Sample group project topics

From Fall 2010

A Study on Memory and Compute Bound Kernels on CPU and GPU Hardware (large team)

Online Auto-Tuning of Collective Communication Operations in MPI

Automatic Pool Parallelization for Recursive Data Structures

Study of Floating point cancellation error

Fault Injection and Tolerance Study

Parallelization and K-Means Extension of a Target-Defeat Monte Carlo Algorithm

Simulating MapReduce Scheduling

From Spring 2010

CUDA for Communication Systems

Parallel Computation of Eigenvector Centrality for Large Networks

PyCuda: Tuning GPU Compute Kernels

Parallell Web Crawler Performance

Program Cache Memory Characterization

HPC for NodeXL

Programmability and Performance Testing using Chapel

Comparison betwen Manycore GPU and MultiCore CPU on posting list compression

Automatically Synthesizing MPI Programs

Parallel Simulation of Information Diffusion on Large Social Network Graphs

Lightweight Analysis of Shared-Memory Programs on Linux

Other suggestions

Application performance studies across one or more parallel machines - e.g. satellite data processing, parallel search, computer vision algorithms, bioinformatics

Application performance studies on GPUs (1 or more machines)

Reproduce a paper results
E.g., scheduling papers (simulation of scheduler algorithms)

Debunking paper

Or one of your own design