Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel algorithms”

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 577 records · Page 32

Optimizing Approximate Weighted Matching on Nvidia Kepler K40

Matching is a fundamental graph problem with numerous applications in science and engineering. While algorithms for computing optimal matchings are difficult to parallelize, approximation algorithms on the other hand generally compute high quality solutions and are amenable to parallelization. In this paper, we present efficient implementations of the current best algorithm for half-approximate weighted matching, the Suitor algorithm, on Nvidia Kepler K-40 platform. We develop four variants of the algorithm that exploit hardware features to address key challenges for a GPU implementation. We also experiment with different combinations of work assigned to a warp. Using an exhaustive set of $269$ inputs, we demonstrate that the new implementation outperforms the previous best GPU algorithm by $10$ to $100\times$ for over $100$ instances, and from $100$ to $1000\times$ for $15$ instances. We also demonstrate up to $20\times$ speedup relative to $2$ threads, and up to $5\times$ relative to $16$ threads on Intel Xeon platform with $16$ cores for the same algorithm. The new algorithms and implementations provided in this paper will have a direct impact on several applications that repeatedly use matching as a key compute kernel. Further, algorithm designs and insights provided in this paper will benefit other researchers implementing graph algorithms on modern GPU architectures.

GPU↗

Parallel and interacting stochastic approximation annealing algorithms for global optimisation

We present the parallel and interacting stochastic approximation annealing (PISAA) algorithm, a stochastic simulation procedure for global optimisation, that extends and improves the stochastic approximation annealing (SAA) by using population Monte Carlo ideas. The efficiency of standard SAA algorithm crucially depends on its selfadjusting mechanism which presents stability issues in high dimensional or rugged optimisation problems. The proposed algorithm involves simulating a population of SAA chains that interact each other in a manner that significantly improves the stability of the self-adjusting mechanism and the search for the global optimum in the sampling space, as well as it inherits SAA desired convergence properties when a square-root cooling schedule is used. It can be implemented in parallel computing environments in order to mitigate the computational overhead. As a result, PISAA can address complex optimisation problems that it would be difficult for SAA to satisfactory address. We demonstrate the good performance of the proposed algorithm on challenging applications including Bayesian network learning and protein folding. Our numerical comparisons suggest that PISAA outperforms the simulated annealing, stochastic approximation annealing, and annealing evolutionary stochastic approximation Monte Carlo.

Local trap↗

Single-Shot Decoding of Good Quantum LDPC Codes

Abstract Quantum Tanner codes constitute a family of quantum low-density parity-check codes with good parameters, i.e., constant encoding rate and relative distance. In this article, we prove that quantum Tanner codes also facilitate single-shot quantum error correction (QEC) of adversarial noise, where one measurement round (consisting of constant-weight parity checks) suffices to perform reliable QEC even in the presence of measurement errors. We establish this result for both the sequential and parallel decoding algorithms introduced by Leverrier and Zémor. Furthermore, we show that in order to suppress errors over multiple repeated rounds of QEC, it suffices to run the parallel decoding algorithm for constant time in each round. Combined with good code parameters, the resulting constant-time overhead of QEC and robustness to (possibly time-correlated) adversarial noise make quantum Tanner codes alluring from the perspective of quantum fault-tolerant protocols.

97 MATHEMATICS AND COMPUTING↗

Parallel implementation of an algorithm for Delaunay triangulation

This work concerns the theory and practice of implementing Tanemura's algorithm for 3D Delaunay triangulation on Intel's Gamma prototype, a 128 processor MIMD computer. Tanemura's algorithm does not vectorize to any significant degree and requires indirect addressing. Efficient implementation on a conventional, vector processing, supercomputer is problematic. Efficient implementation on a parallel architecture is possible, however. In this work, speeds in excess of 8 times a single processor Cray Y-mp are realized on 128 processors of the Intel Gamma prototype.

Merriam, Marshall L.↗

Improved algorithms for mapping pipelined and parallel computations

Recent work on the problem of mapping pipelined or parallel computations onto linear array, shared memory, and host-satellite systems is extended. It is shown how these problems can be solved even more efficiently when computation module execution times are bounded from below, intermodule communication times are bounded from above, and the processors satisfy certain homogeneity constraints. The improved algorithms have significantly lower time and space complexities than the more general algorithms: in one case, an O(nm3) time algorithm for mapping m modules onto n processors is replaced with an O(nm log m) time algorithm, and the space requirements are reduced from O(nm2) to O(m). Run-time complexity is reduced further with parallel mapping algorithms based on these improvements, which run on the architectures for which they create mappings.

Nicol, David M.↗

A computationally efficient parallel Levenberg-Marquardt algorithm for highly parameterized inverse model analyses

Inverse modeling seeks model parameters given a set of observations. However, for practical problems because the number of measurements is often large and the model parameters are also numerous, conventional methods for inverse modeling can be computationally expensive. We have developed a new, computationally-efficient parallel Levenberg-Marquardt method for solving inverse modeling problems with a highly parameterized model space. Levenberg-Marquardt methods require the solution of a linear system of equations which can be prohibitively expensive to compute for moderate to large-scale problems. Our novel method projects the original linear problem down to a Krylov subspace, such that the dimensionality of the problem can be significantly reduced. Furthermore, we store the Krylov subspace computed when using the first damping parameter and recycle the subspace for the subsequent damping parameters. The efficiency of our new inverse modeling algorithm is significantly improved using these computational techniques. We apply this new inverse modeling method to invert for random transmissivity fields in 2D and a random hydraulic conductivity field in 3D. Our algorithm is fast enough to solve for the distributed model parameters (transmissivity) in the model domain. The algorithm is coded in Julia and implemented in the MADS computational framework (http://mads.lanl.gov). By comparing with Levenberg-Marquardt methods using standard linear inversion techniques such as QR or SVD methods, our Levenberg-Marquardt method yields a speed-up ratio on the order of ~10 1 to ~10 2 in a multi-core computational environment. Furthermore, our new inverse modeling method is a powerful tool for characterizing subsurface heterogeneity for moderate- to large-scale problems.

97 MATHEMATICS AND COMPUTING↗

Performance Analysis of Speculative Parallel Adaptive Local Timestepping for Conservation Laws

Stable simulation of conservation laws, such as those used to model fluid dynamics and plasma physics applications, requires the satisfaction of the so-called Courant-Friedrichs-Lewy condition. By allowing regions of the mesh to advance with different timesteps that locally satisfy this stability constraint, significant work reduction can be attained when compared to a time integration scheme using a single timestep size. However, parallelizing this algorithm presents considerable difficulty. Since the stability condition depends on the state of the system, dependencies become dynamic and potentially non-local. In this article, we present an adaptive local timestepping algorithm using an optimistic (Timewarp-based) parallel discrete event simulation. We introduce waiting heuristics to limit misspeculation and a semi-static load balancing scheme to eliminate load imbalance as parts of the mesh require finer or coarser timesteps. Last, we outline an interface for separating the physics of the specific conservation law from the temporal integration allowing for productive adoption of our proposed algorithm. We present a misspeculation study for three conservation laws, demonstrating both the productivity of the local timestepping API, for which 74% of the lines of code are reused across different conservation laws, and the robustness of the waiting heuristics—at most 1.5% of element updates are rolled back. Our performance studies demonstrate up to a 2.8× speedup versus a baseline unoptimized local timestepping approach, a 4x improvement in per-node throughput compared to an MPI parallelization of synchronous timestepping, and scalability up to 3,072 cores on NERSC’s Cori Haswell partition.

97 MATHEMATICS AND COMPUTING↗

Parallel language constructs for tensor product computations on loosely coupled architectures

Distributed memory architectures offer high levels of performance and flexibility, but have proven awkard to program. Current languages for nonshared memory architectures provide a relatively low level programming environment, and are poorly suited to modular programming, and to the construction of libraries. A set of language primitives designed to allow the specification of parallel numerical algorithms at a higher level is described. Tensor product array computations are focused on along with a simple but important class of numerical algorithms. The problem of programming 1-D kernal routines is focused on first, such as parallel tridiagonal solvers, and then how such parallel kernels can be combined to form parallel tensor product algorithms is examined.

Mehrotra, Piyush↗

Parallel language constructs for tensor product computations on loosely coupled architectures

A set of language primitives designed to allow the specification of parallel numerical algorithms at a higher level is described. The authors focus on tensor product array computations, a simple but important class of numerical algorithms. They consider first the problem of programming one-dimensional kernel routines, such as parallel tridiagonal solvers, and then look at how such parallel kernels can be combined to form parallel tensor product algorithms.

Mehrotra, Piyush↗

Mesh-free data transfer algorithms for partitioned multiphysics problems: Conservation, accuracy, and parallelism

In this study we analyze and extend mesh-free algorithms for three-dimensional data transfer problems in partitioned multiphysics simulations. We first provide a direct comparison between a mesh-based weighted residual method using the common-refinement scheme and two mesh-free algorithms leveraging compactly supported radial basis functions: one using a spline interpolation and one using a moving least square reconstruction. Through the comparison we assess both the conservation and accuracy of the data transfer obtained from each of the methods. We do so for a varying set of geometries with and without curvature and sharp features and for functions with and without smoothness and with varying gradients. Our results show that the mesh-based and mesh-free algorithms are complementary with cases where each was demonstrated to perform better than the other. We then focus on the mesh-free methods by developing a set of algorithms to parallelize them based on sparse linear algebra techniques. This includes a discussion of fast parallel radius searching in point clouds and restructuring the interpolation algorithms to leverage data structures and linear algebra services designed for large distributed computing environments. The scalability of our new algorithms is demonstrated on a leadership class computing facility using a set of basic scaling studies. Finally, these scaling studies show that for problems with reasonable load balance, our new algorithms for both spline interpolation and moving least square reconstruction demonstrate both strong and weak scalability using more than 100,000 MPI processes with billions of degrees of freedom in the data transfer operation.

97 MATHEMATICS AND COMPUTING↗

The science of computing - Parallel computation

Although parallel computation architectures have been known for computers since the 1920s, it was only in the 1970s that microelectronic components technologies advanced to the point where it became feasible to incorporate multiple processors in one machine. Concommitantly, the development of algorithms for parallel processing also lagged due to hardware limitations. The speed of computing with solid-state chips is limited by gate switching delays. The physical limit implies that a 1 Gflop operational speed is the maximum for sequential processors. A computer recently introduced features a 'hypercube' architecture with 128 processors connected in networks at 5, 6 or 7 points per grid, depending on the design choice. Its computing speed rivals that of supercomputers, but at a fraction of the cost. The added speed with less hardware is due to parallel processing, which utilizes algorithms representing different parts of an equation that can be broken into simpler statements and processed simultaneously. Present, highly developed computer languages like FORTRAN, PASCAL, COBOL, etc., rely on sequential instructions. Thus, increased emphasis will now be directed at parallel processing algorithms to exploit the new architectures.

Denning, P. J.↗

Eigenvalue computation of large symmetric tridiagonal matrices on concurrent processors

Symmetric tridiagonal eigenvalue problems may arise indirectly in structural dynamic analysis. An algorithm for eigenvalue computation of large symmetric tridiagonal matrices on concurrent processors to meet the challenge of the new emerging computer hardware technology is presented. A standard bisection method in conjunction with Sylvester's Theorem is chosen to be converted into a parallel N-section algorithm. This parallel algorithm takes advantage of the multi-processor environment by carrying out N (number of processors) triangular factorizations of chosen shifted matrices in all processors concurrently and by minimizing communication between processors. The algorithm is designed for local-memory concurrent processors, i.e. message passing type processors. The efficiency and speed-up are given in terms of problem and machine parameters. The algorithm is very efficient when both the number of processors and the number of eigenvalues to be extracted are much smaller than the order of the tridiagonal matrix.

Chang, H. Y.↗

Reconstructing householder vectors from Tall-Skinny QR

The Tall-Skinny QR (TSQR) algorithm is more communication efficient than the standard Householder algorithm for QR decomposition of matrices with many more rows than columns. However, TSQR produces a different representation of the orthogonal factor and therefore requires more software development to support the new representation. Further, implicitly applying the orthogonal factor to the trailing matrix in the context of factoring a square matrix is more complicated and costly than with the Householder representation. We show how to perform TSQR and then reconstruct the Householder vector representation with the same asymptotic communication efficiency and little extra computational cost. We demonstrate the high performance and numerical stability of this algorithm both theoretically and empirically. The new Householder reconstruction algorithm allows us to design more efficient parallel QR algorithms, with significantly lower latency cost compared to Householder QR and lower bandwidth and latency costs compared with Communication-Avoiding QR (CAQR) algorithm. Experiments on supercomputers demonstrate the benefits of the communication cost improvements: in particular, our experiments show substantial improvements over tuned library implementations for tall-and-skinny matrices. Furthermore, we also provide algorithmic improvements to the Householder QR and CAQR algorithms, and we investigate several alternatives to the Householder reconstruction algorithm that sacrifice guarantees on numerical stability in some cases in order to obtain higher performance.

97 MATHEMATICS AND COMPUTING↗

Algorithm for solving the linear Cauchy problem for large systems of ordinary differential equations with the use of parallel computations

An algorithm for solving the linear Cauchy problem for large systems of ordinary differential equations is presented. The algorithm for systems of first-order differential equations is implemented in the EDELWEISS code with the possibility of parallel computations on supercomputers employing the MPI (Message Passing Interface) standard for the data exchange between parallel processes. The solution is represented by a series of orthogonal polynomials on the interval [0, 1]. The algorithm is characterized by simplicity and the possibility to solve nonlinear problems with a correction of the operator in accordance with the solution obtained in the previous iterative process.

74 ATOMIC AND MOLECULAR PHYSICS↗

Dynamic Load Balancing Based on Constrained K-D Tree Decomposition for Parallel Particle Tracing

Particle tracing is a fundamental technique in flow field data visualization. In this work, we present a novel dynamic load balancing method for parallel particle tracing. Specifically, we employ a constrained k-d tree decomposition approach to dynamically redistribute tasks among processes. Each process is initially assigned a regularly partitioned block along with duplicated ghost layer under the memory limit. During particle tracing, the k-d tree decomposition is dynamically performed by constraining the cutting planes in the overlap range of duplicated data. This ensures that each process is reassigned particles as even as possible, and on the other hand the new assigned particles for a process always locate in its block. Result shows good load balance and high efficiency of our method.

Zhang, Jiang↗

Application of NEM-based Pin-by-Pin HCMFD Algorithm to 3-D Core Analysis

A pin-wise reactor analysis is expected to provide a more accurate solution than the conventional nodal methods. However, a pin-wise approach is still computationally very costly though the computational performances have been enormously improved for decades. To overcome such limitation of a pin-by-pin core analysis, the HCMFD (Hybrid Course-Mesh Finite Difference) algorithm has been recently introduced. By adopting the HCMFD algorithm, a parallel computing can be applied very effectively. In the HCMFD algorithm, an iterative local-global strategy is adopted with a combination of two CMFD acceleration methods for the pin-wise core analysis. The global eigenvalue problem is solved by one-node CMFD, while the local fixed-source problems are solved by two-node CMFD based on the NEM (nodal expansion method). In the HCMFD computational scheme, a parallel computing can effectively be applied since most of the computational efforts are consumed to solve the local problems, and they can be solved in parallel. Previously, only a 2-D HCMFD algorithm was developed and its numerical efficiency was evaluated. In this paper, a 3D HCMFD scheme is introduced and some 3-D problems were analyzed to verify its applicability to 3D pin-wise core analysis. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗