Enabling Efficient and Scalable Hybrid Memories Using Fine-Granularity DRAM Cache Management

Authors:
Justin Meza;Jichuan Chang;HanBin Yoon;Onur Mutlu;Parthasarathy Ranganathan
Affiliations:
Carnegie Mellon University, Pittsburgh;Hewlett-Packard Labs, Palo Alto;Carnegie Mellon University, Pittsburgh;Carnegie Mellon University, Pittsburgh;Hewlett-Packard Labs, Palo Alto
Venue:
IEEE Computer Architecture Letters
Year:
2012

Citing 0
Cited 3

Fundamental Latency Trade-off in Architecting DRAM Caches: Outperforming Impractical SRAM-Tags with a Simple and Practical Design

MICRO-45 Proceedings of the 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture
Die-stacked DRAM caches for servers: hit ratio, latency, or bandwidth? have it all with footprint cache

Proceedings of the 40th Annual International Symposium on Computer Architecture
ARI: Adaptive LLC-memory traffic management

ACM Transactions on Architecture and Code Optimization (TACO)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Hybrid main memories composed of DRAM as a cache to scalable non-volatile memories such as phase-change memory (PCM) can provide much larger storage capacity than traditional main memories. A key challenge for enabling high-performance and scalable hybrid memories, though, is efficiently managing the metadata (e.g., tags) for data cached in DRAM at a fine granularity. Based on the observation that storing metadata off-chip in the same row as their data exploits DRAM row buffer locality, this paper reduces the overhead of fine-granularity DRAM caches by only caching the metadata for recently accessed rows on-chip using a small buffer. Leveraging the flexibility and efficiency of such a fine-granularity DRAM cache, we also develop an adaptive policy to choose the best granularity when migrating data into DRAM. On a hybrid memory with a 512MB DRAM cache, our proposal using an 8KB on-chip buffer can achieve within 6% of the performance of, and 18% better energy efficiency than, a conventional 8MB SRAM metadata store, even when the energy overhead due to large SRAM metadata storage is not considered.