IMSEM Papers

Winter Semester 2014-2015

• Boykin, Ritchie, O'Connell, Lin:  Summingbird: A Framework for Integrating Batch and Online MapReduce Computations. VLDB'14 pdf
• Chaiken et al:  SCOPE: easy and efficient parallel processing of massive data sets. VLDB'08 pdf
• Floratou, Minhas, Ozcan: Sql-on-hadoop: Full circle back to shared-nothing database architectures. VLDB'14 pdf
• Bahmani, Chakrabarti, Xin: Fast personalized pagerank on mapreduce. SIGMOD'11  pdf
• Strang: The fundamental theorem of linear algebra.American Mathematical Monthly, 1993 pdf
• Lee et al: Joins on Encoded and Partitioned Data. VLDB'14 pdf
• Crotty et al: Tupleware: Redefining Modern Analytics, arXiv pdf
• Gonzalez et al: PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs, OSDI'12 pdf
• Tzoumas, Deshpande, Jensen:  Lightweight graphical models for selectivity estimation without independence assumptions, VLDB'11 pdf
• Zhou, Larson, Chaiken: Incorporating partitioning and parallel plans into the SCOPE optimizer, ICDE'10 pdf
• Sparks et al:  MLI: An API  for  distributed machine learning. In Data Mining, ICDM'13 pdf
• Ngo, Porat, Ré, Rudra: Worst-case optimal join algorithms, ACM PODS'12 pdf
• Klonatos, Koch, Rompf, Chafi: Building Efficient Query Engines in a High-Level Language, VLDB'14 pdf

Winter Semester 2013-2014

All of you should read the general reading papers:

• MapReduce: Simplified data processing on large clusters
• The Fundamental Theorem of Linear Algebra
• Access Path Selection in a Relational Database Management System

The following topics are available:

(1) Parallel Processing Theory

Upper and lower bounds on the cost of a map-reduce computation

Making queries tractable on big data with preprocessing

(2) Query optimization

Opening the black boxes in data flow optimization

Continuous cloud-scale query optimization and processing

(3) Data-parallel programming

Jet: An Embedded DSL for High Performance Big Data Processing

(4) In-memory databases

HyPer: A Hybrid OLTP&OLAP Main Memory Database System Based on Virtual Memory Snapshots

OLTP through the looking glass, and what we found there

(5) Indexing

Only Aggressive Elephants are Fast Elephants

Database Cracking

(6) Visualization and interaction

Enterprise Data Analysis and Visualization: An Interview Study

dbTouch: Analytics at your Fingertips

(7) Parallel machine learning

SystemML: Declarative machine learning on MapReduce

Distributed stochastic gradient descent

(8) Transactions

Spanner: Google’s globally-distributed database*

Data-oriented transaction execution

(9) Graphs

GraphLab: A New Framework For Parallel Machine Learning

Spinning fast iterative dataflows

(10) In-database analytics

Towards a unified architecture for in-RDBMS analytics

ArrayStore: A Storage Manager for Complex Parallel Array Processing

(11) Distributed streaming

Integrating scale out and fault tolerance in stream processing using operator state management

Naiad: A Timely Dataflow System

(12) Databases on modern hardware

Hardware-Oblivious Parallelism for In-Memory Column-Stores

Data Processing on FPGAs

(13) Scheduling

Apache Hadoop YARN: Yet Another Resource Negotiator

Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center