/DAC-Papers-Collection

A personal collection and evaluation of recent decade's DAC papers.

MIT LicenseMIT

DAC-Papers-Collection

A personal collection and evaluation of recent decade's DAC papers.

My research interests include high-level synthesis, neural network compilation and architecture design for deep learning. In order to construct a systematic view of these research fields, as well as learning fresh ideas. I am collecting and sorting DAC (Design Automation Conference) papers by publishing year and those above mentioned research topics.

Table of Contents

DAC Papers

2020 DAC

Machine learning in solving traditional EDA problems

  • Reinforcement Learning-based Power. Management Policy for Mobile Device Systems
  • A Neural Network that Routes ICs

Neural network accelerator design

  • MEMTONIC: A Neuromorphic Accelerator for Energy Efficient Deep Learning
    • Designed for inference and training
  • Building an On-Chip Deep Learning Memory Hierarchy Brick by Brick
    • Memory access is one of the most important bottlenecks in designing NN accelerators
  • Automated Hardware Generation of CNN Models on FPGAs
  • Bit Parallel 6T SRAM In-memory Computing with Reconfigurable Bit-Precision
  • Factored Radix-8 Systolic Array for Tensor Processing

High-level synthesis

  • DECOY: Deflection-Driven HLS-Based Computation Partitioning for Obfuscating Intellectual Property