Project

Proposal Due Date: Thursday, March 19th (11:59pm PST)

Project Final Report Due Date: Wednesday, May 13th (11:59pm PST)

General Information

• Proposal accounts for 4% of the grade. Proposal pages limit: 2 pages.
• You must include answers to the following questions. Please use them as sections in your document.
  • State the hypothesis of your project. What is the question that you are seeking to explore, understand, and to some extent answer? What might be the results of this investigation?
  • Context. Will you be working with others on this? Is it a subproject in the context of a larger research effort? Are variants of it going to be utilized in other classes?
  • Key prior work. What are a few (~3) pieces of prior work that this builds upon, is motivated by, to be contrasted with?
  • Empirical methodology. What will be done to investigate this question and establish the results? What resources will be needed for that?
  • Challenges and Obstacles. What do you anticipate might present a problem that will prevent you from pursuing this investigation as fully as you would like?
• Poster sessions are scheduled for April 28th, 11am-2pm and April 30th, 11am-12:30pm. It will be at the Wozniak Lounge (430-438 Soda). You will be assigned a session after proposals are evaluated. There will be three sessions: (1) April 30, 11am-12:30pm, (2) April 30, 12:30-2pm, and (3) May 2nd, 11am-12:30pm.
• Project final report length limit: 10 pages, single-column standard latex. Due date May 13. This is a strict deadline as we need to finish grading by the final grades due date. Final project and poster presentation account for 40% of the the grade. Pre-proposal accounted for 1% of grade.
• Group size: max 3 people (no major/grad/undergrad group restrictions).
• You are encouraged to discuss your preliminary project ideas with instructors. Just request an appointment.

Grading

Below are components that will make up your project grade and the first two components are the most important:

1. Practical content/creativity; implementation/tuning effort.
2. Experimental data: scaling/performance analysis/interesting inputs or outputs.
3. Theoretic content/creativity; design/analysis of algorithms.
4. Impact: difficulty and timeliness of the contribution.

We understand that not all projects will have all four components but it is expected that the first two components will be present in all projects. As such, we expect the majority of your final report to be about parallelism, and not the problem description.

Here are videos of oral presentations from previous years:

• Brief oral poster presentations from CS267 in Spring 2019
• Brief oral poster presentations from CS267 in Spring 2016
• Brief oral poster presentations from CS267 in Spring 2015
• Brief oral poster presentations from CS267 in Spring 2014
• Brief oral poster presentations from CS267 in Spring 2013
• Brief oral poster presentations from CS267 in Spring 2012

Submission

Berkeley students please submit a PDF file (only PDF will be accepted) at which the GSIs can retrieve your work to bCourses.

Some Project Ideas for Spring 2020

You are welcome and encouraged to have your own project ideas. This is especially true if you want to bring parallelism to your ongoing research projects. In addition, we (as the CS267 team) have a few potential ideas below:

• Graph partitioning for diBELLA. Contact supervisors: Aydin Buluç, Marquita Ellis, Giulia Guidi.
• Branch and bound using UPC++. Contact supervisors: Aydin Buluç.
  • Implement a simple branch and bound code using UPC++’s RDMA features and/or RPC features. Use this to solve phylogenetic tree construction.
• MetaHipMer performance analysis. Contact supervisors: Kathy Yelick.
• Productivity and Performance Apache Spark on HPC Architectures for Bioinformatics. Contact supervisors: Marquita Ellis, Giulia Guidi, Aydin Buluç, Kathy Yelick.
• Profile HMM on the GPU. Contact supervisors: Aydin Buluç, Israt Nisa.
  • Can you beat HHMer3’s HMM search functionality using GPUs?
• Network Communication Reordering. Contact supervisors: Costin Iancu, Ed Younis.
  • Can you reorder communication to increase overall performance with domain-specific knowledge? It is well-known to work, but doing so with only local knowledge in a generalizable way is a challenge.
• Quantum Computing. Contact supervisors: Costin Iancu, Ed Younis.
  • Different quantum computing project ideas are available. Contact Ed Younis, if you are interested.
• Implement work stealing in BCL and/or UPC++. Contact supervisors: Kathy Yelick, Ben Brock.
  • Implement a (probably randomize) load balancing distributed queue data structure.
• Implement a genome binning data structure for metagenomics. Contact supervisors: Kathy Yelick, Rob Egan.