15-740/18-740 Fall '09
Class Projects

Here are the class projects for 2009 (in no particular order):

Parallelizing Challenging Applications:

• Parallelizable privacy preserving mechanisms. Aaron Roth and Kanat Tangwongsan.
• Parallelizing the AES encryption algorithm. Jonathan Coens, Zongweiz Zhou, and Yanlin Li.
• Parallelizing graphical models for machine learning. Bin Fu.
• A parallel implementation of a sparse singular value decomposition solver. Kevin Waugh.
• GPU acceleration of parallel Joulesort. Kai Ren and Lawrence Tan.

Optimizing Transactional Memory:

• Using static program analysis to improve transactional memories. Alex Grubb and Jiri Simsa.
• Game theory and software transactional memory. Sam Ganzfried and Abe Othman.
• Contention management for transactional memory. Anvesh Komuravelli, Samir Sapra, and Jenn Tam.

Improving Memory Hierarchy Performance:

• Improving memory accesses through data prefetching. B. Aditya Prakash and Ali Kemal Sinop.
• Measuring and improving cache performance of lazy functional programs. Arbob Ahmad and Henry DeYoung.
• Evaluating a parallel real-time garbage collector on modern hardware. Ivan Jager and Chris Martens.

Asymmetric Chip Multiprocessors:

• Performance evaluation of multimedia applications on asymmetric chip multiprocessors. Chintan Parikh, Aniket Ponkshe, and Arvind Gopalakrishnan.
• Optimizing performance on asymmetric chip multiprocessors using online learning. Dafna Shahaf and Or Sheffet.

Measuring and Tuning Performance:

• Virtual application profiler. Sven Stork and Anthony Gitter.
• Using random sampling to auto-tune OpenMP parallel applications Field Cady and Aapo Kyrola.

Scheduling and Migrating Resources on Parallel Machines:

• Thread schedulers for chip multiprocessors. Ravishankar Krishnaswamy and Harsha vardhan Simhadri.
• Inflexion: A framework for distributing threads between the CPU and GPU. Rakesh Iyer and Tarun Goyal.
• Investigating the relationship between on-chip network scheduling and application-level performance. Yoshihisa Abe, Gunhee Kim, and Hyeontaek Lim.
• Exploiting thread motion on a chip multiprocessor with private L1 caches. Athula Balachandran and Lavanya Subramanian.
• BUMP: Balancing usage with migration of pages. Chris Fallin and Chris Craik.

Hardware Accelerators:

• Hardware support for storing metadata. Vivek Seshadri and Kaushik Lakshminarayanan.
• Acceleration of Bloom Filters with FPGAs. Ryan Sakauye and David Lewis.

Back to CS740 home page.