• Skip navigation
  • Skip to navigation
  • Skip to the bottom
Simulate organization breadcrumb open Simulate organization breadcrumb close
Department of Mathematics
  • FAUTo the central FAU website
Suche öffnen
  • de
  • UnivIS
  • StudOn
  • campo
  • CRIS
  • emergency help

Department of Mathematics

Navigation Navigation close
  • Department
    • Chairs and Professorships
    • Boards and Commissions
    • Organisation
    • Development Association
    • System Administration
    • Contact and Directions
    • Actual
    Portal Department of Mathematics
  • Research
    • Research Projects
    • Publications
    • Preprint Series Applied Mathematics
    Portal Research
  • Study
  • Events
  • Colloquium
  1. Home
  2. Applied Mathematics 3
  3. Research
  4. Projects
  5. Interactive High-Performance Computing

Interactive High-Performance Computing

In page navigation: Applied Mathematics 3
  • Members
  • Research
    • Projects
      • Modern approaches to solving the Full-Stokes problem in the context of ice sheet modeling
      • Convective heat transport in nanofluids
      • Besov regularity of parabolic partial differential equations on Lipschitz domains
      • Cooling of a battery module
      • A discontinuous Galerkin method for the subjective surfaces problem
      • Interactive High-Performance Computing
      • Non-newtonian two-phase flow
      • Temporal Multiscale Methods for an Atherosclerosis Model
      • A priori and a posteriori error estimates for time-dependent problems
      • Optimization of Airlay Processes
      • Marangoni convection
      • Solid-liquid phase transitions with a free melt surface
      • Higher order time discretization for free surface flows
      • Fluids in rocket tanks
      • Particulate flows in industrial applications
    • Publications
  • Teaching
  • Guests

Interactive High-Performance Computing

Interactive high-performance computing (HPC)

Participants

AM 3

  • Nicolas Neuß

LS 10 (Informatik)

  • Marco Heisig

Description

Relevant problems for high-performance computing are large-scale industrial problems, problems posed in high-dimensional spaces, high-precision calculations, large parameter studies and optimization problems or a combination of all those. Often these problems arise in domains which are not yet well-known, such that an exploratory approach becomes necessary for treating them effectively.

The standard HPC approach, which consists of using highly effective, but problem- and hardware-specific statically compiled software in a batch environment is ill-suited under these circumstances. Therefore we propose a new approach which embodies interactivity from the bottom up by using the interactive language Common Lisp which can compile to fast machine code on-the-fly.

On top of Common Lisp we have implemented the free software framework Femlisp for solving partial differential equation. A parallel object-oriented layer DDO/CL-MPI shields the Femlisp user/programmer from the underlying parallel machine.

We have tested this setup for computing a homogenized coefficient for a 3D elasticity problem. The first image below shows some displacement vector field for a representative cell subjected to a certain stress situation. The second image shows a graph of the parallel speedup for this calculation on a Linux cluster.

Distortion of a representative cell under a given stress Speedup graphs

Friedrich-Alexander-Universität
Department of Mathematics

Cauerstraße 11
91058 Erlangen
  • Contact and Directions
  • Internal Pages
  • Staff members A-Z
  • Imprint
  • Privacy
  • EN/DE
  • RSS Feed
Up