Download The IC Wall Collaboration between Computer science + Physics

Summary
• Background
– Why do we need parallel processing? Applications
• Introduction in algorithms and applications
– Methodology to develop efficient parallel (distributed-memory) algorithms
– Understand various forms of overhead (communication, load imbalance,
search overhead, synchronization) and various distributions (blockwise,
cyclic)
– Understand correctness problems (e.g. message ordering)
Summary
•
Parallel machines and architectures
– Processor organizations, topologies, criteria
– Types of parallel machines
• arrays/vectors, shared-memory, distributed memory
– Routing
– Flynn’s taxonomy
– What are cluster computers?
– What networks do real machines (like the Blue Gene) use?
– Speedup, efficiency (+ their implications), Amdahl’s law
Summary
•
Programming methods, languages, and environments
– Different forms of message passing
• naming, explicit/implicit receive, synchronous/asynchronous sending
– Select statement
– SR primitives (not syntax)
– Master/worker model, search overhead (TSP)
– MPI: message passing primitives, collective communication
– Java parallel programming model and primitives
– HPF: problems with automatic parallelization; division of work between
programmer and HPF compiler; alignment/distribution primitives;
performance implications
Summary
• Applications
– N-body problems: load balancing and communication (locality)
optimizations, costzones, performance comparison
– Search algorithm (TDS): use asynchronous communication + clever
(transposition-driven) scheduling
– Bioinformatics (repeats detection): combine many forms of parallelism
•
Grid computing
–
–
–
–
What are grids? Why do we need them?
Application-level tools for grid programming and execution
Why is parallel computing on grids feasible?
Ibis: goals, applications, design, programming vs. deployment,
communication primitives, divide&conquer parallelism, performance
behavior on a grid
Summary
• Multimedia content analysis on Grids
– What is Multimedia Content Analysis (MMCA) ? Imaging applications,
feature vectors, low-level patterns
– Why parallel computing in MMCA - and how? Need for speed and
transparency
– Software Platform: Parallel-Horus. Task/data parallelism, Separable
Recursive Filtering, Lazy Parallelization
– Example – Parallel Image Processing on Clusters
– Grids and their specific problems. Promise and problems of the grid
– Towards a Software Platform for MMCA on Grids. Problems with widearea servers
– Large-scale MMCA applications on Grids (TRECVID, object recognition)