日本データベース学会の皆様、首藤です。
分散システムやストレージの分野で影響の大きいお仕事を数多くされてきた
Willy Zwaenepoel 氏(シドニー大 工学部長)の御講演を、
オンラインおよび京都大学で催します。
分散共有メモリ TreadMarks や Nutanix 社をご存知の方は多いと思います。
タイトル:『Software for Fast Storage Hardware』
話者:Prof. Willy Zwaenepoel, Dean of Engineering, University of Sydney
場所:オンライン(Zoom)、および、京都大学 学術情報メディアセンター南館 202号室
(京大関係者以外が会場にいらっしゃる場合、首藤まで御一報下さい。)
日時:2022年 11月 30日(水) 13:15 ~ 14:15
オンライン参加の事前登録:
https://kyoto-u-edu.zoom.us/meeting/register/tZwkdOyrrT8rEtKMYsBB90lhOeK_j3…
(登録すると Zoom URL が返送されます。)
概要:
Storage technologies have entered the market with performance vastly
superior to conventional storage devices. This technology shift
requires a complete rethinking of the software storage stack.
In this talk I will give two examples of our work with Optane-based
solid-state (block) devices that illustrate the need for and the
benefit of a wholesale redesign.
First, I will describe the KVell key-value (KV) store. The key
observation underlying KVell is that conventional KV software on fast
devices is bottlenecked by the CPU rather than by the device. KVell
therefore focuses on minimizing CPU intervention.
Second, I will describe the KVell+ OLTP/OLAP system built on top of
KVell. The key underlying observation here is that these storage
devices have become so fast that the conventional implementation of
snapshot isolation – maintaining multiple versions – leads to
intolerable space amplification. Kvell+ therefore processes versions
as they are created.
This talk describes joint work with Oana Balmau (McGill University),
Karan Gupta (Nutanix) and Baptiste Lepers (University of Neuchatel).
経歴:
Willy Zwaenepoel received his BS from Ghent University in 1979, and
his MS and PhD from Stanford University, in 1980 and 1984,
respectively. He is currently dean of engineering at the University of
Sydney. Previously, he has been on the faculty at Rice University and
head of the school of computer and communication sciences at EPFL. He
has been involved with a number of startups including Nutanix
(Nasdaq:NTNX). He was elected IEEE Fellow in 1998, ACM Fellow in 2000
and ATSE Fellow in 2020. He received a number of awards for his
teaching and research, including the IEEE Kanai Award, the Eurosys
Lifetime Achievement Award, and the IEEE Outstanding Technical
Achievement in Distributed Processing Award. His main interests are in
operating systems and distributed systems.
首藤 一幸 shudo(a)media.kyoto-u.ac.jp http://www.shudo-lab.org/
京都大学 学術情報メディアセンター
日本データベース学会のみなさま
早稲田大学/Naver Corporationの酒井と申します。
ウェブ検索研究のポスドク(Naverと雇用契約、常勤、二年、更新余地あり)を募集いたします。
締切12/23。年収700万、初年度はプラス50万(但し書きあり)。
詳細はこちらです。
https://waseda.box.com/naver-postoc2023
ご検討いただければ幸いです。どうぞよろしくお願いいたします。
###
Professor Tetsuya Sakai (tetsuya(a)waseda.jp)
Department of Computer Science and Engineering, Waseda University
http://sakailab.com/tetsuya/
日本データベース学会の皆様
大阪大学の天方と申します。
ワークショップチェアに代わりましてご案内申し上げます。
以下、是非ご検討下さい。
====
国際会議IEEE MDM 2023が2023/7/3-6にシンガポールで開催されます。
https://mdmconferences.org/mdm2023/
MDM2023では併設ワークショップの提案を募集しています。
提案締切は12/9となっております。ぜひ、ワークショップの
提案をご検討ください。
---
*** IEEE MDM 2023: Call for Workshop Proposals ***
https://mdmconferences.org/mdm2023/wpcall.html
Several workshops will be held together with the IEEE MDM 2023 conference.
Workshops are planned to take place on July 3, 2023, the day before the
main conference, each of them running anywhere between half a day and a
full day.
The logistics of the workshops will be handled by the MDM 2023
organization. Specifically, MDM 2023 will take care of facilities,
catering, and the registration process pertinent to all hosted workshops.
The organizers of accepted workshops are required to announce the workshop
and call for papers, solicit submissions, invite and coordinate with PC
members to ensure that controversial submissions are resolved, and decide
upon the final workshop program that must be published at least two weeks
before the early registration deadline. The submission deadline of the
workshops must be set 1-2 weeks after the notification date of the main
conference. In addition, each workshop must collaborate with the
Proceedings Chair for the purpose of ensuring timely completion of the
camera-ready copies before April 28, 2023 (TBC), when official conference
proceedings are due. A workshop paper is allowed up to 6 proceedings pages.
Publication of call-for-papers and participation as well as eventual
workshop reports in various outlets are encouraged.
Proposal evaluation criteria include the following: relevance to MDM,
scientific quality, perceived interest and past performance (e.g., previous
submission counts and/or workshop participants), and overlap with other
proposals.
Important Dates:
----------------
The deadline for the receipt of proposals to be co-located with MDM 2023
is: December 9, 2022.
Notification of acceptance will occur by: December 23, 2022.
Submission Guidelines:
----------------------
Proposals need to include the following:
1.
Title and Acronym for the workshop.
2.
Concise description of the workshop scope/theme along with a (tentative)
list of topics.
3.
Names and contact info of the organizers.
4.
Preliminary list of (potential) PC members.
5.
Important milestones for the workshop (e.g., announcements, submission).
6.
Proposed duration (half-day or full-day workshop).
7.
Bio-sketches of the organizers.
8.
If the organizers have had such/similar workshops held in the past, a
brief history/description.
9.
Past performance (if applicable), e.g., previous submission counts and
workshop participants.
Please submit the workshop proposals as a PDF attachment to both the
following email addresses: kyriakos(a)smu.edu.sg, yasumoto(a)is.naist.jp. A
verification response will be returned for each submission.
The Review Process will be single-blind (i.e., the reviewers are not
identified).
Workshop Co-Chairs:
-------------------
日本データベース学会のみなさま
京都大学 杉山と申します。
ACM SIGIR 東京支部では、「12月13日 17時」から、
Suppawong Tuarob 准教授 (Mahidol University, Thailand) をお招きし、
"Faster, Sooner, Cheaper: Can Social Media Reflect Real-World Phenomena?"
というタイトルで、ご講演いただきます。
詳細は、以下のとおりです。どなたでも無料で参加できますが、以下のURLから
事前登録をお願い致します。
多くのみなさまのご参加を、お待ちしております。
----------
題目 (Title): "Faster, Sooner, Cheaper: Can Social Media Reflect Real-World
Phenomena?"
講演者 (Speaker): Suppawong Tuarob (Mahidol University, Thailand)
日時 (Date): 2022年12月13日 17:00-18:00 (December 13th, 2022, 17:00-18:00)
場所 (Venue): Zoomによるオンライン (Online via Zoom)
* 以下の事前登録フォームから、参加者の情報をご記入ください。後ほど、
ご登録いただいた電子メールアドレスに、Zoom URLをお送り致します。
(Please register your information via the following registration form.
We will send Zoom URL to your e-mail address later.)
https://docs.google.com/forms/d/e/1FAIpQLSeoQnokmaK_GcMZ5YwwfFcoS2pC-0PGulK…
概要 (Abstract):
Globally, online communities generate enormous volumes of data every day.
A common use of social networks is to give a timely and cost-effective
means of reflecting on real-world events. Although the applications of
information derived from social networks are numerous, only a tiny
portion of them are committed to improving society. For instance,
real-time analysis of Twitter data has been used to model earthquake
warning detection systems, identify medical and emergency needs during
recovery from natural disasters (such as the Haiti Earthquake), detect
the spread of influenza-like illnesses, and uncover abusive behaviors
in social networks. In addition, several studies have examined the use of
social media to monitor population-wide and individual health in the real
world, including drinking issues, epidemics, drug misuse, and mental
illness. Numerous research has shown that social media might be utilized
to track depression and public conversation during the COVID-19 epidemic.
This talk will examine applications that establish online social networks
as viable information sources for estimating real-world phenomena.
略歴(Biography):
Suppawong Tuarob received his PhD in computer science and engineering
and MS in industrial engineering from the Pennsylvania State University
and his BSE and MSE in computer science and engineering from the University
of Michigan-Ann Arbor. Currently, he is an Associate Professor of Computer
Science at Mahidol University, Thailand. His research involves data mining
in large-scale scholarly, social media, and healthcare domains.
対象(Target Audience):
ACM SIGIR 東京支部会員、一般
(Member of Tokyo ACM SIGIR Chapter, Public audience)
主催(Organizer):
本セミナーは、ACM SIGIR 東京支部の主催です。上記のURLから事前登録をして
くだされば、どなたでも無料で参加できます。
(This seminar is organized by Tokyo ACM SIGIR Chapter. Anyone can join if
you register your information via the above registration form URL.)
-----
杉山 一成
京都大学 情報学研究科 社会情報学専攻
(総合研究12号館112号室)
E-mail: kaz.sugiyama(a)i.kyoto-u.ac.jp, zakugus(a)gmail.com
URL: http://www.db.soc.i.kyoto-u.ac.jp/~sugiyama/