CS 744 Big Data Systems - UW Madison, Fall 2021

This class will introduce key concepts and state-of-the-art in big data systems. After covering the basics of modern hardware and software infrastructures that these systems leverage, we will explore the systems themselves from the ground up.

Specifically, topics we cover will include:

Course Learning Objectives

At the end of the course you will be able to

Logistics

Pre-requisites

Course prerequisites: The prerequisites for this course are Database Systems (CS 564 or CS 764) and Operating Systems (CS 537 or CS 736), or equivalent courses.

Grading

Schedule

Class Date Reading Lecture Material Notes
9/9 How to read a paper Slides Slides+Notes Assignment 0
Infrastructure
9/14 The Datacenter as a Computer version 3, Chapter 1 and 2 Slides Slides+Notes
9/16 The Google File System
NFS: Sun's Network File System (optional)
Slides Slides+Notes Assignment 1
9/21 MapReduce:Simplified Data Processing on Large Clusters
MPI Tutorial Introduction and MPI Hello World
Slides Slides+Notes
9/23 Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing Slides Slides+Notes
Scheduling
9/28 Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center
YARN: Yet Another Resource Negotiator (Optional)
Slides Slides+Notes Assignment 1 due
9/29 Assignment 2
9/30 DRF: Dominant Resource Fairness Slides Slides+Notes
Machine Learning
10/5 PyTorch Distributed: Experiences on AcceleratingData Parallel Training
Towards a Unified Architecture for in-RDBMS Analytics (Optional)
Slides Slides+Notes
10/7 PipeDream: Generalized Pipeline Parallelism for DNN Training
Slides Slides+Notes Submit project bids
10/12 Ray: A Distributed Framework for Emerging AI Applications Slides Slides+Notes Assignment 2 due
10/14 Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning Slides Slides+Notes
10/19 Nexus: A GPU Cluster Engine for Accelerating DNN-Based Video Analysis Slides Slides+Notes
SQL Frameworks
10/21 SCOPE: Easy and Efficient Parallel Processing of Massive Data Sets
Spark SQL: Relational Data Processing in Spark(Optional)
Slides Slides+Notes
10/25 Project Introductions Due
10/26 The Snowflake Elastic Data Warehouse
Building An Elastic Query Engine on Disaggregated Storage(Optional)
Slides Slides+Notes
10/28 Midterm 1 In-class midterm
Stream Processing
11/2 The Dataflow Model: A Practical Approach to Balancing Correctness, Latency, and Cost in Massive-Scale, Unbounded, Out-of-Order Data Processing Slides Slides+Notes
11/4 Naiad: A Timely Dataflow System Slides Slides+Notes
11/9 Discretized Streams: Fault-Tolerant Streaming Computation at Scale Slides Slides+Notes
Graph Processing
11/11 PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs Slides Slides+Notes
11/16 GraphX: Graph Processing in a Distributed Dataflow Framework
Scalability! But at what COST?
Slides Slides+Notes
11/18 Marius: Learning Massive Graph Embeddings on a Single Machine Slides Slides+Notes
New Data, Hardware Models
11/23 Occupy the Cloud: Distributed Computing for the 99% Slides Slides+Notes
11/25 Happy Thanksgiving!
11/30 SplitFS: Reducing Software Overhead in File Systems for Persistent Memory Project check-ins due
12/2 In-Datacenter Performance Analysis of a Tensor Processing Unit Project check-in feedback
12/7 Midterm 2 In-class midterm
12/9 Fairness and machine learning: Limitations and Opportunities (Introduction)
Measuring discrepancies in Airbnb guest acceptance rates using anonymized demographic data (Page 1-15) (Optional)
50 Years of Test (Un)fairness: Lessons for Machine Learning (Optional)
12/14 Poster presentations
12/20 Final project reports due