are beneficial to performance, and GDroid can achieve up to 128X speedups against a plain GPU implementation.
High-throughput omics technologies such as DNA sequencing have made the sequencing and computational assembly of microbial genomes recovered from the environment relatively routine. Computational inference of the protein products encoded by these genomes, and the associated biochemical functions, should enable the accurate prediction and modeling of microbial metabolism, organismal interactions, and ecosystem processes. However, a lack of scalable, probabilistic protein annotation tools limits the full potential of modeling for understanding the metabolism and biogeochemical cycles of microbial communities. Our approach to improve inference of protein annotations and metabolic models relied on learning from and emulating expert manual curation, leveraging software engineering and data science best practices to scale up the throughput and accuracy of annotations and metabolic model construction, building software to objectively evaluate different annotation strategies, and more closely linking the protein annotation and metabolic model inference process. Outcomes of this research include several improved or new computational tools, including DRAM (Distilled and Refined Annotation of Metabolism) for annotating microbial genomes with protein function and metabolic traits, CAMPER (Curated Annotations for Microbial Polyphenol Enzymes and Reactions) for annotating key polyphenol metabolisms, EC-Bench for comprehensive and unbiased benchmarking of annotation tools, and several apps available via the DOE Systems Biology Knowledgebase (KBase) for building genome-scale metabolic models. We demonstrate that these tools allow us to scalably annotate and understand thousands of genomes for microbial communities from a variety of systems and test cases, including rivers, thawing permafrost, and gut microbiomes. All of these computational tools are available as open-source software, with most broadly and easily accessible to the scientific community via KBase apps.
Scientific and enterprise data centers, IT equipment product development, and research data center laboratories typically require continuous cooling to control inlet air temperatures within recommended operating levels for the IT equipment. The consolidation and higher density aggregation of slim computing, storage and networking hardware has resulted in higher power density than what the raised-floor system design, coupled with commonly used computer rack air conditioning (CRAC) units, was originally conceived to handle. Many existing data centers and newly constructed data centers adopt CRAC units, which inherently handle heat transfer within data centers via air as the heat transfer media. This results in energy performance of the ventilation and cooling systems being less than optimal. Understanding the current trends toward higher power density in IT computing, more and more IT equipment manufacturers are designing their equipment to operate in 'conventional' data center environments, while considering provisions of alternative cooling solutions to either their equipment or supplemental cooling in rack or row systems. Naturally, the trend toward higher power density resulting from current and future generations of servers has, in the meanwhile, created significant opportunities for precision cooling suppliers to engineer and manufacture packaged modular and scalable systems. The modular and scalable cooling systems aim at significantly improving efficiency while addressing the thermal challenges, improving reliability, and allowing for future needs and growth. Such pre-engineered and manufactured systems may be a significant improvement over current design; however, without an energy efficiency focus, their applications could also lead to even lower energy efficiencies in the overall data center infrastructure. The overall goal of the project supported by California Energy Commission was to characterize four commercially available, modular cooling systems installed in a data center. Such modular cooling systems are all scalable localized units, and will be evaluated in terms of their operating energy efficiency in a real data center, respectively, as compared to the energy efficiency of traditional legacy data center cooling systems. The technical objective of this project was to evaluate the energy performance of one of the four commercially available modular cooling systems installed in a data center in Sun Microsystems, Inc. This report is the result of a test plan that was developed with the industrial participants input, including specific design and operating characteristics of the selected modular localized cooling solution provided by vendor 2. The technical evaluation included monitoring and measurement of selected parameters, and establishing and calculating energy efficiency metrics for the selected cooling product, which is a modular, scalable pair of chilled water cooling modules that were tested in a hot/cold aisle environment with hot aisle containment. The scope of this report is to quantify energy performance of the modular cooling unit in operation as it corresponds to a combination of varied server loads and inlet air temperatures. The information generated from this testing when combined with a concurrent research study to document the energy efficiency of the host data center's central chilled water cooling plant can be used to estimate potential energy savings from implementing modular cooling compared to conventional cooling in data centers.
We have developed the first, holistic, Adaptive Mesh Refinement (AMR) capable, in situ query framework to ensure the tractability of the current- and next-generation AMR simulation analysis on the path to extreme scale. We have addressed key issues pertaining to in situ analysis, memory hierarchy, generalized parallel indexing, index-compression, and real-time access pattern detection. We have published the following research papers in high profile peer reviewed computer science conferences: (a) Parallel In Situ Detection of Connected Components in Adaptive Mesh Refinement Data; (b) AMR-aware In Situ Indexing and Scalable Querying; (c) Pattern-driven dynamic data layout optimization; (d) In situ Storage Layout Optimization for AMR Spatio-temporal Read Accesses; (e) AMRZone: A Runtime AMR Data Sharing Framework for Scientific Applications; (f) Exploring Memory Hierarchy and Network Topology for Runtime AMR Data Sharing Across Scientific Applications.
Execution of heterogeneous workflows on high-performance computing (HPC) platforms present unprecedented resource management and execution coordination challenges for runtime systems. Task heterogeneity increases the complexity of resource and execution management, limiting the scalability and efficiency of workflow execution. Re-source partitioning and distribution of tasks execution over portioned re-sources promises to address those problems but we lack an experimental evaluation of its performance at scale. Here this paper provides a performance evaluation of the Process Management Interface for Exascale (PMIx) and its reference implementation PRRTE on the leadership-class HPC plat-form Summit, when integrated into a pilot-based runtime system called RADICAL-Pilot. We partition resources across multiple PRRTE Distributed Virtual Machine (DVM) environments, responsible for launching tasks via the PMIx interface. We experimentally measure the work-load execution performance in terms of task scheduling/launching rate and distribution of DVM task placement times, DVM startup and termination overheads on the Summit leadership-class HPC platform. Integrated solution with PMIx/PRRTE enables using an abstracted, standardized set of interfaces for orchestrating the launch process, dynamic process management and monitoring capabilities. It extends scaling capabilities allowing to overcome a limitation of other launching mechanisms (e.g., JSM/LSF). Explored different DVM setup configurations provide insights on DVM performance and a layout to leverage it. Our experimental results show that heterogeneous workload of 65,500 tasks on 2048 nodes, and partitioned across 32 DVMs, runs steady with resource utilization not lower than 52%. While having less concurrently executed tasks resource utilization is able to reach up to 85%, based on results of heterogeneous workload of 8200 tasks on 256 nodes and 2 DVMs.
With the rise of general purpose computing on graphics processing units (GPGPU), the influence from consumer markets can now be seen across the spectrum of computer architectures. In fact, many of the high-ranking Top500 HPC systems now include these accelerators. Traditionally, GPUs have connected to the CPU via the PCIe bus, which has proved to be a significant bottleneck for scalable scientific applications. Now, a trend toward tighter integration between CPU and GPU has removed this bottleneck and unified the memory hierarchy for both CPU and GPU cores. We examine the impact of this trend for high performance scientific computing by investigating AMD's new Fusion Accelerated Processing Unit (APU) as a testbed. In particular, we evaluate the tradeoffs in performance, power consumption, and programmability when comparing this unified memory hierarchy with similar, but discrete GPUs.
Graded lattice structures, characterized by smoothly varying mechanical properties, hold significant promise for optimizing material distribution in advanced engineering applications. However, accurately modeling these structures poses substantial computational challenges due to the continuous geometric variations within their unit cells. Here, to address these challenges, this paper introduces a novel Efficient Reduced Order Model (EROM) that integrates the Matrix Discrete Empirical Interpolation Method (MDEIM) and Discrete Empirical Interpolation Method (DEIM) with polynomial regression to efficiently manage geometric parametrization in lattice structures. Unlike traditional reduced order models (ROMs) that require extensive precomputed libraries for each geometric configuration, our approach enables continuous geometric variations through a flexible algebraic formulation, significantly reducing computational costs while preserving high accuracy. The method constructs projection matrices for individual unit cells that can be efficiently assembled into global systems, leveraging the repetitive nature of lattice structures. Numerical studies demonstrate that our EROM achieves displacement errors below 1% and von Mises stress prediction errors below 4%, coupled with computational speedups exceeding two orders of magnitude compared to full-order simulations. The proposed method's modularity and scalability make it particularly suitable for design optimization and real-time simulation of functionally graded lattice structures, with applications spanning aerospace to biomedical engineering.
Plasma-based acceleration (PBA) has emerged as a promising candidate for the accelerator technology used to build a future linear collider and/or an advanced light source. In PBA, a trailing or witness particle beam is accelerated in the plasma wave wakefield (WF) created by a laser or particle beam driver. The WF is often nonlinear and involves the crossing of plasma particle trajectories in real space and thus particle-in-cell methods are used. The distance over which the drive beam evolves is several orders of magnitude larger than the wake wavelength. This large disparity in length scales is amenable to the quasi-static approach. Three-dimensional (3D), quasi-static (QS), particle-in-cell (PIC) codes, e.g., QuickPIC, have been shown to provide high fidelity simulation capability with 2-4 orders of magnitude speedup over 3D fully explicit PIC codes. In PBA, the witness beam needs to be matched to the focusing forces of the WF to reduce the emittance growth. In some linear collider designs, the matched spot size of the witness beam can be 2 to 3 orders of magnitude smaller than the spot size (and wavelength) of the wakefield. Such an additional disparity in length scales is ideal for mesh refinement where the WF within the witness beam is described on a finer mesh than the rest of the WF. A mesh refinement scheme is described that has been implemented into the 3D QS PIC code, QuickPIC. Very fine (high) resolution is used in a small spatial region that includes the witness beam and progressively coarser resolutions in the rest of the simulation domain. A fast multigrid Poisson solver has been implemented for the field solve on the refined meshes and a Fast Fourier Transform (FFT) based Poisson solver is used for the coarse mesh. The code has been parallelized with both MPI and OpenMP, and the parallel scalability has also been improved by using pipelining. A preliminary adaptive mesh refinement technique is described to optimize the computational time for simulations with an evolving witness beam size. Several test problems are used to verify that the mesh refinement algorithm provides accurate results. Additionally, the results are benchmarked against highly resolved simulations exhibiting near-azimuthal symmetry, performed using QPAD—a novel hybrid QS PIC code that uses a PIC description in the coordinates (r, ct – z) and a gridless description in the azimuthal angle, Φ.
Computational modeling of the excited states of molecular aggregates faces significant computational challenges and size heterogeneity. Current machine learning (ML) models, typically trained on specific-sized aggregates, struggle with scalability. We found that the exciton model Hamiltonian of large aggregates can be decomposed into dimer pairs, allowing an ML model trained on dimers to reconstruct Hamiltonians for aggregates of any size. We also proposed a new method to address the phase-correction problem by introducing coupling terms’ approximations. Our model accurately predicted the excitation energies of the trimer and tetramer of perylene and tetracene and estimated S1 oscillator strengths of perylene aggregates. Leveraging our ML model, the optical gaps of nanosized perylene aggregates with up to 50 monomers are analyzed, qualitatively revealing the role of different couplings on their size dependency. Future work will explore transferability across different monomers to predict optical properties in heterogeneous assemblies.
Deep neural network (DNN) potentials are an emerging tool for simulation of dynamical atomistic systems, with the promise of quantum mechanical accuracy at speedups of 10000$\times$. As with other DNN methods, hyperparameters used during training can make a substantial difference in model accuracy, and optimal settings vary with dataset. To enable rapid tuning of hyperparameters for DNN potential training, we developed a scalable multiobjective optimization evolutionary algorithm for supercomputers and tested it on the Summit system at the Oak Ridge Leadership Computing Facility (OLCF). The multiobjective approach is required due to the coupling of two learned values defining the potential: the energy and force. Using a large-scale implementation of the NSGA-II algorithm adapted for training DNN potentials, we discovered several optimal multiobjective combinations, including best choices of activation functions, learning rate scaling scheme, and pairing of the two radial cutoffs used in the three dimensional descriptor function.
Agentic Retrieval-Augmented Code Synthesis with Iterative RefinementIn supercomputing, efficient and optimized code generation is essential to leverage high-performance systems effectively. We have developed Agentic Retrieval-Augmented Code Synthesis (ARCS), an advanced framework for accurate, robust, and efficient code generation, completion, and translation. ARCS integrates Retrieval-Augmented Generation (RAG) with Chain-of-Thought (CoT) reasoning to systematically break down and iteratively refine complex programming tasks. An agent-based RAG mechanism retrieves relevant code snippets, while real-time execution feedback drives the synthesis of candidate solutions. This process is formalized as a state-action search tree optimization, balancing code correctness with editing efficiency. Evaluations on the Geeks4Geeks and HumanEval benchmarks demonstrate that ARCS significantly outperforms traditional prompting methods in translation and generation quality. By enabling scalable and precise code synthesis, ARCS offers transformative potential for automating and optimizing code development in supercomputing applications, enhancing computational resource utilization
This report documents the Resilience Enhancements through Deep Learning Yields (REDLY) project, a three-year effort to improve electrical grid resilience by developing scalable methods for system operators to protect the grid against threats leading to interrupted service or physical damage. The computational complexity and uncertain nature of current real-world contingency analysis presents significant barriers to automated, real-time monitoring. While there has been a significant push to explore the use of accurate, high-performance machine learning (ML) model surrogates to address this gap, their reliability is unclear when deployed in high-consequence applications such as power grid systems. Contemporary optimization techniques used to validate surrogate performance can exploit ML model prediction errors, which necessitates the verification of worst-case performance for the models.
The present report summarizes activities performed over the 3-year (plus one year of NCE) duration of the award DE-SC0022283, “Scalable Data Reduction Techniques for Extreme-Scale Unstructured PDE Simulations,” funded by the DOE Office of Advanced Scientific Computing Research (ASCR).