Research Papers

An important part of this course is reading research papers. High-level synthesis is an active research area and many of the most interesting developments are taking place in the research domain. In addition, reading and reviewing research papers is a good skill to practise, especially for those of you that go on to a research career.

Schedule

Paper reviews are due the day before we discuss the paper in class

# Due Date Paper
1 Mar 27, 11:59pm Jason Cong, Jason Lau, Gai Liu, Stephen Neuendorffer, Peichen Pan, Kees Vissers, Zhiru Zhang, “FPGA HLS Today: Successes, Challenges, and Opportunities”, TRETS 2022.
2 Apr 3, 11:59pm Yi-Hsiang Lai, Yuze Chi, Yuwei Hu, Jie Wang, Cody Hao Yu, Yuan Zhou, Jason Cong, Zhiru Zhang, “HeteroCL: A Multi-Paradigm Programming Infrastructure for Software-Defined Reconfigurable Computing”, FPGA 2019.
3 Apr 10, 11:59pm Hanchen Ye, Cong Hao, Jianyi Cheng, Hyunmin Jeong, Jack Huang, Stephen Neuendorffer, Deming Chen, “ScaleHLS: A New Scalable High-Level Synthesis Framework on Multi-Level Intermediate Representation”, HPCA 2022.

Paper Review Contents

Include the following in your paper review (in marked sections):

  1. A sentence or two giving an overview of the paper.
  2. Describe the 2-3 Major Contributions and/or Novelty of the paper. This should be more than a re-statement of the abstract. What do you think are the important contributions of the paper?
  3. Provide a critical review, discussing several positive and negative aspects of the paper. Try to provide non-trivial arguments, including some points not brought up by the authors. Do not summarize the paper (that’s what the abstract is for); rather, evaluate the merits of the work done by the authors as presented in the paper. You could comment on things like: (not all in one review):
    • importance of the problem being solved
    • soundness/correctness of approach
    • appropriateness of methodology
    • quality, completeness or repeatability of results
    • readability
    • perspective and/or comparison with previous work
  4. Identify at least one aspect of the paper that you didn’t understand, or want to better understand.

Your review should be one page or less (normal fonts and margins). Quality is more important than quantity.

Grading Scheme

Submission Instructions & Late Policy

Send your review as a direct message on Slack. Because we discuss the paper reviews as a class, no late submissions will be accepted. Please make sure to get your paper reviews in on time!