Uploaded October 2016 | Updated November 2026, 3 days ago
Building efficient data centers that can hold thousands of machines is hard enough. Programming thousands of machines is even harder. One approach pioneered by Google is known as MapReduce. MapReduce provides a programming model that simplifies programming thousands of machines by breaking down distributed programs into two steps: map, and reduce.
Credits: Talking: Geoffrey Challen (Assistant Professor, Computer Science and Engineering, University at Buffalo). Producing: Greg Bunyea (Undergraduate, Computer Science and Engineering, University at Buffalo).
Part of the internet-class.org online internet course. A blue Systems Research Group (https://blue.cse.buffalo.edu) production.
Building efficient data centers that can hold thousands of machines is hard enough. Programming thousands of machines is even harder. One approach pioneered by Google is known as MapReduce. MapReduce provides a programming model that simplifies programming thousands of machines by breaking down distributed programs into two steps: map, and reduce.
Credits: Talking: Geoffrey Challen (Assistant Professor, Computer Science and Engineering, University at Buffalo). Producing: Greg Bunyea (Undergraduate, Computer Science and Engineering, University at Buffalo).
Part of the internet-class.org online internet course. A blue Systems Research Group (https://blue.cse.buffalo.edu) production.










