Fast Interconnects: Scalable Co-processing with GPUs

This lecture discusses the use of fast interconnects to enable scalable co-processing with GPUs in databases. The instructor presents the motivation behind leveraging GPUs in the database market, the research problem related to memory capacity and interconnect bandwidth, and the game-changing impact of fast interconnects. Various contributions and the benefits for databases are highlighted, along with detailed explanations of probe-side and build-side scaling. Lessons learned, future work on k-Means, and the evaluation of GPU+CPU cooperation are also covered, emphasizing the importance of overcoming the transfer bottleneck and reevaluating assumptions for performance improvements.