Search NASA⌕ Search

SEARCH · Search NASA

Results for “HPC performance modeling”

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 631 records · Page 35

CASL Enterprise Project Management (EPM) Tool, a Unified PM Platform

The Consortium for Advanced Simulation of Light Water Reactors (CASL) applies existing modeling and simulation (M&S) capabilities and develops advanced capabilities to create a usable environment for predictive simulation of light water reactors (LWRs). This environment, designated the Virtual Environment for Reactor Applications (VERA), incorporates science based models, state of the art numerical methods, multi physics integrated solutions, modern computational science and engineering practices, and uncertainty quantification (UQ). Ongoing validation of VERA relies upon data from operating pressurized water reactors (PWRs), single effect experiments, and integral tests. VERA will be designed for implementation on current desktop computers, capacity platforms (e.g., clusters), and the engineering workstations of the future. Selected components will also be capable of executing on current U.S. Department of Energy (DOE) capability and leadership class high performance computer (HPC) systems.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applications

Run to run variability in parallel programs caused by floating-point non-associativity has been known to significantly affect reproducibility in iterative algorithms, due to accumulating errors. Non-reproducibility can critically affect the efficiency and effectiveness of correctness testing for stochastic programs. Recently, the sensitivity of deep learning training and inference pipelines to floating-point non-associativity has been found to sometimes be extreme. It can prevent certification for commercial applications, accurate assessment of robustness and sensitivity, and bug detection. New approaches in scientific computing applications have coupled deep learning models with high-performance computing, leading to an aggravation of debugging and testing challenges. Here we perform an investigation of the statistical properties of floating-point non-associativity within modern parallel programming models, and analyze performance and productivity impacts of replacing atomic operations with deterministic alternatives on GPUs. We examine the recently-added deterministic options in PyTorch within the context of GPU deployment for deep learning, uncovering and quantifying the impacts of input parameters triggering run to run variability and reporting on the reliability and completeness of the documentation. Finally, we evaluate the strategy of exploiting automatic determinism that could be provided by deterministic hardware, using the Groq LPUTM accelerator for inference portions of the deep learning pipeline. We demonstrate the benefits that a hardware-based strategy can provide within reproducibility and correctness efforts.

Shanmugavelu, Sanjif↗

Automatic Thread-Level Parallelization in the Chombo AMR Library

The increasing on-chip parallelism has some substantial implications for HPC applications. Currently, hybrid programming models (typically MPI+OpenMP) are employed for mapping software to the hardware in order to leverage the hardware?s architectural features. In this paper, we present an approach that automatically introduces thread level parallelism into Chombo, a parallel adaptive mesh refinement framework for finite difference type PDE solvers. In Chombo, core algorithms are specified in the ChomboFortran, a macro language extension to F77 that is part of the Chombo framework. This domain-specific language forms an already used target language for an automatic migration of the large number of existing algorithms into a hybrid MPI+OpenMP implementation. It also provides access to the auto-tuning methodology that enables tuning certain aspects of an algorithm to hardware characteristics. Performance measurements are presented for a few of the most relevant kernels with respect to a specific application benchmark using this technique as well as benchmark results for the entire application. The kernel benchmarks show that, using auto-tuning, up to a factor of 11 in performance was gained with 4 threads with respect to the serial reference implementation.

97 MATHEMATICS AND COMPUTING↗

Modernization and optimization of a legacy open-source CFD code for high-performance computing architectures

Legacy codes remain a crucial element of today's simulation-based engineering ecosystem due to the extensive validation process and investment in such software. The rapid evolution of high-performance computing architectures necessitates the modernization of these codes. One approach to modernization is a complete overhaul of the code. However, this could require extensive investments, such as rewriting in modern languages, new data constructs, etc., which will necessitate systematic verification and validation to re-establish the credibility of the computational models. The current study advocates using a more incremental approach and is a culmination of several modernization efforts of the legacy code MFIX, which is an open-source computational fluid dynamics code that has evolved over several decades, widely used in multiphase flows and still being developed by the National Energy Technology Laboratory. Two different modernization approaches,‘bottom-up’ and ‘top-down’, are illustrated. Here, preliminary results show up to 8.5x improvement at the selected kernel level with the first approach, and up to 50% improvement in total simulated time with the latter were achieved for the demonstration cases and target HPC systems employed.

97 MATHEMATICS AND COMPUTING↗

Performance and energy impact of OpenMP runtime configurations on power constrained systems

Energy consumption of an application has attained the same vitality as execution time in current HPC systems, primarily due to the massive energy consumption of these systems and consequently substantial energy bills. This fact forced software developers as well as hardware vendors to put an extensive focus on energy consumption. This focus becomes even more crucial in power constrained systems, where the amount of power dedicated to applications is limited. In such systems, finding the optimal balance between execution time and energy consumption has a significant impact on utilizing these systems efficiently. A programming model is a necessary layer where optimizations can be applied to find the optimal balance. OpenMP is a standard programming model for intra-node parallelism. In this paper, we give a detailed analysis of how to optimize the execution time and energy consumption of an OpenMP application using the OpenMP runtime environment at different power levels. We studied twenty-eight OpenMP parallel regions from five NAS Parallel Benchmark (NPB) applications. Based on the study, we show that for a given power level, a suitable selection of OpenMP runtime parameters can improve the execution time and energy consumption of a parallel region up to 67% and 72%, respectively. We also show that these fine-grained improvements resulted in up to 26% of execution time and 38% of energy consumption improvement for a given OpenMP application. We finally observed that optimizing the energy consumption behavior alone across all power levels regardless of execution time behavior can lead to an additional energy consumption improvement of up to 55%. However, this improvement comes at the expense of execution time.

97 MATHEMATICS AND COMPUTING↗

DeepFreeze: Towards Scalable Asynchronous Checkpointing of Deep Learning Models

In the age of big data, deep learning has emerged as a powerful tool to extract insight and exploit its value, both in industry and scientific applications. One common pattern emerging in such applications is frequent checkpointing of the state of the learning model during training, needed in a variety of scenarios: analysis of intermediate states to explain features and correlations with training data, exploration strategies involving alternative models that share a common ancestor, knowledge transfer, resilience, etc. However, with increasing size of the learning models and popularity of distributed data-parallel training approaches, simple checkpointing techniques used so far face several limitations: low serialization performance, blocking I/O, stragglers due to the fact that only a single process is involved in checkpointing. This paper proposes a checkpointing technique specifically designed to address the aforementioned limitations, introducing efficient asynchronous techniques to hide the overhead of serialization and I/O, and distribute the load over all participating processes. Experiments with two deep learning applications (CANDLE and ResNet) on a pre-Exascale HPC platform (Theta) shows significant improvement over state-of-art, both in terms of checkpointing duration and runtime overhead.

checkpointing↗

Performance Models for Data Transfers: A Case Study with Molecular Chemistry Kernels

In distributed memory systems, it is paramount to develop strategies to overlap the data transfers between memory nodes with the computations in order to exploit the full potential of these systems. In this paper, we consider the problem of determining the order of data transfers between two memory nodes for a set of independent tasks with the objective of minimizing the makespan. We prove that, with limited memory capacity, the problem of obtaining the optimal order of data transfers is NP-complete. We propose several heuristics to determine this order and discuss the conditions that might be favorable to different heuristics. We analyze our heuristics on traces obtained by running 2 molecular chemistry kernels, namely, Hartree–Fock (HF) and Coupled Cluster Single Double (CCSD) on 10 nodes of an HPC system. Our results show that some of our heuristics achieve significant overlap for moderate memory capacities and resulting in makespans that are very close to the lower bound.

Kumar, Suraj↗

Recent developments in DYNSUB: New models, code optimization and parallelization

DYNSUB is a high-fidelity coupled code system consisting of the reactor simulator DYN3D and the sub-channel code SUBCHANFLOW. It describes nuclear reactor core behavior with pin-by-pin resolution for both steady-state and transient scenarios. In the course of the coupled code system's active development, super-homogenization (SPH) and generalized equivalence theory (GET) discontinuity factors may be computed with and employed in DYNSUB to compensate pin level homogenization errors. Because of the largely increased numerical problem size for pin-by-pin simulations, DYNSUB has bene fitted from HPC techniques to improve its numerical performance. DYNSUB's coupling scheme has been structurally revised. Computational bottlenecks have been identified and parallelized for shared memory systems using OpenMP. Comparing the elapsed time for simulating a PWR core with one-eighth symmetry under hot zero power conditions applying the original and the optimized DYNSUB using 8 cores, overall speed up factors greater than 10 have been observed. The corresponding reduction in execution time enables a routine application of DYNSUB to study pin level safety parameters for engineering sized cases in a scientific environment. (authors)

97 MATHEMATICS AND COMPUTING↗

ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing

The next generation HPC and data centers are likely to be reconfigurable and data-centric due to the trend of hardware specialization and the emergence of data-driven applications. In this work, we propose ARENA – an asynchronous reconfigurable accelerator ring architecture as a potential scenario on how the future HPC and data centers will be like. Despite using the coarse-grained reconfigurable arrays (CGRAs) as the substrate platform, our key contribution is not only the CGRA-cluster design itself, but also the ensemble of a new architecture and programming model that enables asynchronous tasking across a cluster of reconfigurable nodes, so as to bring specialized computation to the data rather than the reverse. We presume distributed data storage without asserting any prior knowledge on the data distribution. Hardware specialization occurs at runtime when a task finds the majority of data it requires are available at the present node. In other words, we dynamically generate specialized CGRA accelerators where the data reside. The asynchronous tasking for bringing computation to data is achieved by circulating the task token, which describes the dataflow graphs to be executed for a task, among the CGRA cluster connected by a fast ring network. Evaluations on a set of HPC and data-driven applications across different domains show that ARENA can provide better parallel scalability with reduced data movement (53.9 percent). Compared with contemporary compute-centric parallel models, ARENA can bring on average 4.37× speedup. The synthesized CGRAs and their task-dispatchers only occupy 2.93mm 2 chip area under 45nm process technology and can run at 800MHz with on average 759.8mW power consumption. ARENA also supports the concurrent execution of multi-applications, offering ideal architectural support for future high-performance parallel computing and data analytics systems.

97 MATHEMATICS AND COMPUTING↗

Direct numerical simulations of turbulent reacting flows with shock waves and stiff chemistry using many-core/GPU acceleration

Compressible reacting flows may display sharp spatial variation related to shocks, contact discontinuities or reactive zones embedded within relatively smooth regions. The presence of such phenomena emphasizes the relevance of shock-capturing schemes such as the weighted essentially non-oscillatory (WENO) scheme as an essential ingredient of the numerical solver. However, these schemes are complex and have more computational cost than the simple high-order compact or non-compact schemes. In this paper, we present the implementation of a seventh-order, minimally-dissipative mapped WENO (WENO7M) scheme in a newly developed direct numerical simulation (DNS) code called KAUST Adaptive Reactive Flows Solver (KARFS). In order to make efficient use of the computer resources and reduce the solution time, without compromising the resolution requirement, the WENO routines are accelerated via graphics processing unit (GPU) computation. The performance characteristics and scalability of the code are studied using different grid sizes and block decomposition. Furthermore, the performance portability of KARFS is demonstrated on a variety of architectures including NVIDIA Tesla P100 GPUs and NVIDIA Kepler K20X GPUs. In addition, the capability and potential of the newly implemented WENO7M scheme in KARFS to perform DNS of compressible flows is also demonstrated with model problems involving shocks, isotropic turbulence, detonations and flame propagation into a stratified mixture with complex chemical kinetics.

97 MATHEMATICS AND COMPUTING↗

Scalability Analysis of Quantum Models for Stress and Emotion Detection

Stress and emotion detection from high-dimensional physiological signals is a challenging task, particularly when aiming for accurate classification across diverse behavioral states. Quantum machine learning (QML) is promising for modeling such high-dimensional data, but scalability is limited by qubit resources and the exponential cost of classical statevector simulation. This work studies the scalability of quantum support vector machines (QSVMs) for binary stress detection and three-class emotion recognition (Negative/Neutral/Positive) under varying qubit counts and angle-encoding strategies. We also present a comparison study with one-feature-per-qubit (1:1) and two-features-per-qubit (2:1) mappings. Experiments are executed on HPC infrastructure using NVIDIA CUDA-Q to evaluate performance, variance, and class-dependent separability at higher-qubit setups. Results show that larger Hilbert spaces can improve peak accuracy but may increase instability. At the same time, dense 2:1 encoding yields more consistent stress detection performance. For emotion recognition, scaling improves discrimination for classes like Negative and Positive more than Neutral. We find that effective QML scaling is task-dependent and benefits more from encoding design than simply increasing qubit count.

Onim, Md. Saif Hassan [University of Tennessee, Kn↗

Improving Gas Reactor Design with Complex Non-Standard Reaction Mechanisms in a Reactive Flow Model

Fluorinated gases are critical to a number of high-technology industries including semiconductor manufacturing and related processes such as flat panel display, LED, and photovoltaic manufacturing. These fluorinated gases have very high global warming potentials (GWPs) and, unfortunately are chemically very stable, in some cases lasting for thousands of years in the atmosphere. For environmental reasons, it is imperative that the release of these gases be minimized, but existing methods to destroy them requires a significant amount of energy. The goal of this project was to develop a more energy efficient method of destroying these high GWP gases using computational fluid dynamics, but the computational requirements are significant. In this project, we bring together resources available at the national labs, including high-performance computing hardware and modern computational methods, in order to explore an industrially important problem with key environmental and economic impact. In this project, we examined the state-of-the-art models for the physical processes involved, and made subtle changes to arrive at alternative formulations considerably better suited for computation and study. We examined several representative scenarios and developed a set of analyses techniques and tools that could be used to explore the systems in much greater detail. This exploratory project has demonstrated to ALZETA that HPC can indeed provide a unique view into their complex engineering problem - one that is simply inaccessible by any other means. The tools allow us to explore the details of the chemical process, and allow one to construct "what-if" scenarios to address shortcomings of the physical device in its current operating modes. However, as with many sources of completely new information, many new questions are illuminated with this capability. It will take considerable time, effort and experience before we learn to probe the solutions, pose operating scenarios and confirm modifications to the device that lead to real engineering advances.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Quantifying Message Aggregation Optimisations for Energy Savings in PGAS Models

Upon breaking past the exascale barrier, HPC systems are facing their greatest challenge yet - a power wall that must be addressed through new methods in both hardware and software. While energy costs are becoming a major issue at all levels, of particular concern is that of the network, as the relative cost of moving data is increasing faster than ever. The partitioned global address space (PGAS) model is critical within certain HPC domains, but is known to suffer from the small message problem, where irregular many-to-many access patterns result in congesting the network with excessive numbers of small messages. To address this, the conveyor aggregation library was developed to defer individual messages and group them for subsequent bulk processing. In this paper, we investigate its impact on energy use related to the network, with a focus on the Slingshot 11 interconnect. We will demonstrate that this strategy is not only highly performant, but also crucial to reducing energy footprints to remain within target power envelopes.

Welch, Aaron [ORNL]↗

OpenSHMEM Reference Implementation using UCCS-uGNI Transport Layer. In: PGAS '14 Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models, Article No. 18

OpenSHMEM is a library interface implementation and specification that enables the implementation of the Partitioned Global Address Space (PGAS) model. It exports modern RDMA network functionality and communication semantics to applications very efficiently. There are many closed source implementations of OpenSHMEM for modern RDMA interconnects such as InfiniBand and Cray's Gemini and Aries. Given the important role that Cray systems play in HPC, in this paper, we present an open source implementation of OpenSHMEM for Cray XE/XK/XC systems. To implement OpenSHMEM, we use the uGNI interface. uGNI is a generic interface that is designed for multiple programming models. The interface fits well the goal of UCCS. Having OpenSHMEM with UCCS-uGNI allows usage of the same implementation over multiple interconnects. This also translates into many advantages that come with common code such as resource sharing, increasing productivity because of less code maintenance, etc. Preliminary results show that OpenSHMEM-UCCS performs comparable to state-of-the-art Cray SHMEM for Put, Get, and AMO operations.

Janjusic, Tomislav↗

Investigating Operating System Noise in Extreme-Scale High-Performance Computing Systems using Simulation

Hardware/software co-design for future-generation high-performance computing (HPC) systems aims at closing the gap between the peak capabilities of the hardware and the performance realized by applications (application-architecture performance gap). Performance profiling of architectures and applications is a crucial part of this iterative process. The work in this paper focuses on operating system (OS) noise as an additional factor to be considered for co-design. It represents the first step in including OS noise in HPC hardware/software co-design by adding a noise injection feature to an existing simulation-based co-design toolkit. It reuses an existing abstraction for OS noise with frequency (periodic recurrence) and period (duration of each occurrence) to enhance the processor model of the Extreme-scale Simulator (xSim) with synchronized and random OS noise simulation. The results demonstrate this capability by evaluating the impact of OS noise on MPI_Bcast() and MPI_Reduce() in a simulated future-generation HPC system with 2,097,152 compute nodes.

Engelmann, Christian↗

Toward Energy-Efficient HPC: Insights from Power Profiling a Cloud-Resolving Earth System Model

Power is a fundamental constraint as supercomputing advances to exascale. Efficient operation within strict power budgets requires application-aware power management based on a detailed understanding of application-level power behavior. This work analyzes the Energy Exascale Earth System Model (E3SM) atmosphere component, SCREAM, on Perlmutter (NERSC) and Frontier (OLCF). We characterize power variation across inputs, concurrency levels, and power caps, evaluate the energy impact of code optimizations, and attribute energy within the code using a newly developed GPU energy model. Results show that SCREAM’s peak power remains stable during its core execution phase and decreases gradually as concurrency increases. Power capping experiments reveal a performance–energy "sweet spot". On Perlmutter, limiting GPU power to 50% of thermal design power (TDP) achieves up to 15% energy savings with a 7% performance penalty. On Frontier, a 40% TDP cap yields up to 10% energy savings with less than 10% performance loss. Code optimizations reduce SCREAM energy by shortening run time without increasing power. Modeling reveals a critical insight: data movement accounts for approximately 70% of SCREAM’s GPU energy. This fundamentally shifts the optimization focus from FLOPS to data transfer reduction for this class of applications, offering the most impactful strategy for improving energy efficiency. This work establishes a foundation for practical, application-aware power management at exascale.

Zhao, Zhengji [Lawrence Berkeley National Laborato↗

Advanced Computing is at the Forefront of a New “Moonshot” Revolutionizing the North American Power Grid

In the 50+ years since the first humans landed on the moon, computing has grown at breakneck speed. We are faced with another challenge that is just as daunting, and just as important to overcome-modernizing the North American electric power grid-and high-performance computing (HPC) systems with specialized software will be an important element in rising to this challenge. We describe at a high level how software developed in the ExaSGD project addresses this "moonshot" goal by utilizing exascale computing and a novel high performance solver software stack to support the mission of decarbonizing power grid operations in an environment of uncertain weather and climate. To reach the exascale benchmark the team has made a number of first-of-their-kind innovations, including novel method for stochastic optimization, fine grained parallel methods for modeling power systems, and GPU resident sparse numerical linear solvers.

17 WIND ENERGY↗

EchemAMR (electro-chemical microsctructure scale models with adaptive meshing) [SWR-23-111]

A 3D microstructure resolving electrochemical transport and interfacial chemistry solver. Electrode microstructure plays an important role in determining the performance of an electrochemical system, e.g. lithium ion battery. EchemAMR is a microstructure scale model that solves the governing equations for ion transport, electrical current continuity, interfacial chemistry and structural mechanics. Complex microstructure geometries from imaging can be directly imported into EchemAMR. A volume fraction based description of the geometry on Cartesian grid with an immersed interface formulation enables simplified meshing and large-scale simulations with millions of degrees of freedom. EchemAMR has been tested against systems with analytic solutions for numerical convergence and highly resolved lithium ion battery microstructures. EchemAMR demonstrates excellent mass conversation and efficient scaling on heterogenous High-Performance Computing (HPC) with central and graphics processing units.

Sitaraman, Hariswaran↗