Project descriptions for ECS201B

Proposal due: Friday, February 3rd
Status Report due: Friday, February 24th
Final Report due: Friday, March 17th

Intro/Overview

Your assignment is to pick some topic that you find interesting and do some original research on that subject. Since you have already had 201A, your goal should be to produce a publishable piece of work. You can work in small groups, if you wish, or by yourself. in a group of 2 or 3 students. The paper should be similar in style to the conference papers that we will read in class. These projects will be graded on roughly 4 different things:

How well the problem is defined and motivated
How extensive the survey of previous work is
The experimental technique used
The quality of the presentation of the results

Alternatively, you may write a survey paper of an area within computer architecture. These papers should contain:

A summary of previous work in an area, including extensive references
A presentation of opinions of other authors both for and against various options (again, with references)
A conclusion containing your opinion of the strengths and weaknesses of the arguments presented above

Since a survey paper is less risky than a reseach project, the survey papers will be expected to meet a higher standard (both of of completeness and analysis of the literature.)

As noted above, there are three milestones associated with this task: The Proposal, the Status Report, and the Final Report.

Milestone 1 - The Proposal

Proposals should be 1 to 2 pages long and should include:

A description of the topic
A statement of why the topic is interesting or important
A description of the methods to be used for evaluating the proposed idea (for projects with original research)
References to at least 3 relevant papers you have obtained and read. The course text and readings cite many papers. Some other important venues for publishing relevant work on Architecture:

Proceedings of the International Symposium on Computer Architecture (ISCA)
Proceedings of the Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)
Proceedings of the International Symposium on Microarchitecture (MICRO)
Proceedings of the High Performance Computer Architecture Symposium (HPCA)
International Journal of Parallel Processing
ACM Transactions on Computer Systems
IEEE Transactions on Computers
IEEE Computer Magazine
IEEE Micro
Microprocessor Report

The proposal *deadline* is given above; however, proposals turned in earlier than the deadline will get feedback sooner. (Remember - up to means less than!)

Milestone 2 - The Status Report

In order to help ensure work on the projects is moving forward in a timely fashion, a 1 to 2 page status report is due midway between the proposal submission and Final Report due dates. This report should clearly describe the progress you are making, so that I can provide some feedback on how you are doing and suggest any mid-course corrections that might be advisable. The status report will not be graded, but should be viewed as an important part of the project.

Milestone 3 - The Final Report

As stated above, your Final Report should be similar in style to a conference paper - an abstract, body, and optional appendices. The abstract should summarize the contributions of the report in one or two paragraphs, while the length of the body should be limited to approximately 5000 words (15-20 pages of double-spaced 10-point text). If you need more space, you can put additional supporting material in appendices.

Project Talks

20-30 minute presentations of your results may replace the in-class final. These talks will be scheduled during finals week, with the in-class finals time being the latest possible available time. This should be viewed as an opportunity to practice your presentation skills - the ability to convey your ideas and results to your peers is critically important in our communication age, and a central part of the research process that should be of interest to those pursuing a Ph.D.

(editor's note - I haven't decided if we will do this for sure or not. A lot will depend on how the class progresses during the quarter.)

Possible Research Topics

Ideally, you should come up with your own topic, one that you find particularly interesting and related to your own interests. For example, if you have an interest in compilers, then code scheduling for instruction level parallelism might be a good topic. If you are more interested in Operating Systems, then the design of a processor to support the OS might be more to your liking. To help you along a list of example projects follows. Keep in mind that this is not an exhaustive list of all possible projects. In addition, if you find one potentially interesting, I would be more than happy to sit down with you and discuss it in more detail.

Compare and contrast different approaches to exploiting instruction level parallelism methods - for example, decoupled vs. VLIW, vectors vs. superscalar, VLIW vs. superscalar, decoupled vs. superscalar, etc.
Study modifications to the decoupled architecture approach that might help provide prefetch capabilities and/or enable it to do limited speculative execution
Evaluate the maximum amount of parallelism available in a representative set of benchmark programs.
Study in detail various memory system enhancements, including victim caches, stream buffers, etc.
It has been suggested that using virtual-mapped caches may actually improve performance in a number of ways. How could this be?
Look at ways to increase the effective bandwidth between processor and external memory.
Extend the current research that has been done on new ways to manage a cache (evaluate and improve the effectiveness of C/NA, for example)
Write a program that takes binaries created for one architecture and produces binaries executable on a different architecture. You should take the input binary code, create program flow graphs, do a analysis of the program, and then recompile it for the target architecture.
Modify an existing compiler to generate code for some other architecture.
Study the "bursty" nature of pipelines; are averages really useful? Is there a way to more accurately model bursty behaviour?
Analyze program basic block size, and look at the branch problem. Evaluate the technique of predicated execution, and give some examples of how it can be used to increase basic block size.
Architectures/implementations for non-load/store architectures. For example, how might a stack or accumulator architecture be implemented to go fast? Can performance advantages be identified?
Look at instruction set enhancements and their effect on performance (e.g., update-mode addressing, conditional register-to-register moves, and multiply-add instructions)
Analyze the static and dynamic instruction frequencies for 3-4 different architectures. Also look at instruction couples and triples. Based on this information, can you propose any new instructions?
Examine Branch prediction methods and performance
Study methods for predicting multiple branches in a single cycle
Cache implementations, especially non-blocking caches -- design methods and performance
Architectural support of operating systems (e.g., user-level traps for lightweight threads)
Revisit the concept of an OS co-processor. What should such a co-processor look like? (what OS tasks could use specific hardware support, how often would it have to be used to be effective, etc.) "Design" the processor (define the instruction set, word size, datapath, number of ALU's, registers, etc) What does this specially designed OS co-processor give you that a 68000 used in a similar manner wouldn't?
What would an OS for a machine like MISC look like?
Is there a way to relate branch predictor behavior to prefetching activity? (Think about changing working sets)
Can the decoupled idea be used to improve data prefetching schemes?
Is there a way to improve the bandwidth of a processor? (Think redundancy and compression)
What does one do with 100 million transistors, anyway?

Possible Survey Topics

Describe, compare and contrast (generally broader than the above research topics):

Is there really a "memory wall", and if so, what do we do about it?
Study new DRAM interfaces (synchronous DRAM, RamBus and RamLink); consider their performance and how they might affect processor and system implementations.
What's all this noise about IRAM, anyway?
Speculative execution: How important is it, how is it implemented, what kind of performance can it provide, etc.
Compiler transformations to improve pipeline/superscalar performance
Compiler transformations to improve memory behavior
The superscalar approach vs. the VLIW approach vs. the vector approach vs. the decoupled approach to exploiting instruction level parallelism
The effect of changing technology on architecture (e.g. flash memories, fiber optics), and the most likely technology changes in the near future.
High-performance I/O (e.g. RAIDS and ATM networks)
The history of some aspect of computer architecture (e.g. stored-programs, caches, virtual memory, pipelining, microcode, protection, dataflow machines).