Massively Parallel NUMA-Aware Hash Joins

Driven by the two main hardware trends increasing main memory and massively parallel multi-core processing in the past few years, there has been much research effort in parallelizing well-known join algorithms. However, the non-uniform memory access (NUMA) of these architectures to main memory has only gained limited attention in the design of these algorithms. We study recent proposals of main memory hash join implementations and identify their major performance problems on NUMA architectures. We then develop a NUMA-aware hash join for massively parallel environments, and show how the specific implementation details affect the performance on a NUMA system. Our experimental evaluation shows that a carefully engineered hash join implementation outperforms previous high performance hash joins by a factor of more than two, resulting in an unprecedented throughput of 3/4 billion join argument quintuples per second.