Persistent Memory Object Storage and Indexing for Scientific Computing

Awais Khan; Hyogi Sim; Sudharshan S. Vazhkudai; Jinsuk Ma; Myeong Hoon Oh; Youngjae Kim

doi:10.1109/MCHPC51950.2020.00006

Persistent Memory Object Storage and Indexing for Scientific Computing

Awais Khan, Hyogi Sim, Sudharshan S. Vazhkudai, Jinsuk Ma, Myeong Hoon Oh, Youngjae Kim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

This paper presents Mosiqs, a persistent memory object storage framework with metadata indexing and querying for scientific computing. We design Mosiqs based on the key idea that memory objects on shared PM pool can live beyond the application lifetime and can become the sharing currency for applications and scientists. Mosiqs provides an aggregate memory pool atop an array of persistent memory devices to store and access memory objects. Mosiqs uses a lightweight persistent memory key-value store to manage the metadata of memory objects such as persistent pointer mappings, which enables memory object sharing for effective scientific collaborations. Mosiqs is implemented atop PMDK. We evaluate the proposed approach on many-core server with an array of real PM devices. The preliminary evaluation confirms a 100% improvement for write and 30% in read performance against a PM-aware file system approach.

Original language	English
Title of host publication	Proceedings of MCHPC 2020
Subtitle of host publication	Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-9
Number of pages	9
ISBN (Electronic)	9781665422789
DOIs	https://doi.org/10.1109/MCHPC51950.2020.00006
State	Published - Nov 2020
Externally published	Yes
Event	2020 IEEE/ACM Workshop on Memory Centric High Performance Computing, MCHPC 2020 - Virtual, Atlanta, United States Duration: Nov 11 2020 → …

Publication series

Name	Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference	2020 IEEE/ACM Workshop on Memory Centric High Performance Computing, MCHPC 2020
Country/Territory	United States
City	Virtual, Atlanta
Period	11/11/20 → …

Funding

This work was supported by Institute for Information communications Technology Planning Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2018-0-00503, researches on next generation memory-centric computing system architecture). This work was also supported by, and used the resources of, the Oak Ridge Leadership Computing Facility, located in the National Center for Computational Sciences at ORNL, which is managed by UT Battelle, LLC for the U.S. DOE (under the contract No. DE-AC05-00OR22725).

Funders	Funder number
Institute for Information communications Technology Planning Evaluation
U.S. Department of Energy	DE-AC05-00OR22725
Institute for Information and Communications Technology Promotion
Ministry of Science and ICT, South Korea

Keywords

Memory-centric Computing
Persistent Memory Storage
Scientific Metadata Indexing and Search

Access to Document

10.1109/MCHPC51950.2020.00006

Cite this

Khan, A., Sim, H., Vazhkudai, S. S., Ma, J., Oh, M. H., & Kim, Y. (2020). Persistent Memory Object Storage and Indexing for Scientific Computing. In Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 1-9). Article 9306949 (Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MCHPC51950.2020.00006

Khan, Awais ; Sim, Hyogi ; Vazhkudai, Sudharshan S. et al. / Persistent Memory Object Storage and Indexing for Scientific Computing. Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 1-9 (Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{10d2f73192094a7cb4c940cdf8b087cb,

title = "Persistent Memory Object Storage and Indexing for Scientific Computing",

abstract = "This paper presents Mosiqs, a persistent memory object storage framework with metadata indexing and querying for scientific computing. We design Mosiqs based on the key idea that memory objects on shared PM pool can live beyond the application lifetime and can become the sharing currency for applications and scientists. Mosiqs provides an aggregate memory pool atop an array of persistent memory devices to store and access memory objects. Mosiqs uses a lightweight persistent memory key-value store to manage the metadata of memory objects such as persistent pointer mappings, which enables memory object sharing for effective scientific collaborations. Mosiqs is implemented atop PMDK. We evaluate the proposed approach on many-core server with an array of real PM devices. The preliminary evaluation confirms a 100% improvement for write and 30% in read performance against a PM-aware file system approach.",

keywords = "Memory-centric Computing, Persistent Memory Storage, Scientific Metadata Indexing and Search",

author = "Awais Khan and Hyogi Sim and Vazhkudai, {Sudharshan S.} and Jinsuk Ma and Oh, {Myeong Hoon} and Youngjae Kim",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE/ACM Workshop on Memory Centric High Performance Computing, MCHPC 2020 ; Conference date: 11-11-2020",

year = "2020",

month = nov,

doi = "10.1109/MCHPC51950.2020.00006",

language = "English",

series = "Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--9",

booktitle = "Proceedings of MCHPC 2020",

}

Khan, A, Sim, H, Vazhkudai, SS, Ma, J, Oh, MH & Kim, Y 2020, Persistent Memory Object Storage and Indexing for Scientific Computing. in Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis., 9306949, Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis, Institute of Electrical and Electronics Engineers Inc., pp. 1-9, 2020 IEEE/ACM Workshop on Memory Centric High Performance Computing, MCHPC 2020, Virtual, Atlanta, United States, 11/11/20. https://doi.org/10.1109/MCHPC51950.2020.00006

Persistent Memory Object Storage and Indexing for Scientific Computing. / Khan, Awais; Sim, Hyogi; Vazhkudai, Sudharshan S. et al.
Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2020. p. 1-9 9306949 (Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Persistent Memory Object Storage and Indexing for Scientific Computing

AU - Khan, Awais

AU - Sim, Hyogi

AU - Vazhkudai, Sudharshan S.

AU - Ma, Jinsuk

AU - Oh, Myeong Hoon

AU - Kim, Youngjae

PY - 2020/11

Y1 - 2020/11

N2 - This paper presents Mosiqs, a persistent memory object storage framework with metadata indexing and querying for scientific computing. We design Mosiqs based on the key idea that memory objects on shared PM pool can live beyond the application lifetime and can become the sharing currency for applications and scientists. Mosiqs provides an aggregate memory pool atop an array of persistent memory devices to store and access memory objects. Mosiqs uses a lightweight persistent memory key-value store to manage the metadata of memory objects such as persistent pointer mappings, which enables memory object sharing for effective scientific collaborations. Mosiqs is implemented atop PMDK. We evaluate the proposed approach on many-core server with an array of real PM devices. The preliminary evaluation confirms a 100% improvement for write and 30% in read performance against a PM-aware file system approach.

AB - This paper presents Mosiqs, a persistent memory object storage framework with metadata indexing and querying for scientific computing. We design Mosiqs based on the key idea that memory objects on shared PM pool can live beyond the application lifetime and can become the sharing currency for applications and scientists. Mosiqs provides an aggregate memory pool atop an array of persistent memory devices to store and access memory objects. Mosiqs uses a lightweight persistent memory key-value store to manage the metadata of memory objects such as persistent pointer mappings, which enables memory object sharing for effective scientific collaborations. Mosiqs is implemented atop PMDK. We evaluate the proposed approach on many-core server with an array of real PM devices. The preliminary evaluation confirms a 100% improvement for write and 30% in read performance against a PM-aware file system approach.

KW - Memory-centric Computing

KW - Persistent Memory Storage

KW - Scientific Metadata Indexing and Search

UR - http://www.scopus.com/inward/record.url?scp=85099530904&partnerID=8YFLogxK

U2 - 10.1109/MCHPC51950.2020.00006

DO - 10.1109/MCHPC51950.2020.00006

M3 - Conference contribution

AN - SCOPUS:85099530904

T3 - Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 1

EP - 9

BT - Proceedings of MCHPC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE/ACM Workshop on Memory Centric High Performance Computing, MCHPC 2020

Y2 - 11 November 2020

ER -

Khan A, Sim H, Vazhkudai SS, Ma J, Oh MH, Kim Y. Persistent Memory Object Storage and Indexing for Scientific Computing. In Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc. 2020. p. 1-9. 9306949. (Proceedings of MCHPC 2020: Workshop on Memory Centric High Performance Computing, Held in conjunction with SC 2020: The International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1109/MCHPC51950.2020.00006

Persistent Memory Object Storage and Indexing for Scientific Computing

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this