Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel 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

A Generalized Framework for Auto-tuning Stencil Computations

This work introduces a generalized framework for automatically tuning stencil computations to achieve superior performance on a broad range of multicore architectures. Stencil (nearest-neighbor) based kernels constitute the core of many important scientific applications involving block-structured grids. Auto-tuning systems search over optimization strategies to find the combination of tunable parameters that maximizes computational efficiency for a given algorithmic kernel. Although the auto-tuning strategy has been successfully applied to libraries, generalized stencil kernels are not amenable to packaging as libraries. Studied kernels in this work include both memory-bound kernels as well as a computation-bound bilateral filtering kernel. We introduce a generalized stencil auto-tuning framework that takes a straightforward Fortran expression of a stencil kernel and automatically generates tuned implementations of the kernel in C or Fortran to achieve performance portability across diverse computer architectures.

97 MATHEMATICS AND COMPUTING↗

Performance of the OVERFLOW-MLP and LAURA-MLP CFD Codes on the NASA Ames 512 CPU Origin System

The shared memory Multi-Level Parallelism (MLP) technique, developed last year at NASA Ames has been very successful in dramatically improving the performance of important NASA CFD codes. This new and very simple parallel programming technique was first inserted into the OVERFLOW production CFD code in FY 1998. The OVERFLOW-MLP code's parallel performance scaled linearly to 256 CPUs on the NASA Ames 256 CPU Origin 2000 system (steger). Overall performance exceeded 20.1 GFLOP/s, or about 4.5x the performance of a dedicated 16 CPU C90 system. All of this was achieved without any major modification to the original vector based code. The OVERFLOW-MLP code is now in production on the inhouse Origin systems as well as being used offsite at commercial aerospace companies. Partially as a result of this work, NASA Ames has purchased a new 512 CPU Origin 2000 system to further test the limits of parallel performance for NASA codes of interest. This paper presents the performance obtained from the latest optimization efforts on this machine for the LAURA-MLP and OVERFLOW-MLP codes. The Langley Aerothermodynamics Upwind Relaxation Algorithm (LAURA) code is a key simulation tool in the development of the next generation shuttle, interplanetary reentry vehicles, and nearly all "X" plane development. This code sustains about 4-5 GFLOP/s on a dedicated 16 CPU C90. At this rate, expected workloads would require over 100 C90 CPU years of computing over the next few calendar years. It is not feasible to expect that this would be affordable or available to the user community. Dramatic performance gains on cheaper systems are needed. This code is expected to be perhaps the largest consumer of NASA Ames compute cycles per run in the coming year.The OVERFLOW CFD code is extensively used in the government and commercial aerospace communities to evaluate new aircraft designs. It is one of the largest consumers of NASA supercomputing cycles and large simulations of highly resolved full aircraft are routinely undertaken. Typical large problems might require 100s of Cray C90 CPU hours to complete. The dramatic performance gains with the 256 CPU steger system are exciting. Obtaining results in hours instead of months is revolutionizing the way in which aircraft manufacturers are looking at future aircraft simulation work. Figure 2 below is a current state of the art plot of OVERFLOW-MLP performance on the 512 CPU Lomax system. As can be seen, the chart indicates that OVERFLOW-MLP continues to scale linearly with CPU count up to 512 CPUs on a large 35 million point full aircraft RANS simulation. At this point performance is such that a fully converged simulation of 2500 time steps is completed in less than 2 hours of elapsed time. Further work over the next few weeks will improve the performance of this code even further.The LAURA code has been converted to the MLP format as well. This code is currently being optimized for the 512 CPU system. Performance statistics indicate that the goal of 100 GFLOP/s will be achieved by year's end. This amounts to 20x the 16 CPU C90 result and strongly demonstrates the viability of the new parallel systems rapidly solving very large simulations in a production environment.

Taft, James R.↗

Scalable Metropolis Monte Carlo for simulation of hard shapes

We design and implement a scalable hard particle Monte Carlo simulation toolkit (HPMC), and release it open source as part of HOOMD-blue. HPMC runs in parallel on many CPUs and many GPUs using domain decomposition. We employ BVH trees instead of cell lists on the CPU for fast performance, especially with large particle size disparity, and optimize inner loops with SIMD vector intrinsics on the CPU. Our GPU kernel proposes many trial moves in parallel on a checkerboard and uses a block-level queue to redistribute work among threads and avoid divergence. HPMC supports a wide variety of shape classes, including spheres/disks, unions of spheres, convex polygons, convex spheropolygons, concave polygons, ellipsoids/ellipses, convex polyhedra, convex spheropolyhedra, spheres cut by planes, and concave polyhedra. NVT and NPT ensembles can be run in 2D or 3D triclinic boxes. Additional integration schemes permit Frenkel–Ladd free energy computations and implicit depletant simulations. In a benchmark system of a fluid of 4096 pentagons, HPMC performs 10 million sweeps in 10 min on 96 CPU cores on XSEDE Comet. The same simulation would take 7.6 h in serial. HPMC also scales to large system sizes, and the same benchmark with 16.8 million particles runs in 1.4 h on 2048 GPUs on OLCF Titan.

Computer Science↗

Dose–volume histogram evaluation scheme for beam orientations in intensity-modulated radiation therapy

Beam orientations in intensity-modulated radiation therapy (IMRT) is an important, but difficult NP-hard optimization problem. A considerable part of this difficulty is due to the essential prerequisite of defining, appropriately, counter-intuitive criteria for a mathematical plan evaluation that coincides with the clinical judgment of the considered plan. Moreover, the quality of beam directions depends heavily on their intensities. Usually a stochastic selector is utilized for optimizing beam orientations, and the intensities are thus calculated many thousands of times, each time for a different selection of beam directions, resulting in excessive time complexity. Therefore, selecting an appropriate set of beam directions in IMRT is still a time-consuming manual trial-and-error search procedure that depends on intuition and empirical knowledge. To overcome these difficulties, this work utilizes the concept of dose–volume histogram (DVH), which is one of the main recognized quantitative measurement tools used for plan judgment, and presents a DVH evaluation scheme that parallelizes plan evaluation with clinical plan judgment. This scheme is then utilized to optimize the intensities of each individual beam, enabling it to be represented by its DVHs, produced for the different irradiated volumes. Finally, an evolutionary algorithm is employed to search for the best combination of those DVHs reflecting the clinical optimal. The presented methods have been applied to three real clinical examples. In comparison to the standard equally spaced beam plans, improvements were reported in all three cases. In comparison with the greedy algorithm, improvements were reported in those examples requiring more than five beam directions.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Parallel Battery: The Framework and Process for an Intelligent and Ecological Battery System and Related Services

The concept, framework, process methodology and applications of parallel battery were proposed from both virtual and real aspects.The parallel battery was an application of ACP-based parallel intelligence in battery and related energy system areas.The real battery system was running with its equivalent, and the artificial battery system was in a virtual space, in a parallel and interactive manner.The artificial battery system contained the descriptive, predictive, and prescriptive functions on the real battery and related energy systems.There was a closed-loop workflow between the real battery system and the artificial battery system, which iteratively optimizes the battery and related energy systems, leading to a new paradigm of intelligent and ecological parallel battery system management.

ACP approach↗

Modelling a Transition-Edge Sensor X-Ray Microcalorimeter Linear Array for Compton Profile Measurements and Energy Dispersive Diffraction

Transition-edge sensors (TES) are a type of superconducting detector that offers high energy resolution based on their sharp resistance-temperature feature in the superconducting-to-normal transition. TES X-ray microcalorimeters have typically been designed and used for spectroscopic applications. In this work, we present a design optimization for a TES X-ray microcalorimeter array for high-energy scattering and diffraction measurements. Specifically, Compton scattering provides information about the electron momentum distribution, while energy dispersive diffraction provides structural information about dense engineering materials. Compton scattering and energy dispersive diffraction experiments must be conducted in the very hard X-ray regime (~100 keV), demanding a high X-ray stopping power in the detector; therefore, an absorber with a large heat capacity is needed in conjunction with the TES. In addition, both applications would benefit from an array composed of parallel strips. We propose a design for a TES X-ray microcalorimeter optimized for such applications. In particular, we model the longitudinal position dependence due to the finite thermal diffusion time in the absorber.

47 OTHER INSTRUMENTATION↗

Dynamic Ride-Matching for Large-Scale Transportation Systems

Efficient dynamic ride-matching (DRM) in large-scale transportation systems is a key driver in transport simulations to yield answers to challenging problems. Although the DRM problem is simple to solve, it quickly becomes a computationally challenging problem in large-scale transportation system simulations. Therefore, this study thoroughly examines the DRM problem dynamics and proposes an optimization-based solution framework to solve the problem efficiently. To benefit from parallel computing and reduce computational times, the problem’s network is divided into clusters utilizing a commonly used unsupervised machine learning algorithm along with a linear programming model. Then, these sub-problems are solved using another linear program to finalize the ride-matching. At the clustering level, the framework allows users adjusting cluster sizes to balance the trade-off between the computational time savings and the solution quality deviation. A case study in the Chicago Metropolitan Area, U.S., illustrates that the framework can reduce the average computational time by 58% at the cost of increasing the average pick up time by 26% compared with a system optimum, that is, non-clustered, approach. Another case study in a relatively small city, Bloomington, Illinois, U.S., shows that the framework provides quite similar results to the system-optimum approach in approximately 62% less computational time.

33 ADVANCED PROPULSION SYSTEMS↗

FOX: A Fault Oblivious Extreme-Scale Execution Environment

The FOX project, funded under the ASCR X-stack I program, developed systems software and runtime libraries for a new approach to the data and work distribution for massively parallel, fault oblivious application execution. Our work was motivated by the premise that exascale computing systems will provide a thousand-fold increase in parallelism and a proportional increase in failure rate relative to today’s machines. To deliver the capability of exascale hardware, the systems software must provide the infrastructure to support existing applications while simultaneously enabling efficient execution of new programming models that naturally express dynamic, adaptive, irregular computation; coupled simulations; and massive data analysis in a highly unreliable hardware environment with billions of threads of execution. Our OS research has prototyped new methods to provide efficient resource sharing, synchronization, and protection in a many-core compute node. We have experimented with alternative task/dataflow programming models and shown scalability in some cases to hundreds of thousands of cores. Much of our software is in active development through open source projects. Concepts from FOX are being pursued in next generation exascale operating systems. Our OS work focused on adaptive, application tailored OS services optimized for multi → many core processors. We developed a new operating system NIX that supports role-based allocation of cores to processes which was released to open source. We contributed to the IBM FusedOS project, which promoted the concept of latency-optimized and throughput-optimized cores. We built a task queue library based on distributed, fault tolerant key-value store and identified scaling issues. A second fault tolerant task parallel library was developed, based on the Linda tuple space model, that used low level interconnect primitives for optimized communication. We designed fault tolerance mechanisms for task parallel computations employing work stealing for load balancing that scaled to the largest existing supercomputers. Finally, we implemented the Elastic Building Blocks runtime, a library to manage object-oriented distributed software components. To support the research, we won two INCITE awards for time on Intrepid (BG/P) and Mira (BG/Q). Much of our work has had impact in the OS and runtime community through the ASCR Exascale OS/R workshop and report, leading to the research agenda of the Exascale OS/R program. Our project was, however, also affected by attrition of multiple PIs. While the PIs continued to participate and offer guidance as time permitted, losing these key individuals was unfortunate both for the project and for the DOE HPC community.

97 MATHEMATICS AND COMPUTING↗

Single- and Multiple-Objective Optimization with Differential Evolution and Neural Networks

Genetic and evolutionary algorithms have been applied to solve numerous problems in engineering design where they have been used primarily as optimization procedures. These methods have an advantage over conventional gradient-based search procedures became they are capable of finding global optima of multi-modal functions and searching design spaces with disjoint feasible regions. They are also robust in the presence of noisy data. Another desirable feature of these methods is that they can efficiently use distributed and parallel computing resources since multiple function evaluations (flow simulations in aerodynamics design) can be performed simultaneously and independently on ultiple processors. For these reasons genetic and evolutionary algorithms are being used more frequently in design optimization. Examples include airfoil and wing design and compressor and turbine airfoil design. They are also finding increasing use in multiple-objective and multidisciplinary optimization. This lecture will focus on an evolutionary method that is a relatively new member to the general class of evolutionary methods called differential evolution (DE). This method is easy to use and program and it requires relatively few user-specified constants. These constants are easily determined for a wide class of problems. Fine-tuning the constants will off course yield the solution to the optimization problem at hand more rapidly. DE can be efficiently implemented on parallel computers and can be used for continuous, discrete and mixed discrete/continuous optimization problems. It does not require the objective function to be continuous and is noise tolerant. DE and applications to single and multiple-objective optimization will be included in the presentation and lecture notes. A method for aerodynamic design optimization that is based on neural networks will also be included as a part of this lecture. The method offers advantages over traditional optimization methods. It is more flexible than other methods in dealing with design in the context of both steady and unsteady flows, partial and complete data sets, combined experimental and numerical data, inclusion of various constraints and rules of thumb, and other issues that characterize the aerodynamic design process. Neural networks provide a natural framework within which a succession of numerical solutions of increasing fidelity, incorporating more realistic flow physics, can be represented and utilized for optimization. Neural networks also offer an excellent framework for multiple-objective and multi-disciplinary design optimization. Simulation tools from various disciplines can be integrated within this framework and rapid trade-off studies involving one or many disciplines can be performed. The prospect of combining neural network based optimization methods and evolutionary algorithms to obtain a hybrid method with the best properties of both methods will be included in this presentation. Achieving solution diversity and accurate convergence to the exact Pareto front in multiple objective optimization usually requires a significant computational effort with evolutionary algorithms. In this lecture we will also explore the possibility of using neural networks to obtain estimates of the Pareto optimal front using non-dominated solutions generated by DE as training data. Neural network estimators have the potential advantage of reducing the number of function evaluations required to obtain solution accuracy and diversity, thus reducing cost to design.

Rai, Man Mohan↗

Global Design Optimization for Aerodynamics and Rocket Propulsion Components

Modern computational and experimental tools for aerodynamics and propulsion applications have matured to a stage where they can provide substantial insight into engineering processes involving fluid flows, and can be fruitfully utilized to help improve the design of practical devices. In particular, rapid and continuous development in aerospace engineering demands that new design concepts be regularly proposed to meet goals for increased performance, robustness and safety while concurrently decreasing cost. To date, the majority of the effort in design optimization of fluid dynamics has relied on gradient-based search algorithms. Global optimization methods can utilize the information collected from various sources and by different tools. These methods offer multi-criterion optimization, handle the existence of multiple design points and trade-offs via insight into the entire design space, can easily perform tasks in parallel, and are often effective in filtering the noise intrinsic to numerical and experimental data. However, a successful application of the global optimization method needs to address issues related to data requirements with an increase in the number of design variables, and methods for predicting the model performance. In this article, we review recent progress made in establishing suitable global optimization techniques employing neural network and polynomial-based response surface methodologies. Issues addressed include techniques for construction of the response surface, design of experiment techniques for supplying information in an economical manner, optimization procedures and multi-level techniques, and assessment of relative performance between polynomials and neural networks. Examples drawn from wing aerodynamics, turbulent diffuser flows, gas-gas injectors, and supersonic turbines are employed to help demonstrate the issues involved in an engineering design context. Both the usefulness of the existing knowledge to aid current design practices and the need for future research are identified.

Shyy, Wei↗

Stability Analysis of Parallel Connected Bidirectional WPT System

This paper presents a stability analysis of parallel-connected bi-directional series-series resonant network wireless power transfer (WPT), optimized for Electric Vehicle (EV) charging and vehicle-to-grid (V2G) applications. The study addresses critical stability challenges in systems integrated with diverse distributed energy resources (DERs), including photovoltaics, fuel cells, wind turbines, energy storage systems, and the AC grid. The stability of such integrated DC grid systems is paramount for ensuring reliable operation, particularly under varying power flow conditions and dynamic interactions between parallel WPT systems. The analysis included system impedance characterization, state-space modeling, and open and closed-loop stability evaluations. The results demonstrated that the integration of a robust control architecture effectively mitigates instability risks and supports scalable, efficient operation. This work underscores the converter's adaptability and its potential for large-scale deployment in wireless EV charging infrastructures and integrated DC grid systems.

Asa, Erdem [ORNL] (ORCID:0000000190884812)↗

Accelerating Simulation for High-Fidelity PV Inverter System Reliability Assessment with High-Performance Computing

The overall cost of photovoltaic (PV) systems has shown a downward trend during the last decade; however, PV inverter failures account for the highest cost of operation and maintenance. To address this, reliability tools with powerful computation and better accuracy are required for the lifetime prediction and degradation evaluation of PV inverters. This paper proposes an event-driven parallel computing-based simulator. The proposed simulator applies high-performance computing techniques and other accessory optimization techniques-including cluster merging, adaptive model updates, and steady-state identification-to make reliability assessments for PV inverters under given input mission profiles and operating conditions with high efficiency and high fidelity. The main idea of the simulator and its workflow are introduced. Then, a demo PV inverter system simulator is implemented, and the speedup of the total simulations of the switching model reaches 123.03 times.

high-performance computing↗

HIGH-MODE RAYLEIGH-TAYLOR GROWTH IN NIF IGNITION CAPSULES

An assessment of short wavelength hydrodynamic stability is an essential component in the optimization of NIF ignition target designs. Using highly-resolved massively-parallel 2-D Hydra simulations, we routinely evaluate target designs up to mode numbers of 2000 ({lambda} {approx} 2 {micro}m). On the outer ablator surface, mode numbers up to {approx}300 ({lambda} {approx} 20 {micro}m) can have significant growth in CH capsule designs. At the internal fuel:ablator interface mode numbers up to {approx}2000 are important for both CH and Be designs. In addition, 'isolated features' on the capsule, such as the 'fill-tube' ({approx} 5 {micro}m scale-length) and defects, can seed short wavelength growth at the ablation front and the fuel:ablator interface, leading to the injection of {approx} 10's ng of ablator material into the central hot-spot. We are developing methods to measure high-mode mix on NIF implosion experiments. X-ray spectroscopic methods are appealing since mix into the hot-spot will result in x-ray emission from the high-Z dopant (Cu or Ge) in the ablator material (Be or CH).

42 ENGINEERING↗

MOOSE ProbML: Parallelizable Probabilistic Machine Learning and Uncertainty Quantification Capabilities

The Multiphysics Object Oriented Simulation Environment (MOOSE) is a widely used open- source finite element software for performing multiphysics multiscale simulations in a massively parallel fashion. Recently, the computational team at Idaho National Laboratory (INL) has implemented Probabilistic Machine Learning (ProbML) capabilities in MOOSE—in a parallelized fashion—and enable active learning with large-scale computational models for tasks such as surrogate model development, scale bridging, forward/inverse uncertainty quantification (UQ), Bayesian optimization, etc. This presentation summarizes these developments in MOOSE along with demonstrations on several real applications relevant to nuclear energy. At the fundamental level, samplers like Monte Carlo/Latin Hypercube, variance reduction, parallelized Markov Chain Monte Carlo (MCMC) support uncertainty propagation in both forward and inverse settings. These samplers can be integrated with the Gaussian processes (GP) suite in MOOSE, which offer several variants like scalar GPs, multi-output GPs, and deep GPs, to enable active learning. These GPs can be tuned using gradient-based optimization methods like Adam and its variants or gradient-free methods like the elliptical slice sampler (a variant of MCMC adept under Gaussian settings) for more complex covariance kernels or likelihoods whose gradient computations can be cumbersome. A variety of batch acquisition functions permit parallelized evaluation of the computational model and support different learning objectives with high efficiency like Bayesian inference, global surrogate development, optimization, etc. Furthermore, libtorch integration supports training, evaluation, and re-training of neural networks and other complex machine learning models in active learning settings. The impacts of these developments are shown on several real applications: (1) nuclear fuel inverse UQ and model inadequacy assessment using the Kennedy O’Hagan framework; (2) uncertainty aware surrogate modeling for additive manufacturing to predict field quantities; (3) nuclear reactor rare events analysis; and (4) complex fluid flow prediction using a global surrogate with quantified prediction uncertainty. Finally, the outlook of MOOSE ProbML is discussed for both outer-loop and inner-loop computations in the broad view to accelerate fuels and materials qualification, address gaps in knowledge and data, and assess new reactor/fuel systems.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Multidisciplinary Design Optimization of a Full Vehicle with High Performance Computing

Multidisciplinary design optimization (MDO) of a full vehicle under the constraints of crashworthiness, NVH (Noise, Vibration and Harshness), durability, and other performance attributes is one of the imperative goals for automotive industry. However, it is often infeasible due to the lack of computational resources, robust simulation capabilities, and efficient optimization methodologies. This paper intends to move closer towards that goal by using parallel computers for the intensive computation and combining different approximations for dissimilar analyses in the MDO process. The MDO process presented in this paper is an extension of the previous work reported by Sobieski et al. In addition to the roof crush, two full vehicle crash modes are added: full frontal impact and 50% frontal offset crash. Instead of using an adaptive polynomial response surface method, this paper employs a DOE/RSM method for exploring the design space and constructing highly nonlinear crash functions. Two NMO strategies are used and results are compared. This paper demonstrates that with high performance computing, a conventionally intractable real world full vehicle multidisciplinary optimization problem considering all performance attributes with large number of design variables become feasible.

Yang, R. J.↗

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↗

The ParaScope parallel programming environment

The ParaScope parallel programming environment, developed to support scientific programming of shared-memory multiprocessors, includes a collection of tools that use global program analysis to help users develop and debug parallel programs. This paper focuses on ParaScope's compilation system, its parallel program editor, and its parallel debugging system. The compilation system extends the traditional single-procedure compiler by providing a mechanism for managing the compilation of complete programs. Thus, ParaScope can support both traditional single-procedure optimization and optimization across procedure boundaries. The ParaScope editor brings both compiler analysis and user expertise to bear on program parallelization. It assists the knowledgeable user by displaying and managing analysis and by providing a variety of interactive program transformations that are effective in exposing parallelism. The debugging system detects and reports timing-dependent errors, called data races, in execution of parallel programs. The system combines static analysis, program instrumentation, and run-time reporting to provide a mechanical system for isolating errors in parallel program executions. Finally, we describe a new project to extend ParaScope to support programming in FORTRAN D, a machine-independent parallel programming language intended for use with both distributed-memory and shared-memory parallel computers.

Cooper, Keith D.↗

Highly Efficient Compensation-Based Parallelism for Wavefront Loops on GPUs

Wavefront loops are widely used in many scientific applications, e.g., partial differential equation (PDE) solvers and sequence alignment tools. However, due to the data dependencies in wavefront loops, it is challenging to fully utilize the abundant compute units of GPUs and to reuse data through their memory hierarchy. Existing solutions can only optimize for these factors to a limited extent. For example, tiling-based methods optimize memory access but may result in load imbalance; while compensation-based methods, which change the original order of computation to expose more parallelism and then compensate for it, suffer from both global synchronization overhead and limited generality. In this paper, we first prove under which circumstances that breaking data dependencies and properly changing the sequence of computation operators in our compensation-based method does not affect the correctness of results. Based on this analysis, we design a highly efficient compensation-based parallelism on GPUs. Our method provides weighted scan-based GPU kernels to optimize the computation and combines with the tiling method to optimize memory access and synchronization. The performance results on the NVIDIA K80 and P100 GPU platforms demonstrate that our method can achieve significant improvements for four types of real-world application kernels over the state-of-the-art research.

Hou, Kaixi↗