Programming Contest


Machine Learning &
Logic Synthesis


IWLS Programming Contest Series
Machine Learning + Logic Synthesis

Logic synthesis is a fundamental step in hardware design whose goal is to find structural representations of Boolean functions while minimizing delay and area. If the function is completely-specified, the implementation accurately represents the function. If the function is incompletely-specified, the implementation has to be true only on the care set. While most of the algorithms in logic synthesis rely on SAT and Boolean methods to exactly implement the care set, we investigate learning in logic synthesis, attempting to trade exactness for generalization. The IWLS Contest series are directly related to machine learning where the care set is the training set and the implementation is expected to generalize on a validation set.

IWLS Contest @2023

IWLS 2023 Programming Contest Call for Contest

It has been recently observed that the cost of silicon wafers has started to grow steeply in the 3rd quarter of 2021. Please note the hockey stick shape of the second graph here https://morethanmoore.substack.com/p/tsmc-financial-year-2022 As a result, the design area contributes more to the design cost, and there is increasing interest in high-effort area optimization methods, which is the topic of this year’s IWLS Programming Contest.

IWLS 2023 Programming Contest Benchmarks

IWLS Contest @2021

The 2021 Contest extends in a fairly significant way the contest from 2020. The goal last year was to learn an unknown boolean function f : {0, 1}^n → {0, 1} from a training set consisting of input-output pairs. The contest generated a large number of interesting ideas and approaches that are summarized in this paper [DATE 21]. This year, we extend it to the multi-output case, that is, to the case of learning a function f : {0, 1}^n → {0, 1}^m. Since this is much more challenging than the task last year, instead of 100 separate benchmarks, we will use only one benchmark dataset: CIFAR-10.

IWLS Contest @2020

TBD

  • Contest Description: Call for Contest
  • Dataset/Benchmarks: Contest Github Page
  • Results: Contest Presentation in IWLS 2020
  • Reference: Rai, Shubham, Walter Lau Neto, Yukio Miyasaka, Xinpei Zhang, Mingfei Yu, Qingyang Yi, Masahiro Fujita et al. "Logic synthesis meets machine learning: Trading exactness for generalization." In 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 1026-1031. IEEE, 2021. [Paper]
Links to Past Workshops

IWLS 2020: July 27 - July 30, 2020, Virtual

IWLS 2019: June 21 - June 23, 2019, San Francisco, California

IWLS 2018: June 23 - June 24, 2018, San Francisco, California

IWLS 2017: June 17 - June 18, 2017, Austin, Texas

IWLS 2016: June 10 - June 11, 2016, Austin, Texas

IWLS 2015: June 12 - June 13, 2015, Mountain View, California

IWLS 2014: May 30 - June 1, 2014, San Francisco, California

IWLS 2013: June 7 - June 8, 2013, Austin, Texas

IWLS 2012: June 1 - June 3, 2012, Berkeley, California

IWLS 2011: June 3 - June 5, 2011, San Diego, California

IWLS 2010: June 18 - June 20, 2010, Irvine, California

IWLS 2009: July 31 - August 2, 2009, Berkeley, California

IWLS 2008: June 4 - 6, 2008, Lake Tahoe, California

IWLS 2007: May 30 - June 1, 2007, San Diego, California

IWLS 2006: June 7 - 9, 2006, Vail, Colorado

IWLS 2005: June 8 - 10, 2005, Lake Arrowhead, California

IWLS 2004: June 2 - 4, 2004, Temecula Creek, California

IWLS 2003: May 28 - 30, 2003, Laguna Beach, California

IWLS 2002: June 4 - 7, 2002, New Orleans, Louisiana

IWLS 2001: June 12 - 15, 2001, Lake Tahoe, California

IWLS 2000: May 31 - June 2, 2000, Dana Point, California

Related Conferences

ICCAD: International Conference on Computer-Aided Design

DATE: Design, Automation and Test in Europe

ASPDAC: Asia and South Pacific Design Automation Conference

DAC: Design Automation Conference

ISPD: International Symposium on Physical Design

ISLPED: International Symposium on Low Power Electronics and Design

IWBDA: International Symposium on Bio-Design Automation