Louis H. Ziantz

Rensselaer Polytechnic Institute, New York City, NY, United States

Are you Louis H. Ziantz?

Claim your profile

Publications (16)0 Total impact

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Functional languages attract the attention of developers of parallelizing compilers because of the implicit parallelism of functional programs and the simplified data dependence analysis of functional statements. A major drawback of functional languages is that naive translation of functional programs results in code that requires excessive memory. In this paper we explore the connection between the memory optimization and communication optimization of parallel codes generated from functional languages. We also show how a functional language can be used as an intermediate form in the translation from FORTRAN to customized, architecture-specific parallel code.
    12/2002;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Sparse matrix-vector multiplication forms the heart of iterative linear solvers used widely in scientific computations (e.g., finite element methods). In such solvers, the matrix-vector product is computed repeatedly, often thousands of times, with updated values of the vector until convergence is achieved. In an SIMD architecture, each processor has to fetch the updated off-processor vector elements while computing its share of the product. In this paper, we report on run-time optimization of array distribution and offprocessor data fetching to reduce both the communication and computation time. The optimization is applied to a sparse matrix stored in a compressed sparse row-wise format. Actual runs on test matrices produced up to a 35 percent relative improvement over a block distribution with a naive multiplication algorithm while simulations over a wider range of processors indicate that up to a 60 percent improvement may be possible in some cases.
    12/2002;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper describes two predictive load balancing schemes designed for use with parallel adaptive finite element methods. We also provide an overview of data structures suitable for distributed storage of finite element mesh data as well as software designed for mesh adaptation and load balancing. During the course of a parallel computation, processor load irabalances are introduced at adaptive enrichment steps. The predictive load balancing methods introduced here use a priori estimates of work load for adaptive refinement and subsequent computation to improve enrichment ciency and reduce total balancing time. These components have been used to build a system for solving compressible flow problems. Computational results on an IBM SP2 computer are presented for transient solutions of the three-dimensional Euler equations of compressible flow.
    12/2002;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: An adaptive technique for a partial differential system automatically adjusts a computational mesh or varies the order of a numerical procedure to obtain a solution satisfying prescribed accuracy criteria in an optimal fashion. We describe data structures for distributed storage of finite element mesh data as well as software for mesh adaptation, load balancing, and solving compressible flow problems. Processor load imbalances are introduced at adaptive enrichment steps during the course of a parallel computation. To correct this, we have developed three dynamic load balancing procedures based, respectively, on load imbalance trees, moment of inertia, and octree traversal. Computational results on an IBM SP2 computer are presented for steady and transient solutions of the three-dimensional Euler equations of compressible flow.
    Applied Numerical Mathematics. 01/1998;
  • [Show abstract] [Hide abstract]
    ABSTRACT: We examine the quality of partitions produced by an iterative load balancer in parallel adaptive finite element calculations. We present several metrics which we use to evaluate the quality of a mesh partitioning, and report statistics generated from our analysis of adaptively refined meshes produced during the solution of computational fluid dynamics problems. Timings from the finite element solution phase for runs involving these meshes on 16 and 32 processors of an IBM SP2 are also presented. 1 INTRODUCTION Adaptive finite element methods (FEMs) have gained importance based on their ability to offer reliable solutions to partial differential equations. In such an analysis, the computational domain is first discretized to create a mesh. During the solution process, portions of this mesh are recursively refined or coarsened (h-refinement) and/or the finite element approximation is varied in order (p-refinement) to improve the convergence rate and concentrate the computational effort ...
    05/1997;
  • Source
    Louis H. Ziantz, Can C, Boleslaw K. Szymanski
    [Show abstract] [Hide abstract]
    ABSTRACT: . Sparse matrix-vector multiplication forms the heart of iterative linear solvers used widely in scientific computations (e.g., finite element methods). In such solvers, the matrix-vector product is computed repeatedly, often thousands of times, with updated values of the vector until convergence is achieved. In an SIMD architecture, each processor has to fetch the updated off-processor vector elements while computing its share of the product. In this paper, we report on run-time optimization of array distribution and offprocessor data fetching to reduce both the communication and computation time. The optimization is applied to a sparse matrix stored in a compressed sparse row-wise format. Actual runs on test matrices produced up to a 35 percent relative improvement over a block distribution with a naive multiplication algorithm while simulations over a wider range of processors indicate that up to a 60 percent improvement may be possible in some cases. 1 Introduction Sparse matrix o...
    03/1997;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We examine the quality of partitions produced by an iterative load balancer in parallel adaptive finite element calculations. We present several metrics which we use to evaluate the quality of a mesh partitioning, and report statistics generated from our analysis of adaptively refined meshes produced during the solution of computational fluid dynamics problems. Timings from the finite element solution phase for runs involving these meshes on 16 and 32 processors of an IBM SP2 are also presented. 1 INTRODUCTION Adaptive finite element methods (FEMs) have gained importance based on their ability to offer reliable solutions to partial differential equations. In such an analysis, the computational domain is first discretized to create a mesh. During the solution process, portions of this mesh are recursively refined or coarsened (h-refinement) and/or the finite element approximation is varied in order (p-refinement) to improve the convergence rate and concentrate the computational effort...
    02/1997;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Conservation laws are solved by a local Galerkin finite element procedure with adaptive space-time mesh refinement and explicit time integration. The Courant stability condition is used to select smaller time steps on smaller elements of the mesh, thereby greatly increasing efficiency relative to methods having a single global time step. Processor load imbalances, introduced at adaptive enrichment steps, are corrected by using traversals of an octree representing a spatial decomposition of the domain. To accommodate the variable time steps, octree partitioning is extended to use weights derived from element size. Partition boundary smoothing reduces the communications volume of partitioning procedures for a modest cost. Computational results comparing parallel octree and inertial partitioning procedures are presented for the three-dimensional Euler equations of compressible flow solved on an IBM SP2 computer.
    Journal of Parallel and Distributed Computing. 01/1997;
  • 01/1997
  • Source
    Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA 1997, June 30 - July 3, 1997, Las Vegas, Nevada, USA; 01/1997
  • [Show abstract] [Hide abstract]
    ABSTRACT: Functional languages attract the attention of developers of parallelizing compilers because of the implicit parallelism of functional programs and the simplified data dependence analysis of functional statements. A major drawback of functional languages is that naive translation of functional programs results in code that requires excessive memory. In this paper we explore the connection between the memory optimization and communication optimization of parallel codes generated from functional languages. We also show how a functional language can be used as an intermediate form in the translation from FORTRAN to customized, architecture-specific parallel code. 1 INTRODUCTION FORTRAN is a common language used in engineering and scientific computing. Recent versions of the language (e.g., Fortran90 and High Performance Fortran) allow programmers to embed special directives for running their programs in parallel. However, many currently used programs are written in older dialects of FORTR...
    08/1996;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Various research applications using the adaptive solution of partial differential equations and parallel discrete event simulation as well as the investigation of object oriented programming paradigms are described. This work utilizes the IBM SP2 at Rensselaer's Scientific Computation Research Center (SCOREC). The software is designed using C, C++ and Fortran 90, together with MPI. Tools described include a parallel mesh database, load balancers and run-time code optimizers. Additionally, using plasma codes as an example, we compare compilers and architecture performance of the SP2 to competing distributed memory parallel machines. Applications studying finite element analysis of problems in biomechanics and fluid dynamics, the simulation of fusion plasma processes and the spread of Lyme disease are presented. 1 Adaptive Finite Element Methods The finite element method (FEM) has become a standard engineering analysis tool for solving partial differential equations (PDEs). Ad...
    07/1996;
  • Source
    PARLE '94: Parallel Architectures and Languages Europe, 6th International PARLE Conference, Athens, Greece, July 4-8, 1994, Proceedings; 01/1994
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: this paper, we have focused on describing and comparing several load balancing schemes. Comparisons by timing are difficult, since times vary between runs having the same parameters. The high-speed switch of the IBM SP2 computer is a shared resource that affects run times. More subtle effects can result from differences in the order in which messages used for migration are processed. Changes in the order in which those messages are received and integrated into the local MDB result in different traversal orders of the mesh entities. These differences cause small changes in load balancings and coarsenings. While such differences in meshes and partitionings do not affect the solution accuracy, they can cause sufficient changes in efficiency to make precise timings difficult. Qualitatively, PSIRB produced the best partitions (measured as a function of total analysis time). Octree-generated partitions were comparable but resulted in slightly longer solution times. In both cases, one or two iterations of partition boundary smoothing led to a quality improvement. ITB by itself resulted in poorer partition quality, but is useful when mesh changes are small between computational stages. Predictive enrichment provided su21 perior performance to our current enrichment process with transient problems where there are frequent enrichment and balancing steps.
    02/1970;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The paper describes predictive load balancing schemes designed for use with parallel adaptive finite element methods. We provide an overview of data structures suitable for distributed storage of finite element mesh data as well as software designed for mesh adaptation and load balancing. During the course of a parallel computation, processor load imbalances are introduced at adaptive enrichment steps. The predictive load balancing methods described here use a priori estimates of work load for adaptive refinement and subsequent computation to improve enrichment efficiency and reduce total balancing time. An analysis code developed with these components for solving compressible flow problems is used to obtain predictive load balancing results on an IBM SP2 computer. Our test problem involves the transient solution of the three dimensional Euler equations of compressible flow inside a perforated shock tube. We also present a message passing library extension in development which allows for automated packing of messages to improve communication efficiency.
    Chilean Computer Science Society, International Conference of the. 02/1970;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Conservation laws are solved by a local Galerkin finite element procedure with adaptive space-time mesh refinement and explicit time integration. A distributed octree structure representing a spatial decomposition of the domain is used for mesh generation, and later may be used to correct for processor load imbalances introduced at adaptive enrichment steps. A Courant stability condition is used to select smaller time steps on smaller elements of the mesh, thereby greatly increasing efficiency relative to methods having a single global time step. To accommodate the variable time steps, octree partitioning is extended to use weights derived from element size. Computational results are presented for the three-dimensional Euler equations of compressible flow solved on an IBM SP2 computer. The problem examined is the flow inside a perforated shock tube. 1 Introduction Adaptive finite element methods that automatically refine or coarsen meshes (h-refinement) and/or vary the ...
    02/1970;

Publication Stats

215 Citations

Top Journals

Institutions

  • 1970–1998
    • Rensselaer Polytechnic Institute
      • Department of Computer Science
      New York City, NY, United States