Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “distributed memory parallel systems”

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 55 records · Page 3

Performance and Application of Parallel OVERFLOW Codes on Distributed and Shared Memory Platforms

The presentation discusses recent studies on the performance of the two parallel versions of the aerodynamics CFD code, OVERFLOW_MPI and _MLP. Developed at NASA Ames, the serial version, OVERFLOW, is a multidimensional Navier-Stokes flow solver based on overset (Chimera) grid technology. The code has recently been parallelized in two ways. One is based on the explicit message-passing interface (MPI) across processors and uses the _MPI communication package. This approach is primarily suited for distributed memory systems and workstation clusters. The second, termed the multi-level parallel (MLP) method, is simple and uses shared memory for all communications. The _MLP code is suitable on distributed-shared memory systems. For both methods, the message passing takes place across the processors or processes at the advancement of each time step. This procedure is, in effect, the Chimera boundary conditions update, which is done in an explicit "Jacobi" style. In contrast, the update in the serial code is done in more of the "Gauss-Sidel" fashion. The programming efforts for the _MPI code is more complicated than for the _MLP code; the former requires modification of the outer and some inner shells of the serial code, whereas the latter focuses only on the outer shell of the code. The _MPI version offers a great deal of flexibility in distributing grid zones across a specified number of processors in order to achieve load balancing. The approach is capable of partitioning zones across multiple processors or sending each zone and/or cluster of several zones into a single processor. The message passing across the processors consists of Chimera boundary and/or an overlap of "halo" boundary points for each partitioned zone. The MLP version is a new coarse-grain parallel concept at the zonal and intra-zonal levels. A grouping strategy is used to distribute zones into several groups forming sub-processes which will run in parallel. The total volume of grid points in each group are approximately balanced. A proper number of threads are initially allocated to each group, and in subsequent iterations during the run-time, the number of threads are adjusted to achieve load balancing across the processes. Each process exploits the multitasking directives already established in Overflow.

Djomehri, M. Jahed↗

Chapel HyperGraph Library (CHGL)

We present the Chapel Hpergraph Library (CHGL), a library for hypergraph computation in the emerging Chapel language. Hypergraphs generalize graphs, where a hypergraph edge can connect any number of vertices. Thus, hypergraphs capture high-order, high-dimensional interactions between mulitple entities that are not directly expressible in graphs. CHGL is designed to provide HPC-class computation with high-level abstractions and modern language support for parallel comptuing on shared memory and distributed memory systems.

Jenkins, Louis P.↗

Towards scaling community detection on distributed-memory heterogeneous systems

Distributed multi-GPU systems pose significant challenges and opportunities for efficient execution of parallel applications. Graph algorithms are generally characterized by irregular memory accesses, low computation to communication ratios, and load balancing problems that are especially hard to address on multi-GPU systems. Graph community detection is an important problem in the emerging domain of graph analytics with numerous applications. In this paper, we present our ongoing work on distributed-memory multi-GPU implementation for graph community detection. Our work parallelizes the widely used (albeit serial) Louvain method on distributed multi-GPU platforms. Supported by an extensive set of experiments on a multi-GPU enabled supercomputer (OLCF Summit) and a single compute node (Nvidia DGX-2®), we demonstrate competitive performance to existing distributed-memory CPU-based implementation, and up to 6.5 better results than Nvidia RAPIDS® CUGRAPH. To the best of our knowledge, this work represents the first effort for community detection on distributed multi-GPU systems. Our approach and related findings can be extended to numerous other iterative graph algorithms on multi-GPU systems.

97 MATHEMATICS AND COMPUTING↗

MPI-hybrid Parallelism for Volume Rendering on Large, Multi-core Systems

This work studies the performance and scalability characteristics of"hybrid'" parallel programming and execution as applied to raycasting volume rendering -- a staple visualization algorithm -- on a large, multi-core platform. Historically, the Message Passing Interface (MPI) has become the de-facto standard for parallel programming and execution on modern parallel systems. As the computing industry trends towards multi-core processors, with four- and six-core chips common today and 128-core chips coming soon, we wish to better understand how algorithmic and parallel programming choices impact performance and scalability on large, distributed-memory multi-core systems. Our findings indicate that the hybrid-parallel implementation, at levels of concurrency ranging from 1,728 to 216,000, performs better, uses a smaller absolute memory footprint, and consumes less communication bandwidth than the traditional, MPI-only implementation.

97 MATHEMATICS AND COMPUTING↗

Hybrid Parallelism for Volume Rendering on Large, Multi-core Systems

This work studies the performance and scalability characteristics of"hybrid'"parallel programming and execution as applied to raycasting volume rendering -- a staple visualization algorithm -- on a large, multi-core platform. Historically, the Message Passing Interface (MPI) has become the de-facto standard for parallel programming and execution on modern parallel systems. As the computing industry trends towards multi-core processors, with four- and six-core chips common today and 128-core chips coming soon, we wish to better understand how algorithmic and parallel programming choices impact performance and scalability on large, distributed-memory multi-core systems. Our findings indicate that the hybrid-parallel implementation, at levels of concurrency ranging from 1,728 to 216,000, performs better, uses a smaller absolute memory footprint, and consumes less communication bandwidth than the traditional, MPI-only implementation.

97 MATHEMATICS AND COMPUTING↗

Hybrid Parallelism for Volume Rendering on Large, Multi-core Systems

This work studies the performance and scalability characteristics of"hybrid" parallel programming and execution as applied to raycasting volume rendering -- a staple visualization algorithm -- on a large, multi-core platform. Historically, the Message Passing Interface (MPI) has become the de-facto standard for parallel programming and execution on modern parallel systems. As the computing industry trends towards multi-core processors, with four- and six-core chips common today and 128-core chips coming soon, we wish to better understand how algorithmic and parallel programming choices impact performance and scalability on large, distributed-memory multi-core systems. Our findings indicate that the hybrid-parallel implementation, at levels of concurrency ranging from 1,728 to 216,000, performs better, uses a smaller absolute memory footprint, and consumes less communication bandwidth than the traditional, MPI-only implementation.

97 MATHEMATICS AND COMPUTING↗

Distributed memory, GPU accelerated Fock construction for hybrid, Gaussian basis density functional theory

With the growing reliance of modern supercomputers on accelerator-based architecture such a graphics processing units (GPUs), the development and optimization of electronic structure methods to exploit these massively parallel resources has become a recent priority. While significant strides have been made in the development GPU accelerated, distributed memory algorithms for many modern electronic structure methods, the primary focus of GPU development for Gaussian basis atomic orbital methods has been for shared memory systems with only a handful of examples pursing massive parallelism. Here in this work, we present a set of distributed memory algorithms for the evaluation of the Coulomb and exact exchange matrices for hybrid Kohn–Sham DFT with Gaussian basis sets via direct density-fitted (DF-J-Engine) and seminumerical (sn-K) methods, respectively. The absolute performance and strong scalability of the developed methods are demonstrated on systems ranging from a few hundred to over one thousand atoms using up to 128 NVIDIA A100 GPUs on the Perlmutter supercomputer.

97 MATHEMATICS AND COMPUTING↗

On the use of flux limiters in the discrete ordinates method for 3D radiation calculations in absorbing and scattering media

The application of flux limiters to the discrete ordinates method (DOM), S{sub N}, for radiative transfer calculations is discussed and analyzed for 3D enclosures for cases in which the intensities are strongly coupled to each other such as: radiative equilibrium and scattering media. A Newton-Krylov iterative method (GMRES) solves the final systems of linear equations along with a domain decomposition strategy for parallel computation using message passing libraries in a distributed memory system. Ray effects due to angular discretization and errors due to domain decomposition are minimized until small variations are introduced by these effects in order to focus on the influence of flux limiters on errors due to spatial discretization, known as numerical diffusion, smearing or false scattering. Results are presented for the DOM-integrated quantities such as heat flux, irradiation and emission. A variety of flux limiters are compared to 'exact' solutions available in the literature, such as the integral solution of the RTE for pure absorbing-emitting media and isotropic scattering cases and a Monte Carlo solution for a forward scattering case. Additionally, a non-homogeneous 3D enclosure is included to extend the use of flux limiters to more practical cases. The overall balance of convergence, accuracy, speed and stability using flux limiters is shown to be superior compared to step schemes for any test case.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

YAPPA: a Compiler-Based Parallelization Framework for Irregular Applications on MPSoCs

Modern embedded systems include hundreds of cores. Because of the difficulty in providing a fast, coherent memory architecture, these systems usually rely on non-coherent, non-uniform memory architectures with private memories for each core. However, programming these systems poses significant challenges. The developer must extract large amounts of parallelism, while orchestrating communication among cores to optimize application performance. These issues become even more significant with irregular applications, which present data sets difficult to partition, unpredictable memory accesses, unbalanced control flow and fine grained communication. Hand-optimizing every single aspect is hard and time-consuming, and it often does not lead to the expected performance. There is a growing gap between such complex and highly-parallel architectures and the high level languages used to describe the specification, which were designed for simpler systems and do not consider these new issues. In this paper we introduce YAPPA (Yet Another Parallel Programming Approach), a compilation framework for the automatic parallelization of irregular applications on modern MPSoCs based on LLVM. We start by considering an efficient parallel programming approach for irregular applications on distributed memory systems. We then propose a set of transformations that can reduce the development and optimization effort. The results of our initial prototype confirm the correctness of the proposed approach.

Irregular applications↗

Reinforcement Learning for Load-balanced Parallel Particle Tracing

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.

Distributed and parallel particle tracing↗

Integrating Cache Performance Modeling and Tuning Support in Parallelization Tools

With the resurgence of distributed shared memory (DSM) systems based on cache-coherent Non Uniform Memory Access (ccNUMA) architectures and increasing disparity between memory and processors speeds, data locality overheads are becoming the greatest bottlenecks in the way of realizing potential high performance of these systems. While parallelization tools and compilers facilitate the users in porting their sequential applications to a DSM system, a lot of time and effort is needed to tune the memory performance of these applications to achieve reasonable speedup. In this paper, we show that integrating cache performance modeling and tuning support within a parallelization environment can alleviate this problem. The Cache Performance Modeling and Prediction Tool (CPMP), employs trace-driven simulation techniques without the overhead of generating and managing detailed address traces. CPMP predicts the cache performance impact of source code level "what-if" modifications in a program to assist a user in the tuning process. CPMP is built on top of a customized version of the Computer Aided Parallelization Tools (CAPTools) environment. Finally, we demonstrate how CPMP can be applied to tune a real Computational Fluid Dynamics (CFD) application.

Waheed, Abdul↗

Sparse distributed memory overview

The Sparse Distributed Memory (SDM) project is investigating the theory and applications of massively parallel computing architecture, called sparse distributed memory, that will support the storage and retrieval of sensory and motor patterns characteristic of autonomous systems. The immediate objectives of the project are centered in studies of the memory itself and in the use of the memory to solve problems in speech, vision, and robotics. Investigation of methods for encoding sensory data is an important part of the research. Examples of NASA missions that may benefit from this work are Space Station, planetary rovers, and solar exploration. Sparse distributed memory offers promising technology for systems that must learn through experience and be capable of adapting to new circumstances, and for operating any large complex system requiring automatic monitoring and control. Sparse distributed memory is a massively parallel architecture motivated by efforts to understand how the human brain works. Sparse distributed memory is an associative memory, able to retrieve information from cues that only partially match patterns stored in the memory. It is able to store long temporal sequences derived from the behavior of a complex system, such as progressive records of the system's sensory data and correlated records of the system's motor controls.

Raugh, Mike↗

High Order Anchoring and Reinitialization of Level Set Function for Simulating Interface Motion

A second order interface anchoring method has been developed and used with fast sweeping algorithm for reinitialization of a level set function. The algebraic anchoring formulation ensures that the location of the actual interface is preserved, leading to better mass conservation property. It also provides high order accurate algebraic constraint for solving the Eikonal equation on a finite difference grid. Geometric properties of the interface such as surface normal and curvature are subsequently computed from the reinitialized distance function. Various analytical functions for modeling distortion in level set field are considered and accuracy of reinitialization is evaluated using first and second order anchoring schemes. It is also shown that accurate computation of interface curvature requires a high order anchor in addition to a high order fast sweeping method. Mass conservation property of reinitialization is also analyzed by considering test problems from literature including the classic Rider–Kothe single vortex problem. The formulation is suitable for efficient parallelization for both distributed memory and on-node shared memory parallel systems. In conclusion, scalability and performance of the reinitialization scheme on multiple architectures are demonstrated.

97 MATHEMATICS AND COMPUTING↗

A parallel, distributed memory implementation of the adaptive sampling configuration interaction method

The many-body simulation of quantum systems is an active field of research that involves several different methods targeting various computing platforms. Many methods commonly employed, particularly coupled cluster methods, have been adapted to leverage the latest advances in modern high-performance computing. Selected configuration interaction (sCI) methods have seen extensive usage and development in recent years. However, the development of sCI methods targeting massively parallel resources has been explored only in a few research works. Here, we present a parallel, distributed memory implementation of the adaptive sampling configuration interaction approach (ASCI) for sCI. In particular, we will address the key concerns pertaining to the parallelization of the determinant search and selection, Hamiltonian formation, and the variational eigenvalue calculation for the ASCI method. Load balancing in the search step is achieved through the application of memory-efficient determinant constraints originally developed for the ASCI-PT2 method. The presented benchmarks demonstrate near optimal speedup for ASCI calculations of Cr 2 (24e, 30o) with 10 6 , 10 7 , and 3 × 10 8 variational determinants on up to 16 384 CPUs. Importantly, to the best of the authors’ knowledge, this is the largest variational ASCI calculation to date.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Job Management Requirements for NAS Parallel Systems and Clusters

A job management system is a critical component of a production supercomputing environment, permitting oversubscribed resources to be shared fairly and efficiently. Job management systems that were originally designed for traditional vector supercomputers are not appropriate for the distributed-memory parallel supercomputers that are becoming increasingly important in the high performance computing industry. Newer job management systems offer new functionality but do not solve fundamental problems. We address some of the main issues in resource allocation and job scheduling we have encountered on two parallel computers - a 160-node IBM SP2 and a cluster of 20 high performance workstations located at the Numerical Aerodynamic Simulation facility. We describe the requirements for resource allocation and job management that are necessary to provide a production supercomputing environment on these machines, prioritizing according to difficulty and importance, and advocating a return to fundamental issues.

Saphir, William↗

Design and performance of a scalable, parallel statistics toolkit.

Most statistical software packages implement a broad range of techniques but do so in an ad hoc fashion, leaving users who do not have a broad knowledge of statistics at a disadvantage since they may not understand all the implications of a given analysis or how to test the validity of results. These packages are also largely serial in nature, or target multicore architectures instead of distributed-memory systems, or provide only a small number of statistics in parallel. This paper surveys a collection of parallel implementations of statistics algorithm developed as part of a common framework over the last 3 years. The framework strategically groups modeling techniques with associated verification and validation techniques to make the underlying assumptions of the statistics more clear. Furthermore it employs a design pattern specifically targeted for distributed-memory parallelism, where architectural advances in large-scale high-performance computing have been focused. Moment-based statistics (which include descriptive, correlative, and multicorrelative statistics, principal component analysis (PCA), and k-means statistics) scale nearly linearly with the data set size and number of processes. Entropy-based statistics (which include order and contingency statistics) do not scale well when the data in question is continuous or quasi-diffuse but do scale well when the data is discrete and compact. We confirm and extend our earlier results by now establishing near-optimal scalability with up to 10,000 processes.

99 GENERAL AND MISCELLANEOUS↗

Design considerations for parallel graphics libraries

Applications which run on parallel supercomputers are often characterized by massive datasets. Converting these vast collections of numbers to visual form has proven to be a powerful aid to comprehension. For a variety of reasons, it may be desirable to provide this visual feedback at runtime. One way to accomplish this is to exploit the available parallelism to perform graphics operations in place. In order to do this, we need appropriate parallel rendering algorithms and library interfaces. This paper provides a tutorial introduction to some of the issues which arise in designing parallel graphics libraries and their underlying rendering algorithms. The focus is on polygon rendering for distributed memory message-passing systems. We illustrate our discussion with examples from PGL, a parallel graphics library which has been developed on the Intel family of parallel systems.

Crockett, Thomas W.↗

Performance Characterization of a Hierarchical MPI Implementations on Large-scale Distributed-memory Platforms

The building blocks of emerging Petascale massively parallel processing (MPP) systems are multi-core processors with four or more cores as a single processing element and a customized network interface. The resulting memory and communication hierarchy of these platforms are now exposed to application developers and end users by creating a hierarchical or multi-core aware message-passing (MPI) programming interface and by providing a handful of runtime, tunable parameters that allows mapping and control of MPI tasks and message handling. We characterize performance of MPI communication patterns and present strategies for optimizing applications performance on Cray XT series systems that are composed of contemporary AMD processors and a proprietary network infrastructure. We highlight dependencies in its memory and network subsystems, which could influence production-level applications performance. We demonstrate that MPI micro-benchmarks could mislead an application developer or end user since these benchmarks often do not expose the interplay between memory allocation and usage in the user space, which depends on the number of tasks or cores and workload characteristics. Our studies show performance improvements compared to the default options for our target scientific benchmarks and production-level applications.

99 GENERAL AND MISCELLANEOUS↗