TRAVOLTA: GPU acceleration and algorithmic improvements for constructing quantum optimal control fields in photo-excited systems
Not Available
97 MATHEMATICS AND COMPUTING↗
SEARCH · Engineering Papers
Results for “Parallel Optimization Algorithms”
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.
Fast Mesh-to-Mesh Remaps Using Hash Algorithms
Here, we explore the potential uses of hash-based algorithms in the remap operation, mapping one computational mesh onto another. We implement and test optimizations designed to reduce memory operations and compare these optimizations in order to evaluate the performance impact across different meshes. In particular, we created a new remap method that creates a structured hierarchy of hashes. Tests were run on 2D meshes on up to 14 levels of mesh refinement and hundreds of millions of cells to measure the algorithms' relative speeds under differing circumstances. We show that our methods perform two orders of magnitude better than the standard kD-tree algorithm and that on different meshes different hash methods can be optimal. We explore these algorithms on serial CPUs, GPUs using OpenCL, and multi-core CPUs using OpenMP.
97 MATHEMATICS AND COMPUTING↗
Efficient Parallelization of Irregular Applications on GPU Architectures
With the enlarging computation capacity of general Graphics Processing Units (GPUs), leveraging GPUs to accelerate parallel applications has become a critical topic in academia and industry. However, a wide range of irregular applications with the computation-/memory-intensive nature cannot easily achieve high GPU utilization. The challenges mainly involve the following aspects: first, data dependence leads to coarse-grained kernel and inefficient parallelism; second, heavy GPU memory usage may cause frequent memory evictions and extra overhead of I/O; third, specific computation patterns produce memory redundancies; last, workload balance and data reusability conjunctly benefit the overall performance, but there may exist a dynamic trade-off between them. Targeting these challenges, this dissertation proposes multiple optimizations to accelerate two real-world applications: many-body correlation functions to simulate nuclear physics in a large-scale scientific system; the other is the eALS-based matrix factorization recommendation system. To accelerate the calculations of many-body correlation functions, this dissertation presents three frameworks in GPU memory management and multi-GPU scheduling. Firstly, an optimized systematic GPU memory management framework, MemHC, utilizes a series of new memory reduction designs in GPU memory allocation, CPU/GPU communications, and GPU memory oversubscription. Secondly, an enhanced multi-GPU scheduling framework, MICCO, particularly by taking both data dimension (e.g., data reuse and data eviction) and computation dimension into account. MICCO designs a heuristic scheduling algorithm and a machine learning-based regression model to generate the optimal settings of a proposed new concept to manage the trade-off. Thirdly, a locality-aware multi-GPU scheduling framework. This scheduler leverages pipeline batch generation with a looking-ahead strategy by building local dependency graphs for memory transfer reduction and better data reuse, achieving up to 79.92% memory cost reduction and 1.67x speedup. To parallelize the eALS-based recommendation system, this dissertation proposes an efficient CPU/GPU heterogeneous recommendation system, HEALS. HEALS employs newly designed architecture-adaptive data formats to achieve load balance and good data locality on CPU and GPU. To mitigate the data dependence, HEALS presents a CPU/GPU collaboration model for both task parallelism and data parallelism with multiple kernel computation optimizations. In summary, this dissertation efficiently accelerates two typical irregular applications on GPUs by building four frameworks, including CPU/GPU collaboration, GPU memory management, and multi-GPU scheduling.
Wang, Qihan↗
Tail queues: A multi-threaded matching architecture
As we approach exascale, computational parallelism will have to drastically increase in order to meet throughput targets. Many–core architectures have exacerbated this problem by trading reduced clock speeds, core complexity, and computation throughput for increasing parallelism. This presents two major challenges for communication libraries such as MPI: the library must leverage the performance advantages of thread level parallelism and avoid the scalability problems associated with increasing the number of processes to that scale. Hybrid programming models, such as MPI+X, have been proposed to address these challenges. MPI THREAD MULTIPLE is MPI's thread safe mode. While there has been work to optimize it, it largely remains non–performant in most implementations. While current applications avoid MPI multithreading due to performance concerns, it is expected to be utilized in future applications. One of the major synchronous data structures required by MPI is the matching engine. In this paper, we present a parallel matching algorithm that can improve MPI matching for multithreaded applications. We then perform a feasibility study to demonstrate the performance benefit of the technique.
97 MATHEMATICS AND COMPUTING↗
Autonomous attitude estimation via star sensing and pattern recognition
Results are reported on the development of an autonomous, onboard, near real time spacecraft attitude estimation technique. The approach uses CCD based star sensors to digitize relative star positions. Three microcomputers are envisioned, configured in parallel, to: (1) determine star image centroids and delete spurious images; (2) identify measured stars with stars in an onboard catalog and determine discrete attitude estimates; (3) integrate gyro rate measurements and determine optimal real time attitude estimates for use in the control system and for feedback to the star identification algorithm. Algorithms for the star identification are presented. The discrete attitude estimation algorithm recovers thermally varying interlock angles between two star sensors. The optimal state estimation process recovers rate gyro biases in addition to real time attitude estimates.
Junkins, J. L.↗
m-CUBES An efficient and portable implementation of multi-dimensional integration for gpus
The task of multi-dimensional numerical integration is frequently encountered in physics and other scientific fields, e.g., in modeling the effects of systematic uncertainties in physical systems and in Bayesian parameter estimation. Multi-dimensional integration is often time-prohibitive on CPUs. Efficient implementation on many-core architectures is challenging as the workload across the integration space cannot be predicted a priori. We propose m-Cubes, a novel implementation of the well-known Vegas algorithm for execution on GPUs. Vegas transforms integration variables followed by calculation of a Monte Carlo integral estimate using adaptive partitioning of the resulting space. m-Cubes improves performance on GPUs by maintaining relatively uniform workload across the processors. As a result, our optimized Cuda implementation for Nvidia GPUs outperforms parallelization approaches proposed in past literature. We further demonstrate the efficiency of m-Cubes by evaluating a six-dimensional integral from a cosmology application, achieving significant speedup and greater precision than the CUBA library's CPU implementation of VEGAS. We also evaluate m-Cubes on a standard integrand test suite. m-Cubes outperforms the serial implementations of the Cuba and GSL libraries by orders of magnitude speedup while maintaining comparable accuracy. Our approach yields a speedup of at least 10 when compared against publicly available Monte Carlo based GPU implementations. In summary, m-Cubes can solve integrals that are prohibitively expensive using standard libraries and custom implementations. A modern C++ interface header-only implementation makes m-Cubes portable, allowing its utilization in complicated pipelines with easy to define stateful integrals. Compatibility with non-Nvidia GPUs is achieved with our initial implementation of m-Cubes using the Kokkos framework.
Sakiotis, Ioannis↗
Drive-pressure optimization in ramp-wave compression experiments through differential evolution
Ramp-wave dynamic-compression experiments are used to examine quasi-isentropic loading paths in materials. The gradual and continuous increase in pressure created by ramp waves make these types of experiments ideal for studying nonequilibrium material behavior, such as solidification kinetics. In ramp-wave compression experiments, the input drive pressure to the experimental setup may be exerted through one of a number of different mechanisms (e.g., magnetic fields, gas-gun-driven impactors, or high-energy lasers) and is generally required for simulating such experiments. Yet, regardless of the specific mechanism, this drive pressure cannot be measured directly (measurements are generally taken at a location near the back of the experimental setup through a transparent window), leading to an inverse problem where one must determine the drive pressure at the front of the experimental setup (i.e., the input) that corresponds to the particle velocity (the output) measured near the back of the experimental setup. Furthermore, we solve this inverse problem using a heuristic optimization algorithm, known as differential evolution, coupled with a multiphysics, hydrodynamics code that simulates the compression of the experimental setup. By running many rounds of forward simulations of the experimental setup, our optimization process iteratively searches for a drive pressure that is optimized to closely reproduce the experimentally measured particle velocity near the back of the experimental setup. While our optimization methodology requires a significant number of hydrodynamics simulations to be conducted, many of these can be performed in parallel, which greatly reduces the time cost of our methodology. One novel aspect of our method for determining the drive pressure is that it does not require physical modeling of the drive mechanism and can thus be broadly applied to many types of ramp-compression experiments, regardless of the drive mechanism.
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
Dictionary Learning with Accumulator Neurons
The Locally Competitive Algorithm (LCA) uses local competition between non-spiking leaky integrator neurons to infer sparse representations, allowing for potentially real-time execution on massively parallel neuromorphic architectures such as Intel's Loihi processor. Here, we focus on the problem of inferring sparse representations from streaming video using dictionaries of spatiotemporal features optimized in an unsupervised manner for sparse reconstruction. Non-spiking LCA has previously been used to achieve unsupervised learning of spatiotemporal dictionaries composed of convolutional kernels from raw, unlabeled video. We demonstrate how unsupervised dictionary learning with spiking LCA (\hbox{S-LCA}) can be efficiently implemented using accumulator neurons, which combine a conventional leaky-integrate-and-fire (\hbox{LIF}) spike generator with an additional state variable that is used to minimize the difference between the integrated input and the spiking output. We demonstrate dictionary learning across a wide range of dynamical regimes, from graded to intermittent spiking, for inferring sparse representations of both static images drawn from the CIFAR database as well as video frames captured from a DVS camera. On a classification task that requires identification of the suite from a deck of cards being rapidly flipped through as viewed by a DVS camera, we find essentially no degradation in performance as the LCA model used to infer sparse spatiotemporal representations migrates from graded to spiking. We conclude that accumulator neurons are likely to provide a powerful enabling component of future neuromorphic hardware for implementing online unsupervised learning of spatiotemporal dictionaries optimized for sparse reconstruction of streaming video from event based DVS cameras.
artificial intelligence↗
TEAM Project Review, Year 2
This report summarizes our research activities within the TEAM project between December 2020 and December 2021, funded by the ASCR Advanced Research in Quantum Computing program. During the reporting period the LLNL-MSU team has made progress on several fronts. An overarching goal of the team is to provide a comprehensive suite of software tools that can be used for the Characterize-Optimize-Compute loop needed to implement and execute algorithms on quantum devices. We are concurrently developing lightweight solvers that can be used on desktop computers to find optimal control pulses and to characterize small quantum systems (consisting of a few transmons and cavities). However, desktop computers are insufficient for simulating and characterizing larger quantum systems. We have therefore also developed parallel, distributed memory, simulators and optimization solvers, both for open and closed quantum systems. These parallel solvers have, for example, been used to study quantum optimal control for pure-state preparation, utilizing 1000’s of cores on a modern high-performance computing (HPC) platform.
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
Distributed Reinforcement Learning with ADMM-RL
This paper presents a new algorithm for distributed Reinforcement Learning (RL). RL is an artificial intelligence (AI) control strategy such that controls for highly nonlinear systems over multi-step time horizons may be learned by experience, rather than directly computed on the fly by optimization. Here we introduce ADMM-RL, a combination of the Alternating Direction Method of Multipliers (ADMM) and reinforcement learning that allows for integrating learned controllers as subsystems in generally convergent distributed control applications. ADMM has become the workhorse algorithm for distributed control, combining the advantages of dual decomposition (namely, enabling decoupled, parallel, distributed solution) with the advantages of the method of multipliers (namely, convexification/stability). Our ADMM-RL algorithm replaces one or more of the subproblems in ADMM with several steps of RL. When the nested iterations converge, we are left with a pretrained subsolver that can potentially increase the efficiency of the deployed distributed controller by orders of magnitude. We illustrate ADMM-RL in both distributed wind farm yaw control and distributed grid-aware demand aggregation for water heaters.
ADMM↗
Increased accuracy of multiphysics simulations through flexible execution, transient algorithms, and modular physics
The MOOSE framework is a foundational capability used by the NEAMS program to create over 15 different simulation tools for advanced nuclear reactors. Due to MOOSE’s broad use, improvements to the framework in support of modeling and simulation goals are critical to the program. Such improvements can take many forms, including optimization, improved user experience, streamlined application programming interfaces (APIs), parallelism, and new capabilities. The work described in this report was conducted in direct support of the simulation tools and has already been deployed. The capabilities were implemented in the same order as they are covered in this report: multiple time integrators in the same input file, initial design of framework Components, an input file Application block, extension of NetGen to 3D geometries in MOOSE, and deployment of executors in the multi-system paradigm. These five additions are fundamental capabilities that will be leveraged by many NEAMS applications.
97 MATHEMATICS AND COMPUTING↗
Parallel processors and nonlinear structural dynamics algorithms and software
Techniques are discussed for the implementation and improvement of vectorization and concurrency in nonlinear explicit structural finite element codes. In explicit integration methods, the computation of the element internal force vector consumes the bulk of the computer time. The program can be efficiently vectorized by subdividing the elements into blocks and executing all computations in vector mode. The structuring of elements into blocks also provides a convenient way to implement concurrency by creating tasks which can be assigned to available processors for evaluation. The techniques were implemented in a 3-D nonlinear program with one-point quadrature shell elements. Concurrency and vectorization were first implemented in a single time step version of the program. Techniques were developed to minimize processor idle time and to select the optimal vector length. A comparison of run times between the program executed in scalar, serial mode and the fully vectorized code executed concurrently using eight processors shows speed-ups of over 25. Conjugate gradient methods for solving nonlinear algebraic equations are also readily adapted to a parallel environment. A new technique for improving convergence properties of conjugate gradients in nonlinear problems is developed in conjunction with other techniques such as diagonal scaling. A significant reduction in the number of iterations required for convergence is shown for a statically loaded rigid bar suspended by three equally spaced springs.
Belytschko, Ted↗
Approximate algorithms for partitioning and assignment problems
The problem of optimally assigning the modules of a parallel/pipelined program over the processors of a multiple computer system under certain restrictions on the interconnection structure of the program as well as the multiple computer system was considered. For a variety of such programs it is possible to find linear time if a partition of the program exists in which the load on any processor is within a certain bound. This method, when combined with a binary search over a finite range, provides an approximate solution to the partitioning problem. The specific problems considered were: a chain structured parallel program over a chain-like computer system, multiple chain-like programs over a host-satellite system, and a tree structured parallel program over a host-satellite system. For a problem with m modules and n processors, the complexity of the algorithm is no worse than O(mnlog(W sub T/epsilon)), where W sub T is the cost of assigning all modules to one processor and epsilon the desired accuracy.
Iqbal, M. A.↗
CG-Kit: Code Generation Toolkit for performant and maintainable variants of source code applied to Flash-X hydrodynamics simulations
CG-Kit is a new Code Generation tool-Kit that we have developed as a part of the solution for portability and maintainability for multiphysics computing applications. The development of CG-Kit is rooted in the urgent need created by the shifting landscape of high-performance computing platforms and the algorithmic complexities of a particular large-scale multiphysics application: Flash-X. To efficiently use computing resources on a heterogeneous node, an application must have a map of computation to resources and a mechanism to move the data and computation to the resources according to the map. Most existing performance portability solutions are focussed on abstracting the expression of computations so that a unified source code can be specialized to run on different resources. However, such an approach is insufficient for a code like Flash-X, which has a multitude of code components that can be assembled in various permutations and combinations to form different instances of applications. Similar challenges apply to any code that has composability, where a single specified way of apportioning work among devices may not be optimal. Additionally, use cases arise where the optimal control flow of computation may differ for different devices while the underlying numerics remain identical. This combination leads to unique challenges including handling an existing large code base in Fortran and/or C/C++, subdivision of code into a great variety of units supporting a wide range of physics and numerical methods, different parallelization techniques for distributed and shared memory systems and accelerator devices, and heterogeneity of computing platforms requiring coexisting variants of parallel algorithms. All of these challenges demand that scientific software developers apply existing knowledge about domain applications, algorithms, and computing platforms to determine custom abstractions and granularity for code generation. There is a critical lack of tools to tackle those problems. CG-Kit is designed to fill this gap by providing a user with the ability to express their desired control flow and computation-to-resource map in the form a pseudocode-like recipe. It consists of standalone tools that can be combined into highly specific and, we argue, highly effective portability and maintainability toolchains. Here we present the design of our new tools: parametrized source trees, control flow graphs, and recipes. The tools are implemented in Python. They are agnostic to the programming language of the source code targeted for code generation. In conclusion, we demonstrate the capabilities of the toolkit with two examples, first, multithreaded variants of the basic AXPY operation, and second, variants of parallel algorithms within a hydrodynamics solver, called Spark, from Flash-X that operates on block-structured adaptive meshes.
Algorithmic portability↗
TAO Users Manual (Rev. 3.15)
The Toolkit for Advanced Optimization (TAO) focuses on the development of algorithms and software for the solution of large-scale optimization problems on high-performance architectures. Areas of interest include unconstrained and bound-constrained optimization, nonlinear least squares problems, optimization problems with partial differential equation constraints, and variational inequalities and complementarity constraints. The development of TAO was motivated by the scattered support for parallel computations and the lack of reuse of external toolkits in current optimization software. Our aim is to produce high-quality optimization software for computing environments ranging from workstations and laptops to massively parallel high-performance architectures. Our design decisions are strongly motivated by the challenges inherent in the use of large-scale distributed memory architectures and the reality of working with large, often poorly structured legacy codes for specific applications.
97 MATHEMATICS AND COMPUTING↗
Algebraic Multigrid Solvers for Coupled PDE Systems (Final Report – B619169)
The Pennsylvania State University (“Subcontractor”) worked on the design of multigrid solvers for coupled systems of partial differential equations arising in numerical modeling of various applications, with a main emphasis on the design of new optimal algebraic multigrid interpolation. Generally, the aim of this work was to develop geometric and algebraic multilevel solvers that are robust and lend themselves to efficient implementation on massively parallel heterogeneous computers. The research in these areas built on previous works, focusing on the following topics: (1) design and analysis of algebraic coarsening algorithms for coupled PDE systems including Stokes equation, Maxwell equation and linear elasticity; (2) development of non-Galerkin coarsening techniques for the Wilson Dirac system; and (3) the use of this same Wilson MG solver for preconditioning the Overlap and Domain Wall formulations of the Dirac equation.
97 MATHEMATICS AND COMPUTING↗
Parallel algorithms for simulating continuous time Markov chains
We have previously shown that the mathematical technique of uniformization can serve as the basis of synchronization for the parallel simulation of continuous-time Markov chains. This paper reviews the basic method and compares five different methods based on uniformization, evaluating their strengths and weaknesses as a function of problem characteristics. The methods vary in their use of optimism, logical aggregation, communication management, and adaptivity. Performance evaluation is conducted on the Intel Touchstone Delta multiprocessor, using up to 256 processors.
Nicol, David M.↗
Extended ecosystem signatures with application to Eos synergism requirements
The primary objective is to define the advantages of synergistically combining optical and microwave remote sensing measurements for the determination of biophysical properties important in ecosystem modeling. This objective was approached in a stepwise fashion starting with ground-based observations of controlled agricultural and orchard canopies and progressing to airborne observations of more natural forest ecosystems. This observational program is complemented by a parallel effort to model the visible reflectance and microwave scattering properties of composite vegetation canopies. The goals of the modeling studies are to verify our basic understanding of the sensor-scene interaction physics and to provide the basis for development of inverse models optimized for retrieval of key biophysical properties. These retrieval algorithms can then be used to simulate the expected performance of various aspects of Eos including the need for simultaneous SAR and HIRIS observations or justification for other (non-synchronous) relative timing constraints and the frequency, polarization, and angle of incidence requirements for accurate biophysical parameter extractions. This program completed a very successful series of truck-mounted experiments, made remarkable progress in development and validation of optical reflectance and microwave scattering models for vegetation, extended the scattering models to accommodate discontinuous and periodic canopies, developed inversion approaches for surface and canopy properties, and disseminated these results widely through symposia and journal publications. In addition, the third generation of the computer code for the microwave scattering models was provided to a number of other US, Canadian, Australian, and European investigators who are currently presenting and publishing results using the MIMICS research code.
Ulaby, Fawwaz T.↗