Search NASA⌕ Search

SEARCH · Search NASA

Results for “architecture 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 91 records · Page 5

Software for Sparse Tensor Decomposition on Emerging Computing Architectures

In this paper, we develop software for decomposing sparse tensors that is portable to and performant on a variety of multicore, manycore, and GPU computing architectures. The result is a single code whose performance matches optimized architecture-specific implementations. The key to a portable approach is to determine multiple levels of parallelism that can be mapped in different ways to different architectures, and we explain how to do this for the matricized tensor times Khatri--Rao product (MTTKRP), which is the key kernel in canonical polyadic tensor decomposition. Our implementation leverages the Kokkos framework, which enables a single code to achieve high performance across multiple architectures that differ in how they approach fine-grained parallelism. We also introduce a new construct for portable thread-local arrays, which we call compile-time polymorphic arrays. Not only are the specifics of our approaches and implementation interesting for tuning tensor computations, but they also provide a roadmap for developing other portable high-performance codes. As a last step in optimizing performance, we modify the MTTKRP algorithm itself to do a permuted traversal of tensor nonzeros to reduce atomic-write contention. Lastly, we test the performance of our implementation on 16- and 68-core Intel CPUs and the K80 and P100 NVIDIA GPUs, showing that we are competitive with state-of-the-art architecture-specific codes while having the advantage of being able to run on a variety of architectures.

97 MATHEMATICS AND COMPUTING↗

Molecular Mechanisms Affecting Cell Wall Properties and Leaf Architecture [Chapter 8]

Leaf architecture is determined by cell shape, size, and density. As plant cells are enclosed by a rigid cell wall, changes to leaf architecture have to occur through downstream genetic systems that induce alterations in (1) cell wall composition, (2) synthesis, assembly, and orientation of cytoskeletal elements and/or (3) the degree of cross-linkage between wall components in response to upstream developmental and environmental cues. This chapter reviews how leaf architecture is influenced by molecular mechanisms that modulate the above wall modification processes. Upstream signaling systems such as salicylic (SA), jasmonic (JA), and gibberellic (GA) acid have significant effects on leaf architecture. GA promotes and JA and SA suppress growth. Leaf architectural changes are brought about by these upstream systems in concert or in an interactive manner, and the associated downstream molecular systems that are involved in executing changes to cell wall properties will be discussed. Evidence will be provided to show that xyloglucan endotransglucosylase/hydrolase and pectin methyltransferase/pectin methylesterase/pectin methylesterase inhibitor systems are key downstream execution points of leaf architectural changes common to different upstream molecular systems. Optimization of leaf architecture maximizes light interception,gas exchange properties, and photosynthesis. In addition, plant growth has been shown to be more sensitive to leaf area than to area-based photosynthesis rate. Therefore, understanding genes and molecular mechanisms that affect cell wall properties and leaf architecture has broader implications in terms of crop improvement, and candidate genes that can be manipulated to optimize leaf architecture in order to maximize net carbon assimilation and plant growth will be proposed.

59 BASIC BIOLOGICAL SCIENCES↗

Final Report A Multi-Language Environment For Programmable Code Optimization and Empirical Tuning

This report summarizes our effort and results of building an integrated optimization environment to effectively combine the programmable control and the empirical tuning of source-to-source compiler optimizations within the framework of multiple existing languages, specifically C, C++, and Fortran. The environment contains two main components: the ROSE analysis engine, which is based on the ROSE C/C++/Fortran2003 source-to-source compiler developed by Co-PI Dr.Quinlan et. al at DOE/LLNL, and the POET transformation engine, which is based on an interpreted program transformation language developed by Dr. Yi at University of Texas at San Antonio (UTSA). The ROSE analysis engine performs advanced compiler analysis, identifies profitable code transformations, and then produces output in POET, a language designed to provide programmable control of compiler optimizations to application developers and to support the parameterization of architecture-sensitive optimizations so that their configurations can be empirically tuned later. This POET output can then be ported to different machines together with the user application, where a POET-based search engine empirically reconfigures the parameterized optimizations until satisfactory performance is found. Computational specialists can write POET scripts to directly control the optimization of their code. Application developers can interact with ROSE to obtain optimization feedback as well as provide domain-specific knowledge and high-level optimization strategies. The optimization environment is expected to support different levels of automation and programmer intervention, from fully-automated tuning to semi-automated development and to manual programmable control.

97 MATHEMATICS AND COMPUTING↗

Long-term missing value imputation for time series data using deep neural networks

We present an approach that uses a deep learning model, in particular, a MultiLayer Perceptron, for estimating the missing values of a variable in multivariate time series data. We focus on filling a long continuous gap (e.g., multiple months of missing daily observations) rather than on individual randomly missing observations. Our proposed gap filling algorithm uses an automated method for determining the optimal MLP model architecture, thus allowing for optimal prediction performance for the given time series. We tested our approach by filling gaps of various lengths (three months to three years) in three environmental datasets with different time series characteristics, namely daily groundwater levels, daily soil moisture, and hourly Net Ecosystem Exchange. We compared the accuracy of the gap-filled values obtained with our approach to the widely used R-based time series gap filling methods ImputeTS and mtsdi. The results indicate that using an MLP for filling a large gap leads to better results, especially when the data behave nonlinearly. Thus, our approach enables the use of datasets that have a large gap in one variable, which is common in many long-term environmental monitoring observations.

97 MATHEMATICS AND COMPUTING↗

Neural Networks for Prediction of Complex Chemistry in Water Treatment Process Optimization

Water chemistry plays a critical role in the design and operation of water treatment processes. Detailed chemistry modeling tools use a combination of advanced thermodynamic models and extensive databases to predict phase equilibria and reaction phenomena. The complexity and formulation of these models preclude their direct integration in equation-oriented modeling platforms, making it difficult to use their capabilities for rigorous water treatment process optimization. Neural networks (NN) can provide a pathway for integrating the predictive capability of chemistry software into equation-oriented models and enable optimization of complex water treatment processes across a broad range of conditions and process designs. Herein, we assess how NN architecture and training data impact their accuracy and use in equation-oriented water treatment models. We generate training data using PhreeqC software and determine how data generation and sample size impact the accuracy of trained NNs. The effect of NN architecture on optimization is evaluated by optimizing hypothetical black-box desalination processes using a range of feed compositions from USGS brackish water data set, tracking the number of successful optimizations, and testing the impact of initial guess on the final solution. Our results clearly demonstrate that data generation and architecture impact NN accuracy and viability for use in equation-oriented optimization problems.

Dudchenko, Alexander V↗

From Physics Model to Results: An Optimizing Framework for Cross-Architecture Code Generation

Starting from a high-level problem description in terms of partial differential equations using abstract tensor notation, the Chemora framework discretizes, optimizes, and generates complete high performance codes for a wide range of compute architectures. Chemora extends the capabilities of Cactus, facilitating the usage of large-scale CPU/GPU systems in an efficient manner for complex applications, without low-level code tuning. Chemora achieves parallelism through MPI and multi-threading, combining OpenMP and CUDA. Optimizations include high-level code transformations, efficient loop traversal strategies, dynamically selected data and instruction cache usage strategies, and JIT compilation of GPU code tailored to the problem characteristics. The discretization is based on higher-order finite differences on multi-block domains. Chemora's capabilities are demonstrated by simulations of black hole collisions. This problem provides an acid test of the framework, as the Einstein equations contain hundreds of variables and thousands of terms.

Blazewicz, Marek↗

Analysis of Vector Particle-In-Cell (VPIC) memory usage optimizations on cutting-edge computer architectures

Vector Particle-In-Cell (VPIC) is one of the fastest plasma simulation codes in the world, with particle numbers ranging from one trillion on the first petascale system, Roadrunner, to ten trillion particles on the more recent Blue Waters supercomputer. As supercomputers continue to grow rapidly in size, so too does the gap between computing capability and memory capability. Current memory systems limit VPIC simulations greatly as the maximum number of particles that can be simulated directly depends on the available memory. In this study, we present a suite of VPIC memory optimizations (i.e., particle weight, half-precision, and fixed-point optimizations) that enable a significant increase in the number of particles in VPIC simulations. Here, we assess the optimizations’ impact on memory and runtime performance for a suite of cutting-edge computer architectures such has the NVIDIA V100 GPU, the IBM Power9, and the Fujitsu A64FX architectures. Our optimizations enable a 31.25% reduction in memory usage and up to 40% increase in the number of particles. This paper extends our work on developing particle storage format optimizations Tan et al.

97 MATHEMATICS AND COMPUTING↗

Real-Time Optimization of Distribution-level Energy Resources [SWR-18-27]

Researchers at NREL have developed a novel real-time control architecture to optimize the operation of DERs at residential, commercial, and industrial levels. The real-time system enables (portions of) feeders to emulate virtual power plants providing services to the rest of the grid, while ensuring satisfaction of electrical limits and maximizing customers’ benefits. This system can be integrated with legacy hardware and/or new advanced systems to optimally manage both individually-controlled DERs and aggregations of DERs. By virtue of the proposed engineering approach, the DERs collectively regulate the powers at an electrical point to respond to grid dispatch signals such as an automatic generation control, a ramping signal, or a 5-minute dispatch. Overall, this architecture allows end customers to minimize their payments and partake in grid operations while guaranteeing power quality in the distribution network.

Dall-Anese, Emiliano↗

Advancing Scientific Productivity through Better Scientific Software: Developer Productivity and Software Sustainability Report

The Exascale Computing Project (ECP) provides a unique opportunity to advance computational science and engineering (CSE) through an accelerated growth phase in extreme-scale computing. Central to the project is the development of next-generation applications and software technologies that can exploit emerging architectures for optimal performance and provide high-fidelity, multiphysics, multiscale capabilities. However, disruptive changes in computer architectures and the complexities of tackling new frontiers in extreme-scale modeling, simulation, and analysis present daunting challenges to the productivity of software developers and the sustainability of software artifacts. Members of the CSE community - especially at extreme scales but more broadly at all scales of computing - face an urgent need to improve developer productivity, positively impacting product quality, development time, and staffing resources, and software sustainability, reducing the cost of maintaining, sustaining, and evolving software capabilities.

97 MATHEMATICS AND COMPUTING↗

Cummins MD & HD Accessory Hybridization CRADA -Annual Report FY15

There are many areas of MD and HD vehicles that can be improved by new technologies and optimized control strategies. Component optimization and idle reduction need to be addressed, this is best done by a two part approach that includes selecting the best component technology, and/or architecture, and optimized controls that are vehicle focused. While this is a common focus in the light duty industry it has been gaining momentum in the MD and HD market as the market gets more competitive and the regulations become more stringent. When looking into systems optimization and idle reduction technologies, affected vehicle systems must first be considered, and if possible included in the new architecture to get the most benefit out of these new capabilities. Typically, when looking into idle reduction or component optimization for MD/HD, the vehicle s accessories become a prime candidate for electrification or hybridization. While this has already been studied on light duty vehicles (especially on hybrids and electric vehicles) it has not made any head way or market penetration in most MD and HD applications. If hybrids and electric MD and HD vehicles begin to break into the market this would be a necessary step into the ability to make those vehicles successful by allowing for independent, optimized operation separate from the engine.

33 ADVANCED PROPULSION SYSTEMS↗

System, methods and apparatus for program optimization for multi-threaded processor architectures

Methods, apparatus and computer software product for source code optimization are provided. In an exemplary embodiment, a first custom computing apparatus is used to optimize the execution of source code on a second computing apparatus. In this embodiment, the first custom computing apparatus contains a memory, a storage medium and at least one processor with at least one multi-stage execution unit. The second computing apparatus contains at least two multi-stage execution units that allow for parallel execution of tasks. The first custom computing apparatus optimizes the code for parallelism, locality of operations and contiguity of memory accesses on the second computing apparatus. This Abstract is provided for the sole purpose of complying with the Abstract requirement rules. This Abstract is submitted with the explicit understanding that it will not be used to interpret or to limit the scope or the meaning of the claims.

42 ENGINEERING↗

Practical implications of SFQ-based two-qubit gates

Scalability of today’s superconducting quantum computers is limited due to the huge costs of generating/routing microwave control pulses per qubit from room temperature. One active research area in both industry and academia is to push the classical controllers to the dilution refrigerator in order to increase the scalability of quantum computers. Superconducting Single Flux Quantum (SFQ) is a classical logic technology with low power consumption and ultra-high speed, and thus is a promising candidate for in-fridge classical controllers with maximized scalability. Prior work has demonstrated high-fidelity SFQ-based single-qubit gates. However, little research has been done on SFQ-based multi-qubit gates, which are necessary to realize SFQ-based universal quantum computing.In this paper, we present the first thorough analysis of SFQ-based two-qubit gates. Our observations show that SFQ-based two-qubit gates tend to have high leakage to qubit non-computational subspace, which presents severe design challenges. We show that despite these challenges, we can realize gates with high fidelity by carefully designing optimal control methods and qubit architectures. We develop optimal control methods that suppress leakage, and also investigate various qubit architectures that reduce the leakage. After carefully engineering our SFQ-friendly quantum system, we show that it can achieve similar gate fidelity and gate time to microwave-based quantum systems. Furthermore, the promising results of this paper show that (1) SFQ-based universal quantum computation is both feasible and effective; and (2) SFQ is a promising approach in designing classical controller for quantum machines because it can increase the scalability while preserving gate fidelity and performance.

42 ENGINEERING↗

Optimizing Hydrogen Fueling Infrastructure Plans on Freight Corridors for Heavy-Duty Fuel Cell Electric Vehicles

The development of a future hydrogen energy economy will require the development of several hydrogen market and industry segments including a hydrogen-based commercial freight transportation ecosystem. For a sustainable freight transportation ecosystem, the supporting fueling infrastructure and the associated vehicle powertrains making use of hydrogen fuel will need to be co-established. This article introduces the OR-AGENT (Optimal Regional Architecture Generation for Electrified National Transportation) tool developed at the Oak Ridge National Laboratory, which has been used to optimize the hydrogen refueling infrastructure requirements on the I-75 corridor for heavy-duty (HD) fuel cell electric commercial vehicles (FCEV). This constraint-based optimization model considers existing fueling locations, regional-specific vehicle fuel economy and weight, vehicle origin and destination (O-D), and vehicle volume by class and infrastructure costs to characterize in-mission refueling requirements for a given freight corridor. The authors applied this framework to determine the ideal public access locations for hydrogen refueling (constrained by existing fueling stations), the minimal viable cost to deploy sufficient hydrogen fuel dispensers, and associated equipment, to accommodate a growing population of hydrogen fuel cell trucks. The framework discussed in this article can be expanded and applied to a larger interstate system, expanded regional corridor, or other transportation network. This article is the third in a series of papers that defined the model development to optimize a national hydrogen refueling infrastructure ecosystem for HD commercial vehicles.

33 ADVANCED PROPULSION SYSTEMS↗

Optimizing Long Term Hydrogen Fueling Infrastructure Plans on Freight Corridors for Heavy Duty Fuel Cell Electric Vehicles

The development of a future hydrogen energy economy will require the development of several hydrogen market and industry segments including a hydrogen based commercial freight transportation ecosystem. For a sustainable freight transportation ecosystem, the supporting fueling infrastructure and the associated vehicle powertrains making use of hydrogen fuel will need to be co-established. This paper develops a long-term plan for refueling infrastructure deployment using the OR-AGENT (Optimal Regional Architecture Generation for Electrified National Transportation) tool developed at the Oak Ridge National Laboratory, which has been used to optimize the hydrogen refueling infrastructure requirements on the I-75 corridor for heavy duty (HD) fuel cell electric commercial vehicles (FCEV). This constraint-based optimization model considers existing fueling locations, regional specific vehicle fuel economy and weight, vehicle origin and destination (OD), vehicle volume by class and infrastructure costs to characterize in-mission refueling requirements for a given freight corridor. The authors applied this framework to determine the ideal long term public access locations for hydrogen refueling (constrained by existing fueling stations and dispensing technology), the minimal viable cost to deploy sufficient hydrogen fuel dispensers, and associated equipment, to accommodate a growing population of hydrogen fuel cell trucks. So the framework discussed in this paper can be expanded and applied to additional electrified powertrains as well as a larger interstate system, expanded regional corridor, or other transportation networks.

08 HYDROGEN↗

Ensembles of Networks Produced from Neural Architecture Search

Neural architecture search (NAS) is a popular topic at the intersection of deep learning and high performance computing. NAS focuses on optimizing the architecture of neural networks along with their hyperparameters in order to produce networks with superior performance. Much of the focus has been on how to produce a single best network to solve a machine learning problem, but as NAS methods produce many networks that work very well, this affords the opportunity to ensemble these networks to produce an improved result. Additionally, the diversity of network structures produced by NAS drives a natural bias towards diversity of predictions produced by the individual networks. This results in an improved ensemble over simply creating an ensemble that contains duplicates of the best network architecture retrained to have unique weights.

Herron, Emily↗

Hardware-Conscious Optimization of the Quantum Toffoli Gate

While quantum computing holds great potential in combinatorial optimization, electronic structure calculation, and number theory, the current era of quantum computing is limited by noisy hardware. Many quantum compilation approaches can mitigate the effects of imperfect hardware by optimizing quantum circuits for objectives such as critical path length. Few approaches consider quantum circuits in terms of the set of vendor-calibrated operations (i.e., native gates) available on target hardware. This manuscript expands the analytical and numerical approaches for optimizing quantum circuits at this abstraction level. We present a procedure for combining the strengths of analytical native gate-level optimization with numerical optimization. Although we focus on optimizing Toffoli gates on the IBMQ native gate set, the methods presented are generalizable to any gate and superconducting qubit architecture. Our optimized Toffoli gate implementation demonstrates an 18% reduction in infidelity compared with the canonical implementation as benchmarked on IBM Jakarta with quantum process tomography. Assuming the inclusion of multi-qubit cross-resonance (MCR) gates in the IBMQ native gate set, we produce Toffoli implementations with only six multi-qubit gates, a 25% reduction from the canonical eight multi-qubit implementations for linearly connected qubits.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

HPS-RL: Hyperparameter tuning for deep RL applications (HPS-RL) v1

Genetic Algorithms meets Deep RL for Hyperparameters Hyperparameter optimization and architecture search can easily become cumbersome and finding the right hyperparameters can seriously impact the robustness of the deep RL application being developed. We use genetic algorithms to evolve optimum deep RL architectures in a scalable manner. HPS-RL is designed to work with multiple gym enviornments, allow users to test their own optimization functions and tune multi-objective parameters in multiple deep RL algorithms. HPS-RL uses multi-threading and is being extended with mpipy for distributed processing on HPC. https://arxiv.org/abs/2201.11182

Kiran, Mariam↗

Engineering catalytical electrodes for applications in energy areas

An ink formulation and electrode that enhances hydrogen production, oxygen production, carbon dioxide reduction and other electrocatalytic reactions. Embodiments include an ink formulation with polymer binders having different catalytical precursors and a 3D electrode produced by additive manufacturing from the inventor's ink formulation. Various embodiments of the inventor's apparatus, systems, and methods provide inks that that are 3D-printed into patterns that optimize surface area and flow. The catalytic materials are imbedded into the ink matrix which is then printed into a 3D structure that has architecture that optimizes surface area and flow properties.

Liang, Siwei↗