User Tools

Site Tools


Schedule : Fall 2021

This is the tentative schedule of Mélange group for the Fall 2021 semester.
Meeting time & Place : Tuesdays 9:30 AM - 10:30 AM (MST/MDT) in ISTeC Room (CSB 305), and via Webex.

1 8/24/2021 First meeting
2 8/31/2021 Tracking schema statistics in Leela with GPU‐efficient mathematics Steve Kommrusch
3 9/07/2021 Increasing FPGA Accelerators Memory Bandwidth with a Burst-Friendly Memory Layout Corentin Ferry
4 9/14/2021 There's plenty of room at the Top: What will drive computer performance after Moore's law? Sanjay Rajopadhye
5 9/21/2021 From micro-OPs to abstract resources: constructing a simpler CPU performance model through microbenchmarking Nicolas Derumigny
6 9/28/2021 Improved Parallel Cache-Oblivious Algorithms for Dynamic Programming and Linear Algebra Malek Mechergui
7 10/05/2021 Compilation of Sparse Array Programming Models TBD
8 10/12/2021 TBD Chiranjeb Mondal
9 10/19/2021
10 10/26/2021
11 11/02/2021
12 11/09/2021 TBD Alexandre Dubois
13 11/16/2021 TBD Steve Kommrusch
14 11/30/2021
15 12/07/2021

Previous Semesters, including legacy reading lists

Standard paper study questions

  1. Write a short (max 5 sentences) summary of the paper.
  2. What is the problem addressed in the paper?
  3. Why is the problem important?
  4. How do the authors address the problem?
  5. How do they evaluate their approach?
  6. What is the punch-line (key cool idea, or “what I got out of this paper”)? This is often different for different people and different from what the authors may have intended.
  7. Make a list of deeper questions that you would like discussed in the meeting.

Current Reading Pool

  • Akimasa Morihata, Shigeyuki Sato. Reverse Engineering for Reduction Parallelization via Semiring Polynomials. In Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, 2021, 2021.
  • Guy E. Blleloch, Yan Gu. Improved Parallel Cache-Oblivious Algorithms for Dynamic Programming and Linear Algebra. In arXiv, 1809.09330, 2019.
  • Peng Jiang, Linchuan Chen, Gagan Agrawal. Revealing Parallel Scans and Reductions in Recurrences through Function Reconstruction. In Proceedings of the 27th International Conference on Parallel Architectures and Compilation Techniques, 2018, 2018.
  • C. Mauras, P. Quinton, S. Rajopadhye, Y. Saouter. Scheduling affine parameterized recurrences by means of Variable Dependent Timing Functions. In [1990] Proceedings of the International Conference on Application Specific Array Processors, , 1990.
melange/schedule.txt · Last modified: 2021/09/23 07:59 by corentin