18-742 Research in Parallel Computer Architecture, Fall 2014

• List of Project ideaspdf (require login with andrewid)
• Talk with the course staff if you'd like to propose your own project idea.
• LaTeX template
• Project Statement
• Literature Survey due: 9/23/2014
• Project Proposal due: 10/3/2014
• Milestone 1 due: 10/29/2014
• Milestone 2 due: 11/17/2014
• Final report due: 12/8/2014
• Detailed requirements are in the project statement document above.

When Due on Monday, Dec 15, 2014

When: Friday, December 12, 2014 @ 1:30-4:00pm

Where: CIC 4th floor, Panthor Hollow room

Presentation Guidelines: The plan is to have 20-minute talks + 5-minute Q&A for each group, and then an open-ended poster session with cookies, etc. Please polish your talks, just like top conference (e.g., ISCA, MICRO, ASPLOS, HPCA) talks should be. We will have attendees from outside the class who can ask you questions.

We will provide easels, poster boards and pushpins. Light food/beverages will also be provided.

Printing: You'll be individually responsible for printing your poster. The default recommendation is the Fedex Kinko's in the UC. The recommended size is 32x40in. 24x30in is minimum size. Please be aware that printing takes time, so we recommend you submit it for printing at least 24hrs in advance.

example poster 1 pdf, example poster 1 ppt example poster 2 pdf, example poster 2 ppt

more example posters

• Format: 20-min presentation + 10-min Q&A. Please practice for this length.
• Submission: You must send your slides to us by Oct 29. Everyone should be ready to present on Oct 30.
• Goal for milestone presentation: The presentation should be clear and well done. It should state the goals, key ideas, what is accomplished and what remains (see details below).

• The problem you are solving + your goal
• How is this different from past work? What is your novelty?
• Your solution ideas + strengths and weaknesses
• Your methodology to test your ideas
• Concrete mechanisms you have implemented so far
• Concrete results you have so far
• What will you do next?
• What hypotheses you have for future?
• How close were you to your target?
• Make a lot of progress and find breakthroughs

• Example 1
• Example 2
• Example 3

Step 1: Decide your project direction based on your interest.
Step 2: Pick 3 research papers broadly related to your project.
Step 3: Prepare a 30-min presentation on the 3 selected papers - 30 talk, 30 minute Q&A
Step 4: Deliver the presentation in class, Sept. 23-25.

• Understand the solution space and tradeoffs
• Analyze and synthesize three papers
• Explain how they relate to your project, how they can enhance it, or why your potential solution will be better
• Read the papers very carefully
• Attention to detail is important

• The problem: What is the general problem targeted by the papers and what are the specific problems?
• The solutions: What are the key ideas and solution approaches of the proposed papers?
• Key results and insights: What are the key results, insights, and conclusions of the papers?
• Tradeoffs and analyses: How do the solutions differ or interact with each other? Can they be combined? What are the tradeoffs between them? This is where you will need to analyze the approaches and find a way to synthesize a common framework to describe and qualitatively compare & contrast the approaches.
• Comparison to your project: How do these approaches relate to your project? Why is your potential approach novel, different, better, or complementary?
• Key conclusions and new ideas: What have you learned? Do you have new ideas/approaches based on what you have learned?

Watch the recorded recitation session on 9/13 in the ECE Learning Environment for an overview of computer architecture simulation.

• Pin dynamic binary instrumentation tool
• Multi2Sim
• SAFARI group simulators (contact course staff)

• Marsx86
• SESC
• Gem5
• Sniper
• GPGPU-sim