Fakultät für Informatik der Technischen Universität München Informatik X: Rechnertechnik und Rechnerorganisation / Parallelrechnerarchitektur Prof. Dr. Arndt Bode , Prof. Dr. Hans Michael Gerndt

Home  | Adressen  | Personen  | Forschung  | Lehrveranstaltungen

Suche

Time/Lecture,Place:	Wednesday 8:30-10:00, S2221 (South Building)
Time/Exercise,Place:	Wednesday 16:00-16:45, A009 (Augustenstrasse)
Audience:	Students in Informatik (Diplom) and Computational Science and Engineering (Master of Science)

Contents

1. Design Principles for Parallel Algorithms
   1. Divide et Impera
   2. Recursive Doubling
   3. Restructuring

2. Algorithms for SIMD-Arrays
   1. Summation for Different Topologies
   2. Matrix-Transpose
   3. Matrix-Multiplication
   4. Masively Parallel Poisson Solvers

3. Algorithms for a SIMD System with the Associative Memory
   1. Triangular Systems of Linear Equations
   2. Gauss-Jordan Method
   3. CORDIC-Technique for Elementary Functions
   4. Fast Fourier Transform
   5. Histogram Evaluation

4. Hypercube Algorithms
   1. Matrix Multiplication
   2. Linear Systems with Band Matrices
   3. Singular Value Decomposition
   4. Bitonic Sorting

5. VLSI Algorithms
   1. Complexity Model
   2. Cyclic Odd-Even Technique
   3. Capacitance-Matrix Method
   4. Scalable Designs

Back: Mikroprozessoren

Up

Next: Parallel Programming