Accelerating Large-Scale Nearest Neighbor Search with Computational Storage Device

Kim, Jihoon; Park, Yeo-Reum; Do, Jaeyoung; Ji, Soo-Young; Kim, Joo-Young

doi:10.1109/fccm51124.2021.00041

Cited by 2 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among many examples of the bump-in-the-wire architecture, SmartSSD is an actively used devices both in academia and industry [41], [42], [47], [53], [58]. As shown in Figure 3, it integrates a Xilinx UltraScale+ FPGA with 4GB DRAM and 3.84TB NAND Flash arrays in the U.2 form factor for data processing in the storage device.…”

Section: Smartssd: Computational Storage Devicementioning

confidence: 99%

“…Between these two models, as the volume of data increases, the out-of-the-wire architecture suffers from the time and energy overhead required for additional data movement between the host and specialized hardware. As a result, dataintensive applications such as recommendation system [46], [62], nearest neighbor search [41], [42], and data analytics [47], [53], [58] have been widely accelerated using the bumpin-the-wire architecture.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Trinity: In-Database Near-Data Machine Learning Acceleration Platform for Advanced Data Analytics

Kim,

Han,

Park

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

The ability to perform machine learning (ML) tasks in a database management system (DBMS) is a new paradigm for conventional database systems as it enables advanced data analytics on top of well-established capabilities of DBMSs. However, the integration of ML in DBMSs introduces new challenges in traditional CPU-based systems because of its higher computational demands and bigger data bandwidth requirements. To address this, hardware acceleration has become even more important in database systems, and the computational storage device (CSD) placing an accelerator near storage is considered as an effective solution due to its high processing power with no extra data movement cost. In this paper, we propose Trinity, an end-to-end database system that enables in-database, in-storage platform that accelerates advanced analytics queries invoking trained ML models along with complex data operations. By designing a full stack from DBMS's internal software components to hardware accelerator, Trinity enables in-database ML pipelines on the CSD. On the software side, we extend the internals of conventional DBMSs to utilize the accelerator in the SmartSSD. Our extended analyzer evaluates the compatibility of the current query with our hardware accelerator and compresses compatible queries into a 24-byte numeric format for efficient hardware processing. Furthermore, the predictor is extended to integrate our performance cost models to always offload queries into the optimal hardware backend. The proposed SmartSSD cost model mathematically models our hardware, including host operations, data transfers, FPGA kernel execution time, and the CPU cost model uses polynomial regression ML models to predict complex CPU latency. On the hardware side, we introduce the in-database processing accelerator (i-DPA), a custom FPGA-based accelerator. i-DPA includes database page decoder to fully exploit the bandwidth benefit of near-storage processing. It also employs dynamic tuple binding to enhance the overall parallelism and hardware utilization. i-DPA's architecture having heterogeneous computing units with a reconfigurable on-chip interconnect also allows seamless data streaming, enabling task-level pipeline across different computing units. Finally, our evaluation shows that Trinity improves the end-to-end performance of analytics queries by 15.21× on average and up to 57.18× compared to the conventional CPU-based DBMS platform. We also show that the Trinity's performance can linearly scale up with multiple SmartSSDs, achieving nearly up to 200× speedup over the baseline with four SmartSSDs.

show abstract

Section: Smartssd: Computational Storage Devicementioning

confidence: 99%