“"Analytical database systems are typically designed to use a column-first data layout that maps better to analytical queries of access patterns. This choice is premised on the assumption that storing data in a row-first format leads to accessing unwanted fields; moreover, transforming rows to columns at runtime is expensive. On the other hand, new data it…”
Relational Memory: Native In-Memory Accesses on Rows and Columns
Analytical database systems are typically designed to use a column-first data layout to access only the desired fields. On the other hand, storing data row-first works great for accessing, inserting, or updating entire rows. Transforming rows to columns at runtime is expensive, hence, many analytical systems ingest data in row-first form and transform it in the background to columns to facilitate future analytical queries. How will this design change if we can always efficiently access only the desired set of columns? To address this question, we present a radically new approach to data transformation from rows to columns. We build upon recent advancements in embedded platforms with re-programmable logic to design native in-memory access on rows and columns. Our approach, termed Relational Memory, relies on an FPGA- based accelerator that sits between the CPU and main memory and transparently transforms base data to any group of columns with minimal overhead at runtime. This design allows accessing any group of columns as if it already exists in memory. We implement and deploy Relational Memory in real hardware, and we show that we can access the desired columns up to 1.63x faster than accessing them from their row-wise counterpart, while matching the performance of a pure columnar access for low projectivity, and outperforming it by up to 1.87x as projectivity (and tuple re-construction cost) increases. Moreover, our approach can be easily extended to support offloading of a number of operations to hardware, e.g., selection, group by, aggregation, and joins, having the potential to vastly simplify the software logic and accelerate the query execution.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“This paper is a slightly different approach to a similar problem: https://arxiv.org/abs/2109.14349 They are inserting an FPGA fabric between standard CPUs and standard DDR RAM, allowing the memory to be reorganized on the fly. For example you can flip columns and rows in arrays, or turn ordinary row-oriented databases into column-first databases. I thi…”
“Something similar in this paper, putting an FPGA between the processor and DRAM so you can arbitrarily remap bits of it: https://arxiv.org/abs/2109.14349”
“But the bet was customers would buy Xeons with an FPGA block that would "do magic". What magic it would do and how you'd program it in a sane way was never specified in great detail. In any case for those that really want this it turns out you can put the FPGA on the end of a regular PCIe link and get all the same benefits. Edit: By the way there is some…”
“Red Hat supported a lot of research into this and there's some really interesting stuff, but nothing that is very compelling for commercial use. What uses do you have in mind? To my mind the more interesting stuff are the PCIe FPGA boards like https://www.xilinx.com/products/boards-and-kits/alveo/u200.html One particularly interesting research project w…”
- Relational Memory: Native In-Memory Accesses on Rows and Columns ↗belter · 2021-10-03 · 3 分
- Using an FPGA to transform rows to columns on in-memory databases ↗rwmj · 2022-10-18 · 7 分