The 3rd International Workshop of Software-Defined Data Communications and Storage (SDDCS) 2017, in conjunction with ACM ASPLOS 2017, on April 8, 2017, in Xi'an, China.
Keynote Speech: Memory-Centric Architectures to Close the Gap Between Computing and Memory/Storage
Yuan Xie, University of California at Santa Barbara
Abstract: Traditional computer systems usually follow the so-called classic Von Neumann architecture, with separated processing units (such as CPUs and GPUs) to do computing and separated memory units for data storage. The increasing gap between the computing of processor and the memory has created the “memory wall” problem in which the data movement between the processing units (PUs) and the data storage is becoming the bottleneck of the entire computing system, ranging from cloud servers to end-user devices. As we enter the era of big data, many emerging data-intensive workloads become pervasive and mandate very high bandwidth and heavy data movement between the computing units and the memory/storage. This talk will discuss the design opportunities and challenges for memory-centric architecture, which is proposed to close the gap between computing and data storage, with the emerging data-intensive applications such as neural computing and graph analytics as application drivers to guide the architecture optimization.
Bio: Yuan Xie is a professor at UC Santa Barbara (UCSB). He received Ph.D. from Princeton University, and then joined IBM Microelectronics as advisory engineer. From 2003 to 2014 he was with Penn State as Assistant/Associate/Full professor. He also worked with AMD research between 2012-2013. His research interests include EDA/architecture/VLSI, and has published more than 200 papers in IEEE/ACM venues. He was elevated to IEEE Fellow for contributions in design automation and architecture for 3D ICs. He is currently the Editor-in-Chief for ACM Journal of Emerging Technologies in Computing Systems.
8:30-8:40 Opening Remarks
8:40-10:00 Invited Technical Talks-I
Leverage Software Defined Storage Devices with Enhanced Interface
Guangyu Sun, Peking University
Cache Partitioning and Data Placement for Hybrid DRAM-NVM Memory
Dejun Jiang, ICT, CAS
10:00-10:30 Coffee Break
10:30-11:30 Paper Presentation-I
Ning Zheng (Rensselaer Polytechnic Institute), Minjie Lv (Xi'an Jiaotong University) and Tong Zhang (Rensselaer Polytechnic Institute)
Raghavendra Rao Ananta, Jian Zhou and Jun Wang (University of Central Florida)
13:30-14:30 Keynote Speech
Memory-Centric Architectures to Close the Gap Between Computing and Memory/Storage
Yuan Xie, University of California at Santa Barbara
14:30-15:00 Invited Technical Talks-II
Software-Defined Data Center : the eight years practices in Baidu
Jian Ouyang, Baidu Inc.
15:00-15:30 Coffee Break
15:30-16:30 Paper Presentation-II
Haitao Wang, Zhanhuai Li, Xiao Zhang, Zhen Chen and Xiaonan Zhao (Northwestern Polytechnical University)
Tianming Jiang (Huazhong University of Science and Technology), Ping Huang (Temple University), Hao Xu (Baidu, Inc.), Yongfeng Ji (Baidu, Inc.), Wenjie Liu (Huazhong University of Science and Technology) and Ke Zhou (Huazhong University of Science and Technology)
Authors of accepted papers:
For one-page abstract of the accepted paper:
Single-spaced 8.5" x 11" pages, including figures, tables, and references; two-column format, using 10-point type on 12-point (single-spaced) leading; and a text block 6.5" wide x 9" deep.
For extended submissions to ACM TOS (after April 8):
All accepted papers must be presented in the workshop. The presented and selected papers need to follow the submission formats and requirements of ACM Transactions on Storage (TOS). The submission files need to include: (1) New manuscript, (2) Summary of changes (compared with 6-page workshop submission), (3) All review comments by SDDCS workshop and (4) Original workshop submission. Please indicate that this is an extended version from SDDCS 2017 workshop submission in the cover letter to facilitate identification.
Making an infrastructure “software defined” takes cross community efforts. Just like the theme of ASPLOS that brings together the architecture, systems and programming language community, SDDCS provides a multi-disciplinary forum for system research, spanning from storage devices, software systems, network virtualization and applications, focusing on the important problem of making future systems software-defined.
The future infrastructures of the data centers and cloud computing are becoming increasingly software-defined. Although the infrastructures consist of communications and storage resources, they are generally studied separately. Hence, applications and platforms have to precisely define the virtual environment in which they wish to run. The communication performance decreases due to overlooking the properties of storage devices, and vice versa. Software-defined methodologies offer an opportunity to bridge their gap and deliver high performance.
The SDDCS workshop provides the forum for multi-disciplinary research spanning data communications, networking, storage systems and devices, as well as the applications. SDDCS aims to bring together industry and academia to jointly explore recent progresses related to the potential performance bottleneck and the gap between communications and storage in the software-defined context. We particularly encourage contributions containing highly novel ideas, new approaches, and/or groundbreaking results.
Topics of interests in SDDCS include but are not limited to:
Software-defined memory system for cloud computing
Software-defined non-volatile devices
Convergent design for communications and storage
Non-volatile storage support for network transmission
Storage deduplication for remote cloud backups
Data collection and analytics for system optimization
Dynamic workload redistribution and scheduling
Non-volatile devices in network switches
Cross-layer coordination in data centers
Storage virtualization in data centers
Security for SDDCS schemes
Programmable interfaces for convergent design
User studies and experiences of
Submitted papers must be no longer than 6
single-spaced 8.5" x 11" pages, including figures, tables, and references;
two-column format, using 10-point type on 12-point (single-spaced) leading; and
a text block 6.5" wide x 9" deep. Author names and affiliations should appear on
the title page.
The submitted papers should present original theoretical and/or experimental research in any of the areas listed above that has not been previously published, accepted for publication, or is not currently under review by another conference or journal.
Submission Site: The Easychair submission
SDDCS workshop has no proceedings. The abstract will be put on the website. Selected and extended papers will be further recommended to ACM Transactions on Storage (TOS) for fast-track processing (no guarantee of acceptance).
Paper submission due: February 17, 2017 (11:59pm EDT)
Notification to authors: March 15, 2017
Final papers due: March 24, 2017
Yu Hua, Huazhong University of Science and Technology
Xue Liu, McGill University
Pin Zhou, Datos IO, Inc
Vaneet Aggarwal, Purdue University
Wei Xu, Tsinghua University
Jishen Zhao, University of California, Santa Cruz
Shaolei Ren, University of California, Riverside
Edith Ngai, Uppsala University
Program Committee Member:
Bharath Balasubramanian, AT&T Labs Research
Feng Chen, Louisiana State University
Darrell D. E. Long, University of California, Santa Cruz
Song Jiang, University of Texas, Arlington
Mahmut Kandemir, Pennsylvania State University
Hyojun Kim, Google
Scott Klasky, Oak Ridge National Laboratory
Tian Lan, George Washington University
Patrick P. C. Lee, The Chinese University of Hong Kong
Ao Ma, Uber
Rajesh Panta, AT&T Labs Research
Marco Paolieri, University of Southern California
Mohit Saxena, IBM Research
Alan Sussman, University of Maryland College Park
Itzhak Tamo, Tel Aviv University
Vasily Tarasov, IBM Research
Peter J. Varman, Rice University
Youjip Won, Hanyang University
Ming Zhao, Arizona State University
Qing Yang, University of Rhode Island
Hong Jiang, University of Texas at Arlington
Peng-Jun Wan, Illinois Institute of Technology