Exploring the future of out-of-core computing with compute-local non-volatile memory

Myoungsoo Jung, Ellis H. Wilson, Wonil Choi, John Shalf, Hasan Metin Aktulga, Chao Yang, Erik Saule, Umit V. Catalyurek, Mahmut Kandemir

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Drawing parallels to the rise of general purpose graphical processing units (GPGPUs) as accelerators for specific high performance computing (HPC) workloads, there is a rise in the use of non-volatile memory (NVM) as accelerators for I/O-intensive scientific applications. However, existing works have explored use of NVM within dedicated I/O nodes, which are distant from the compute nodes that actually need such acceleration. As NVM bandwidth begins to out-pace point-to-point network capacity, we argue for the need to break from the archetype of completely separated storage. Therefore, in this work we investigate co-location of NVM and compute by varying I/O interfaces, file systems, types of NVM, and both current and future SSD architectures, uncovering numerous bottlenecks implicit in these various levels in the I/O stack. We present novel hardware and software solutions, including the new Unified File System (UFS), to enable fuller utilization of the new compute-local NVM storage. Our experimental evaluation, which employs a real-world Out-of-Core (OoC) HPC application, demonstrates throughput increases in excess of an order of magnitude over current approaches.

Original languageEnglish (US)
Title of host publicationProceedings of SC 2013
Subtitle of host publicationThe International Conference for High Performance Computing, Networking, Storage and Analysis
PublisherIEEE Computer Society
ISBN (Print)9781450323789
DOIs
StatePublished - Jan 1 2013
Event2013 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2013 - Denver, CO, United States
Duration: Nov 17 2013Nov 22 2013

Publication series

NameInternational Conference for High Performance Computing, Networking, Storage and Analysis, SC
ISSN (Print)2167-4329
ISSN (Electronic)2167-4337

Other

Other2013 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2013
CountryUnited States
CityDenver, CO
Period11/17/1311/22/13

Fingerprint

Data storage equipment
Particle accelerators
Interfaces (computer)
Computer systems
Throughput
Hardware
Bandwidth
Processing

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Software

Cite this

Jung, M., Wilson, E. H., Choi, W., Shalf, J., Aktulga, H. M., Yang, C., ... Kandemir, M. (2013). Exploring the future of out-of-core computing with compute-local non-volatile memory. In Proceedings of SC 2013: The International Conference for High Performance Computing, Networking, Storage and Analysis [75] (International Conference for High Performance Computing, Networking, Storage and Analysis, SC). IEEE Computer Society. https://doi.org/10.1145/2503210.2503261
Jung, Myoungsoo ; Wilson, Ellis H. ; Choi, Wonil ; Shalf, John ; Aktulga, Hasan Metin ; Yang, Chao ; Saule, Erik ; Catalyurek, Umit V. ; Kandemir, Mahmut. / Exploring the future of out-of-core computing with compute-local non-volatile memory. Proceedings of SC 2013: The International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE Computer Society, 2013. (International Conference for High Performance Computing, Networking, Storage and Analysis, SC).
@inproceedings{64cbd1052f1840e4b5b686ddccbc880d,
title = "Exploring the future of out-of-core computing with compute-local non-volatile memory",
abstract = "Drawing parallels to the rise of general purpose graphical processing units (GPGPUs) as accelerators for specific high performance computing (HPC) workloads, there is a rise in the use of non-volatile memory (NVM) as accelerators for I/O-intensive scientific applications. However, existing works have explored use of NVM within dedicated I/O nodes, which are distant from the compute nodes that actually need such acceleration. As NVM bandwidth begins to out-pace point-to-point network capacity, we argue for the need to break from the archetype of completely separated storage. Therefore, in this work we investigate co-location of NVM and compute by varying I/O interfaces, file systems, types of NVM, and both current and future SSD architectures, uncovering numerous bottlenecks implicit in these various levels in the I/O stack. We present novel hardware and software solutions, including the new Unified File System (UFS), to enable fuller utilization of the new compute-local NVM storage. Our experimental evaluation, which employs a real-world Out-of-Core (OoC) HPC application, demonstrates throughput increases in excess of an order of magnitude over current approaches.",
author = "Myoungsoo Jung and Wilson, {Ellis H.} and Wonil Choi and John Shalf and Aktulga, {Hasan Metin} and Chao Yang and Erik Saule and Catalyurek, {Umit V.} and Mahmut Kandemir",
year = "2013",
month = "1",
day = "1",
doi = "10.1145/2503210.2503261",
language = "English (US)",
isbn = "9781450323789",
series = "International Conference for High Performance Computing, Networking, Storage and Analysis, SC",
publisher = "IEEE Computer Society",
booktitle = "Proceedings of SC 2013",
address = "United States",

}

Jung, M, Wilson, EH, Choi, W, Shalf, J, Aktulga, HM, Yang, C, Saule, E, Catalyurek, UV & Kandemir, M 2013, Exploring the future of out-of-core computing with compute-local non-volatile memory. in Proceedings of SC 2013: The International Conference for High Performance Computing, Networking, Storage and Analysis., 75, International Conference for High Performance Computing, Networking, Storage and Analysis, SC, IEEE Computer Society, 2013 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2013, Denver, CO, United States, 11/17/13. https://doi.org/10.1145/2503210.2503261

Exploring the future of out-of-core computing with compute-local non-volatile memory. / Jung, Myoungsoo; Wilson, Ellis H.; Choi, Wonil; Shalf, John; Aktulga, Hasan Metin; Yang, Chao; Saule, Erik; Catalyurek, Umit V.; Kandemir, Mahmut.

Proceedings of SC 2013: The International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE Computer Society, 2013. 75 (International Conference for High Performance Computing, Networking, Storage and Analysis, SC).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Exploring the future of out-of-core computing with compute-local non-volatile memory

AU - Jung, Myoungsoo

AU - Wilson, Ellis H.

AU - Choi, Wonil

AU - Shalf, John

AU - Aktulga, Hasan Metin

AU - Yang, Chao

AU - Saule, Erik

AU - Catalyurek, Umit V.

AU - Kandemir, Mahmut

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Drawing parallels to the rise of general purpose graphical processing units (GPGPUs) as accelerators for specific high performance computing (HPC) workloads, there is a rise in the use of non-volatile memory (NVM) as accelerators for I/O-intensive scientific applications. However, existing works have explored use of NVM within dedicated I/O nodes, which are distant from the compute nodes that actually need such acceleration. As NVM bandwidth begins to out-pace point-to-point network capacity, we argue for the need to break from the archetype of completely separated storage. Therefore, in this work we investigate co-location of NVM and compute by varying I/O interfaces, file systems, types of NVM, and both current and future SSD architectures, uncovering numerous bottlenecks implicit in these various levels in the I/O stack. We present novel hardware and software solutions, including the new Unified File System (UFS), to enable fuller utilization of the new compute-local NVM storage. Our experimental evaluation, which employs a real-world Out-of-Core (OoC) HPC application, demonstrates throughput increases in excess of an order of magnitude over current approaches.

AB - Drawing parallels to the rise of general purpose graphical processing units (GPGPUs) as accelerators for specific high performance computing (HPC) workloads, there is a rise in the use of non-volatile memory (NVM) as accelerators for I/O-intensive scientific applications. However, existing works have explored use of NVM within dedicated I/O nodes, which are distant from the compute nodes that actually need such acceleration. As NVM bandwidth begins to out-pace point-to-point network capacity, we argue for the need to break from the archetype of completely separated storage. Therefore, in this work we investigate co-location of NVM and compute by varying I/O interfaces, file systems, types of NVM, and both current and future SSD architectures, uncovering numerous bottlenecks implicit in these various levels in the I/O stack. We present novel hardware and software solutions, including the new Unified File System (UFS), to enable fuller utilization of the new compute-local NVM storage. Our experimental evaluation, which employs a real-world Out-of-Core (OoC) HPC application, demonstrates throughput increases in excess of an order of magnitude over current approaches.

UR - http://www.scopus.com/inward/record.url?scp=84899675402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899675402&partnerID=8YFLogxK

U2 - 10.1145/2503210.2503261

DO - 10.1145/2503210.2503261

M3 - Conference contribution

SN - 9781450323789

T3 - International Conference for High Performance Computing, Networking, Storage and Analysis, SC

BT - Proceedings of SC 2013

PB - IEEE Computer Society

ER -

Jung M, Wilson EH, Choi W, Shalf J, Aktulga HM, Yang C et al. Exploring the future of out-of-core computing with compute-local non-volatile memory. In Proceedings of SC 2013: The International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE Computer Society. 2013. 75. (International Conference for High Performance Computing, Networking, Storage and Analysis, SC). https://doi.org/10.1145/2503210.2503261