Table 1 Datasets used in the experiments
From: iiHadoop: an asynchronous distributed framework for incremental iterative computations
Algorithm | Dataset | Size (GB) | Description |
|---|---|---|---|
PageRank | ClueWeb | 30 | 616,516,725 pages, 2,903,017,060 edges |
SSSP | ClueWeb1 | 10 | 428,136,613 pages, 454,075,638 edges |
Connected components | ClueWeb2 | 12 | 428,136,613 pages, 530,014.595 edges |
K-means | BigCross | 16 | 104,582,700 points, 57 dimensions |