Abstract The join and group-by aggregation are two memory intensive operators that are affecting the performance of relational databases. Hashing is a common approach used to implement both operators. Recent paradigm shifts in multi-core processor architectures have reinvigorated research into how the join and group-by aggregation operators can leverage these advances. However, the poor spatial locality of the hashing approach has hindered performance on multi-core processor architectures which rely on using large cache hierarchies for latency mitigation. Multithreaded architectures can better cope with poor spatial locality by masking memory latency with many outstanding requests. Nevertheless, the number of parallel threads, even in the most advanced multithreaded processors, such as UltraSPARC, is not enough to fully cover the main memory access latency. In this paper, we explore the hardware re-configurability of FPGAs to enable deeper execution pipelines that maintain hundreds (instead of tens) of outstanding memory requests across four FPGAs-drastically increasing concurrency and throughput. We present two end-to-end in-memory accelerators for the join and group-by aggregation operators using FPGAs. Both accelerators use massive multithreading to mask long memory delays of traversing linked-list data structures, while concurrently managing hundreds of thread states across four FPGAs locally. We explore how content addressable memories can be intermixed within our multithreaded designs to act as a synchronizing cache, which enforces locks and merges jobs together before they are written to memory. Throughput results for our hash-join operator accelerator show a speedup between 2 $$\times $$ × and 3.4 $$\times $$ × over the best multi-core approaches with comparable memory bandwidths on uniform and skewed datasets. The accelerator for the hash-based group-by aggregation operator demonstrates that leveraging CAMs achieves average speedup of 3.3 $$\times $$ × with a best case of 9.4 $$\times $$ × in terms of throughput over CPU implementations across five types of data distributions.

Inexpensive DRAMs have created new opportunities for in-memory data analytics. However, the major bottleneck in such systems is high memory access latency. Traditionally, this problem is solved with large cache hierarchies that only benefit regular applications. Alternatively, many data-intensive applications exhibit irregular behavior. Hardware multithreading can better cope with high latency seen in such applications. This article implements a multithreaded prototype (MTP) on FPGAs for the relational selection operator that exhibits control flow irregularity. On a standard TPC-H query evaluation, MTP achieves a bandwidth utilization of 83%, while the CPU and the GPU implementations achieve 61% and 64%, respectively. Besides being bandwidth efficient, MTP is also 14.2× and 4.2× more power efficient than CPU and GPU, respectively.

Data sources, such as social media, mobile apps and IoT sensors, generate billions of records each day. Keeping up with this influx of data while providing useful analytics to the users is a major challenge for today's data-intensive systems. A popular solution that allows such systems to handle rapidly incoming data is to rely on log-structured merge (LSM) storage models. LSM-based systems provide a tunable trade-off between ingesting vast amounts of data at a high rate and running efficient analytical queries on top of that data. For queries, it is well-known that the query processing performance largely depends on the ability to generate efficient execution plans. Previous research showed that OLAP query workloads rely on having small, yet precise, statistical summaries of the underlying data, which can drive the cost-based query optimization.

Recent trends in hardware have dramatically dropped the price of RAM and shifted focus from systems operating on disk-resident data to in-memory solutions. In this environment high memory access latency, also known as memory wall, becomes the biggest data processing bottleneck. Traditional CPU-based architectures solved this problem by introducing large cache hierarchies. However algorithms which experience poor locality can limit the benefits of caching. In turn, hardware multithreading provides a generic solution that does not rely on algorithm-specific locality properties.