Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision		 Previous revision
wiki:aca2019:project [2019/02/28 00:33] – created Andreas Moshovoswiki:aca2019:project [2019/02/28 01:04] (current) – [Suggested Papers to Validate/Expand] Andreas Moshovos
Line 1: Line 1:
 ====== Project Options ====== ====== Project Options ======
  
-There are four project options. All require that you submit a written proposal by March. 21st online.+There are two project options. All require that you submit a written proposal by March. 21st online.
  
   - Propose your own topic.    - Propose your own topic. 
   - Pick a recent paper from a top-tier architecture conference and validate part of its results. You may choose to validate one of the papers that were discussed in the course. I will provide suggestion. Preference will be for accelerators and more so for Machine Learning accelerators.    - Pick a recent paper from a top-tier architecture conference and validate part of its results. You may choose to validate one of the papers that were discussed in the course. I will provide suggestion. Preference will be for accelerators and more so for Machine Learning accelerators. 
  
- I will set aside a day for meeting in person and discussing your plans prior to submitting your proposal.+ I will set aside a day for meeting in person and discussing your plans prior to submitting your proposal. My current plan is to hold the meetings on March 14th or 15th.
  
 ===== Deliverables ===== ===== Deliverables =====
  
 You will have to deliver the following: You will have to deliver the following:
-  - A tar.gz file with all source files plus how to compile.  +  - Proposal, due March 21st. 
-  - An at most five page report (10 pt size) with figures preferably in PDF. +  - A tar.gz file with all source files plus how to compile. Due April 30th. 
-  - Due April 30, 2019.+  - A final report. Due April 30th. 
 +  - A presentation. Due April 30th. 
 + 
 +See below for format/suggestions.
  
 ===== Proposal and Final Report Format ===== ===== Proposal and Final Report Format =====
Line 54: Line 57:
  
  
 +===== Suggested Papers to Validate/Expand =====
  
 +  * [[https://ieeexplore.ieee.org/document/8416871|Bit-Fusion]]
 +  * [[https://dl.acm.org/citation.cfm?id=3001163| Efficient Inference Engine]]
 +  * [[https://www.cc.gatech.edu/~hadi/doc/paper/2018-isca-snapea.pdf|SnapPea]]
 +  * [[https://ieeexplore.ieee.org/document/8192478|SCNN]]
 +  * [[https://ieeexplore.ieee.org/document/7783723|Cambricon-X]]
 +  * [[https://ieeexplore.ieee.org/abstract/document/7284058/|ShiDaDianNao]]
 +  * [[https://dl.acm.org/citation.cfm?id=3195664|Fused-layer CNN accelerators]]
 +  * [[https://dl.acm.org/citation.cfm?id=3037702|TETRIS]]
 +  * [[https://dl.acm.org/citation.cfm?id=3021745|ESE: efficient speech recognition engine with sparse LSTM on FPGA]]
 +  * Or take a look at this list [[https://github.com/fengbintu/Neural-Networks-on-Silicon|https://github.com/fengbintu/Neural-Networks-on-Silicon]]
 + 
 +And feel free to search online for others. There is tons of very interesting and excellent work that I have not had the chance to include above. By no means is the above a complete list.  I listed works that I thought would be "reasonable" to try to recreate (in part) as part of a course project. Keep in mind, we are validating work. We get the benefit of knowing what to look for and what to evaluate. It is a lot harder and time consuming to start from scratch. There was a lot more time/work spent to arrive at these configurations and choices.