Nemo: Accelerating Memory-Disaggregated Key-Value Store with Near Memory Processing
TL;DR
Nemo provides a set of new techniques that enable fast task dispatch, cache-conscious task offloading without CPU modifications, and versatile support of custom data types to address the CPU-accelerator latency.
Abstract
Memory disaggregation provides key-value stores larger memory capacity at low cost. Emerging compute express link (CXL) enables efficient memory disaggregation. It, however, dramatically slows down the system performance as disaggregated memory accesses are considerably slower than local memory accesses. This paper presents Nemo, a near-memory accelerator architecture for CXL-based memory-disaggregated key-value stores. To address the CPU-accelerator latency, Nemo provides a set of new techniques that enable fast task dispatch, cache-conscious task offloading without CPU modifications, and versatile support of custom data types. We evaluate Nemo on the core in-memory index of RocksDB and six widely used in-memory indexing microbenchmarks under YCSB query workloads. Nemo reduces up to 91.8% of slow disaggregated memory accesses, achieves a 2.05 × average speedup over the CPU-only configuration, and accelerates key-value stores by up to 4.5 ×.