Publications

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

We present PuLP, a parallel and memory-efficient graph partitioning method specifically designed to partition low-diameter networks with skewed degree distributions. Graph partitioning is an important Big Data problem because it impacts the execution time and energy efficiency of graph analytics on distributed-memory platforms. Partitioning determines the in-memory layout of a graph, which affects locality, intertask load balance, communication time, and overall memory utilization of graph analytics. A novel feature of our method PuLP (Partitioning using Label Propagation) is that it optimizes for multiple objective metrics simultaneously, while satisfying multiple partitioning constraints. Using our method, we are able to partition a web crawl with billions of edges on a single compute server in under a minute. For a collection of test graphs, we show that PuLP uses 8-39× less memory than state-of-the-art partitioners and is up to 14.5× faster, on average, than alternate approaches (with 16-way parallelism). We also achieve better partitioning quality results for the multi-objective scenario.

Abstract not provided.

The computer-aided design (CAD) applications that are fundamental to the electronic design automation industry need to harness the available hardware resources to be able to perform full-chip simulation for modern technology nodes (45nm and below). We will present a hybrid (MPI+threads) approach for parallel transistor-level transient circuit simulation that achieves scalable performance for some challenging large-scale integrated circuits. This approach focuses on the computationally expensive part of the simulator: the linear system solve. Hybrid versions of two iterative linear solver strategies are presented, one takes advantage of block triangular form structure while the other uses a Schur complement technique. Results indicate up to a 27x improvement in total simulation time on 256 cores.

Trilinos is an object-oriented software framework for the solution of large-scale, complex multi-physics engineering and scientific problems. While Trilinos was originally designed for scalable solutions of large problems, the fidelity needed by many simulations is significantly greater than what one could have envisioned two decades ago. When problem sizes exceed a billion elements even scalable applications and solver stacks require a complete revision. The second-generation Trilinos employs C++ templates in order to solve arbitrarily large problems. We present a case study of the integration of Trilinos with a low Mach fluids engineering application (SIERRA low Mach module/Nalu). Through the use of improved algorithms and better software engineering practices, we demonstrate good weak scaling for up to a nine billion element large eddy simulation (LES) problem on unstructured meshes with a 27 billion row matrix on 524,288 cores of an IBM Blue Gene/Q platform.

Abstract not provided.

Abstract not provided.

Abstract not provided.

As computer systems grow in both size and complexity, the need for applications and run-time systems to adjust to their dynamic environment also grows. The goal of the RAAMP LDRD was to combine static architecture information and real-time system state with algorithms to conserve power, reduce communication costs, and avoid network contention. We devel- oped new data collection and aggregation tools to extract static hardware information (e.g., node/core hierarchy, network routing) as well as real-time performance data (e.g., CPU uti- lization, power consumption, memory bandwidth saturation, percentage of used bandwidth, number of network stalls). We created application interfaces that allowed this data to be used easily by algorithms. Finally, we demonstrated the benefit of integrating system and application information for two use cases. The first used real-time power consumption and memory bandwidth saturation data to throttle concurrency to save power without increasing application execution time. The second used static or real-time network traffic information to reduce or avoid network congestion by remapping MPI tasks to allocated processors. Results from our work are summarized in this report; more details are available in our publications [2, 6, 14, 16, 22, 29, 38, 44, 51, 54].

Abstract not provided.

The Computer Science Research Institute (CSRI) brings university faculty and students to Sandia National Laboratories for focused collaborative research on computer science, computational science, and mathematics problems that are critical to the mission of the laboratories, the Department of Energy, and the United States. The CSRI provides a mechanism by which university researchers learn about and impact national— and global—scale problems while simultaneously bringing new ideas from the academic research community to bear on these important problems. A key component of CSRI programs over the last decade has been an active and productive summer program where students from around the country conduct internships at CSRI. Each student is paired with a Sandia staff member who serves as technical advisor and mentor. The goals of the summer program are to expose the students to research in mathematical and computer sciences at Sandia and to conduct a meaningful and impactful summer research project with their Sandia mentor. Every effort is made to align summer projects with the student's research objectives and all work is coordinated with the ongoing research activities of the Sandia mentor in alignment with Sandia technical thrusts. For the 2013 CSRI Proceedings, research articles have been organized into the following broad technical focus areas — Computational Mathematics and Algorithms, Combinatorial Algorithms and Visualization, Advanced Architectures and Systems Software, Computational Applications — which are well aligned with Sandia's strategic thrusts in computer and information sciences.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Krylov subspace projection methods are widely used iterative methods for solving large-scale linear systems of equations. Researchers have demonstrated that communication avoiding (CA) techniques can improve Krylov methods' performance on modern computers, where communication is becoming increasingly expensive compared to arithmetic operations. In this paper, we extend these studies by two major contributions. First, we present our implementation of a CA variant of the Generalized Minimum Residual (GMRES) method, called CAGMRES, for solving no symmetric linear systems of equations on a hybrid CPU/GPU cluster. Our performance results on up to 120 GPUs show that CA-GMRES gives a speedup of up to 2.5x in total solution time over standard GMRES on a hybrid cluster with twelve Intel Xeon CPUs and three Nvidia Fermi GPUs on each node. We then outline a domain decomposition framework to introduce a family of preconditioners that are suitable for CA Krylov methods. Our preconditioners do not incur any additional communication and allow the easy reuse of existing algorithms and software for the sub domain solves. Experimental results on the hybrid CPU/GPU cluster demonstrate that CA-GMRES with preconditioning achieve a speedup of up to 7.4x over CAGMRES without preconditioning, and speedup of up to 1.7x over GMRES with preconditioning in total solution time. These results confirm the potential of our framework to develop a practical and effective preconditioned CA Krylov method.

We present a new method for mapping applications' MPI tasks to cores of a parallel computer such that communication and execution time are reduced. We consider the case of sparse node allocation within a parallel machine, where the nodes assigned to a job are not necessarily located within a contiguous block nor within close proximity to each other in the network. The goal is to assign tasks to cores so that interdependent tasks are performed by 'nearby' cores, thus lowering the distance messages must travel, the amount of congestion in the network, and the overall cost of communication. Our new method applies a geometric partitioning algorithm to both the tasks and the processors, and assigns task parts to the corresponding processor parts. We show that, for the structured finite difference mini-app Mini Ghost, our mapping method reduced execution time 34% on average on 65,536 cores of a Cray XE6. In a molecular dynamics mini-app, Mini MD, our mapping method reduced communication time by 26% on average on 6144 cores. We also compare our mapping with graph-based mappings from the LibTopoMap library and show that our mappings reduced the communication time on average by 15% in MiniGhost and 10% in MiniMD. © 2014 IEEE.

Finding the strongly connected components (SCCs) of a directed graph is a fundamental graph-theoretic problem. Tarjan's algorithm is an efficient serial algorithm to find SCCs, but relies on the hard-to-parallelize depth-first search (DFS). We observe that implementations of several parallel SCC detection algorithms show poor parallel performance on modern multicore platforms and large-scale networks. This paper introduces the Multistep method, a new approach that avoids work inefficiencies seen in prior SCC approaches. It does not rely on DFS, but instead uses a combination of breadth-first search (BFS) and a parallel graph coloring routine. We show that the Multistep method scales well on several real-world graphs, with performance fairly independent of topological properties such as the size of the largest SCC and the total number of SCCs. On a 16-core Intel Xeon platform, our algorithm achieves a 20X speedup over the serial approach on a 2 billion edge graph, fully decomposing it in under two seconds. For our collection of test networks, we observe that the Multistep method is 1.92X faster (mean speedup) than the state-of-the-art Hong et al. SCC method. In addition, we modify the Multistep method to find connected and weakly connected components, as well as introduce a novel algorithm for determining articulation vertices of biconnected components. These approaches all utilize the same underlying BFS and coloring routines. © 2014 IEEE.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

We design, implement, and evaluate algorithms for computing a matching of maximum cardinality in a bipartite graph on multicore and massively multithreaded computers. As computers with larger numbers of slower cores dominate the commodity processor market, the design of multithreaded algorithms to solve large matching problems becomes a necessity. Recent work on serial algorithms for the matching problem has shown that their performance is sensitive to the order in which the vertices are processed for matching. In a multithreaded environment, imposing a serial order in which vertices are considered for matching would lead to loss of concurrency and performance. But this raises the question: Would parallel matching algorithms on multithreaded machines improve performance over a serial algorithm? We answer this question in the affirmative. We report efficient multithreaded implementations of three classes of algorithms based on their manner of searching for augmenting paths: breadth-first-search, depth-first-search, and a combination of both. The Karp-Sipser initialization algorithm is used to make the parallel algorithms practical. We report extensive results and insights using three shared-memory platforms (a 48-core AMD Opteron, a 32-coreIntel Nehalem, and a 128-processor Cray XMT) on a representative set of real-world and synthetic graphs. To the best of our knowledge, this is the first study of augmentation-based parallel algorithms for bipartite cardinality matching that demonstrates good speedups on multithreaded shared memory multiprocessors. © 2012 IEEE.

With the ubiquity of multicore processors, it is crucial that solvers adapt to the hierarchical structure of modern architectures. We present ShyLU, a "hybrid-hybrid" solver for general sparse linear systems that is hybrid in two ways: First, it combines direct and iterative methods. The iterative part is based on approximate Schur complements where we compute the approximate Schur complement using a value-based dropping strategy or structure-based probing strategy. Second, the solver uses two levels of parallelism via hybrid programming (MPI+threads). ShyLU is useful both in shared-memory environments and on large parallel computers with distributed memory. In the latter case, it should be used as a sub domain solver. We argue that with the increasing complexity of compute nodes, it is important to exploit multiple levels of parallelism even within a single compute node. We show the robustness of ShyLU against other algebraic preconditioners. ShyLU scales well up to 384 cores for a given problem size. We also study the MPI-only performance of ShyLU against a hybrid implementation and conclude that on present multicore nodes MPI-only implementation is better. However, for future multicore machines (96 or more cores) hybrid/ hierarchical algorithms and implementations are important for sustained performance. © 2012 IEEE.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.