Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Programming model”

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 235 records · Page 13

GPU COMPUTING FOR PARTICLE TRACKING

This is a feasibility study of using a modern Graphics Processing Unit (GPU) to parallelize the accelerator particle tracking code. To demonstrate the massive parallelization features provided by GPU computing, a simplified TracyGPU program is developed for dynamic aperture calculation. Performances, issues, and challenges from introducing GPU are also discussed. General purpose Computation on Graphics Processing Units (GPGPU) bring massive parallel computing capabilities to numerical calculation. However, the unique architecture of GPU requires a comprehensive understanding of the hardware and programming model to be able to well optimize existing applications. In the field of accelerator physics, the dynamic aperture calculation of a storage ring, which is often the most time consuming part of the accelerator modeling and simulation, can benefit from GPU due to its embarrassingly parallel feature, which fits well with the GPU programming model. In this paper, we use the Tesla C2050 GPU which consists of 14 multi-processois (MP) with 32 cores on each MP, therefore a total of 448 cores, to host thousands ot threads dynamically. Thread is a logical execution unit of the program on GPU. In the GPU programming model, threads are grouped into a collection of blocks Within each block, multiple threads share the same code, and up to 48 KB of shared memory. Multiple thread blocks form a grid, which is executed as a GPU kernel. A simplified code that is a subset of Tracy++ [2] is developed to demonstrate the possibility of using GPU to speed up the dynamic aperture calculation by having each thread track a particle.

42 ENGINEERING↗

Exploring Asynchronous Many-Task Runtime Systems toward Extreme Scales

Major exascale computing reports indicate a number of software challenges to meet the dramatic change of system architectures in near future. While several-orders-of-magnitude increase in parallelism is the most commonly cited of those, hurdles also include performance heterogeneity of compute nodes across the system, increased imbalance between computational capacity and I/O capabilities, frequent system interrupts, and complex hardware architectures. Asynchronous task-parallel programming models show a great promise in addressing these issues, but are not yet fully understood nor developed su ciently for computational science and engineering application codes. We address these knowledge gaps through quantitative and qualitative exploration of leading candidate solutions in the context of engineering applications at Sandia. In this poster, we evaluate MiniAero code ported to three leading candidate programming models (Charm++, Legion and UINTAH) to examine the feasibility of these models that permits insertion of new programming model elements into an existing code base.

97 MATHEMATICS AND COMPUTING↗

A Study of Performance Portability of Low-bit Fused Matrix-Vector Multiplication Kernels in SYCL

Understanding the causes of performance gaps between a portable programming model and a vendor-specific programming model is important for improving performance portability. This paper studies performance portability of low-bit fused general matrix-vector multiplication kernels in SYCL on vendors’ graphics processing units (GPUs). This work introduces the use case, explains the kernel implementations in detail, evaluates the performance of the CUDA, HIP, and SYCL kernels on datacenter, desktop, and laptop GPUs, and investigates the causes of performance gaps. The results show that loop unrolling, kernel dispatch overhead, and sum reduction contribute to the gaps.

Jin, Zheming [ORNL] (ORCID:000000027197780X)↗

Harnessing billions of tasks for a scalable portable hydrodynamic simulation of the merger of two stars

We propose a highly scalable demonstration of a portable asynchronous many-task programming model and runtime system applied to a grid-based adaptive mesh refinement hydrodynamic simulation of a double white dwarf merger with 14 levels of refinement that spans 17 orders of magnitude in astrophysical densities. The code uses the portable C++ parallel programming model that is embodied in the HPX library and being incorporated into the ISO C++ standard. The model reflects a significant shift from existing bulk synchronous parallel programming models under consideration for exascale systems. Through the use of the Futurization technique, seemingly sequential code is transformed into wait-free asynchronous tasks. We demonstrate the potential of our model by showing results from strong scaling runs on National Energy Research Scientific Computing Center’s Cori system (658,784 Intel Knight’s Landing cores) that achieve a parallel efficiency of 96.8% using billions of asynchronous tasks.

79 ASTRONOMY AND ASTROPHYSICS↗

Optimal Strategies for Hybrid Battery‐Storage Systems Design

As stationary hybrid energy‐storage systems (HESS) for power systems applications have recently drawn interest due to their enhanced performance and decreasing cost, developing systematic approaches for HESS design while considering controls is gaining traction. Herein, a method is presented to optimally design hybrid battery storage by proposing a mathematical modeling framework, formulated as a mixed integer linear programming model. The optimization is capable of handling multiple subsystems of batteries, considering their economic and technological performance. Decisions involve sizing of the batteries, optimal temporal and strategic dispatch to end uses, and energy sources for charging each battery. The applicability of the model is tested on four case studies for three battery chemistries representing distinct objectives: high‐power, high‐energy, and second life. Compared to traditionally designed battery storage with a homogeneous battery, optimally designed hybrid systems can save 12%–26% of system costs, depending on the nature of the dispatch profile. Findings point to design preference toward the second life battery supplemented with some high‐power or high‐energy battery capacity, or both. With the utilized electricity price structure, customers can experience approximately 10%–35% reduction in their bills.

Koleva, Mariya↗

Roofline scaling trajectories: A method for parallel application and architectural performance analysis

The end of Dennard scaling signaled a shift in HPC supercomputer architectures from systems built from single-core processor architectures to systems built from multicore and eventually manycore architectures. This transition substantially complicated performance optimization and analysis as new programming models were created, new scaling methodologies deployed, and on-chip contention became a bottleneck to performance. Existing distributed memory performance models like logP and logGP were unable to capture this contention. The Roofline model was created to address this contention and its interplay with locality. However, to date, the Roofline model has focused on full-node concurrency. In this paper, we extend the Roofline model to capture the effects of concurrency on data locality and on-chip contention. We demonstrate the value of this new technique by evaluating the NAS parallel benchmarks on both multicore and manycore architectures under both strong-And weak-scaling regimes. In order to quantify the interplay between programming model and locality, we evaluate scaling under both the OpenMP and flat MPI programming models.

Ibrahim, K↗

Reaching bandwidth saturation using transparent injection parallelization

Although logically available, applications may not exploit enough instantaneous communication concurrency to maximize network utilization on HPC systems. This is exacerbated in hybrid programming models that combine single program multiple data with OpenMP or CUDA. We present the design of a “multi-threaded” runtime able to transparently increase the instantaneous network concurrency and to provide near saturation bandwidth, independent of the application configuration and dynamic behavior. The runtime offloads communication requests from application level tasks to multiple communication servers. The servers use system specific performance models to attain network saturation. Our techniques alleviate the need for spatial and temporal application level message concurrency optimizations. Experimental results show improved message throughput and bandwidth by as much as 150% for 4 KB messages on InfiniBand and by as much as 120% for 4 KB messages on Cray Aries. For more complex operations such as all-to-all collectives, we observe as much as 30% speedup. This translates into 23% speedup on 12,288 cores for a NAS FT implemented using FFTW. We observe as much as 76% speedup on 1500 cores for an already optimized UPC+OpenMP geometric multigrid application using hybrid parallelism. For the geometric multigrid GPU implementation, we observe as much as 44% speedup on 512 GPUs.

Chaimov, Nicholas↗

A Testbed of Parallel Kernels for Computer Science Research

For several decades, computer scientists have sought guidance on how to evolve architectures, languages, and programming models for optimal performance, efficiency, and productivity. Unfortunately, this guidance is most often taken from the existing software/hardware ecosystem. Architects attempt to provide micro-architectural solutions to improve performance on fixed binaries. Researchers tweak compilers to improve code generation for existing architectures and implementations, and they may invent new programming models for fixed processor and memory architectures and computational algorithms. In today's rapidly evolving world of on-chip parallelism, these isolated and iterative improvements to performance may miss superior solutions in the same way gradient descent optimization techniques may get stuck in local minima. In an initial study, we have developed an alternate approach that, rather than starting with an existing hardware/software solution laced with hidden assumptions, defines the computational problems of interest and invites architects, researchers and programmers to implement novel hardware/ software co-designed solutions. Our work builds on the previous ideas of computational dwarfs, motifs, and parallel patterns by selecting a representative set of essential problems for which we provide: An algorithmic description; scalable problem definition; illustrative reference implementations; verification schemes. For simplicity, we focus initially on the computational problems of interest to the scientific computing community but proclaim the methodology (and perhaps a subset of the problems) as applicable to other communities. We intend to broaden the coverage of this problem space through stronger community involvement. Previous work has established a broad categorization of numerical methods of interest to the scientific computing, in the spirit of the NAS Benchmarks, which pioneered the basic idea of a 'pencil and paper benchmark' in the 1990s. The initial result of the more modern study was the seven dwarfs, which was subsequently extended to 13 motifs. These motifs have already been useful in defining classes of applications for architecture-software studies. However, these broad-brush problem statements often miss the nuance seen in individual kernels. For example, the computational requirements of particle methods vary greatly between the naive (but more accurate) direct calculations and the particle-mesh and particle-tree codes. Thus we commenced our study with an enumeration of problems, but then proceeded by providing not only reference implementations for each problem, but more importantly a mathematical definition that allows one to escape iterative approaches to software/hardware optimization. To ensure long term value, we have augmented each of our reference implementations with both a scalable problem generator and a verification scheme. In a paper we have prepared that documents our efforts, we describe in detail this process of problem definition, scalable input creation, verification, and implementation of reference codes for the scientific computing domain. Table 1 enumerates and describes the level of support we've developed for each kernel. We group these important kernels using the Berkeley dwarfs/motifs taxonomy using a red box in the appropriate column. As kernels become progressively complex, they build upon other, simpler computational methods. We note this dependency via orange boxes. After enumeration of the important numerical problems, we created a domain-appropriate high-level definition of each problem. To ensure future endeavors are not tainted by existing implementations, we specified the problem definition to be independent of both computer architecture and existing programming languages, models, and data types. Then, to provide context as to how such kernels productively map to existing architectures, languages and programming models, we produced reference implementations for most of the kernel (see table). These sample codes should be viewed as 'hints,' designed to show how other designers have mapped a problem's operands and operators to existing hardware and software. Since we wanted such implementations to be illustrative, we tried to ensure they were the most straightforward implementation in the easiest to understand languages using familiar architectures. To that end, most of the linear algebra-oriented computations are written in MATLAB using array indexing to process matrices, rather than one-line library calls to compute the same kernel. This ensures that the kernel's computation is explicit and readable in the implementation and not hidden behind a library. For other problems, such as the Barnes-Hut n-Body solver, the implementations were written in pure C, without any supporting library computations. Along this line, we have also created a scalable problem generator to accompany each computation.

97 MATHEMATICS AND COMPUTING↗

Generation Expansion Planning With Large Amounts of Wind Power via Decision-Dependent Stochastic Programming

Power generation expansion planning needs to deal with future uncertainties carefully, given that the invested generation assets will be in operation for a long time. Many stochastic programming models have been proposed to tackle this challenge. However, most previous works assume predetermined future uncertainties (i.e., fixed random outcomes with given probabilities). In several recent studies of generation assets' planning (e.g., thermal versus renewable), new findings show that the investment decisions could affect the future uncertainties as well. To this end, this paper proposes a multistage decision-dependent stochastic optimization model for long-term large-scale generation expansion planning, where large amounts of wind power are involved. In the decision-dependent model, the future uncertainties are not only affecting but also affected by the current decisions. In particular, the probability distribution function is determined by not only input parameters but also decision variables. To deal with the nonlinear constraints in our model, a quasi-exact solution approach is then introduced to reformulate the multistage stochastic investment model to a mixed-integer linear programming model. The wind penetration, investment decisions, and the optimality of the decision-dependent model are evaluated in a series of multistage case studies. The results show that the proposed decision-dependent model provides effective optimization solutions for long-term generation expansion planning.

Zhan, Yiduo↗

Framework for Extensible, Asynchronous Task Scheduling (FEATS) in Fortran

Most parallel scientific programs contain compiler directives (pragmas) such as those from OpenMP, explicit calls to runtime library procedures such as those implementing the Message Passing Interface (MPI), or compiler-specific language extensions such as those provided by CUDA. By contrast, the recent Fortran standards empower developers to express parallel algorithms without directly referencing lower-level parallel programming models. Fortran’s parallel features place the language within the Partitioned Global Address Space (PGAS) class of programming models. When writing programs that exploit data-parallelism, application developers often find it straightforward to develop custom parallel algorithms. Problems involving complex, heterogeneous, staged calculations, however, pose much greater challenges. Such applications require careful coordination of tasks in a manner that respects dependencies prescribed by a directed acyclic graph. When rolling one’s own solution proves difficult, extending a customizable framework becomes attractive. The paper presents the design, implementation, and use of the Framework for Extensible Asynchronous Task Scheduling (FEATS), which we believe to be the first task-scheduling tool written in modern Fortran. We describe the benefits and compromises associated with choosing Fortran as the implementation language, and we propose ways in which future Fortran standards can best support the use case in this paper.

Richardson, Brad↗

A survey of software implementations used by application codes in the Exascale Computing Project

The US Department of Energy Office of Science and the National Nuclear Security Administration initiated the Exascale Computing Project (ECP) in 2016 to prepare mission-relevant applications and scientific software for the delivery of the exascale computers starting in 2023. The ECP currently supports 24 efforts directed at specific applications and six supporting co-design projects. These 24 application projects contain 62 application codes that are implemented in three high-level languages—C, C++, and Fortran—and use 22 combinations of graphical processing unit programming models. The most common implementation language is C++, which is used in 53 different application codes. The most common programming models across ECP applications are CUDA and Kokkos, which are employed in 15 and 14 applications, respectively. This article provides a survey of the programming languages and models used in the ECP applications codebase that will be used to achieve performance on the future exascale hardware platforms.

97 MATHEMATICS AND COMPUTING↗

Modeling Mathematical Programs with Equilibrium Constraints in Pyomo

We describe new capabilities for modeling MPEC problems within the Pyomo modeling software. These capabilities include new modeling components that represent complementarity conditions, modeling transformations for re-expressing models with complementarity conditions in other forms, and meta-solvers that apply transformations and numeric optimization solvers to optimize MPEC problems. We illustrate the breadth of Pyomo's modeling capabilities for MPEC problems, and we describe how Pyomo's meta-solvers can perform local and global optimization of MPEC problems.

97 MATHEMATICS AND COMPUTING↗

ASC Trilab L2 Codesign Milestone 2015

For the FY15 ASC L2 Trilab Codesign milestone Sandia National Laboratories performed two main studies. The first study investigated three topics (performance, cross-platform portability and programmer productivity) when using OpenMP directives and the RAJA and Kokkos programming models available from LLNL and SNL respectively. The focus of this first study was the LULESH mini-application developed and maintained by LLNL. In the coming sections of the report the reader will find performance comparisons (and a demonstration of portability) for a variety of mini-application implementations produced during this study with varying levels of optimization. Of note is that the implementations utilized including optimizations across a number of programming models to help ensure claims that Kokkos can provide native-class application performance are valid. The second study performed during FY15 is a performance assessment of the MiniAero mini-application developed by Sandia. This mini-application was developed by the SIERRA Thermal-Fluid team at Sandia for the purposes of learning the Kokkos programming model and so is available in only a single implementation. For this report we studied its performance and scaling on a number of machines with the intent of providing insight into potential performance issues that may be experienced when similar algorithms are deployed on the forthcoming Trinity ASC ATS platform.

97 MATHEMATICS AND COMPUTING↗

Compiled MPI: Cost-Effective Exascale Applications Development

The complexity of petascale and exascale machines makes it increasingly difficult to develop applications that can take advantage of them. Future systems are expected to feature billion-way parallelism, complex heterogeneous compute nodes and poor availability of memory (Peter Kogge, 2008). This new challenge for application development is motivating a significant amount of research and development on new programming models and runtime systems designed to simplify large-scale application development. Unfortunately, DoE has significant multi-decadal investment in a large family of mission-critical scientific applications. Scaling these applications to exascale machines will require a significant investment that will dwarf the costs of hardware procurement. A key reason for the difficulty in transitioning today's applications to exascale hardware is their reliance on explicit programming techniques, such as the Message Passing Interface (MPI) programming model to enable parallelism. MPI provides a portable and high performance message-passing system that enables scalable performance on a wide variety of platforms. However, it also forces developers to lock the details of parallelization together with application logic, making it very difficult to adapt the application to significant changes in the underlying system. Further, MPI's explicit interface makes it difficult to separate the application's synchronization and communication structure, reducing the amount of support that can be provided by compiler and run-time tools. This is in contrast to the recent research on more implicit parallel programming models such as Chapel, OpenMP and OpenCL, which promise to provide significantly more flexibility at the cost of reimplementing significant portions of the application. We are developing CoMPI, a novel compiler-driven approach to enable existing MPI applications to scale to exascale systems with minimal modifications that can be made incrementally over the application's lifetime. It includes: (1) New set of source code annotations, inserted either manually or automatically, that will clarify the application's use of MPI to the compiler infrastructure, enabling greater accuracy where needed; (2) A compiler transformation framework that leverages these annotations to transform the original MPI source code to improve its performance and scalability; (3) Novel MPI runtime implementation techniques that will provide a rich set of functionality extensions to be used by applications that have been transformed by our compiler; and (4) A novel compiler analysis that leverages simple user annotations to automatically extract the application's communication structure and synthesize most complex code annotations.

97 MATHEMATICS AND COMPUTING↗

Early experiences evaluating the HPE/Cray ecosystem for AMD GPUs

Summary The Oak Ridge Leadership Computing Facility (OLCF) has a long history of supporting and promoting GPU‐accelerated computing starting with the deployment of the Titan supercomputer in 2021 and continuing with the Summit supercomputer which has a theoretical peak performance of approximately 200 petaflops. Because the majority of Summit's computational power comes from its 27,972 GPUs, users must port their applications to one of the supported programming models in order to make efficient use of the system. To prepare the transition to Frontier, the OLCF's exascale supercomputer, users will need to adapt to an entirely new ecosystem which will include new hardware and software technologies. First, users will need to familiarize themselves with the AMD Radeon GPU architecture. Furthermore, users who have been previously relying on CUDA will need to transition to the Heterogeneous‐Computing Interface for Portability (HIP) or one of the other supported programming models (e.g., OpenMP, OpenACC). In this work, we describe our initial experiences and lessons learned in porting three applications or proxy apps currently running on Summit to the HPE/Cray ecosystem to leverage the compute power from AMD GPUs: minisweep, GenASiS, and Sparkler. Each one is representative of current production workloads utilized at the OLCF, different programming languages, and different programming models.

Melesse Vergara, Verónica G.↗

Optimally configuring a measurement system to detect diversions from a nuclear fuel cycle

The civilian nuclear fuel cycle is an industrial process that produces electrical power from the nuclear fission of uranium. Using a measurement system to accurately account for nuclear material, such as uranium, in a fuel cycle is important because of the possible loss or diversion of this potentially dangerous material. A measurement system is defined by a set of measurement methods, or “devices,” used to account for material flows and inventory values at specific locations in the fuel cycle. Here, we develop a simulation-optimization algorithm and an integer-programming model to find the best, or near-best, resource-limited measurement system with a high degree of confidence. The simulation-optimization algorithm minimizes a weighted sum of false positive and false negative diversion-detection probabilities while accounting for material quantities and measurement errors across a finite, discrete time horizon in hypothetical non-diversion and diversion contexts. In each time period, the estimated cumulative material unaccounted for is compared to a fixed or an optimized threshold value to assess if a “significant amount of material” is lost from a measurement system. The integer-programming model minimizes the population variance of the estimated material loss, i.e., material unaccounted for, in a measurement system. We analyze three potential problems in nuclear fuel cycle measurement systems: (i) given location-dependent device precisions, find the configuration of n devices at n locations ( n = 3) that gives the lowest corresponding objective values using the simulation-optimization algorithm and integer-programming model, (ii) find the location at which improving device precision reduces objective values the most using the simulation-optimization algorithm, and determine the effect of measurement frequency on measurement system configurations and objective values using the simulation-optimization algorithm. We obtain comparable results for each problem at least an order of magnitude faster than existing methods do. Using an optimized, rather than fixed, detection threshold in the simulation-optimization algorithm reduces the weighted sum of false positive and false negative probabilities.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Case Study of Using Kokkos and SYCLs Performance-Portable Frameworks for Milc-Dslash Benchmark on NVIDIA, AMD and Intel GPUs

Six of the top ten supercomputers in the TOP500 list from June 2021 rely on NVIDIA GPUs to achieve their peak compute bandwidth. With the announcement of Aurora, Frontier, and El Capitan, Intel and AMD have also entered the domain of providing GPUs for scientific computing. A consequence of the increased diversity in the GPU landscape is the emergence of portable programming models such as Kokkos, SYCL, OpenCL, and OpenMP, which allow application developers to maintain a single-source code across a diverse range of hardware architectures. While the portable frameworks try to optimize the compute resource usage on a given architecture, it is the programmers responsibility to expose parallelism in an application that can take advantage of thousands of processing elements available on GPUs. In this paper, we introduce a GPU-friendly parallel implementation of Milc-Dslash that exposes multiple hierarchies of parallelism in the algorithm. Milc-Dslash was designed to serve as a benchmark with highly optimized matrix-vector multiplications to measure the resource utilization on the GPU systems. The parallel hierarchies in the Milc-Dslash algorithm are mapped onto a target hardware using Kokkos and SYCL programming models. We present the performance achieved by Kokkos and SYCL implementations of Milc-Dslash on NVIDIA A100 GPU, AMD MI100 GPU, and Intel Gen9 GPU. Additionally, we compare the Kokkos and SYCL performances with those obtained from the versions written in CUDA and HIP programming models on NVIDIA A100 GPU and AMD MI100 GPU, respectively.

Dufek, Amanda S↗