ACM/CS 114

Parallel Algorithms for Scientific Applications

prerequisites: ACM11, ACM106 or equivalent

Introduction to parallel program design for numerically intensive scientific applications. Parallel programming methods; distributed-memory model with message passing using the message passing interface; shared-memory model with threads using OpenMP, CUDA; object-based models using a problem-solving environment with parallel objects. Parallel numerical algorithms: numerical methods for linear algebraic systems, such as LU decomposition, QR method, CG solvers; parallel implementations of numerical methods for PDEs, including finite-difference, finite-element; particle-based simulations. Performance measurement, scaling and parallel efficiency, load balancing strategies.

Latest news

◊ 
mga
:
2012.01.27
posted the 2012.01.27 lecture notes
◊ 
mga
:
2012.01.25
posted the 2012.01.25 lecture notes
◊ 
mga
:
2012.01.23
posted the 2012.01.23 lecture notes
◊ 
mga
:
2012.01.23
posted the assignment due on 2012.02.01
◊ 
mga
:
2012.01.20
posted the 2012.01.20 lecture notes
◊ 
mga
:
2012.01.13
posted the 2012.01.13 lecture notes
◊ 
mga
:
2012.01.12
posted the 2012.01.11 lecture notes
◊ 
mga
:
2012.01.09
posted the 2012.01.09 lecture notes
◊ 
mga
:
2012.01.06
posted the assignment due on 2012.01.20
◊ 
mga
:
2012.01.06
posted the 2012.01.06 lecture notes
◊ 
mga
:
2012.01.04
posted the 2012.01.04 lecture notes
◊ 
mga
:
2012.01.01
class web site for Winter 2012 is now up
Last update: 20 January 2012