Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computational Performance”

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 1,621 records · Page 90

Supporting the Development of Resilient Message Passing Applications using Simulation

An emerging aspect of high-performance computing (HPC) hardware/software co-design is investigating performance under failure. The work in this paper extends the Extreme-scale Simulator (xSim), which was designed for evaluating the performance of message passing interface (MPI) applications on future HPC architectures, with fault-tolerant MPI extensions proposed by the MPI Fault Tolerance Working Group. xSim permits running MPI applications with millions of concurrent MPI ranks, while observing application performance in a simulated extreme-scale system using a lightweight parallel discrete event simulation. The newly added features offer user-level failure mitigation (ULFM) extensions at the simulated MPI layer to support algorithm-based fault tolerance (ABFT). The presented solution permits investigating performance under failure and failure handling of ABFT solutions. The newly enhanced xSim is the very first performance tool that supports ULFM and ABFT.

Engelmann, Christian↗

Tools for Simulation and Benchmark Generation at Exascale

The path to exascale high-performance computing (HPC) poses several challenges related to power, performance, resilience, productivity, programmability, data movement, and data management. Investigating the performance of parallel applications at scale on future architectures and the performance impact of different architecture choices is an important component of HPC hardware/software co-design. Simulations using models of future HPC systems and communication traces from applications running on existing HPC systems can offer an insight into the performance of future architectures. This work targets technology developed for scalable application tracing of communication events and memory profiles, but can be extended to other areas, such as I/O, control flow, and data flow. It further focuses on extreme-scale simulation of millions of Message Passing Interface (MPI) ranks using a lightweight parallel discrete event simulation (PDES) toolkit for performance evaluation. Instead of simply replaying a trace within a simulation, the approach is to generate a benchmark from it and to run this benchmark within a simulation using models to reflect the performance characteristics of future-generation HPC systems. This provides a number of benefits, such as eliminating the data intensive trace replay and enabling simulations at different scales. The presented work utilizes the ScalaTrace tool to generate scalable trace files, the ScalaBenchGen tool to generate the benchmark, and the xSim tool to run the benchmark within a simulation.

Lagadapati, Mahesh↗

Developing And Scaling an OpenFOAM Model to Study Turbulent Flow in a HFIR Coolant Channel

Improving the understanding of how computational fluid dynamics (CFD) direct numerical simulations (DNS) of flows in the High Flux Isotope Reactor (HFIR) perform when run in parallel using the high performance computing (HPC) platform Summit at the Oak Ridge Leadership Computing Facility (OLCF) is of particular importance to boost the computational tools used to support HFIR conversion to low enriched fuel (LEU). Evaluation of scaling performance was driven by the increasing importance of graphics processing unit (GPU) usage in HPC, which is becoming the standard for modern supercomputers such as Summit. The desired results are to obtain a strong positive correlation between the computational resources dedicated to a problem and the relative speed-up of the simulation in comparison to a benchmark. This capability will allow substantially improvement in HFIR flow analytical capabilities, specifically when predicting turbulence properties at high Reynolds numbers. The study leverages previous simulation results performed with code PHASTA (finite element) on HPC platforms Cori (NERSC) and Theta (ALCF) [1] with computing options provided in the computing platform OpenFOAM (finite volume) at OLCF. Transitioning from PHASTA to OpenFOAM will (1) eliminate dependence on third-party software for mesh generation and manipulation, (2) reduce resource needs by employing modern architectures, and (3) build expertise for future modeling of HFIR-specific problems like heat transfer in involute geometry, entrance effects, flow structure in channel corners, and so on—all important issues when defining the available thermal margins in the transition to LEU. CPUs and GPUs differ significantly in their architecture and utilization, as discussed in the literature [2]. The most important differences are in the approach to computations and their memory. A single GPU contains a large quantity of cores, enabling it to perform with a much higher throughput than a CPU, but execution requires a different approach. GPU codes execute instructions using the Single-Instruction Multiple-Thread (SIMT) approach in which a single instruction is used for groups of threads called warps. A warp typically consists of 32 threads which must execute the same set of instructions, although on separate threads. Alternately, a CPU has far fewer cores that are much more flexible in their operation, excelling at quickly performing more complex serial computations. This is why GPUs have greater throughput when properly utilized. The second important difference is seen when comparing their memory spaces. Limited memory allocations and CPU–GPU communications cause a significant bottleneck in GPU-accelerated programs. Further study was required to properly take advantage of GPU resources. A comprehensive analysis of code performance and the model-specific features of turbulence constitutes the core of this work. In this study, a DNS simulation of HFIR channel turbulence was performed with the finite volume CFD code OpenFOAM v2112 and CUDA v11.0 on Red Hat Enterprise Linux v8.2. The OpenFOAM installation had AMGx integrated to enable GPU acceleration and utilizes the PETSc4FOAM library. The computational resources and the problem size were scaled on CPU and CPU + GPU architectures to gain a better understanding of the performance of a DNS problem on modern computing hardware. The study aimed to analyze the scaling of the code exclusively on CPUs and then to examine the scaling of the codes with GPU acceleration enabled. Scaling studies included CPU and GPU acceleration on a mesh of varying resolution to analyze the impact of problem size relative to computational resources. In the course of preparing the GPU configuration on Summit, mainly using the AMGX solvers, difficulties were encountered stemming from constant changes resulting from extensive ongoing development activities and the changing environment. This resulted in the inability to complete the GPU portion of the work. The code was compiled and tested, but production runs to assess acceleration were not performed because the used discretional compute time allocation expired as year-end approached. The Summit HPC platform is scheduled for decommissioning in 2024, making it unattractive for future use with Nvidia-based GPUs. Therefore, the work will be moved onto NERSC machines in FY24. An application was prepared and submitted, and sufficient node-hours were awarded to continue the research in the next calendar year. This report summarizes work performed thus far, which mostly focused on CPU OpenFOAM computing.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Establishing the quantum supremacy frontier with a 281 Pflop/s simulation

Noisy intermediate-scale quantum (NISQ) computers are entering an era in which they can perform computational tasks beyond the capabilities of the most powerful classical computers, thereby achieving 'quantum supremacy', a major milestone in quantum computing. NISQ supremacy requires comparison with a state-of-the-art classical simulator. In this paper, we report HPC simulations of hard random quantum circuits (RQC), which have been recently used as a benchmark for the first experimental demonstration of quantum supremacy, sustaining an average performance of 281 Pflop/s (true single precision) on Summit, currently the fastest supercomputer in the world. These simulations were carried out using qFlex, a tensor-network-based classical high-performance simulator of RQCs. Our results show an advantage of many orders of magnitude in energy consumption of NISQ devices over classical supercomputers. In addition, we propose a standard benchmark for NISQ computers based on qFlex.

97 MATHEMATICS AND COMPUTING↗

DRAGON: breaking GPU memory capacity limits with direct NVM access

Heterogeneous computing with accelerators is growing in importance in high performance computing (HPC). Recently, application datasets have expanded beyond the memory capacity of these accelerators, and often beyond the capacity of their hosts. Meanwhile, nonvolatile memory (NVM) storage has emerged as a pervasive component in HPC systems because NVM provides massive amounts of memory capacity at affordable cost. Currently, for accelerator applications to use NVM, they must manually orchestrate data movement across multiple memories and this approach only performs well for applications with simple access behaviors. To address this issue, we developed DRAGON, a solution that enables all classes of GP-GPU applications to transparently compute on terabyte datasets residing in NVM. DRAGON leverages the page-faulting mechanism on the recent NVIDIA GPUs by extending capabilities of CUDA Unified Memory (UM). Our experimental results show that DRAGON transparently expands memory capacity and obtain additional speedups via automated I/O and data transfer overlapping.

Markthub, Pak↗

Estimating Lossy Compressibility of Scientific Data Using Deep Neural Networks

Simulation based scientific applications generate increasingly large amounts of data on high-performance computing (HPC) systems. To allow data to be stored and analyzed efficiently, data compression is often utilized to reduce the volume and velocity of data. However, a question often raised by domain scientists is the level of compression that can be expected so that they can make more informed decisions, balancing between accuracy and performance. In this letter, we propose a deep neural network based approach for estimating the compressibility of scientific data. To train the neural network, we build both general features as well as compressor-specific features so that the characteristics of both data and lossy compressors are captured in training. Our approach is demonstrated to outperform a prior analytical model as well as a sampling based approach in the case of a biased estimation, i.e., for SZ. However, for the unbiased estimation (i.e., ZFP), the sampling based approach yields the best accuracy, despite the high overhead involved in sampling the target dataset.

97 MATHEMATICS AND COMPUTING↗

Architecture Adaptive Computing Environment

Architecture Adaptive Computing Environment (aCe) is a software system that includes a language, compiler, and run-time library for parallel computing. aCe was developed to enable programmers to write programs, more easily than was previously possible, for a variety of parallel computing architectures. Heretofore, it has been perceived to be difficult to write parallel programs for parallel computers and more difficult to port the programs to different parallel computing architectures. In contrast, aCe is supportable on all high-performance computing architectures. Currently, it is supported on LINUX clusters. aCe uses parallel programming constructs that facilitate writing of parallel programs. Such constructs were used in single-instruction/multiple-data (SIMD) programming languages of the 1980s, including Parallel Pascal, Parallel Forth, C*, *LISP, and MasPar MPL. In aCe, these constructs are extended and implemented for both SIMD and multiple- instruction/multiple-data (MIMD) architectures. Two new constructs incorporated in aCe are those of (1) scalar and virtual variables and (2) pre-computed paths. The scalar-and-virtual-variables construct increases flexibility in optimizing memory utilization in various architectures. The pre-computed-paths construct enables the compiler to pre-compute part of a communication operation once, rather than computing it every time the communication operation is performed.

Dorband, John E.↗

Quantum/AI Topology-Aware Latency-Adaptive HPC Workflow Scheduling Optimization

The growing demand for more powerful high-performance computing (HPC) systems has led to a steady rise in energy consumption by supercomputing worldwide. This study is focused on comparing our Application-Topology Mapper (ATMapper) to the popular Simple Linux Utility for Resource Management (SLURM) for the purpose of exploring methods that can further optimize job-scheduling within HPC systems. ATMapper is an Artificial-Intelligence based approach to job-scheduling that is currently being enhanced with quantum annealing (QA) to generate optimal schedules faster. We are applying QA to speedup our ATMapper process to achieve higher computing efficiency, thereby reducing HPC energy consumption. Here, we examine how four job-scheduling approaches perform in processor node assignment when using an example network architecture of 4 interconnected nodes. Using a specialized script, we are assessing the schedule of a computation flow with 11 interdependent tasks. The data movements among nodes were tracked to count for the number of interactions (network hops) between nodes needed to complete the tasks. The total number of hops and the job completion time were then used to quantify the efficiency of the different mapping approaches. In addition to SLURM, we also compare our ATMapper to the QA-enabled LBNL TIGER and the D-Wave Distributed Computing processor assignment approaches. The preliminary results showed that our topology-aware, latency-adaptive ATMapper is significantly more efficient when compared to the other scheduling approaches due to its load-imbalance network allocation. The scheduler displayed a computing efficiency of 53% by performing significantly fewer network hops than its alternatives. By reducing the number of hops, ATMapper was able to perform all 11 tasks by using only 3 nodes out of given 4. This research indicates the potential to use QA/AI for HPC job-scheduling. Later, we will test a SLURM simulator program to draw further comparisons on the effectiveness of ATMapper's scheduling approach. The results of this comparison will serve as a baseline for later improving SLURM's performance using a QA-enhanced ATMapper approach.

Caraveo, Braulio [University of Huston - Clear Lak↗

FORTRAN program for predicting off-design performance of radial-inflow turbines

The FORTRAN IV program uses a one-dimensional solution of flow conditions through the turbine along the mean streamline. The program inputs needed are the design-point requirements and turbine geometry. The output includes performance and velocity-diagram parameters over a range of speed and pressure ratio. Computed performance is compared with the experimental data from two radial-inflow turbines and with the performance calculated by a previous computer program. The flow equations, program listing, and input and output for a sample problem are given.

Wasserbauer, C. A.↗

Mixed-Precision S/DGEMM Using the TF32 and TF64 Frameworks on Low-Precision AI Tensor Cores

Using NVIDIA graphics processing units (GPUs) equipped with Tensor Cores has enabled the significant acceleration of general matrix multiplication (GEMM) for applications in machine learning (ML) and artificial intelligence (AI) and in high-performance computing (HPC) generally. The use of such power-efficient, specialized accelerators can provide a performance increase between 8 × and 20 ×, albeit with a loss in precision. However, a high level of precision is required in many large scientific and HPC applications, and computing in single or double precision is still necessary for many of these applications to maintain accuracy. Fortunately, mixed-precision methods can be employed to maintain a higher level of numerical precision while also taking advantage of the performance increases from computing with lower-precision AI cores. With this in mind, we extend the state of the art by using NVIDIA’s new TF32 framework. This new framework not only burdens some constraints of the previous frameworks, such as costly 32 16-bit castings but also provides an equivalent precision and performance by using a much simpler approach. We also propose a new framework called TF64 that attempts double-precision arithmetic with low-precision Tensor Cores. Although this framework does not exist yet, we validated the correctness of this idea and achieved an equivalent of 64-bit precision on 32-bit hardware.

Valero Lara, Pedro↗

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↗

Comparison of model and human observer performance for detection and discrimination tasks using dual-energy x-ray images

Model observer performance, computed theoretically using cascaded systems analysis (CSA), was compared to the performance of human observers in detection and discrimination tasks. Dual-energy (DE) imaging provided a wide range of acquisition and decomposition parameters for which observer performance could be predicted and measured. This work combined previously derived observer models (e.g., Fisher-Hotelling and non-prewhitening) with CSA modeling of the DE image noise-equivalent quanta (NEQ) and imaging task (e.g., sphere detection, shape discrimination, and texture discrimination) to yield theoretical predictions of detectability index (d{sup '}) and area under the receiver operating characteristic (A{sub Z}). Theoretical predictions were compared to human observer performance assessed using 9-alternative forced-choice tests to yield measurement of A{sub Z} as a function of DE image acquisition parameters (viz., allocation of dose between the low- and high-energy images) and decomposition technique [viz., three DE image decomposition algorithms: standard log subtraction (SLS), simple-smoothing of the high-energy image (SSH), and anti-correlated noise reduction (ACNR)]. Results showed good agreement between theory and measurements over a broad range of imaging conditions. The incorporation of an eye filter and internal noise in the observer models demonstrated improved correspondence with human observer performance. Optimal acquisition and decomposition parameters were shown to depend on the imaging task; for example, ACNR and SSH yielded the greatest performance in the detection of soft-tissue and bony lesions, respectively. This study provides encouraging evidence that Fourier-based modeling of NEQ computed via CSA and imaging task provides a good approximation to human observer performance for simple imaging tasks, helping to bridge the gap between Fourier metrics of detector performance (e.g., NEQ) and human observer performance.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Performance Optimization Methods for a Memory-Bound, Unstructured-Grid CFD Application on Massively Parallel GPU Platforms

Computational performance of the FUN3D unstructured-grid computational fluid dynamics (CFD) application on massively parallel GPU environments is memory-bound and highly dependent upon efficient reads from and atomic updates to the irregular cell-, edge-, and node-based data structures. In this talk, we present recent efforts into optimizing select performance-critical kernels on NVIDIA Tesla V100 and A100 GPUs and AMD CDNA MI100 GPUs. A novel use of L2 cache residency controls and asynchronous loads into on-chip shared memory are explored on the A100 GPU for the sparse iterative solver, which is dominated by mixed-precision, sparse matrix vector multiplication. Demonstrations show that these methods improve global memory bandwidth utilization by 13.5% on the A100 GPU. Several techniques are also presented that use registers and/or shared memory to facilitate array transposition and aggregation which combine to reduce the frequency and increase the cache efficiency of floating-point atomic updates to the irregular data structures. These methods are demonstrated to improve the kernel throughput by nearly 500% on select kernels on the AMD MI100 over atomic updates directly to global memory. Overall, both V100 and A100 GPUs outperformed the MI100 GPU on kernels dominated by double-precision atomic updates; however, the techniques demonstrated here reduced the performance gap and improved the MI100 performance.

GPU CPU unstructured CFD memory↗

ORCHA: A performance portability system for extreme heterogeneity

Heterogeneity is the prevalent trend in the rapidly evolving high-performance computing (HPC) landscape in both hardware and application software. The diversity in hardware platforms, currently comprising various accelerators and a future possibility of specializable chiplets, poses a significant challenge for scientific software developers aiming to harness optimal performance across different computing platforms while maintaining the quality of solutions when their applications are simultaneously growing more complex. Code synthesis and code generation can provide mechanisms to mitigate this challenge. We have developed a divide and conquer approach where different aspects of performance are handled by different stand-alone tools that are interfaced with the application through generated code. This portability system, ORCHA, enables users to configure and orchestrate their computations among available resources on a platform by specifying a high-level recipe, thereby permitting a many-to-many paradigm where each recipe results in a different variant of the application. The core design goal is to let users decide the application’s hardware mapping and orchestration by editing only the high-level recipe—without modifying the maintained source code or binding the application to a particular runtime system. Tools in ORCHA distribution are: CG-Kit for translating the recipe into an execution graph; Milhoja to execute the graph by orchestrating data and task movement among hardware resources; and Macroprocessor that enables users to define their own code-shorthand for higher composability and easier management of code variants. Additionally, the design of ORCHA permits tools to work in a plug-and-play mode where the application can build and run without CG-Kit and Milhoja, and either tool can be swapped out for other tools with similar capabilities by modifying the code generation portion of ORCHA. In this paper, we describe the design of ORCHA and the role that code-generation plays in isolating applications from tools. We demonstrate the breadth of configurations ORCHA enables with a case study in which an application configuration is realized on three distinct hardware mappings—a GPU-centric, a CPU/GPU balanced, and a CPU/GPU concurrent layouts by using different recipes.

Lee, Youngjun↗

Computational study of the adsorption of bimetallic clusters on alumina substrate

We performed computational investigation of the adsorption of bimetallic Pd 3 M 2 (where M changes from Ag, Au, Co, Cu, Mn, Ni, Pt, and Ru) cluster on the hydroxylated alumina surface. Previously, it was shown that small silver cluster can control the rate of discharge at the cathode of lithium-oxygen battery. The gap near the fermi energy was shown to control the oxygen reduction, an important reaction for LiO 2 formation. Controlling the gap would ultimately control the rate of LiO 2 formation. One can vary the size of the cluster to vary the gap, however, this "knob" provides limited variance in the gap. Alloying, in combination with size variation offer a much wider control of the gap, hence the LiO 2 formation. Using Density Functional Theory (DFT), we determined the most stable geometry of the bimetallic clusters Pd 3 M 2 and calculated the binding energies of these clusters on the alumina substrate which ranges from 0.2 eV to 0.25 eV depending upon the composition of the alloy-cluster, its orientation and the adsorption site. We also find that Pd atoms bind strongly with the substrate oxygen atoms with an average short bond-length of about 2.2 angstrom. We explored how the gap at the Fermi level of the system varies as a function of elemental composition and the calculated gap ranges from 0 meV to 90 meV. Charges distribution using Bader analysis was also performed to probe how charges are transferred between the cluster and the substrate. These preliminary results will open the door for more systematic studies of alloy clusters of different size and stoichiometry for Li-O 2 battery cathode design.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Projection-Based Reduced Order Modeling for Spacecraft Thermal Analysis

This paper presents a mathematically rigorous, subspace projection-based reduced order modeling (ROM) methodology and an integrated framework to automatically generate reduced order models for spacecraft thermal analysis. Two key steps in the reduced order modeling procedure are described: (1) the acquisition of a full-scale spacecraft model in the ordinary differential equation (ODE) and differential algebraic equation (DAE) form to resolve its dynamic thermal behavior; and (2) the ROM to markedly reduce the dimension of the full-scale model. Specifically, proper orthogonal decomposition (POD) in conjunction with discrete empirical interpolation method (DEIM) and trajectory piece-wise linear (TPWL) methods are developed to address the strong nonlinear thermal effects due to coupled conductive and radiative heat transfer in the spacecraft environment. Case studies using NASA-relevant satellite models are undertaken to verify the capability and to assess the computational performance of the ROM technique in terms of speed-up and error relative to the full-scale model. ROM exhibits excellent agreement in spatiotemporal thermal profiles (<0.5% relative error in pertinent time scales) along with salient computational acceleration (up to two orders of magnitude speed-up) over the full-scale analysis. These findings establish the feasibility of ROM to perform rational and computationally affordable thermal analysis, develop reliable thermal control strategies for spacecraft, and greatly reduce the development cycle times and costs.

0000↗

Multi-threaded Sparse Matrix Sparse Matrix Multiplication for Many-Core and GPU Architectures.

Sparse Matrix-Matrix multiplication is a key kernel that has applications in several domains such as scientific computing and graph analysis. Several algorithms have been studied in the past for this foundational kernel. In this paper, we develop parallel algorithms for sparse matrix- matrix multiplication with a focus on performance portability across different high performance computing architectures. The performance of these algorithms depend on the data structures used in them. We compare different types of accumulators in these algorithms and demonstrate the performance difference between these data structures. Furthermore, we develop a meta-algorithm, kkSpGEMM, to choose the right algorithm and data structure based on the characteristics of the problem. We show performance comparisons on three architectures and demonstrate the need for the community to develop two phase sparse matrix-matrix multiplication implementations for efficient reuse of the data structures involved.

97 MATHEMATICS AND COMPUTING↗

Vectorization, threading, and cache-blocking considerations for hydrocodes on emerging architectures

This work reports on considerations for improving computational performance in preparation for current and expected changes to computer architecture. The algorithms studied will include increasingly complex prototypes for radiation hydrodynamics codes, such as gradient routines and diffusion matrix assembly (e.g., in [1-6]). The meshes considered for the algorithms are structured or unstructured meshes. The considerations applied for performance improvements are meant to be general in terms of architecture (not specifically graphical processing unit (GPUs) or multi-core machines, for example) and include techniques for vectorization, threading, tiling, and cache blocking. Out of a survey of optimization techniques on applications such as diffusion and hydrodynamics, we make general recommendations with a view toward making these techniques conceptually accessible to the applications code developer. Published 2015. This article is a U.S. Government work and is in the public domain in the USA.

97 MATHEMATICS AND COMPUTING↗