A compiler for throughput optimization of graph algorithms on GPUs
Abstract
Writing high-performance GPU implementations of graph algorithms can be challenging. In this paper, we argue that three optimizations called throughput optimizations are key to high-performance for this application class. These optimizations describe a large implementation space making it unrealistic for programmers to implement them by hand.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Oct 19, 2016
- Source ID
- 10.1145/3022671.2984015
Entities
People
- Keshav Pingali
- Sreepathi Pai
Organizations
- Defense Advanced Research Projects Agency
- National Science Foundation
- University of Texas at Austin