Hash-Based Join Algorithms for Multiprocessor Computers

This paper studies a number of hash-based join algorithms for general purpose multiprocessor computers with shared memory where the amount of memory allocated to the join operation is proportional to the number of processors assigned to the operation and a global hash table is built in this shared memory. The concurrent update and access to this global hash table is studied. The elapsed time and total processing time for these algorithms are analyzed. The results indicate that, hybrid hash join that outperforms other hash-based algorithms in uniprocessor systems does not always performs the best. A simpler algorithm, hash-based nested loops join, performs better in terms of elapsed time when both the relations are of similar sizes.

• Type: Conference
• Year: 1990
• Where: VLDB
• Authors: Hongjun Lu, Kian-Lee Tan, Ming-Chien Shan
• Keywords: Database, Elapsed Time, Global Hash Table, Shared Memory, VLDB 1990