Scalable Parallel Nonlinear Optimization with PyNumero and Parapint.
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.
Abstract—The field of bioinformatics and computational biol- ogy is experiencing a data revolution — experimental techniques to procure data have increased in throughput, improved in accuracy and reduced in costs. This has spurred an array of high profile sequencing and data generation projects. While the data repositories represent untapped reservoirs of rich information critical for scientific breakthroughs, the analytical software tools that are needed to analyze large volumes of such sequence data have significantly lagged behind in their capacity to scale. In this paper, we address homology detection, which is a funda- mental problem in large-scale sequence analysis with numerous applications. We present a scalable framework to conduct large- scale optimal homology detection on massively parallel super- computing platforms. Our approach employs distributed memory work stealing to effectively parallelize optimal pairwise alignment computation tasks. Results on 120,000 cores of the Hopper Cray XE6 supercomputer demonstrate strong scaling and up to 2.42 × 107 optimal pairwise sequence alignments computed per second (PSAPS), the highest reported in the literature.
We introduce Bayesian Optimization for Anything (BOA), a high-level Bayesian Optimization (BO) framework and model wrapping toolkit, which presents a novel approach to simplifying BO, with the goal of making it more accessible and user-friendly, particularly for those with limited expertise in the field. BOA addresses common barriers in implementing BO, focusing on ease of use, reducing the need for deep domain knowledge, and cutting down on extensive coding requirements. A notable feature of BOA is its language-agnostic architecture, which facilitates broader application in various fields and to a wider audience. We showcase BOA's application through three examples: a high-dimensional optimization with parameters of the SWAT+ watershed model, a highly parallelized optimization of this intrinsically non-parallel model, and a multi-objective optimization of the FETCH Tree-Crown Hydrodynamics model. Furthermore, these test cases illustrate BOA's effectiveness in addressing complex optimization challenges in diverse scenarios.
HOPSPACK (Hybrid Optimization Parallel Search PACKage) solves derivative-free optimization problems using an open source, C++ software framework. The framework enables parallel operation using MPI or multithreading, and allows multiple solvers to run simultaneously and interact to find solution points. HOPSPACK comes with an asynchronous pattern search solver that handles general optimization problems with linear and nonlinear constraints, and continuous and integer-valued variables. This user manual explains how to install and use HOPSPACK to solve problems, and how to create custom solvers within the framework.
The parallel variable metric optimization algorithms of Straeter (1973) and van Laarhoven (1985) are reviewed, and the possible drawbacks of the algorithms are noted. By including Davidon (1975) projections in the variable metric updating, researchers can generalize Straeter's algorithm to a family of parallel projected variable metric algorithms which do not suffer the above drawbacks and which retain quadratic termination. Finally researchers consider the numerical performance of one member of the family on several standard example problems and illustrate how the choice of the displacement vectors affects the performance of the algorithm.
This report gives the result from the Phase-1 work on demonstrating greater than 10x speedup of the Barracuda computer program using parallel methods and GPU processors (General-Purpose Graphics Processing Unit or Graphics Processing Unit). Phase-1 demonstrated a 12x speedup on a typical Barracuda function using the GPU processor. The problem test case used about 5 million particles and 250,000 Eulerian grid cells. The relative speedup, compared to a single CPU, increases with increased number of particles giving greater than 12x speedup. Phase-1 work provided a path for reformatting data structure modifications to give good parallel performance while keeping a friendly environment for new physics development and code maintenance. The implementation of data structure changes will be in Phase-2. Phase-1 laid the ground work for the complete parallelization of Barracuda in Phase-2, with the caveat that implemented computer practices for parallel programming done in Phase-1 gives immediate speedup in the current Barracuda serial running code. The Phase-1 tasks were completed successfully laying the frame work for Phase-2. The detailed results of Phase-1 are within this document. In general, the speedup of one function would be expected to be higher than the speedup of the entire code because of I/O functions and communication between the algorithms. However, because one of the most difficult Barracuda algorithms was parallelized in Phase-1 and because advanced parallelization methods and proposed parallelization optimization techniques identified in Phase-1 will be used in Phase-2, an overall Barracuda code speedup (relative to a single CPU) is expected to be greater than 10x. This means that a job which takes 30 days to complete will be done in 3 days. Tasks completed in Phase-1 are: Task 1: Profile the entire Barracuda code and select which subroutines are to be parallelized (See Section Choosing a Function to Accelerate) Task 2: Select a GPU consultant company and jointly parallelize subroutines (CPFD chose the small business EMPhotonics for the Phase-1 the technical partner. See Section Technical Objective and Approach) Task 3: Integrate parallel subroutines into Barracuda (See Section Results from Phase-1 and its subsections) Task 4: Testing, refinement, and optimization of parallel methodology (See Section Results from Phase-1 and Section Result Comparison Program) Task 5: Integrate Phase-1 parallel subroutines into Barracuda and release (See Section Results from Phase-1 and its subsections) Task 6: Roadmap of Phase-2 (See Section Plan for Phase-2) With the completion of Phase 1 we have the base understanding to completely parallelize Barracuda. An overview of the work to move Barracuda to a parallelized code is given in Plan for Phase-2.
Energy consumption is one of the top challenges for achieving the next generation of supercomputing. Codesign of hardware and software is critical for improving energy efficiency (EE) for future large-scale systems. Many architectural power-saving techniques have been developed, and most hardware components are approaching physical limits. Accordingly, parallel computing software, including both applications and systems, should exploit power-saving hardware innovations and manage efficient energy use. In addition, new power-aware parallel computing methods are essential to decrease energy usage further. This article surveys software-based methods that aim to improve EE for parallel computing. It reviews the methods that exploit the characteristics of parallel scientific applications, including load imbalance and mixed precision of floating-point (FP) calculations, to improve EE. In addition, this article summarizes widely used methods to improve power usage at different granularities, such as the whole system and per application. In particular, it describes the most important techniques to measure and to achieve energy-efficient usage of various parallel computing facilities, including processors, memories, and networks. Overall, this article reviews the state-of-the-art of energy-efficient methods for parallel computing to motivate researchers to achieve optimal parallel computing under a power budget constraint.
A parallel Particle Swarm Optimization (PSO) algorithm is presented. Particle swarm optimization is a fairly recent addition to the family of non-gradient based, probabilistic search algorithms that is based on a simplified social model and is closely tied to swarming theory. Although PSO algorithms present several attractive properties to the designer, they are plagued by high computational cost as measured by elapsed time. One approach to reduce the elapsed time is to make use of coarse-grained parallelization to evaluate the design points. Previous parallel PSO algorithms were mostly implemented in a synchronous manner, where all design points within a design iteration are evaluated before the next iteration is started. This approach leads to poor parallel speedup in cases where a heterogeneous parallel environment is used and/or where the analysis time depends on the design point being analyzed. This paper introduces an asynchronous parallel PSO algorithm that greatly improves the parallel e ciency. The asynchronous algorithm is benchmarked on a cluster assembled of Apple Macintosh G5 desktop computers, using the multi-disciplinary optimization of a typical transport aircraft wing as an example.
Over five years of research in Computational Fluid Dynamics and its applications are covered in this report. Using CFD as an established tool, aerodynamic optimization on parallel architectures is explored. The objective of this work is to provide better tools to vehicle designers. Submarine design requires accurate force and moment calculations in flow with thick boundary layers and large separated vortices. Low noise production is critical, so flow into the propulsor region must be predicted accurately. The High Speed Civil Transport (HSCT) has been the subject of recent work. This vehicle is to be a passenger vehicle with the capability of cutting overseas flight times by more than half. A successful design must surpass the performance of comparable planes. Fuel economy, other operational costs, environmental impact, and range must all be improved substantially. For all these reasons, improved design tools are required, and these tools must eventually integrate optimization, external aerodynamics, propulsion, structures, heat transfer and other disciplines.
Cloud platforms can provide flexible and cost-effective environments for parallel applications. However, the resource over-commitment issues, i.e., cloud providers often provide much more executable virtual CPUs than available physical CPUs, still impede the synchronization operations of parallel applications, causing severe performance degradation. Existing methods optimize parallel applications by promoting the priorities of involved VMs. They cannot fully explore the performance of parallel applications, because they ignore the time-slice requirements of different phases of parallel applications. Furthermore, non-parallel applications experience unsatisfied performance because of low scheduling priorities. Given empirical analysis on time-slices of virtual machines (VMs), we find that shortening time-slices can mitigate synchronization overhead which incurs during communication phases, while over-short time-slices cause frequent cache misses in computation phases. Accordingly, we propose an Adaptive Time-slice Control (ATC) mechanism. ATC first detects the phases of parallel applications based on lock latency or cache misses. Then, ATC shortens time-slices during communication phases and prolongs time-slices during computation phases for parallel applications, and sets a uniform time-slice for non-parallel applications. Finally, we evaluate ATC using seven well-known benchmarks with 25+ applications. Experiments show that ATC obtains 1.5-75x performance gain for running parallel applications than state-of-the-art solutions, with nearly unaffected impact on non-parallel applications.
Discretization of dynamical models defined through partial differential equations leads to large-scale systems. Time-depending condition involves an iterative integration of such kind of systems. In this paper, a novel technique based on overlapped domain decomposition, without preconditioner and scalable, is presented. Due to the domain decomposition, subproblems are solved in parallel without communications, cutting off the computation time and optimizing the computational cost. This direct method describes an optimized parallel strategy to solve the initial problem, providing the exact solution, up to rounding errors. Moreover, it takes into account both physical nature of the problem and deriving numerical properties of the system. It is highly recommended in case of band matrices and a long time interval because of an increasing gain in terms of performance and computational cost with the number of integrations. A deep analysis of the computational cost concludes the paper.
Ordinary-extraordinary mode conversion in the electron cyclotron frequency range is revisited in the presence of a flowing electron component. The analytical expressions of optimal parallel refraction index and conversion efficiency are obtained from a one-dimensional cold plasma model. The presence of flowing electrons leads to an outward shift of the conversion layer and therefore increases the optimal value of parallel refraction index. If this effect is not considered, the efficiency of mode conversion degenerates. In typical tokamak plasmas, this degeneration is about a few percentages, which may induce the reflection of several tens of kilowatts of power from the cutoff layer when injecting megawatts of ECRF power into fusion plasma.
We explore an online reinforcement learning (RL) paradigm to dynamically optimize parallel particle tracing performance in distributed-memory systems. Our method combines three novel components: (1) a work donation algorithm, (2) a high-order workload estimation model, and (3) a communication cost model. First, we design an RL-based work donation algorithm. Our algorithm monitors workloads of processes and creates RL agents to donate data blocks and particles from high-workload processes to low-workload processes to minimize program execution time. The agents learn the donation strategy on the fly based on reward and cost functions designed to consider processes' workload changes and data transfer costs of donation actions. Second, we propose a workload estimation model, helping RL agents estimate the workload distribution of processes in future computations. Third, we design a communication cost model that considers both block and particle data exchange costs, helping RL agents make effective decisions with minimized communication costs. We demonstrate that our algorithm adapts to different flow behaviors in large-scale fluid dynamics, ocean, and weather simulation data. Our algorithm improves parallel particle tracing performance in terms of parallel efficiency, load balance, and costs of I/O and communication for evaluations with up to 16,384 processors.
In this paper, parallel O(log n) algorithms for computation of rigid multibody dynamics are developed. These parallel algorithms are derived by parallelization of new O(n) algorithms for the problem. The underlying feature of these O(n) algorithms is a drastically different strategy for decomposition of interbody force which leads to a new factorization of the mass matrix (M). Specifically, it is shown that a factorization of the inverse of the mass matrix in the form of the Schur Complement is derived as M(exp -1) = C - B(exp *)A(exp -1)B, wherein matrices C, A, and B are block tridiagonal matrices. The new O(n) algorithm is then derived as a recursive implementation of this factorization of M(exp -1). For the closed-chain systems, similar factorizations and O(n) algorithms for computation of Operational Space Mass Matrix lambda and its inverse lambda(exp -1) are also derived. It is shown that these O(n) algorithms are strictly parallel, that is, they are less efficient than other algorithms for serial computation of the problem. But, to our knowledge, they are the only known algorithms that can be parallelized and that lead to both time- and processor-optimal parallel algorithms for the problem, i.e., parallel O(log n) algorithms with O(n) processors. The developed parallel algorithms, in addition to their theoretical significance, are also practical from an implementation point of view due to their simple architectural requirements.
Optimizing collective operations using direct memory access controller on a parallel computer, in one aspect, may comprise establishing a byte counter associated with a direct memory access controller for each submessage in a message. The byte counter includes at least a base address of memory and a byte count associated with a submessage. A byte counter associated with a submessage is monitored to determine whether at least a block of data of the submessage has been received. The block of data has a predetermined size, for example, a number of bytes. The block is processed when the block has been fully received, for example, when the byte count indicates all bytes of the block have been received. The monitoring and processing may continue for all blocks in all submessages in the message.
A set of Computational Fluid Dynamics (CFD) routines and flow transition prediction tools are integrated into a network based parallel numerical optimization routine. Through this optimization routine, the design of a 2-D airfoil and an infinitely swept wing will be studied in order to advance the design cycle capability of supersonic laminar flow wings. The goal of advancing supersonic laminar flow wing design is achieved by wisely choosing the design variables used in the optimization routine. The design variables are represented by the theory of Fourier series and potential theory. These theories, combined with the parallel CFD flow routines and flow transition prediction tools, provide a design space for a global optimal point to be searched. Finally, the parallel optimization routine enables gradient evaluations to be performed in a fast and parallel fashion.
This report summarizes the existing statistical engines in VTK/Titan and presents the parallel versions thereof which have already been implemented. The ease of use of these parallel engines is illustrated by the means of C++ code snippets. Furthermore, this report justifies the design of these engines with parallel scalability in mind; then, this theoretical property is verified with test runs that demonstrate optimal parallel speed-up with up to 200 processors.
This report summarizes existing statistical engines in VTK/Titan and presents the recently parallelized multi-correlative and principal component analysis engines. It is a sequel to [PT08] which studied the parallel descriptive and correlative engines. The ease of use of these parallel engines is illustrated by the means of C++ code snippets. Furthermore, this report justifies the design of these engines with parallel scalability in mind; then, this theoretical property is verified with test runs that demonstrate optimal parallel speed-up with up to 200 processors.