A Comparison of Backfilling and Coscheduling for High-Performance Computing
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.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
INL HPC team provided updates related to the INL HPC program and HPC systems for HPC User Group Quarterly Review - December 10, 2025
INL HPC team provided updates related to the INL HPC program and HPC systems for HPC User Group Quarterly Review - March 11, 2026
Explore the source record for details and available documents.
Computational Fluid Dynamics - Discrete Element Method is used to model gas-solid systems in several applications in energy, pharmaceutical and petrochemical industries. Computational performance bottlenecks often limit the problem sizes that can be simulated at industrial scale. The data structures used to store several millions of particles in such large-scale simulations have a large memory footprint that does not fit into the processor cache hierarchies on current high-performance-computing platforms, leading to reduced computational performance. This paper specifically addresses this aspect of memory access bottlenecks in industrial scale simulations. The use of space-filling curves to improve memory access patterns is described and their impact on computational performance is quantified in both shared and distributed memory parallelization paradigms. The Morton space filling curve applied to uniform grids and k-dimensional tree partitions are used to reorder the particle data-structure thus improving spatial and temporal locality in memory. The performance impact of these techniques when applied to two benchmark problems, namely the homogeneous-cooling-system and a fluidized-bed, are presented. We report these optimization techniques lead to approximately two-fold performance improvement in particle focused operations such as neighbor-list creation and data-exchange, with ~ 1.5 times overall improvement in a fluidization simulation with 1.27 million particles.
Scientific data analytics in high-performance computing environments has been evolving along with the advancement of computing capabilities. With the onset of exascale computing, the increasing gap between compute performance and I/O bandwidth has rendered the traditional post-simulation processing a tedious process. Despite the challenges due to increased data production, there exists an opportunity to benefit from "cheap" computing power to perform query-driven exploration and visualization during simulation time. To accelerate such analyses, applications traditionally augment, post-simulation, raw data with large indexes, which are then repeatedly utilized for data exploration. However, the generation of current state-of-the-art indexes involves a compute- and memory-intensive processing, thus rendering them inapplicable in an in situ context. In this paper we propose DIRAQ, a parallel in situ, in network data encoding and reorganization technique that enables the transformation of simulation output into a query-efficient form, with negligible runtime overhead to the simulation run. DIRAQ's effective core-local, precision-based encoding approach incorporates an embedded compressed index that is 3---6 $$\times $$ ? smaller than current state-of-the-art indexing schemes. Its data-aware index adjustmentation improves performance of group-level index layout creation by up to 35 % and reduces the size of the generated index by up to 27 %. Moreover, DIRAQ's in network index merging strategy enables the creation of aggregated indexes that speed up spatial-context query responses by up to $$10\times $$ 10 ? versus alternative techniques. DIRAQ's topology-, data-, and memory-aware aggregation strategy results in efficient I/O and yields overall end-to-end encoding and I/O time that is less than that required to write the raw data with MPI collective I/O.
The NAS Parallel Benchmarks (NPB) are a suite of parallel computer performance benchmarks. They were originally developed at the NASA Ames Research Center in 1991 to assess high-end parallel supercomputers. Although they are no longer used as widely as they once were for comparing high-end system performance, they continue to be studied and analyzed a great deal in the high-performance computing community. The acronym 'NAS' originally stood for the Numerical Aeronautical Simulation Program at NASA Ames. The name of this organization was subsequently changed to the Numerical Aerospace Simulation Program, and more recently to the NASA Advanced Supercomputing Center, although the acronym remains 'NAS.' The developers of the original NPB suite were David H. Bailey, Eric Barszcz, John Barton, David Browning, Russell Carter, LeoDagum, Rod Fatoohi, Samuel Fineberg, Paul Frederickson, Thomas Lasinski, Rob Schreiber, Horst Simon, V. Venkatakrishnan and Sisira Weeratunga. The original NAS Parallel Benchmarks consisted of eight individual benchmark problems, each of which focused on some aspect of scientific computing. The principal focus was in computational aerophysics, although most of these benchmarks have much broader relevance, since in a much larger sense they are typical of many real-world scientific computing applications. The NPB suite grew out of the need for a more rational procedure to select new supercomputers for acquisition by NASA. The emergence of commercially available highly parallel computer systems in the late 1980s offered an attractive alternative to parallel vector supercomputers that had been the mainstay of high-end scientific computing. However, the introduction of highly parallel systems was accompanied by a regrettable level of hype, not only on the part of the commercial vendors but even, in some cases, by scientists using the systems. As a result, it was difficult to discern whether the new systems offered any fundamental performance advantage over vector supercomputers, and, if so, which of the parallel offerings would be most useful in real-world scientific computation. In part to draw attention to some of the performance reporting abuses prevalent at the time, the present author wrote a humorous essay 'Twelve Ways to Fool the Masses,' which described in a light-hearted way a number of the questionable ways in which both vendor marketing people and scientists were inflating and distorting their performance results. All of this underscored the need for an objective and scientifically defensible measure to compare performance on these systems.
High-performance computing (HPC) and the cloud have evolved independently, specializing their innovations into performance or productivity. Acceleration as a Service (XaaS) is a recipe to empower both fields with a shared execution platform that provides transparent access to computing resources, regardless of the underlying cloud or HPC service provider. Bridging HPC and cloud advancements, XaaS presents a unified architecture built on performance-portable containers. Here, our converged model concentrates on low-overhead, high-performance communication and computing, targeting resource-intensive workloads from climate simulations to machine learning. XaaS lifts the restricted allocation model of Function as a Service (FaaS), allowing users to benefit from the flexibility and efficient resource utilization of serverless computing while supporting long-running and performance-sensitive workloads from HPC.
The Neutron Science Portal at Oak Ridge National Laboratory submits jobs to the TeraGrid for remote job execution. The TeraGrid is a network of high performance computers supported by the US National Science Foundation. There are eleven partner facilities with over a petaflop of peak computing performance and sixty petabytes of long-term storage. Globus is installed on a local machine and used for job submission. The graphical user interface is produced by java coding that reads an XML file. After submission, the status of the job is displayed in a Job Information Service window which queries globus for the status. The output folder produced in the scratch directory of the TeraGrid machine is returned to the portal with globus-url-copy command that uses the gridftp servers on the TeraGrid machines. This folder is copied from the stage-in directory of the community account to the user's results directory where the output can be plotted using the portal's visualization services. The primary problem with remote job execution is diagnosing execution problems. We have daily tests of submitting multiple remote jobs from the portal. When these jobs fail on a computer, it is difficult to diagnose the problem from the globus output. Successes and problems will be presented.
The Spallation Neutron Source (SNS) and the Neutron Science TeraGrid Gateway (NSTG) are collaborating on software development. SNS at Oak Ridge National Laboratory is a world center for materials research with neutron scattering. NSTG connects large neutron science instrument facilities with the cyber infrastructure of the TeraGrid. The TeraGrid is a network of high performance computers supported by the US National Science Foundation. There are eleven partner facilities with over a petaflop of peak computing performance, 136,740 CPU-cores, and sixty petabytes of long-term storage.
Neuromorphic computers perform computations by emulating the human brain and are expected to be indispensable for energy-efficient computing in the future. They are primarily used in spiking neural network-based machine learning applications. However, neuromorphic computers are unable to preprocess data for these applications. Currently, data is preprocessed on a CPU or a GPU-this incurs a significant cost of transferring data from the CPU/GPU to the neuromorphic processor and vice versa. This cost can be avoided if preprocessing is done on the neuromorphic processor. To efficiently preprocess data on a neuromorphic processor, we first need an efficient mechanism for encoding data that can lend itself to all general-purpose preprocessing operations. Current encoding approaches have limited applicability and may not be suitable for all preprocessing operations. In this paper, we present the virtual neuron as a mechanism for encoding integers and rational numbers on neuromorphic processors. We evaluate the performance of the virtual neuron on physical and simulated neuromorphic hardware and show that it can perform an addition operation using 23 nJ of energy on average using a mixed-signal, memristor-based neuromorphic processor. The virtual neuron encoding approach is the first step in preprocessing data on a neuromorphic processor.
In recent years, it has become increasingly common for high performance computers (HPC) to possess some level of heterogeneous architecture - typically in the form of GPU accelerators. In some machines these are isolated within a dedicated partition, whilst in others they are integral to all compute nodes - often with multiple GPUs per node - and provide the majority of a machine's compute performance. In light of this trend, it is becoming essential that codes deployed on HPC are updated to execute on accelerator hardware. Here, in this paper, we introduce a GPU implementation of the 3D blood flow simulation code HemeLB that has been developed using CUDA C++. We demonstrate how taking advantage of NVIDIA GPU hardware can achieve significant performance improvements compared to the equivalent CPU only code on which it has been built whilst retaining the excellent strong scaling characteristics that have been repeatedly demonstrated by the CPU version. With HPC positioned on the brink of the exascale era, we use HemeLB as a motivation to provide a discussion on some of the challenges that many users will face when deploying their own applications on upcoming exascale machines.
Coupling multiphase flow with energy transport due to high temperature heat sources introduces significant new challenges since boiling and condensation processes can lead to dry-out conditions with subsequent re-wetting. The transition between two-phase and single-phase behavior can require changes to the primary dependent variables adding discontinuities as well as extending constitutive nonlinear relations to extreme physical conditions. Practical simulations of large-scale engineered domains lead to Jacobian systems with a very large number of unknowns that must be solved efficiently using iterative methods in parallel on high-performance computers. Performance assessment of potential nuclear repositories, carbon sequestration sites and geothermal reservoirs can require numerous Monte-Carlo simulations to explore uncertainty in material properties, boundary conditions, and failure scenarios. Due to the numerical challenges, standard NR iteration may not converge over the range of required simulations and require more sophisticated optimization method like trust-region. In this study, we use the open-source simulator PFLOTRAN for the important practical problem of the safety assessment of future nuclear waste repositories in the U.S. DOE geologic disposal safety assessment Framework. The simulator applies the PETSc parallel framework and a backward Euler, finite volume discretization. We demonstrate failure of the conventional NR method and the success of trust-region modifications to Newton’s method for a series of test problems of increasing complexity. Trust-region methods essentially modify the Newton step size and direction under some circumstances where the standard NR iteration can cause the solution to diverge or oscillate. Furthermore, we show how the Newton Trust-Region method can be adapted for Primary Variable Switching (PVS) when the multiphase state changes due to boiling or condensation. The simulations with high-temperature heat sources which led to extreme nonlinear processes with many state changes in the domain did not converge with NR, but they do complete successfully with the trust-region methods modified for PVS. This implementation effectively decreased weeks of simulation time needing manual adjustments to complete a simulation down to a day. Finally, we show the strong scalability of the methods on a single node and multiple nodes in an HPC cluster.
The performance promise of machine learning surrogates of molecular dynamics simulations of soft materials is significant but generally comes at the cost of acquiring large training datasets to learn the complex relationships between input soft material attributes and output properties. Under the constraint of limited high-performance computing resources, optimizing the size of the training datasets becomes paramount. Using an artificial neural network based surrogate for molecular dynamics simulations of confined electrolytes, we explore the tradeoff between surrogate accuracy and computational gains. Accuracy is assessed by computing the root-mean-square errors between the surrogate predictions and the ground truth results obtained via molecular dynamics simulations. The computational performance is judged by evaluating the speedup which incorporates the training dataset creation time. Improvement in accuracy occurs with a loss of speedup, which scales as the inverse of the training dataset size. Furthermore, the link between surrogate generalizability and the accuracy-speedup tradeoff is assessed by examining the errors incurred in surrogate predictions on unseen, interpolated input variables and developing a net speedup metric to capture the associated gains.
As buildings age, retrofits are becoming an increasingly important topic for the ever-growing and aging existing building stock. To compare designs or evaluate in-service building envelopes, thermal modeling is utilized to evaluate the thermal performance of envelope assemblies; however, it can be difficult to model the thermal performance of as-built assemblies due to degradation or missing documentation. To address this issue, inverse modeling can be applied to infer the properties of as-built envelope assemblies. This paper presents a review of the literature and published methods to model and infer the transient conductive performance of building envelopes. This review serves as a survey of existing transient conduction algorithms to evaluate performance, computational speed, and relevance for inverse modeling applications. In addition to the literature review, this work also evaluates the computational performance of the most prevalent transient conduction algorithms against the ASHRAE 1052RP toolkit to assess inverse modeling potential. This methodology serves as a foundation for future research to characterize the transient thermal performance of as-built building envelope assemblies.
Quantum computers perform computations exploiting quantum mechanics to a possible advantage, allowing us to prepare and manipulate states that do not have a classical equivalent. In particular, phenomena like superposition and entanglement may enable quantum computers to outperform their classical counterparts in certain applications. Implementing these useful quantum algorithms is contingent upon building accurate quantum hardware that is not affected by noise. Environmental noise decreases coherence time of qubits, meaning that qubits do not stay in a desired state long enough to carry out a complex computation. To that end, harnessing the full power of quantum computers necessitate characterization of noise sources and how they impact a given quantum system. Often times, T1and T2 are used to quantify noise. In this project, we provide an approach as to how T1 and T2 values are calculated and simulated for quantum systems. In addition, we compare simulated values of T1 and T2 with those of real quantum computer’s measurements. IBMQ Experience, an open source software allowing users to simulate and use real quantum hardware, is used. QuTip, a Python-based toolbox offering quantum simulation tools for open quantum systems, is also used.