SIMD-MIMD cocktail in a hybrid memory glass
- 14 June 2021
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM) in Proceedings of the 14th ACM International Conference on Systems and Storage
Abstract
Hybrid memory systems consisting of DRAM and NVRAM offer a great opportunity for column-oriented data systems to persistently store and to efficiently process columnar data completely in main memory. While vectorization (SIMD) of query operators is state-of-the-art to increase the single-thread performance, it has to be combined with thread-level parallelism (MIMD) to satisfy growing needs for higher performance and scalability. However, it is not well investigated how such a SIMD-MIMD interplay could be leveraged efficiently in hybrid memory systems. On the one hand, we deliver an extensive experimental evaluation of typical workloads on columnar data in this paper. We reveal that the choice of the most performant SIMD version differs greatly for both memory types. Moreover, we show that the throughput of concurrent queries can be boosted (up to 2x) when combining various SIMD flavors in a multi-threaded execution. On the other hand, to enable that optimization, we propose an adaptive SIMD-MIMD cocktail approach incurring only a negligible runtime overhead.Keywords
Funding Information
- Deutsche Forschungsgemeinschaft (LE-1416/27-1)
This publication has 36 references indexed in Scilit:
- Persistent B + -trees in non-volatile main memoryProceedings of the VLDB Endowment, 2015
- Write-limited sorts and joins for persistent memoryProceedings of the VLDB Endowment, 2014
- DB2 with BLU accelerationProceedings of the VLDB Endowment, 2013
- Sharing data and work across concurrent analytical queriesProceedings of the VLDB Endowment, 2013
- Decoding billions of integers per second through vectorizationSoftware: Practice and Experience, 2013
- The Design and Implementation of Modern Column-Oriented Database SystemsFoundations and Trends® in Databases, 2012
- SIMD-scanProceedings of the VLDB Endowment, 2009
- Breaking the memory wall in MonetDBCommunications of the ACM, 2008
- Main-memory scan sharing for multi-core CPUsProceedings of the VLDB Endowment, 2008
- An overview of data warehousing and OLAP technologyACM SIGMOD Record, 1997