Graph + AI World 2020
Graph + AI World:
Delivering Large Scale Real-time Graph Analytics with Dell Infrastructure and TigerGraph
Graph + AI World Session - Recorded September 2020
This presentation describes how we used TigerGraph’s graph analytics capability over Dell’s high performing infrastructure to resolve Customer’s performance challenges with NoSQL based real-time graph queries. The Dell team was asked by the customer to conduct a POC with the TigerGraph NoSQL platform and Dell’s PowerEdge servers over simulated patient data using an open-source tool called Synthea to execute queries similar to their nurse call support where they need sub-second response to improve customer service experience. Dell and TigerGraph worked together on this effort and picked Dell’s Power Edge servers with AMD EPYC processors and generated 10 TB patient data ingested on 8 node clusters and conducted benchmark tests using queries provided by the customer. In order to simulate a real-time query scenario, master-slave architecture was followed using Jmeter as a utility tool on the master node to send concurrent queries with up-to 25000 patients sending the traffic to the cluster concurrently. The tests exceeded customer’s expectations as they were 10x faster than what they were expecting with billions of graph edges traversed by the query within a seconds response time
Watch the Session
