Catalyst: Optimizing Cache Management for Large In-memory Key-value Systems
Summary: Exposes metadata-management bottlenecks in fine-grained in-memory KV caches at large scale and introduces Catalyst, a compact metadata structure for scalable temporal-locality estimation. Offloads nonessential metadata ops to GPU and integrates with Memcached, yielding up to 4.3× throughput/latency improvements. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Kefei Wang
- 2. Feng Chen
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,565 | Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation | 2025 | SIGMOD | 6.9655362e-05 |
| 9,529 | Mnemosyne: Dynamic Workload-Aware BF Tuning via Accurate Statistics in LSM trees | 2025 | SIGMOD | 4.32934e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 10 of 10 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next