Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “distributed memory parallel algorithm”

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 127 records · Page 7

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (Distributed Parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve an optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively, the performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

Sattar, Naw Safrin↗

A Massively Parallel Adaptive Fast-Multipole Method on Heterogeneous Architectures

We present new scalable algorithms and an implementation of the kernel-independent fast multiple method (KIFMM), employing hybrid distributed memory message passing (via MPI) and shared memory/streaming using graphics processing unit (GPU) acceleration to rapidly evaluate two-body non-oscillatory potentials. On traditional CPU-only systems, our implementation scales well up to 30 billion unknowns on 65k cores (AMD/CRAY-based Kraken system at NSF/NICS) on tree data structures with 25 levels between leaves. On GPU-enabled systems, we achieve 30 x speedup for problems of up to 256 million points on 256 GPUs (Lincoln at NSF/NCSA) over a comparable CPU-only implementation. Both of these demonstrations represent the largest and fastest of their kind of which we are aware. We achieve scalability at extreme core counts by extending the initial work of Ying et al. (ACM/IEEE SC 03) with a new approach to scalable MPI-based tree construction and partitioning. For the sub-components of KIFMM, which direct- and approximate-interactions, target evaluation, and source-to-multipole translations, we use CUDA-based GPU-acceleration to achieve excellent performance. To do so requires carefully constructed data structure transformations, which we describe, and whose cost we show is minor. Taken together, these components show promise for ultrascalable FMM in the petascale era and beyond.

99 GENERAL AND MISCELLANEOUS↗

Distributed-Memory Parallel Symmetric Nonnegative Matrix Factorization

We develop the first distributed-memory parallel implementation of Symmetric Nonnegative Matrix Factorization (SymNMF), a key data analytics kernel for clustering and dimensionality reduction. Our implementation includes two different algorithms for SymNMF, which give comparable results in terms of time and accuracy. The first algorithm is a parallelization of an existing sequential approach that uses solvers for non symmetric NMF. The second algorithm is a novel approach based on the Gauss-Newton method. It exploits second-order information without incurring large computational and memory costs. We evaluate the scalability of our algorithms on the Summit system at Oak Ridge National Laboratory, scaling up to 128 nodes (4,096 cores) with 70% efficiency. Additionally, we demonstrate our software on an image segmentation task.

Eswar, Srinivas↗

Frameworks, Algorithms, and Scalable Technologies for Mathematics (FASTMath) SciDAC Institute

The FASTMath SciDAC Institute addressed two key challenges that application scientists faced at the beginning of SciDAC-3. First, FASTMath helped them continue to improve the quality of their simulations by increasing accuracy and reliability of both their software and algorithms. Second, FASTMath helped them adapt their computations to make effective use of high-end computing facilities acquired by DOE over the past five years. This required the development of new mathematical algorithms that were appropriate for the physics problems being solved, implementations that scaled to million-way parallelism, and software that effectively leveraged both distributed memory and on-node parallelism. The Rensselaer Polytechnic Institute team’s efforts focused on the unstructured mesh technologies developed by FASTMath.

97 MATHEMATICS AND COMPUTING↗

MASSIVE HYBRID PARALLELISM FOR FULLY IMPLICIT MULTIPHYSICS

As hardware advances continue to modify the supercomputing landscape, traditional scientific software development practices will become more outdated, ineffective, and inefficient. The process of rewriting/retooling existing software for new architectures is a Sisyphean task, and results in substantial hours of development time, effort, and money. Software libraries which provide an abstraction of the resources provided by such architectures are therefore essential if the computational engineering and science communities are to continue to flourish in this modern computing environment. The Multiphysics Object Oriented Simulation Environment (MOOSE) framework enables complex multiphysics analysis tools to be built rapidly by scientists, engineers, and domain specialists, while also allowing them to both take advantage of current HPC architectures, and efficiently prepare for future supercomputer designs. MOOSE employs a hybrid shared-memory and distributed-memory parallel model and provides a complete and consistent interface for creating multiphysics analysis tools. In this paper, a brief discussion of the mathematical algorithms underlying the framework and the internal object-oriented hybrid parallel design are given. Representative massively parallel results from several applications areas are presented, and a brief discussion of future areas of research for the framework are provided.

97 MATHEMATICS AND COMPUTING↗

Massive hybrid parallelism for fully implicit multiphysics

As hardware advances continue to modify the supercomputing landscape, traditional scientific software development practices will become more outdated, ineffective, and inefficient. The process of rewriting/retooling existing software for new architectures is a Sisyphean task, and results in substantial hours of development time, effort, and money. Software libraries which provide an abstraction of the resources provided by such architectures are therefore essential if the computational engineering and science communities are to continue to flourish in this modern computing environment. The Multiphysics Object Oriented Simulation Environment (MOOSE) framework enables complex multiphysics analysis tools to be built rapidly by scientists, engineers, and domain specialists, while also allowing them to both take advantage of current HPC architectures, and efficiently prepare for future supercomputer designs. MOOSE employs a hybrid shared-memory and distributed-memory parallel model and provides a complete and consistent interface for creating multiphysics analysis tools. In this paper, a brief discussion of the mathematical algorithms underlying the framework and the internal object-oriented hybrid parallel design are given. Representative massively parallel results from several applications areas are presented, and a brief discussion of future areas of research for the framework are provided. (authors)

97 MATHEMATICS AND COMPUTING↗

Parallel-vector algorithms for particle simulations on shared-memory multiprocessors

Over the last few decades, the computational demands of massive particle-based simulations for both scientific and industrial purposes have been continuously increasing. Hence, considerable efforts are being made to develop parallel computing techniques on various platforms. In such simulations, particles freely move within a given space, and so on a distributed-memory system, load balancing, i.e., assigning an equal number of particles to each processor, is not guaranteed. However, shared-memory systems achieve better load balancing for particle models, but suffer from the intrinsic drawback of memory access competition, particularly during (1) paring of contact candidates from among neighboring particles and (2) force summation for each particle. Here, novel algorithms are proposed to overcome these two problems. For the first problem, the key is a pre-conditioning process during which particle labels are sorted by a cell label in the domain to which the particles belong. Then, a list of contact candidates is constructed by pairing the sorted particle labels. For the latter problem, a table comprising the list indexes of the contact candidate pairs is created and used to sum the contact forces acting on each particle for all contacts according to Newton's third law. With just these methods, memory access competition is avoided without additional redundant procedures. The parallel efficiency and compatibility of these two algorithms were evaluated in discrete element method (DEM) simulations on four types of shared-memory parallel computers: a multicore multiprocessor computer, scalar supercomputer, vector supercomputer, and graphics processing unit. The computational efficiency of a DEM code was found to be drastically improved with our algorithms on all but the scalar supercomputer. Thus, the developed parallel algorithms are useful on shared-memory parallel computers with sufficient memory bandwidth.

97 MATHEMATICS AND COMPUTING↗

Optimizing High Performance Markov Clustering for Pre-Exascale Architectures

HipMCL is a high-performance distributed memory implementation of the popular Markov Cluster Algorithm (MCL) and can cluster large-scale networks within hours using a few thousand CPU-equipped nodes. It relies on sparse matrix computations and heavily makes use of the sparse matrix-sparse matrix multiplication kernel (SpGEMM). The existing parallel algorithms in HipMCL are not scalable to Exascale architectures, both due to their communication costs dominating the runtime at large concurrencies and also due to their inability to take advantage of accelerators that are increasingly popular. In this work, we systematically remove scalability and performance bottlenecks of HipMCL. We enable GPUs by performing the expensive expansion phase of the MCL algorithm on GPU. Additionally, we propose a CPU-GPU joint distributed SpGEMM algorithm called pipelined Sparse SUMMA and integrate a probabilistic memory requirement estimator that is fast and accurate. Furthermore, we develop a new merging algorithm for the incremental processing of partial results produced by the GPUs, which improves the overlap efficiency and the peak memory usage. We also integrate a recent and faster algorithm for performing SpGEMM on CPUs. We validate our new algorithms and optimizations with extensive evaluations. With the enabling of the GPUs and integration of new algorithms, HipMCL is up to 12.4x faster, being able to cluster a network with 70 million proteins and 68 billion connections just under 15 minutes using 1024 nodes of ORNL's Summit supercomputer.

97 MATHEMATICS AND COMPUTING↗

Development of a CPU/GPU portable software library for Lagrangian–Eulerian simulations of liquid sprays

The Lagrangian–Eulerian method is widely used for simulations of fuel sprays in turbulent combustion because of the advantage of treating the spray droplets as discrete points. One challenge of the Lagrangian–Eulerian method is the intense computational requirement when tracking the large number of Lagrangian particles needed for high fidelity. We have developed a performance-portable library, Grit, to track the Lagrangian particles in parallel on central processing unit (CPU) and graphics processing unit (GPU) accelerated high performance computing (HPC) architectures. Grit is a C++ library which employs Message Passing Interface (MPI) for distributed memory parallelism and Kokkos programming model for on-node shared memory parallelism with performance portability across different architectures of GPUs and multi-core/manycore CPUs. The parallel algorithms, key parallel kernels, and their performances on the pre-exascale supercomputer, Summit, are presented. Grit is coupled with a direct numerical simulation (DNS) solver, S3D, for multiphase simulations. A conservative formulation has been developed and implemented in Grit for phase coupling with thermodynamic consistency. The formulation separates the conservation of mass, momentum and energy from the physical models to prevent accidental violation of conservation laws due to inconsistent models. The formulation also enforces consistent definitions of enthalpies of the fuel for both phases and the latent heat of evaporation. Finally, simulations of turbulent particle-laden flow and the evaporation of dilute turbulent spray jet are performed to verify the software implementation, and to demonstrate the scalability of Grit for large-scale multiphase simulations.

97 MATHEMATICS AND COMPUTING↗

Scaling and Quality of Modularity Optimization Methods for Graph Clustering

Real-world graphs exhibit structures known as “communities” or “clusters” consisting of a group of vertices with relatively high connectivity between them, as compared to the rest of the vertices in the network. Graph clustering or community detection is a fundamental graph operation used to analyze real-world graphs occurring in the areas of computational biology, cybersecurity, electrical grids, etc. Similar to other graph algorithms, owing to irregular memory accesses and inherently sequential nature, current algorithms for community detection are challenging to parallelize. However, in order to analyze large networks, it is important to develop scalable parallel implementations of graph clustering that are capable of exploiting the architectural features of modern supercomputers. In response to the 2019 Streaming Graph Challenge, we present quality and performance analysis of our distributed- memory community detection using Vite, which is our distributed memory implementation of the popular Louvain method, on the ALCF Theta supercomputer. Clustering methods such as Louvain that rely on modularity maximization are known to suffer from the resolution limit problem, preventing identification of clusters of certain sizes. Hence, we also include quality analysis of our shared-memory implementation of the Fast-tracking Resistance method, in comparison with Louvain on the challenge datasets. Furthermore, we introduce an edge-balanced graph distribution for our distributed memory implementation, that significantly reduces communication, offering up to 80% improvement in the overall execution time. In addition to performance/quality analysis, we also include details on the power/energy consumption, and memory traffic of the distributed-memory clustering implementation using real-world graphs with over a billion edges.

Ghosh, Sayan↗

A second-order distributed memory parallel fast sweeping method for the Eikonal equation

The Eikonal equation is used to calculate wave propagation and distance fields, and due to its complexity requires numerical treatment for its solution. In this work, we present a second-order distributed memory parallel fast sweeping method. The second-order solution switches on a two-point stencil when two upwind points are available, and reverts to first-order otherwise. In all examples, the second-order method improves the solution over the first-order, allowing for significant savings in memory while achieving the same accuracy. Parallelization over distributed memory saw good weak scaling with optimal convergence. The computational time for second-order was approximately 2.5 times slower than first-order, where the largest amount of mesh points ran on 144 cores (512 GB) was ≈20 billion. The savings in memory from the second-order method combined with the distributed memory algorithm result in the ability to solve problems much larger than are possible with the serial first-order method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Scalable Parallel Methods for Analyzing Metagenomics Data at Extreme Scale

The field of bioinformatics and computational biology is currently experiencing a data revolution. The exciting prospect of making fundamental biological discoveries is fueling the rapid development and deployment of numerous cost-effective, high-throughput next-generation sequencing technologies. The result is that the DNA and protein sequence repositories are being bombarded with new sequence information. Databases are continuing to report a Moore’s law-like growth trajectory in their database sizes, roughly doubling every 18 months. In what seems to be a paradigm-shift, individual projects are now capable of generating billions of raw sequence data that need to be analyzed in the presence of already annotated sequence information. While it is clear that data-driven methods, such as sequencing homology detection, are becoming the mainstay in the field of computational life sciences, the algorithmic advancements essential for implementing complex data analytics at scale have mostly lagged behind. Sequence homology detection is central to a number of bioinformatics applications including genome sequencing and protein family characterization. Given millions of sequences, the goal is to identify all pairs of sequences that are highly similar (or “homologous”) on the basis of alignment criteria. While there are optimal alignment algorithms to compute pairwise homology, their deployment for large-scale is currently not feasible; instead, heuristic methods are used at the expense of quality. In this dissertation, we present the design and evaluation of a parallel implementation for conducting optimal homology detection on distributed memory supercomputers. Our approach uses a combination of techniques from asynchronous load balancing (viz. work stealing, dynamic task counters), data replication, and exact-matching filters to achieve homology detection at scale. Results for a collection of 2.56M sequences show parallel efficiencies of ~75-100% on up to 8K cores, representing a time-to-solution of 33 seconds. We extend this work with a detailed analysis of single-node sequence alignment performance using the latest CPU vector instruction set extensions. Preliminary results reveal that current sequence alignment algorithms are unable to fully utilize widening vector registers.

59 BASIC BIOLOGICAL SCIENCES↗

cuTS: Scaling Subgraph Isomorphism on Distributed Multi-GPUSystems Using Trie Based Data Structure

Subgraph isomorphism is a pattern-matching algorithm widely used in many domains such as chem-informatics, bioinformatics, databases, and social network analysis. It is computationally expensive and is a proven NP-hard problem. The massive parallelism offered by the GPU hardware is well suited for solving the subgraph isomorphism. However, current GPU implementations are far from the achievable performance. Moreover, the enormous memory requirement of current approaches limits the problem size that can be handled. This work analyzes the fundamental challenges associated with processing the subgraph isomorphism on GPUs and develops an efficient GPU hardware-aware implementation. We also develop a new GPU-friendly trie-based data structure to drastically reduce the intermediate storage space requirement. Hence, our approach runs larger benchmarks than the competitors. We also develop the first distributed sub-graph isomorphism algorithm for GPUs. Our experimental evaluation section demonstrates the efficacy of our approach by comparing the execution time and number of cases that we can handle against the state-of-the-art GPU implementations.

Xiang, Lizhi↗

An Efficient Multicore Implementation of a Novel HSS-Structured Multifrontal Solver Using Randomized Sampling

Here, we present a sparse linear system solver that is based on a multifrontal variant of Gaussian elimination and exploits low-rank approximation of the resulting dense frontal matrices. We use hierarchically semiseparable (HSS) matrices, which have low-rank off-diagonal blocks, to approximate the frontal matrices. For HSS matrix construction, a randomized sampling algorithm is used together with interpolative decompositions. The combination of the randomized compression with a fast ULV HSS factoriz ation leads to a solver with lower computational complexity than the standard multifrontal method for many applications, resulting in speedups up to 7 fold for problems in our test suite. The implementation targets many-core systems by using task parallelism with dynamic runtime scheduling. Numerical experiments show performance improvements over state-of-the-art sparse direct solvers. The implementation achieves high performance and good scalability on a range of modern shared memory parallel systems, including the Intel Xeon Phi (MIC). The code is part of a software package called STRUMPACK - STRUctured Matrices PACKage, which also has a distributed memory component for dense rank-structured matrices.

97 MATHEMATICS AND COMPUTING↗

Livermore Random I/O Testbench

LRIOT is a test bench framework that is designed to generate sophisticated I/O rates that can stress high-performance memory and storage systems, such as non-volatile random access memories (NVRAM)and storage class memory. Furthermore, LRIOT provides the capabilities to mix multiple types of concurrency, namely threading and task parallelism, as well as distributed execution using Message Passing Interface (MPI) libraries. It will be used by algorithm designers to generate access patterns that mimic their application's behavior, and by system designers to test high-performance NVRAM storage.

Source record↗

Livermore Random I/O Testbench

LRIOT is a test bench framework that is designed to generate sophisticated I/O rates that can stress high-performance memory and storage systems, such as non-volatile random access memories (NVRAM)and storage class memory. Furthermore, LRIOT provides the capabilities to mix multiple types of concurrency, namely threading and task parallelism, as well as distributed execution using Message Passing Interface (MPI) libraries. It will be used by algorithm designers to generate access patterns that mimic their application's behavior, and by system designers to test high-performance NVRAM storage.

Van Essen, Brian↗

A communication-avoiding, hybrid-parallel, rank-revealing orthogonalization method.

Orthogonalization consumes much of the run time of many iterative methods for solving sparse linear systems and eigenvalue problems. Commonly used algorithms, such as variants of Gram-Schmidt or Householder QR, have performance dominated by communication. Here, 'communication' includes both data movement between the CPU and memory, and messages between processors in parallel. Our Tall Skinny QR (TSQR) family of algorithms requires asymptotically fewer messages between processors and data movement between CPU and memory than typical orthogonalization methods, yet achieves the same accuracy as Householder QR factorization. Furthermore, in block orthogonalizations, TSQR is faster and more accurate than existing approaches for orthogonalizing the vectors within each block ('normalization'). TSQR's rank-revealing capability also makes it useful for detecting deflation in block iterative methods, for which existing approaches sacrifice performance, accuracy, or both. We have implemented a version of TSQR that exploits both distributed-memory and shared-memory parallelism, and supports real and complex arithmetic. Our implementation is optimized for the case of orthogonalizing a small number (5-20) of very long vectors. The shared-memory parallel component uses Intel's Threading Building Blocks, though its modular design supports other shared-memory programming models as well, including computation on the GPU. Our implementation achieves speedups of 2 times or more over competing orthogonalizations. It is available now in the development branch of the Trilinos software package, and will be included in the 10.8 release.

99 GENERAL AND MISCELLANEOUS↗

Hierarchical computation in the SPMD programming model

Large-scale parallel machines are programmed mainly with the single program, multiple data (SPMD) model of parallelism. While this model has advantages of scalability and simplicity, it does not fit well with divide-and-conquer parallelism or hierarchical machines that mix shared and distributed memory. In this paper, we define the recursive single program, multiple data model (RSPMD) that extends SPMD with a hierarchical team mechanism to support hierarchical algorithms and machines. We implement this model in the Titanium language and describe how to eliminate a class of deadlocks by ensuring alignment of collective operations. We present application case studies evaluating the RSPMD model, showing that it enables divide-and-conquer algorithms such as sorting to be elegantly expressed and that team collective operations increase performance of conjugate gradient by up to a factor of two. The model also facilitates optimizations for hierarchical machines, improving scalability of particle in cell by 8x and performance of sorting and a stencil code by up to 40% and 14%, respectively.

Kamil, A↗