Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “core optimization”

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 1,171 records · Page 65

Web-Based Tools for Data-Informed Remedy Optimization: Software Theory and User Guide

This report documents the development and application of two web-based decision-support tools for pump-and-treat (P&T) groundwater remediation systems: PTOLEMY (Pump-and-Treat Optimized Location Evaluation to Maximize Yields) and OPTIMA (Optimization for Pump-and-Treat Implementation, Management, & Assessment). These tools enhance remedy design and management by leveraging advanced computational methods – specifically deep learning and multi-objective optimization – within a user-friendly platform. By integrating data-driven models with established hydrogeological knowledge, PTOLEMY and OPTIMA enable more efficient evaluation of well placement and operational strategies, helping site managers balance multiple remediation objectives under complex conditions. Both tools are implemented as modules within the SOCRATES (Suite Of Comprehensive Rapid Analysis Tools for Environmental Sites) web platform, which provides data access, visualization, and analytics to support remedy optimization across sites in the U.S. Department of Energy Office of Environmental Management complex. PTOLEMY is a rapid screening module designed to identify promising locations for new extraction wells. It employs a multi-channel three-dimensional convolutional neural network (MC3D-CNN) trained on high-fidelity simulation data to predict the relative performance (in terms of contaminant mass recovery) of potential well sites. Through an interactive web interface, PTOLEMY visualizes the probability of high performance across a site, highlighting areas where an extraction well is likely to yield above-threshold contaminant removal over a multi-year period. PTOLEMY’s map-based displays and exportable results support transparent communication of screening analyses. By focusing attention on the most favorable candidate locations, the tool augments traditional engineering judgment and physics-based modeling, providing a data informed basis for subsequent detailed evaluations. OPTIMA is a multi objective optimization module designed to find wellfield layouts and operating schedules that meet various cleanup goals. It quickly evaluates thousands of candidate setups – combinations of well locations, timing, and rates – and returns a small set of best trade-off options for comparison. At its core, OPTIMA uses a U-Net-based surrogate model – a deep-learning emulator of a groundwater flow and transport simulator – to dramatically accelerate scenario evaluations. Coupling this fast surrogate with the NSGA-II (Non-dominated Sorting Genetic Algorithm II) evolutionary algorithm, OPTIMA explores a wide decision space of well locations and schedules to identify Pareto-optimal solutions that trade off key objectives (e.g., minimizing cleanup time, maximizing contaminant mass removal, and minimizing plume extent). The tool outputs a family of optimal configurations and visualizes their trade-offs (Pareto frontiers of cleanup metrics and maps of optimized well placements). Site managers can use these results to understand the range of viable strategies and to select candidate designs for more detailed verification. OPTIMA is currently under active development and not yet fully released; this guide provides early documentation to support planning and gather user feedback.

54 ENVIRONMENTAL SCIENCES↗

(U) Validation and Optimization of a 1-Dimensional Quasi-Isentropic Compression Model Using a Functionally Graded Material Flyer Plate

The fields studying highly compressed materials have been around for many years. These fields have given birth to better understandings of the solar fusion cycle and the liquid-metallic core of Jupiter. The highest pressures achieved have been at the National Ignition Facility (NIF) and more recently, the Z-Machine. One method to achieve higher levels of compression is to use quasi-isentropic (QI) compression. In practice, this means minimizing the amount of temperature increase of the target material. In their paper, J.H. Nguyen et. al. manufactured a functionally graded material (FGM) in order to help them achieve QI compression. The aim of the study described in this paper is to validate a 1-dimensional (1D) FLAG model that uses an FGM flyer to compress a copper (Cu) target. Once validated, the density/composition profile of the FGM is varied and optimized using Markov Chain Monte Carlo, specifically using a Metropolis-Hastings algorithm to find the optimal FGM profile that minimizes the temperature increase in the copper.

36 MATERIALS SCIENCE↗

Data Locality Enhancement of Dynamic Simulations for Exascale Computing (Final Report)

The development of modern processors exhibits two trends that complicate the optimizations of modern software. The first is the increasing sensitivity of processors' throughput to irregularities in computation. With more processors produced through a massive integration of simple cores, future systems will increasingly favor regular data-level parallel computations, but deviate from the needs of applications with complex patterns. Some evidences are already shown on Graphic Processing Units (GPU): Irregular data accesses (e.g., indirect references A[D[i]]) and conditional branches are limiting many GPU applications' performance at a level an order of magnitude lower than the peak of GPU. The second hardware trend is the growing gap between memory bandwidth and the aggregate speed—that is, the sum of all cores' computing power—of a Chip Multiprocessor (CMP). Despite the capped growth of the peak CPU speed, the aggregate speed of a CMP keeps increasing as more cores get into a single chip. It is expected that by 2018, node concurrency in an exascale system will increase by hundreds of times, whereas, memory bandwidth will expand by only 10 to 20 times. Consequently, data movement and storage is expected to consume more than 70% of the total system power. Bridging this gap is difficult; the complexities of modern CMP memory hierarchy make it even harder: Data cache becomes shared among computing units, and the sharing is often non-uniform—whether two computing units share a cache depends on their proximity and the level of the cache. On the recent IBM Power7 architecture, for instance, four hardware contexts (or SMT threads) in a core share the entire memory hierarchy, all cores in one chip share an on-chip L3 cache, and cores across chips share L3 and main memory through off-chip connections. These two trends complicate the translation of computing power into performance, especially for a program with either intensive data accesses or complex patterns in data accesses or control flow paths. Unfortunately, both attributes present and will persist in a class of important applications. For instance, many scientific simulations deal with a large volume of data. And meanwhile, as most real-world processes are non-uniform and evolving (e.g., the evolution of a galaxy or the process of a drug injection), both the computations and data accesses of these programs tend to be irregular and dynamically changing. Currently, the lack of support to these applications on modern CMP severely limits their performance. On GPU, as our recent study shows and other studies echo, performance enhancement of a factor of integers is possible when memory accesses or control flows are streamlined for a set of GPU applications. On multicore CPU, our studies show that traditional locality enhancement, for being oblivious to the new features of multicore memory hierarchy, may even cause large slowdown to data-intensive dynamic applications. The severity of the issues is expected to worsen as the two hardware trends continue. Some recent studies try to match software with the trends, but in a limited scope or manner. For irregularities on GPU, most studies focus on irregularities analyzable through static analysis (e.g., data accesses in regular loops). Dynamic irregularities are harder to address because the needed analysis and transformations typically have to happen at run time. Some other research resorts to hardware extensions, an actual adoption of which is unclear for the entailed space cost and complexity. For data locality, recent years have seen some exploitations of the new memory hierarchy on multicore for performance, but most of them are on process or thread scheduling, rather than program transformations. Our recent study reveals that program-level transformations may magnify the scheduling benefits by a factor of seven, concluding that program-level transformation should play a central role for data locality enhancement on modern CMP. But research in this direction has been sparse, and most have focused on data layout or cache performance modeling, rather than program transformations to match with the new memory hierarchy features. Overall, it is still an open question how to bridge the gap between dynamic computations and the two prominent properties of modern processors. The goal of this project is to develop a set of techniques and software tools to enhance the matching between memory accesses in dynamic simulations and the prominent features of modern and future CMP, alleviating the memory performance issues for petascale and exascale computing. This report summarizes the discoveries and products produced throughout this project. It includes free launch, a new software approach to overcoming the shortcomings of both methods; coherence-free multiview, an approach that allows multiple views of a single data object to co-exist on GPU memory during a GPU kernel execution; algorithmic optimizations to data analytics problems, especially those that involve lots of distance calculations. Supporting dynamic parallelism is important for GPU to benefit a broad range of applications. There are currently two fundamental ways for programs to exploit dynamic parallelism on GPU: a software-based approach with software-managed worklists, and a hardware-based approach through dynamic subkernel launches. Neither is satisfactory. The former is complicated to program and is often subject to some load imbalance; the latter suffers large runtime overhead. In this work, we propose free launch, a new software approach to overcoming the shortcomings of both methods. It allows programmers to use subkernel launches to express dynamic parallelism. It employs a novel compiler-based code transformation named subkernel launch removal to replace the subkernel launches with the reuse of parent threads. Coupled with an adaptive task assignment mechanism, the transformation reassigns the tasks in the subkernels to the parent threads with a good load balance. The technique requires no hardware extensions, immediately deployable on existing GPUs. It keeps the programming convenience of the subkernel launch-based approach while avoiding its large runtime overhead. Meanwhile, its superior load balancing makes it outperform manual worklist-based techniques by 3X on average. The work was published at the 48th Annual IEEE/ACM International Symposium on Microarchitecture (Micro'2015). A Graphic Processing Unit (GPU) system is typically equipped with many types of memory (e.g., global, constant, texture, shared, cache). Data placement determines what data are placed on which type of memory, essential for GPU memory performance. Prior optimizations of data placement always require a single view of a data object on memory, which limits the optimization effectiveness. In this work, we propose coherence-free multiview, an approach that allows multiple views of a single data object to co-exist on GPU memory during a GPU kernel execution. We demonstrate that under certain conditions, the multiple views can remain incoherent while facilitating enhanced data placement. We present a theorem and some compiler support to ensure the soundness of the usage of coherence-free multiview. We further develop reference-discerning data placement, a new way to enhance data placements on GPU. It enables more flexible data placements by using coherence-free multiview to leverage the slack in coherence requirement of some GPU programs. Experiments on three types of GPU systems show that, with less than 200KB space cost, the new data placement technique can provide a 1.6X average (up to 4.27X) speedup. In addition, we have examined algorithmic optimizations to data analytics problems, especially those that involve lots of distance calculations. Computing distances among data points is an essential part of many important algorithms in data analytics, graph analysis, and other domains. In each of these domains, developers have spent significant manual effort optimizing algorithms, often through novel applications of the triangle equality, in order to minimize the number of distance computations in the algorithms. In this work, we observe that many algorithms across these domains can be generalized as an instance of a generic distance-related abstraction. Based on this abstraction, we derive seven principles for correctly applying the triangular inequality to optimize distance-related algorithms. Guided by the findings, we develop Triangular OPtimizer (TOP), the first software framework that is able to automatically produce optimized algorithms that either matches or outperforms manually designed algorithms for solving distance-related problems. TOP achieves up to 237x speedups and 2.5X on average. The work has been published at the 32nd International Conference on Machine Learning (ICML'15) and the 41st International Conference on Very Large Data Bases (VLDB'15).

42 ENGINEERING↗

Gyrokinetic toroidal simulations on leading multi- and manycore HPC systems

The gyrokinetic Particle-in-Cell (PIC) method is a critical computational tool enabling petascale fusion simulation re-search. In this work, we present novel multi- and manycore-centric optimizations to enhance performance of GTC, a PIC-based production code for studying plasma microtur-bulence in tokamak devices. Our optimizations encompass all six GTC sub-routines and include multi-level particle and grid decompositions designed to improve multi-node parallel scaling, particle binning for improved load balance, GPU acceleration of key subroutines, and memory-centric optimizations to improve single-node scaling and reduce memory utilization. The new hybrid MPI-OpenMP and MPI-OpenMP-CUDA GTC versions achieve up to a 2× speedup over the production Fortran code on four parallel systems - clusters based on the AMD Magny-Cours, Intel Nehalem-EP, IBM BlueGene/P, and NVIDIA Fermi architectures. Finally, strong scaling experiments provide insight into parallel scalability, memory utilization, and programmability trade-offs for large-scale gyrokinetic PIC simulations, while attaining a 1.6× speedup on 49,152 XE6 cores.

97 MATHEMATICS AND COMPUTING↗

Thermal neutron filter design for the neutron radiography facility at the LVR-15 reactor

In 2011 a decision was made to build a neutron radiography facility at one of the unused horizontal channels of the LVR-15 research reactor in Rez, Czech Republic. One of the key conditions for operating an effective radiography facility is the delivery of a high intensity, homogeneous and collimated thermal neutron beam at the sample location. Additionally the intensity of fast neutrons has to be kept as low as possible as the fast neutrons may damage the detectors used for neutron imaging. As the spectrum in the empty horizontal channel roughly copies the spectrum in the reactor core, which has a high ratio of fast neutrons, neutron filter components have to be installed inside the channel in order to achieve desired beam parameters. As the channel design does not allow the instalment of complex filters and collimators, an optimal solution represent neutron filters made of large single-crystal ingots of proper material composition. Single-crystal silicon was chosen as a favorable filter material for its wide availability in sufficient dimensions. Besides its ability to reasonably lower the ratio of fast neutrons while still keeping high intensities of thermal neutrons, due to its large dimensions, it suits as a shielding against gamma radiation from the reactor core. For designing the necessary filter dimensions the Monte-Carlo MCNP transport code was used. As the code does not provide neutron cross-section libraries for thermal neutron transport through single-crystalline silicon, these had to be created by approximating the theory of thermal neutron scattering and modifying the original cross-section data which are provided with the code. Carrying out a series of calculations the filter thickness of 1 m proved good for gaining a beam with desired parameters and a low gamma background. After mounting the filter inside the channel several measurements of the neutron field were realized at the beam exit. The results have justified the expected calculated values. After the successful filter installing and a series of measurements, first test neutron radiography attempts with test samples could been carried out. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Structure of a HIV-1 IN-Allosteric inhibitor complex at 2.93 Å resolution: Routes to inhibitor optimization

HIV integrase (IN) inserts viral DNA into the host genome and is the target of the strand transfer inhibitors (STIs), a class of small molecules currently in clinical use. Another potent class of antivirals is the allosteric inhibitors of integrase, or ALLINIs. ALLINIs promote IN aggregation by stabilizing an interaction between the catalytic core domain (CCD) and carboxy-terminal domain (CTD) that undermines viral particle formation in late replication. Ongoing challenges with inhibitor potency, toxicity, and viral resistance motivate research to understand their mechanism. Here, we report a 2.93 Å X-ray crystal structure of the minimal ternary complex between CCD , CTD , and the ALLINI BI-224436. This structure reveals an asymmetric ternary complex with a prominent network of π-mediated interactions that suggest specific avenues for future ALLINI development and optimization.

60 APPLIED LIFE SCIENCES↗

A THREE-PHASE CHEMICAL MODEL OF HOT CORES: THE FORMATION OF GLYCINE

A new chemical model is presented that simulates fully coupled gas-phase, grain-surface, and bulk-ice chemistry in hot cores. Glycine (NH{sub 2}CH{sub 2}COOH), the simplest amino acid, and related molecules such as glycinal, propionic acid, and propanal, are included in the chemical network. Glycine is found to form in moderate abundance within and upon dust-grain ices via three radical-addition mechanisms, with no single mechanism strongly dominant. Glycine production in the ice occurs over temperatures {approx}40-120 K. Peak gas-phase glycine fractional abundances lie in the range 8 Multiplication-Sign 10{sup -11}-8 Multiplication-Sign 10{sup -9}, occurring at {approx}200 K, the evaporation temperature of glycine. A gas-phase mechanism for glycine production is tested and found insignificant, even under optimal conditions. A new spectroscopic radiative-transfer model is used, allowing the translation and comparison of the chemical-model results with observations of specific sources. Comparison with the nearby hot-core source NGC 6334 IRS1 shows excellent agreement with integrated line intensities of observed species, including methyl formate. The results for glycine are consistent with the current lack of a detection of this molecule toward other sources; the high evaporation temperature of glycine renders the emission region extremely compact. Glycine detection with ALMA is predicted to be highly plausible, for bright, nearby sources with narrow emission lines. Photodissociation of water and subsequent hydrogen abstraction from organic molecules by OH, and NH{sub 2}, are crucial to the buildup of complex organic species in the ice. The inclusion of alternative branches within the network of radical-addition reactions appears important to the abundances of hot-core molecules; less favorable branching ratios may remedy the anomalously high abundance of glycolaldehyde predicted by this and previous models.

79 ASTRONOMY AND ASTROPHYSICS↗

Evaluating LULESH Kernels on OpenCL FPGA

FPGAs are becoming promising heterogeneous computing components for high-performance computing. In this paper, we evaluate the resource utilizations, performance, and performance per watt of our implementations of the LULESH kernels in OpenCL on an Arria10-based FPGA platform. LULESH is a complex proxy application in the CORAL benchmark suite. We choose two representative kernels “CalcFBHourglassForceForElems” and “EvalEOSForElems” from the application in our study. Compared with the baseline implementations, our optimizations improve the performance by a factor of 1.65X and 2.96X for the two kernels on the FPGA, respectively. Using directives for accelerator programming, we also evaluate the performance of the kernels on an Intel Xeon 16-core CPU and an Nvidia K80 GPU. We find that the FPGA, constrained by the memory bandwidth, can perform 1.05X to 3.4X better than the CPU and GPU for small problem sizes. For the first kernel, the performance per watt on the FPGA is 1.59X and 7.1X higher than that on an Intel Xeon 16-core CPU and an Nvidia K80 GPU, respectively. For the second kernel, the performance per watt on the GPU is 1.82X higher than that on the FPGA. However, the performance per watt on the FPGA is 1.77X higher than that on the CPU.

FPGA↗

A Novel Transverse Flux Machine for Vehicle Traction Applications

A novel transverse flux machine topology for electric vehicle traction application using ferrite magnets is presented in this paper. The proposed transverse flux topology utilizes novel magnet arrangements in the rotor that are similar to Halbach-array to boost flux linkage; on the stator side, cores are alternately arranged around a pair of ring windings in each phase to make use of the entire rotor flux that eliminates end windings. Analytical design considerations and finite element methods are used for an optimized design of a scooter in-wheel motor. Simulation results from Finite Element Analysis (FEA) show the motor achieved comparable torque density to conventional rare-earth permanent magnet machines. This machine is a viable candidate for direct drive applications with low cost and high torque density.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Global Optimization of Adsorbate Covered Supported Cluster Catalysts: The Case of Pt 7 H 10 CH 3 on α-Al 2 O 3

Determining structures of supported sub-nanometer catalytic clusters is important for finding binding sites, active sites, and reaction mechanisms. In realistic conditions, the cluster may be covered with adsorbed reactants and intermediates, which strongly affect the structure of the cluster compared to the low coverage regime. The global optimization of supported adsorbate-covered clusters is not possible with existing methods. In this paper, we present a customized Basin Hopping (BH) approach, with a core (metal cluster) – shell (adsorbates) separation scheme, and perform first applications to the search of low-energy isomers of Pt 7 /α-Al 2 O 3 at high hydrogen coverage (10H). The presence of adsorbates significantly alters the low-energy isomers compared to bare Pt 7 /α-Al 2 O 3 . Molecular dynamics simulations additionally show the different time-scales associated with the mobility of H and Pt atoms. The revised BH method with core-shell separation presents key advantages for the structural exploration of adsorbate-covered supported catalysts, relevant to realistic catalytic conditions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Fabrication and Characterization of Core–Shell Density-Graded 316L Stainless Steel Porous Structure

In the present work, cylindrical shape 316 L cellular structure with different densities in its core and outer layer (shell) is fabricated by using carbamide as a space holder, via powder metallurgy route and layer-by-layer technique. The arrangement of the created pore is the same as face-centered cubic atomic structure, and different densities are created in two regions by using carbamide particles having two different sizes in the range of 1.7-2 and 2-2.4 mm. The effect of creating a structure with higher porosity (64.5%) in the core and lower porosity (53.8%) in the shell and vice versa and also change in the ratio of the core to the cylinder cross-sectional areas, on the mechanical properties and compaction load bearing of the fabricated foam samples were investigated. In leaching process of the carbamide particles, as an important step of porous structure’s fabrication, it is shown that discontinuous leaching process is more favorable than continuous, by which it would be possible to remove more carbamide particles (around 20%) at the same time. Furthermore, the deformation of the density-graded foam shows the parallel mechanism in the core and shell sections, and the contribution of each part depends on its density and thickness. The energy absorption behavior of the fabricated specimens is evaluated optimally in terms of the energy absorption value associated with the ideal adsorption behavior. The maximum ideal energy absorption efficiency for the samples with more porosity in the shell was approximately equal to 0.91, while for the sample includes the lower amount of porosity in the shell, this value was in the range of 0.85 and 0.89.

36 MATERIALS SCIENCE↗

Discovery of imidazo[1,2- a ]-pyridine inhibitors of pan-PI3 kinases that are efficacious in a mouse xenograft model

Alterations in PI3K/AKT signaling are known to be implicated with tumorigenesis. The PI3 kinases family of lipid kinases has been an attractive therapeutic target for cancer treatment. Imidazopyridine compound 1, a potent, selective, and orally available pan-PI3K inhibitor, identified by scaffold morphing of a benzothiazole hit, was further optimized in order to achieve efficacy in a PTEN-deleted A2780 ovarian cancer mouse xenograft model. With a hypothesis that a planar conformation between the core and the 6-heteroaryl ring will allow for the accommodation of larger 5'-substituents in a hydrophobic area under P-loop, SAR efforts focused on 5'-alkoxy heteroaryl rings at the 6-position of imidazopyridine and imidazopyridazine cores that have the same dihedral angle of zero degrees. 6'-Alkoxy 5'-aminopyrazines in the imidazopyridine series were identified as the most potent compounds in the A2780 cell line. Compound 14 with 1,1,1-trifluoroisopropoxy group at 6'-position demonstrated excellent potency and selectivity, good oral exposure in rats and in vivo efficacy in A2780 tumor-bearing mouse. Also, we disclose the X-ray co-crystal structure of one enantiomer of compound 14 in PI3Kα, confirming that the trifluoromethyl group fits nicely in the hydrophobic hot spot under P-loop.

59 BASIC BIOLOGICAL SCIENCES↗

The influence of an ITER-like wall on disruptions at JET

In order to preserve the integrity of large tokamaks such as ITER, the number of disruptions has to be limited. JET has operated previously with a low frequency of disruptions (i.e., disruption rate) of 3.4% [P. C. de Vries et al., Nucl. Fusion 51, 053018 (2011)]. The start of operations with the new full-metal ITER-like wall at JET showed a marked rise in the disruption rate to 10%. A full survey was carried out to identify the root causes, the chain-of-events and classifying each disruption, similar to a previous analysis for carbon-wall operations. It showed the improvements made to avoid various disruption classes, but also indicated those disruption types responsible for the enhanced disruption rate. The latter can be mainly attributed to disruptions due to too high core radiation but also due to density control issues and error field locked modes. Detailed technical and physics understanding of disruption causes is essential for devising optimized strategies to avoid or mitigate these events.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion

In this Letter, we introduce FusionNet, a multi-modality deep learning framework designed to predict and analyze output pulses in high-power rare-earth-doped laser systems driving parametric conversion in homogeneous guided nonlinear media. FusionNet integrates temporal, spectral, and physical experimental conditions to model ultrafast nonlinear phenomena, including parametric nonlinear frequency conversion, self-phase modulation, and cross-phase modulation in homogeneous guided systems such as gas-filled hollow-core fibers. These systems bridge physical models with experimental data, advancing our understanding of light-guiding principles and nonlinear interactions while expediting the design and optimization of on-demand high-power, high-brightness systems. Our results demonstrate a 73% reduction in prediction error and an 83% improvement in computational efficiency compared to conventional neural networks. This work establishes a new paradigm for accelerating parametric simulations and optimizing experimental designs in high-power laser systems, with further implications for high-precision spectroscopy, quantum information science, and distributed entangled interconnects.

47 OTHER INSTRUMENTATION↗

Integrating External Resources with a Task-Based Programming Model

Accessing external resources (e.g., loading input data, checkpointing snapshots, and out-of-core processing) can have a significant impact on the performance of supercomputer applications. However, no existing programming systems for high-performance computing directly manage and optimize these external accesses. As a result, users must explicitly manage external accesses alongside their computation at the application level, which can result in both correctness and performance issues. We address this limitation by introducing Iris, a task-based programming model with semantics for external resources. Iris allows applications to describe their access requirements to external resources and the relationship of those accesses to the computation. Iris incorporates external I/O into a deferred execution model, reschedules external I/O to overlap I/O with computation, and reduces external I/O when possible. We evaluate Iris on three microbenchmarks representative of important workloads in HPC and a full combustion simulation, S3D. We demonstrate that the Iris implementation of S3D reduces the external I/O overhead by up to 20×, compared to the Legion and the Fortran implementations.

97 MATHEMATICS AND COMPUTING↗

Optimizing Sparse Matrix-Multiple Vectors Multiplication for Nuclear Configuration Interaction Calculations

Obtaining highly accurate predictions on the properties of light atomic nuclei using the configuration interaction (CI) approach requires computing a few extremal Eigen pairs of the many-body nuclear Hamiltonian matrix. In the Many-body Fermion Dynamics for nuclei (MFDn) code, a block Eigen solver is used for this purpose. Due to the large size of the sparse matrices involved, a significant fraction of the time spent on the Eigen value computations is associated with the multiplication of a sparse matrix (and the transpose of that matrix) with multiple vectors (SpMM and SpMM-T). Existing implementations of SpMM and SpMM-T significantly underperform expectations. Thus, in this paper, we present and analyze optimized implementations of SpMM and SpMM-T. We base our implementation on the compressed sparse blocks (CSB) matrix format and target systems with multi-core architectures. We develop a performance model that allows us to understand and estimate the performance characteristics of our SpMM kernel implementations, and demonstrate the efficiency of our implementation on a series of real-world matrices extracted from MFDn. In particular, we obtain 3-4 speedup on the requisite operations over good implementations based on the commonly used compressed sparse row (CSR) matrix format. The improvements in the SpMM kernel suggest we may attain roughly a 40% speed up in the overall execution time of the block Eigen solver used in MFDn.

97 MATHEMATICS AND COMPUTING↗

A Hartree-Fock Application Using UPC++ and the New DArray Library

The Hartree-Fock (HF) method is the fundamental first step for incorporating quantum mechanics into many-electron simulations of atoms and molecules, and it is an important component of computational chemistry toolkits like NWChem. The GTFock code is an HF implementation that, while it does not have all the features in NWChem, represents crucial algorithmic advances that reduce communication and improve load balance by doing an up-front static partitioning of tasks, followed by work stealing whenever necessary. To enable innovations in algorithms and exploit next generation exascale systems, it is crucial to support quantum chemistry codes using expressive and convenient programming models and runtime systems that are also efficient and scalable. Here, this paper presents an HF implementation similar to GTFock using UPC++, a partitioned global address space model that includes flexible communication, asynchronous remote computation, and a powerful multidimensional array library. UPC++ offers runtime features that are useful for HF such as active messages, a rich calculus for array operations, hardware-supported fetch-and-add, and functions for ensuring asynchronous runtime progress. We present a new distributed array abstraction, DArray, that is convenient for the kinds of random-access array updates and linear algebra operations on block-distributed arrays with irregular data ownership. Finally, we analyze the performance of atomic fetch-and-add operations (relevant for load balancing) and runtime attentiveness, then compare various techniques and optimizations for each. Our optimized implementation of HF using UPC++ and the DArrays library shows up to 20% improvement over GTFock with Global Arrays at scales up to 24,000 cores.

97 MATHEMATICS AND COMPUTING↗