Towards practical vectorized analytical query engines

Abstract

Query execution engines are adapting to the underlying hardware in order to maximize performance. Wider SIMD registers and more complex SIMD instruction sets are emerging in mainstream CPUs as well as new processor designs, such as the many-core platforms that rely on data parallelism via SIMD vectorization to pack a larger number of smaller cores per chip. In the database literature, using SIMD to optimize standalone operators with key - rid pairs is common, yet the state-of-the-art query engines rely on compilation of tightly coupled operators where hand-optimized individual operators become impractical. In this paper, we present VIP, an analytical query engine designed and built bottom-up from pre-compiled column-oriented data-parallel sub-operators and implemented entirely in SIMD. In our evaluation derived from the TPC-H workload, VIP outperforms query-specific hand-optimized scalar code.