Data Path Fusion in GPU for Analytical Query Processing
Tsuyoshi Ozawa, Kazuo Goda

TL;DR
This paper introduces Data Path Fusion (DPF), a GPU architecture that fuses data processing steps into a single kernel to reduce overhead and improve analytical query performance.
Contribution
The paper presents DPF, a novel GPU data processing architecture that integrates multiple data path operations into one kernel, enhancing efficiency for analytical workloads.
Findings
DPF achieves 2.66 to 6.22x speedup on TPC-H benchmarks.
DPF attains 3.84 to 16.81x speedup on SSB benchmarks.
Experimental results validate DPF's effectiveness over existing approaches.
Abstract
One major technical challenge for modern analytical database systems is how to leverage GPU to exploit their massive parallelism and high bandwidth. Yet, existing GPU-driven database engines suffer from inefficiencies caused by frequent host-device interactions and fragmented execution across multiple GPU kernels, limiting their ability to fully utilize GPU's computational and IO capabilities. This paper proposes Data Path Fusion (DPF), a novel GPU-driven data processing architecture that integrates a sequence of data path operations -- including IOs, decompression, and query operations -- into a single GPU kernel. By fusing the data path, DPF reduces host-device communication overheads and enables more efficient utilization of GPU resources for analytical query workloads. DPF seamlessly integrates GPU-friendly optimization techniques, including type-specific compression/decompression,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
