Processing-in-Memory for Databases: Query Processing and Data Transfer Article Swipe

PDF

Related Concepts

Computer science Bottleneck In-Memory Processing Memory map Memory management Database Computation Data processing Interleaved memory Interleaving Parallel computing Operating system Shared memory Semiconductor memory Embedded system Query by Example Web search query Information retrieval Programming language Search engine

Alexander Baumstark , Muhammad Attahir Jibril , Kai-Uwe Sattler ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.1145/3592980.3595323 · OA: W4380624154

The Processing-in-Memory (PIM) paradigm promises to accelerate data processing by pushing down computation to memory, reducing the amount of data transfer between memory and CPU, and – in this way – relieving the CPU from processing. Particularly, in inmemory databases memory access becomes a performance bottleneck. Thus, PIM seems to offer an interesting solution for database processing. In this work, we investigate how commercially available PIM technology can be leveraged to accelerate query processing by offloading (parts of) query operators to memory. Furthermore, we show how to address the problem of limited PIM storage capacity by interleaving transfer and computation and present a cost model for the data placement problem.