Rexsss PDE Solver Performance Analysis: Scalability Estimates Using the SST/macro Architecture Simulator.
Abstract not provided.
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.
Abstract not provided.
Explore the source record for details and available documents.
Abstract not provided.
Abstract not provided.
Abstract not provided.
Explore the source record for details and available documents.
A technique for accessing memory in an accelerated processing device coupled to stacked memory dies is provided herein. The technique includes receiving a memory access request from an execution unit and identifying whether the memory access request corresponds to memory cells of the stacked dies that are considered local to the execution unit or non-local. For local accesses, the access is made “directly”, that is, without using a bus. A control die coordinates operations for such local accesses, activating particular through-silicon-vias associated with the memory cells that include the data for the access. Non-local accesses are made via a distributed cache fabric and an interconnect bus in the control die. Various other features and details are provided below.
Abstract not provided.
Explore the source record for details and available documents.
Abstract not provided.
Deep learning models are efficient computational tools that can accelerate the inverse design of molecules with desired functional properties by generating predictions at a fraction of the time required by traditional quantum chemical approaches. To ensure that a model maintains accuracy and transferability across broad regions of the chemical space explored during the inverse design, it must be trained on massively large volumes of simulation data. This requires running large-scale ensemble quantum chemical calculations on high-performance computing (HPC) systems for data collection. However, the efficient execution of such large ensemble calculations and the management of large volumes of output data require tools that can judiciously utilize computational resources and manage metadata overhead on the file system. Therefore, we present a high-performance, scalable, ensemble management framework for performing data-intensive quantum chemical electronic structure calculations for organic molecules. This framework provides abstractions to plug different ab initio, first principles, and first principles-based semi-empirical methods and executes them efficiently at large scale on HPC systems. It dynamically distributes tasks to resources and uses tiered storage for managing large collections of files. We employed this framework to process over ten million organic molecules and generate open-source datasets that provide UV-vis absorption spectra by running time-dependent density-functional tight-binding calculations. It is the largest database containing molecular optical spectra that were simulated with quantum chemical methods in a consistent manner.
In this paper, we study uncertainty quantification and visualization of orientation distribution functions (ODF), which corresponds to the diffusion profile of high angular resolution diffusion imaging (HARDI) data. The shape inclusion probability (SIP) function is the state‐of‐the‐art method for capturing the uncertainty of ODF ensembles. The current method of computing the SIP function with a volumetric basis exhibits high computational and memory costs, which can be a bottleneck to integrating uncertainty into HARDI visualization techniques and tools. We propose a novel spherical sampling framework for faster computation of the SIP function with lower memory usage and increased accuracy. In particular, we propose direct extraction of SIP isosurfaces, which represent confidence intervals indicating spatial uncertainty of HARDI glyphs, by performing spherical sampling of ODFs. Our spherical sampling approach requires much less sampling than the state‐of‐the‐art volume sampling method, thus providing significantly enhanced performance, scalability, and the ability to perform implicit ray tracing. Our experiments demonstrate that the SIP isosurfaces extracted with our spherical sampling approach can achieve up to 8164× speedup, 37282× memory reduction, and 50.2% less SIP isosurface error compared to the classical volume sampling approach. We demonstrate the efficacy of our methods through experiments on synthetic and human‐brain HARDI datasets.
Bioelectrochemical hydrogen production via microbial electrolysis cells (MECs) is a promising method for sustainable energy production and decarbonization of energy systems. However, the application of MECs is limited by the electrochemical performance, scalability, and the cost associated with expensive materials. Here, in this study, a scalable MEC (500 mL) with novel compact electrode assemblies and high electrode surface area to volume ratio (160 m 2 /m 3 ) was designed and constructed. The use of membranes, precious metal catalyst, and current collectors with high costs was avoided. A high current density at the steady state of 49.5 ± 5.3 A/m 2 was achieved using acetate as the substrate with phosphate buffer under the applied voltage of 1.01 V. The corresponding volumetric current density was 3948 ± 422 A/m 3 . The compact electrode assembly design limited methane production rate to 3.9 ± 0.2 L/L/D, while achieving a hydrogen production rate of 33.7 ± 1.7 L/L/D. With the suppression of microbial hydrogen consumption, the hydrogen production rate was 39.8 ± 1.9 L/L/D, higher by almost one order of magnitude than those of MECs with scaling up attempts. The compact electrode configuration reduced internal resistance to 88.5 ± 4.4 Ω cm 2 . The energy efficiency based on input electricity was 146 ± 7 % to 189 ± 9 % within the applied voltage range of 0.71 to 1.05 V. The results in this study demonstrated successful scaling up of high performance small MECs and offered a new possible approach of scaling up MECs by stacking high-performance subunits, with no trade-offs on electrochemical performance.
The OpenSHMEM reference implementation was developed towards the goal of developing an open source and high-performing OpenSHMEM implementation. To achieve portability and performance across various networks, the OpenSHMEM reference implementation uses GASNet and UCCS for network operations. Recently, new network layers have emerged with the promise of providing high-performance, scalability, and portability for HPC applications. In this paper, we implement the OpenSHMEM reference implementation to use the UCX framework for network operations. Then, we evaluate its performance and scalability on Cray XK systems to understand UCX’s suitability for developing the OpenSHMEM programming model. Further, we develop a benchmark called SHOMS for evaluating the OpenSHMEM implementation. Our experimental results show that OpenSHMEM-UCX outperforms the vendor supplied OpenSHMEM implementation in most cases on the Cray XK system by up to 40% with respect to message rate and up to 70% for the execution of application kernels.
The PRIMA-X (Performance Retargeting of Instrumentation, Measurement, and Analysis Technologies for Exascale Computing) project is the successor of the DOE PRIMA (Performance Refactoring of Instrumentation, Measurement, and Analysis Technologies for Petascale Computing) project, which addressed the challenge of creating a core measurement infrastructure that would serve as a common platform for both integrating leading parallel performance systems (notably TAU and Scalasca) and developing next-generation scalable performance tools. The PRIMA-X project shifts the focus away from refactorization of robust performance tools towards a re-targeting of the parallel performance measurement and analysis architecture for extreme scales. The massive concurrency, asynchronous execution dynamics, hardware heterogeneity, and multi-objective prerequisites (performance, power, resilience) that identify exascale systems introduce fundamental constraints on the ability to carry forward existing performance methodologies. In particular, there must be a deemphasis of per-thread observation techniques to significantly reduce the otherwise unsustainable flood of redundant performance data. Instead, it will be necessary to assimilate multi-level resource observations into macroscopic performance views, from which resilient performance metrics can be attributed to the computational features of the application. This requires a scalable framework for node-level and system-wide monitoring and runtime analyses of dynamic performance information. Also, the interest in optimizing parallelism parameters with respect to performance and energy drives the integration of tool capabilities in the exascale environment further. Initially, PRIMA-X was a collaborative project between the University of Oregon (lead institution) and the German Research School for Simulation Sciences (GRS). Because Prof. Wolf, the PI at GRS, accepted a position as full professor at Technische Universitaet Darmstadt (TU Darmstadt) starting February 1st, 2015, the work of GRS was continued at TU Darmstadt. This report covers the work at TU Darmstadt after the transition. The first main accomplishment of TU Darmstadt is the development of different techniques to aggregate performance data on the level of threads. TU Darmstadt evaluated different schemes designed at GRS during the first phase of this project and integrated them into Score-P, a widely used performance measurement framework for HPC applications. The second main accomplishment is a substantial increase of Score-P’s scalability, achieved by improving its internal representation of the underlying system. Third, we extended our performance-modeling tool Extra-P to automatically create models with more than one input parameter (e.g., process count and input size), which was previously impossible. These models allow the performance behavior of an application to be extrapolated to larger machines. Specific applications of the new multi-parameter capability realized in this project include modeling the isoefficiency function of task-based applications and a novel co-design methodology. Further extensions of Extra-P comprise online modeling functionality, automatic refinement of the model search space, and segmented performance modeling. Further contributions include new locality metrics for both shared- and distributed-memory applications, a new way of measuring the impact of inter-application inference on the execution time of an application, and finally an automatic method that selects appropriate OpenMP constructs for the parallelization of sequential code and classifies the affected variables based on their sharing semantics.
A system is provided for the high-speed and high-fidelity collection of network traffic. The system can collect traffic at gigabit-per-second (Gbps) speeds, scale to terabit-per-second (Tbps) speeds, and support additional functions such as real-time network intrusion detection. The present system uses a dedicated operating system for traffic collection to maximize efficiency, scalability, and performance. A scalable infrastructure and apparatus for the present system is provided by splitting the work performed on one host onto multiple hosts. The present system simultaneously addresses the issues of scalability, performance, cost, and adaptability with respect to network monitoring, collection, and other network tasks. In addition to high-speed and high-fidelity network collection, the present system provides a flexible infrastructure to perform virtually any function at high speeds such as real-time network intrusion detection and wide-area network emulation for research purposes.
The high-performance, scalability and miniaturization requirements together with the power, mass and cost constraints mandate the use of commercial-off-the-shelf (COTS) components and standards in the X2000 avionics system architecture for deep-space missions. In this paper, we report our experiences and findings on the design of an IEEE 1394 compliant fault-tolerant COTS-based bus architecture. While the COTS standard IEEE 1394 adequately supports power management, high performance and scalability, its topological criteria impose restrictions on fault tolerance realization. To circumvent the difficulties, we derive a "stack-tree" topology that not only complies with the IEEE 1394 standard but also facilitates fault tolerance realization in a spaceborne system with limited dedicated resource redundancies. Moreover, by exploiting pertinent standard features of the 1394 interface which are not purposely designed for fault tolerance, we devise a comprehensive set of fault detection mechanisms to support the fault-tolerant bus architecture.
Here, we consider the problem of finding a mesh such that 1) it is the closest, with respect to a suitable metric, to a given source mesh having the same connectivity, and 2) the volumes of its cells match a set of prescribed positive values that are not necessarily equal to the cell volumes in the source mesh. Also, this volume correction problem arises in important simulation contexts, such as satisfying a discrete geometric conservation law and solving transport equations by incremental remapping or similar semi-Lagrangian transport schemes. In this paper we formulate volume correction as a constrained optimization problem in which the distance to the source mesh defines an optimization objective, while the prescribed cell volumes, mesh validity and/or cell convexity specify the constraints. We solve this problem numerically using a sequential quadratic programming (SQP) method whose performance scales with the mesh size. To achieve scalable performance we develop a specialized multigrid-based preconditioner for optimality systems that arise in the application of the SQP method to the volume correction problem. Numerical examples illustrate the importance of volume correction, and showcase the accuracy, robustness and scalability of our approach.