Conduit: Programmer-Transparent Near-Data Processing Using Multiple Compute-Capable Resources in Solid State Drives
Rakesh Nadig, Vamanan Arulchelvan, Mayank Kabra, Harshita Gupta, Rahul Bera, Nika Mansouri Ghiasi, Nanditha Rao, Qingcai Jiang, Andreas Kosmas Kakolyris, Yu Liang, Mohammad Sadrosadati, Onur Mutlu
TL;DR
Conduit tackles data-movement bottlenecks in data-intensive workloads by enabling general-purpose, programmer-transparent near-data processing on SSDs. It combines compile-time vectorization with a runtime holistic offloading policy that selects among ISP, PuD-SSD, and IFP for fine-grained instructions, guided by six features including operation type, operand location, data dependencies, queueing, data movement, and expected computation latency. Across six real-world workloads, Conduit significantly outperforms prior SSD-based NDP offloads and reduces energy consumption, achieving substantial speedups while mitigating tail latency. The approach demonstrates the practical viability and broad applicability of coordinated, multi-resource NDP in storage systems, with notable implications for databases, genomics, and ML workloads.
Abstract
Solid-state drives (SSDs) are well suited for near-data processing (NDP) because they: (1) store large application datasets, and (2) support three NDP paradigms: in-storage processing (ISP), processing using DRAM in the SSD (PuD-SSD), and in-flash processing (IFP). A large body of prior SSD-based NDP techniques operate in isolation, mapping computations to only one or two NDP paradigms (i.e., ISP, PuD-SSD, or IFP) within the SSD. These techniques (1) are tailored to specific workloads or kernels, (2) do not exploit the full computational potential of an SSD, and (3) lack programmer-transparency. While several prior works propose techniques to partition computation between the host and near-memory accelerators, adapting these techniques to SSDs has limited benefits because they (1) ignore the heterogeneity of the SSD resources, and (2) make offloading decisions based on limited factors such as bandwidth utilization, or data movement cost. We propose Conduit, a general-purpose, programmer-transparent NDP framework for SSDs that leverages multiple SSD computation resources. At compile time, Conduit executes a custom compiler (e.g., LLVM) pass that (i) vectorizes suitable application code segments into SIMD operations that align with the SSD's page layout, and (ii) embeds metadata (e.g., operation type, operand sizes) into the vectorized instructions to guide runtime offloading decisions. At runtime, within the SSD, Conduit performs instruction-granularity offloading by evaluating six key features, and uses a cost function to select the most suitable SSD resource. We evaluate Conduit and two prior NDP offloading techniques using an in-house event-driven SSD simulator on six data-intensive workloads. Conduit outperforms the best-performing prior offloading policy by 1.8x and reduces energy consumption by 46%.