Author:
Avargues Miguel A.,Lurbe Manel,Petit Salvador,Gomez Maria E.,Yang Rui,Zhu Xiaoping,Wang Guanhao,Sahuquillo Julio
Abstract
AbstractSRAM and DRAM memory technologies have been dominant in the implementations of memory subsystems. In recent years, and mainly driven by the huge memory demands of big data applications, NVRAM technology has emerged as a denser memory technology, enabling the design of new hybrid DRAM/NVRAM memory hierarchies that combine multiple memory media technologies to balance memory capacity, latency, cost, and endurance. Two main approaches are being applied to the design of hybrid memory hierarchies: the hybrid address space approach, which relies on the programmer or the operating system to choose the memory technology where each memory page should be stored; and the (only) NVM address space approach, where a faster technology (e.g. commodity DRAM) is needed to acts as a cache of NVRAM to boost the performance. This approach presents architectural challenges such the organization of metadata (e.g. cache tags) and the selection of the proper technology for each memory component. In contrast to existing approaches, this work proposes a memory controller that leverages novel memory technologies such as eDRAM and MRAM to mitigate NVRAM bus contention and improve the performance of the NVM address space. The devised solution proposes a two-level cache hierarchy in the memory controller: a SRAM sector cache and a (x)RAM cache. The (x)RAM cache, much denser, helps significantly reduce the number of accesses to NVRAM. Experimental results show that implementing the (x)RAM cache with eDRAM or MRAM is the best performing approach. Moreover, the eRAM is able to improve the SRAM cache miss penalty by up to 50% and 80%, and overall system performance by 15% and 23%.
Funder
Huawei Technologies
Ministerio de Ciencia e Innovación
Publisher
Springer Science and Business Media LLC
Subject
Information Systems and Management,Computer Networks and Communications,Hardware and Architecture,Information Systems
Reference44 articles.
1. Altman A, Arafa M, Balasubramanian K, Cheng K, Damle P, Datta S, Douglas C, Gibson K, Graniello B, Grooms J, et al. Intel optane data center persistent memory. In: IEEE Hot Chips 31 Symposium (HCS). 2019; p. i–xxv.
2. Anghel A, Dittmann G, Jongerius R, Luijten R. Spatio-temporal locality characterization. 1st Workshop on Near-Data Processing (WoNDP). 2013; p. 1–5.
3. Apalkov D, Dieny B, Slaughter JM. Magnetoresistive random access memory. Proceed IEEE. 2016;104(10):1796–830.
4. Balasubramonian R, Jouppi NP. Multi-core cache hierarchies. Berlin: Springer; 2022.
5. Bock S, Childers BR, Melhem RG, Mossé D. Concurrent page migration for mobile systems with os-managed hybrid memory. Computing Frontiers Conference, CF’14, Cagliari, Italy, 2014; p. 31:1–31:10.