Abstract
As fast storage media like Optane has emerged recently, the traditional memory and storage architecture consisting of DRAM and hard disk drive needs to be revisited. This paper explores the performance of emerging computing systems that adopt fast storage and analyzes the implications of such systems. If storage becomes very fast, the current memory and storage configurations need to be reassessed. This paper quantifies the performance of systems with fast storage through extensive measurement studies, and finds that decreasing the memory size does not degrade the performances if fast storage is made use of. The effect of I/O modes is also varied as fast storage is adopted. Specifically, the effect of synchronous write and direct I/O in fast storage is less significant than that in hard disks. Based on these observations, this paper discusses an emerging computing device with minimized memory size and fast storage, and compares it with conventional computer systems composed of regular memory size and slow disk storage. We argue that such new memory-storage setting may be used in future computing systems that should accommodate applications with ever growing memory footprints. We expect that our analysis will guide directions for designing a new memory and storage hierarchy of emerging computing devices.
Original language | English |
---|---|
Title of host publication | Proceedings - 2020 7th International Conference on Information Science and Control Engineering, ICISCE 2020 |
Editors | Shaozi Li, Ying Dai, Jianwei Ma, Yun Cheng |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 719-723 |
Number of pages | 5 |
ISBN (Electronic) | 9781728164069 |
DOIs | |
State | Published - Dec 2020 |
Event | 7th International Conference on Information Science and Control Engineering, ICISCE 2020 - Changsha, Hunan, China Duration: 18 Dec 2020 → 20 Dec 2020 |
Publication series
Name | Proceedings - 2020 7th International Conference on Information Science and Control Engineering, ICISCE 2020 |
---|
Conference
Conference | 7th International Conference on Information Science and Control Engineering, ICISCE 2020 |
---|---|
Country/Territory | China |
City | Changsha, Hunan |
Period | 18/12/20 → 20/12/20 |
Bibliographical note
Funding Information:ACKNOWLEDGMENT This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. 2019R1A2C1009275) and also by the ICT R&D program of MSIP/IITP (2019-0-00074, developing system software technologies for emerging new memory that adaptively learn workload characteristics).
Publisher Copyright:
© 2020 IEEE.
Keywords
- computing device
- fast storage
- hard disk
- memory hierarchy