chuqingG / reading_notes

Reading notes

This repo is not up to date.

Deep Learning Compiler

• TVM: An Automated End-to-End Optimizing Compiler for Deep Learning, paper link

• Ansor: Generating High-Performance Tensor Programs for Deep Learning, paper link

CPU optimizations

• Optimizing CNN Model Inference on CPUs, paper link

GPU optimizations

• Matmul Optimization

RNN optimizations

• Persistent RNNs, blog link

• Optimizing RNN performance, blog link

• Optimizing RNNs with Differentiable Graphs, blog link

• Echo: Compiler-based GPU Memory Footprint Reduction for LSTM RNN Training, paper link

• Optimizing Recurrent Neural Networks in cuDNN 5, blog link

Parallel & Vectorizing

• A Loop Transformation Theory and an Algorithm to Maximize Parallelism, paper link
• Auto-vectorizing TensorFlow Graphs: Jacobians, Auto-batching and Beyond, paper link

Decentralized algorithms

Autonomous Driving

• Too Afraid to Drive: Systematic Discovery of Semantic DoS Vulnerability in Autonomous Driving Planning under Physical-World Attacks, paper link
• Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks, paper link