Prefetching in hybrid main memory systems
Article No.: 11, Page 11
Abstract
The architecture of main memory has experienced a paradigm shift in recent years, with non volatile memory technologies (NVM) like Phase Change Memory (PCM) being incorporated into the hierarchy at the same level as DRAM. This transformation is being carried out by either splitting the memory address across two or more memory technologies, or using a faster technology with higher lifetimes, typically the DRAM, as a cache for the higher capacity, albeit slower main memory made up of a NVM.
Design of such hybrid architectures remains an active area of research from the perspective of DRAM-as-a-cache design, since DRAM could quickly become the bottleneck, as cache lookups require multiple accesses for reading tag and data. In this paper, we augment the DRAM-as-a-cache model with a novel DRAM cache prefetcher that builds on state of the art Alloy Cache. The new DRAM cache architecture allows for prefetching data at both cacheline and page granularities from the NVM, and as a result, provides upto a maximum of 2× performance improvement over a state of the art baseline.
References
[1]
DRAM Scaling Challenges Grow. https://semiengineering.com/dram-scaling-challenges-grow/. Accessed: 21-03-2020.
[2]
Frank Bellosa. When physical is not real enough. In Proceedings of the 11th Workshop on ACM SIGOPS European Workshop, EW 11, page 25-es, New York, NY, USA, 2004. Association for Computing Machinery.
[3]
Christian Bienia, Sanjeev Kumar, Jaswinder Pal Singh, and Kai Li. The parsec benchmark suite: Characterization and architectural implications. In Proceedings of the 17th international conference on Parallel architectures and compilation techniques, pages 72-81, 2008.
[4]
Asif Ali Khan, Fazal Hameed, and Jeronimo Castrillon. Nvmain extension for multi-level cache systems. In Proceedings of the Rapido'18 Workshop on Rapid Simulation and Performance Evaluation: Methods and Tools, pages 1-6, 2018.
[5]
Benjamin C. Lee, Engin Ipek, Onur Mutlu, and Doug Burger. Architecting phase change memory as a scalable dram alternative. In Proceedings of the 36th Annual International Symposium on Computer Architecture, ISCA '09, page 2-13, New York, NY, USA, 2009. Association for Computing Machinery.
[6]
Gabriel H. Loh and Mark D. Hill. Efficiently enabling conventional block sizes for very large die-stacked dram caches. In Proceedings of the 44th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO-44, page 454-464, New York, NY, USA, 2011. Association for Computing Machinery.
[7]
Darsen Lu. Tutorial on emerging memory devices. Available at people.oregonstate.edu/~sllu/Micro_MT/presentations/micro16_emerging_mem_tutorial_darsen.pdf, 2016.
[8]
Sparsh Mittal and Jeffrey S Vetter. A survey of techniques for architecting dram caches. IEEE Transactions on Parallel and Distributed Systems, 27(6):1852-1863, 2015.
[9]
Moin Qureshi and Gabriel H Loh. Fundamental latency trade-offs in architecturing dram caches: Outperforming impractical sram-tags with a simple and practical design. In Proc. of the 45th Intl. Symp. on Microarchitecture, Vancouver, Canada, volume 10, 2012.
[10]
Daniel Sanchez and Christos Kozyrakis. Zsim: Fast and accurate microarchitectural simulation of thousand-core systems. ACM SIGARCH Computer architecture news, 41(3):475-486, 2013.
[11]
Shyamkumar Thoziyoor, N Muralimanohar, J Ahn, and N Jouppi. Cacti 6.5. hpl.hp.com, 2009.
[12]
Zi Yan, Ján Veselý, Guilherme Cox, and Abhishek Bhattacharjee. Hardware translation coherence for virtualized systems. In Proceedings of the 44th Annual International Symposium on Computer Architecture, ISCA '17, page 430-443, New York, NY, USA, 2017. Association for Computing Machinery.
Index Terms
- Prefetching in hybrid main memory systems
Index terms have been assigned to the content through auto-classification.
Recommendations
Power management of hybrid DRAM/PRAM-based main memory
DAC '11: Proceedings of the 48th Design Automation ConferenceHybrid main memory consisting of DRAM and non-volatile memory is attractive since the non-volatile memory can give the advantage of low standby power while DRAM provides high performance and better active power. In this work, we address the power ...
Migration based page caching algorithm for a hybrid main memory of DRAM and PRAM
SAC '11: Proceedings of the 2011 ACM Symposium on Applied ComputingAs the DRAM based main memory significantly increases the power and cost budget of a computer system, new memory technologies such as Phase-change RAM (PRAM), Ferroelectric RAM (FRAM), and Magnetic RAM (MRAM) have been proposed to replace the DRAM. ...
Redesign the Memory Allocator for Non-Volatile Main Memory
Special Issue on Hardware and Algorithms for Learning On-a-chip and Special Issue on Alternative Computing SystemsThe non-volatile memory (NVM) has the merits of byte-addressability, fast speed, persistency and low power consumption, which make it attractive to be used as main memory. Commonly, user process dynamically acquires memory through memory allocators. ...
Comments
Information & Contributors
Information
Published In
Copyright © 2020.
Sponsors
- ORACLE
- VMware
Publisher
USENIX Association
United States
Publication History
Published: 13 July 2020
Qualifiers
- Research-article
Acceptance Rates
Overall Acceptance Rate 34 of 87 submissions, 39%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 31Total Downloads
- Downloads (Last 12 months)15
- Downloads (Last 6 weeks)5
Reflects downloads up to 27 Jul 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in