Professor/Director Taisuke Boku in CCS received the Asia HPC Leadership Award of SCA20 (SuperComputingAsia 2020).
The Asia HPC Leadership Award recognises an outstanding individual with excellence in leadership, long standing contributions to the HPC community and held in high regard by their international peers.
For detail, please refer to the following URL.
SCA20 Awards
Professor/Director Taisuke Boku
国立大学法人筑波大学 計算科学研究センター 稲垣祐司教授、生命環境系 石田健一郎教授、独立行政法人国立科学博物館 動物研究部 谷藤吾朗研究主幹、国立大学法人東北大学 大学院生命科学研究科 中山卓郎助教、国立大学法人東京大学 アジア生物資源環境研究センター 岩滝光儀准教授らの研究グループは、渦鞭毛藻の新規系統であるMGD株とTGD株を発見し、両種において、細胞内共生をした藻類が葉緑体として遺伝的に統合される中途段階を見出しました。
光合成をおこなう真核生物（いわゆる藻類）の中には、細胞内共生した緑藻あるいは紅藻を葉緑体化した系統が複数あります。細胞内共生した緑藻や紅藻は葉緑体のみを残し、宿主細胞の一部となります。葉緑体化の過程では、共生した藻類が遺伝的にも宿主細胞に統合されますが、これまで適切な研究対象がなく、葉緑体化に必要な遺伝的な統合過程の詳細は不明のままでした。
本研究では渦鞭毛藻MGD株とTGD株の細胞内構造を精査し、渦鞭毛藻細胞内の葉緑体周辺に核のような構造を発見しました。その中にはDNAが存在し、それは共生藻由来の残存核（ヌクレオモルフ）であることが明らかとなりました。ヌクレオモルフはこれまで、クロララクニオン藻とクリプト藻でしか見つかっておらず、MGD株とTGD株は30年ぶりのヌクレオモルフをもつ新規系統の発見となります。また、網羅的な遺伝子解析により、多数の遺伝子が共生体核ゲノムから宿主核ゲノムへ転移していること、すなわち宿主細胞は共生藻を葉緑体として遺伝的に制御していることが判明しました。
さらに、どちらの渦鞭毛藻でも、宿主核ゲノムに転移した共生藻遺伝子のオリジナルコピーが共生藻ゲノムに残っていました。宿主核と共生藻核両方のゲノムに同一遺伝子がコードされている状態は、これまでに提唱されている遺伝子転移の中間的段階に相当しており、MGD株とTGD株は、実在の生物でその仮説を裏付けた初めての例となります。
渦鞭毛藻MGD株およびTGD株は、共生藻が宿主細胞へ遺伝的に統合されていく中途段階に相当する生物だと考えられ、葉緑体確立プロセスを理解するための鍵となることが期待されます。
本研究の成果は、2020年2月24日付Proc. Natl. Acad. Sci. U. S. A.で公開されました。
| Date | February 19th (Wed), 20th (Thu), 21st (Fri), 2020 |
| Place | Center for Computational Sciences, University of Tsukuba |
| Chair | Prof. William Gropp (National Center for Supercomputing Applications, USA) |
| Vice Chair | Prof. Masaki Sato (Atmosphere and Ocean Research Institute, The University of Tokyo, Japan) |
|
| Chair: K. Yabana | |
| 9:30-10:30 | Opening & Introduction to CCS (T. Boku, Director of CCS) |
| 10:30-11:00 | Activities and Results 2014-2018 (M.Umemura, ex-Director of CCS) |
| 11:00-11:20 | Coffee Break |
| Chair: H. Kitagawa | |
| 11:20-11:40 | Supercomputer-I: Oakforest-PACS System (O. Tatebe) |
| 11:40-12:00 | Supercomputer-II: Cygnus System (T. Boku, Director of CCS) |
| 12:00-12:20 | ILDG/JLDG activities (T. Yoshie) |
| 12:20-12:35 | Multidisciplinary Cooperative Research Program (T. Nakatsukasa) |
| 12:35-12:45 | Visiting Cygnus Supercomputer |
| 12:45-14:00 | Lunch |
| Chair: D. Takahashi | |
| 14:00-14:30 | REPORT: Division of Particle Physics(Y. Kuramashi) |
| 14:30-15:00 | REPORT: Division of Astrophysics (M. Umemura) |
| 15:00-15:30 | REPORT: Division of Nuclear Physics (T. Nakatsukasa) |
| 15:30-15:50 | Coffee Break |
| Chair: T. Amagasa | |
| 15:50-16:20 | REPORT: Division of Quantum Condensed Matter Physics (K. Yabana) |
| 16:20-16:50 | REPORT: Division of Life Science (Y. Shigeta & Y. Inagaki) |
| 16:50-17:20 | REPORT: Division of Global Environmental Science (H. Kusaka) |
| 17:20 | Wrapping up DAY-1 |
| 17:30-18:30 | Reception (Meeting Room A) |
| Chair: M. Umemura | |
| 9:30-10:00 | REPORT: Division of High Performance Computing Systems (T. Boku) |
| 10:00-10:30 | REPORT: Division of Computational Informatics: Database Group (H. Kitagawa) |
| 10:30-11:00 | REPORT: Division of Computational Informatics: Computational Media Group (Y. Kameda) |
| 11:00-11:20 | Coffee Break |
| Chair: Y. Shigeta | |
| 11:20-11:35 | Project Office for Exascale Computational Sciences (K. Yabana) |
| 11:35-11:50 | Project Office for Exascale Computing System Development (T. Boku) |
| 11:50-12:05 | Department of Computational Medical Science (M. Umemura) |
| 12:05-12:20 | Project Office for AI & Big Data (T. Amagasa) |
| 12:20-12:35 | Project Office for HPCI (Y. Kuramashi) |
| 12:35-14:00 | Lunch |
| 14:00-18:30 | Division of Particle Physics Reviewer: Chris Sachrajda |
Room: SB-1112 |
| Division of Astrophsyics Reviewer: Lars Hemquist |
Room: CCS-Workshop |
|
| Division of Nuclear Physics Reviewer: Pieter Maris |
Room: SB-911-1 |
|
| Division of Quantum Condensed Matter Physics Reviewer: Angel Rubio |
Room: CCS-C |
|
| Division of Life Science Reviewer: John Zhang |
Room: SB-1001 |
|
| Division of Global Environmental Science Reviewer: Masaki Sato, Shiguang Miao |
Room: CCS-B |
|
| Division of High Performance Computing Systems Reviewer: Hiroshi Nakashima, William Gropp |
Room: CCS-A |
|
| Division of Computational Informatics: Database Group Reviewer: Jeffrey Xu Yu |
Room: SB-911-2 |
|
| Division of Computational Informatics: Computational Media Group Reviewer: Bruce H. Thomas |
Room: SB-1111 |
|
| 19:00-21:00 | Committee Meeting with Dinner | |
| Chair: T. Nakatsukasa | |
| 9:30-9:45 | Liaison Office for Multidisciplinary Computational Sciences (D. Takahashi) |
| 9:30-10:00 | Promotion Office for Computational Sciences (D. Takahashi) |
| 10:00-10:15 | The Bureau of Public Relations and Strategy (K. Sekiya) |
| 10:15-10:35 | Coffee Break |
| 10:35-11:05 | Future Plan of CCS (T. Boku) |
| 11:05-12:40 | Private Lunch Meeting by Committee |
| 12:40-13:40 | Open Discussion |
Title: Enhancing Human performance using Virtual Reality, Wearable Computing, Cognitive Neuroscience and Mental Training
Speaker: Prof. Bruce H. Thomas (the University of South Australia)
Date: February 17, 2020 (Mon)
Time: 10:00-11:30
Venue: Center for Computational Sciences, International Workshop Room
Language: English
Abstract:
The talk will provide an over of IVE: Australian Research Centre for Interactive and Virtual Environments. Advanced and futuristic technologies, such as integrated augmented reality displays and drone
control systems. The cognitive impact of the user’s use of these technologies is important for designers of these systems, yet little research has been conducted in this area. The experiment presented in this work we measured brain alpha power while participants completed a maze navigation task, aided by a virtual drone and augmented reality-like annotations in a virtual environment. Different conditions were designed to test whether varying drone control systems and visualizations could result in different measured alpha power. The results show that alpha power fluctuations are sensitive to manipulation of the virtual drone control system, making it a powerful and potentially real-time measure of a control system’s difficulty of use and cognitive impact on the user.
Coordinator :Yoshinari Kameda
第134回計算科学コロキウムを、2月17日（月）に開催いたします。多数のご来聴をお待ちしております。
場所：筑波大学 計算科学研究センター 国際ワークショップ室
日時：2020年2月17日（月）10:00-11:30
講演タイトル：
Enhancing Human performance using Virtual Reality, Wearable Computing, Cognitive Neuroscience and Mental Training
講演者氏名：Prof. Bruce H. Thomas (the University of South Australia)
使用言語：英語
アブストラクト：
The talk will provide an over of IVE: Australian Research Centre for Interactive and Virtual Environments. Advanced and futuristic technologies, such as integrated augmented reality displays and drone control systems. The cognitive impact of the user’s use of these technologies is important for designers of these systems, yet little research has been conducted in this area. The experiment presented in this work we measured brain alpha power while participants completed a maze navigation task, aided by a virtual drone and augmented reality-like annotations in a virtual environment. Different conditions were designed to test whether varying drone control systems and visualizations could result in different measured alpha power. The results show that alpha power fluctuations are sensitive to manipulation of the virtual drone control system, making it a powerful and potentially real-time measure of a control system’s difficulty of use and cognitive impact on the user.
世話人：亀田能成
計算科学研究センター 計算情報学研究部門の北原 格教授が、筑波大学2019 BEST FACULTY MEMBERに選ばれました。
表彰式
日 時： 2020年2月10日（月）14:00-16:40
配信会場： 中央図書館本館2階チャットフレームC
次 第： 14:00－ 14:30 表彰式
14:30－ 16:40 表彰された教員による講演
詳しくは大学ホームページをご覧ください。
Title: I/O on Hierarchical Storage Systems: The Past, Present, and Future
Speaker: Dr. Kathryn Mohror (Lawrence Livermore National Laboratory)
Date: February 12, 2020 (Wed)
Time: 13:00-14:00
Venue: Center for Computational Sciences, International Workshop Room
Language: English
Abstract:
High-end supercomputing systems generally achieve increased computing
speeds by increasing the number of computing cores in the system. This
strategy is successful in achieving system FLOP goals, but as
applications running on theses systems complete their compute
activities more quickly or at a finer granularity, they ingest and
produce data at faster rates. The performance of data management tasks
is critical for achieving practical scientific throughput on
leadership class systems, but data management infrastructure is
generally an afterthought compared to the spotlight given to compute
infrastructure. In this talk, I will discuss issues surrounding I/O
and data management performance on high-end systems and several
strategies that we have employed over the years to address these
issues. In particular, I will discuss multilevel checkpointing with
the Scalable Checkpoint/Restart Library (SCR) and disjoint storage
utilization with the UnifyFS burst buffer file system. Additionally, I
will briefly discuss our plans for supporting more complex application
workflows on future platforms.
Biography：
Kathryn Mohror is the Group Leader for the Data Analysis Group in the
Center for Applied Scientific Computing (CASC) at Lawrence Livermore
National Laboratory (LLNL). Kathryn’s research on high-end computing
systems is currently focused on I/O for extreme scale systems. Her
other research interests include scalable performance analysis and
tuning, fault tolerance, and parallel programming paradigms. Kathryn
has been working at LLNL since 2010 and is a 2019 recipient of the DOE
Early Career Award.
Kathryn’s current research focuses primarily on user-level file
systems for HPC in the Unify project and on scalable I/O with the
Scalable Checkpoint/Restart Library (SCR), an R&D100 Award-winning
multilevel checkpointing library that has been shown to significantly
reduce checkpointing overhead. She is also a Co-Chair of the
Administrative Steering Committee for PMIx, a portable interface for
tools and applications to interact with system management
software. She was the lead for the Tools Working Group for the MPI
Forum from 2013-2019 and served as the Scientific Editor for LLNL’s
Science & Technology Review in 2018.
Kathryn received her Ph.D. in Computer Science in 2010, an M.S. in
Computer Science in 2004, and a B.S. in Chemistry in 1999 from
Portland State University (PSU) in Portland, OR.
Coordinator :Osamu Tatebe
第133回計算科学コロキウムを、2月12日（水）に開催いたします。多数のご来聴をお待ちしております。
場所：筑波大学 計算科学研究センター 国際ワークショップ室
日時：2020年2月12日（水）13:00-14:00
講演タイトル：
I/O on Hierarchical Storage Systems: The Past, Present, and Future
講演者氏名：Dr. Kathryn Mohror (Lawrence Livermore National Laboratory)
使用言語：英語
アブストラクト：
High-end supercomputing systems generally achieve increased computing
speeds by increasing the number of computing cores in the system. This
strategy is successful in achieving system FLOP goals, but as
applications running on theses systems complete their compute
activities more quickly or at a finer granularity, they ingest and
produce data at faster rates. The performance of data management tasks
is critical for achieving practical scientific throughput on
leadership class systems, but data management infrastructure is
generally an afterthought compared to the spotlight given to compute
infrastructure. In this talk, I will discuss issues surrounding I/O
and data management performance on high-end systems and several
strategies that we have employed over the years to address these
issues. In particular, I will discuss multilevel checkpointing with
the Scalable Checkpoint/Restart Library (SCR) and disjoint storage
utilization with the UnifyFS burst buffer file system. Additionally, I
will briefly discuss our plans for supporting more complex application
workflows on future platforms.
Biography：
Kathryn Mohror is the Group Leader for the Data Analysis Group in the
Center for Applied Scientific Computing (CASC) at Lawrence Livermore
National Laboratory (LLNL). Kathryn’s research on high-end computing
systems is currently focused on I/O for extreme scale systems. Her
other research interests include scalable performance analysis and
tuning, fault tolerance, and parallel programming paradigms. Kathryn
has been working at LLNL since 2010 and is a 2019 recipient of the DOE
Early Career Award.
Kathryn’s current research focuses primarily on user-level file
systems for HPC in the Unify project and on scalable I/O with the
Scalable Checkpoint/Restart Library (SCR), an R&D100 Award-winning
multilevel checkpointing library that has been shown to significantly
reduce checkpointing overhead. She is also a Co-Chair of the
Administrative Steering Committee for PMIx, a portable interface for
tools and applications to interact with system management
software. She was the lead for the Tools Working Group for the MPI
Forum from 2013-2019 and served as the Scientific Editor for LLNL’s
Science & Technology Review in 2018.
Kathryn received her Ph.D. in Computer Science in 2010, an M.S. in
Computer Science in 2004, and a B.S. in Chemistry in 1999 from
Portland State University (PSU) in Portland, OR.
世話人：建部 修見
Center for Computational Sciences, University of Tsukuba, is inviting applications for the post of Full Professor or Associate Professor in Division of Quantum Condensed Matter Physics.
Position:
Full Professor or Associate Professor, full-time, tenured.
Affiliation:
Division of Quantum Condensed Matter Physics
Center for Computational Sciences, University of Tsukuba
https://www.ccs.tsukuba.ac.jp
Contents of work, Research field:
Theoretical condensed matter physics in a broad sense. Center for Computational Sciences is promoting “Multidisciplinary Computational Science” through enhanced cooperation between, and the fusion of, computational and computer sciences. The successful candidate is expected to contribute actively to the mission of the Center. The candidate will also take part in education and supervision in College of Physics (undergraduate) and Degree Program in Physics, Graduate School of Science and Technology.
Qualifications:
Applicants must hold a Ph. D.
Expected Start Date:
The earliest possible date after the hiring decision is made.
Term of Employment, Compensation:
Tenured. The University has mandatory retirement, requiring employees to retire at age 65. Salary, working hours, social insurance, etc. are based on regulations of University of Tsukuba.
Closing Date for Application:
Applications must be received by March 27, 2020.
Selection Process:
Selection will be based on a comprehensive review of applications and interviews.
Required Documents:
The following (1) to (8) has to be e-mailed with PDF format. An incomplete document may not be accepted.
(1) Note for an expected position (full professor, associate professor, or either)
(2) Curriculum Vitae (with photograph)
(3) List of publications (separate lists for refereed and non-refereed papers)
(4) Summary of research activities
(5) Research and education plan
(6) List of research grants
(7) Reprints of five major papers (Four or more should be published within last five years)
(8) Two and more reference letters, or names and contact information of two or more reference persons. The reference letters should be sent directly to
koubo-condmat[at]ccs.tsukuba.ac.jp ([at] should be replaced with @)
with the subject line “Reference-NAME” where NAME is the applicant’s name.
Contact Information:
Prof. Kazuhiro Yabana
Division of Quantum Condensed Matter Physics,
Center for Computational Sciences, University of Tsukuba
Tel: +81-29-853-4202
Email: yabana[at]nucl.ph.tsukuba.ac.jp ([at] should be replaced with @)
Submission:
Application materials (1)-(6) should be combined into a single PDF file with a password. This PDF file together with PDF files of major papers (7) should be submitted by e-mail to the following address:
koubo-condmat[at]ccs.tsukuba.ac.jp ([at] should be replaced with @).
The subject line should be written as “Application for Division of Quantum Condensed Matter Physics”. The password of the PDF file should be sent by e-mail to the following address:
yabana[at]nucl.ph.tsukuba.ac.jp ([at] should be replaced with @).
Contact us if you do not receive confirmation within two days after you submit the documents.
Other:
1．公募する職名・人数
教授または准教授・１名
2．所属部門、講座、研究室等
計算科学研究センター量子物性研究部門
3．専門分野、仕事の内容
広い意味の物性理論分野。計算科学研究センターにおける学際計算科学の活動に意欲的に取り組み、研究と教育に熱意を持つ方を望みます。理工学群物理学類、数理物質科学研究群（物理学学位プログラム）において、教育・研究指導を担当します。
4．着任時期
決定後できるだけ早い時期
5．任期
なし (定年は筑波大学規則に従う)
6．応募資格
博士の学位を有する者
7．提出書類
以下の(1)-(7)の内容を含む電子ファイルをメールで送付してください。
（１）希望する職位（「教授希望」「准教授希望」「教授または准教授希望」のいずれか）
（２）履歴書（写真添付）
（３）業績リスト（査読論文とその他を区別すること）
（４）これまでの研究の概要
（５）着任後の研究計画と教育に関する抱負
（６）外部資金の獲得状況
（７）主要論文別刷５編（うち４編以上は最近5年以内のもの）
（８）意見書2通以上、または照会可能者2名以上の氏名・所属・連絡先
意見書は、作成者が応募書類の送付先に直接電子メールの添付ファイルとして送付してください。メールの件名は、「〇〇氏意見書」または「Reference-Name」（Nameは応募者の氏名）としてください。
8．応募締切
2020年3月27日(金)必着
9．問い合わせ先
筑波大学計算科学研究センター量子物性研究部門主任 矢花一浩
Tel: 029-853-4202
Email: yabana[at]nucl.ph.tsukuba.ac.jp （[at]を@に置き換える）
10．応募書類送付先
提出書類の(1)-(6)を一つのPDFファイルにまとめパスワードをかけ、(7)の各論文のPDFファイルとともに電子メールの添付ファイルとして、下記のアドレス
koubo-condmat[at]ccs.tsukuba.ac.jp （[at]を@に置き換える）
にお送りください。PDFファイルのパスワードは、別途下記のアドレス
yabana[at]nucl.ph.tsukuba.ac.jp （[at]を＠に置き換える）
にお送りください。ファイルサイズの合計が10MBを超える場合は、問い合わせ先に連絡してください。メールの件名は、「量子物性研究部門応募書類」としてください。メール送信後、２日以内に受領確認のメールが届かない場合は、問い合わせ先に連絡してください。
11．その他
(1) 応募書類に含まれる個人情報は、本人事選考のみに使用し、他の目的には一切使用しません。選考終了後はすべての個人情報を適切に破棄します。
(2) 計算科学研究センターは、文部科学省共同利用・共同研究拠点に認定されており、計算機共同利用を含む学際計算科学を推進しています。筑波大学では男女雇用機会均等法を遵守した人事選考を行っています。
第132回計算科学コロキウムを、1月21日（火）に開催いたします。多数のご来聴をお待ちしております。
場所：筑波大学 計算科学研究センター 国際ワークショップ室
日時：2020年1月21日（火）13:00-14:50
プログラム
| 13:00-13:50 | 高速流体解析プログラムの高速化チューニング ー FX100から「富岳」へ ー 高木 亮治 先生（JAXA宇宙科学研究所・准教授） |
| 休憩（10分） | |
| 14:00-14:50 | 「はやぶさ2」関連の可視化 三浦 昭 先生（JAXA宇宙科学研究所・助教） |
使用言語：日本語
世話人：重田育照
The mission of CCS is the promotion of “Multidisciplinary Computational Science” through enhanced cooperation and fusion of computational and computer sciences. For that purpose, the CCS provides a part of resources of supercomputer systems to Multidisciplinary Cooperative Research Program (MCRP).
The application for MCRP in 2020 is open now.
Application for MCRP *Online submission only
Deadline of online submission：January 31, 2020 (24:00 JST)
2020年度筑波大学計算科学研究センター「学際共同利用」プログラムの公募が始まりました。
詳しくは学際共同利用のページをご覧ください。
奮ってのご応募をお持ち申し上げます。
公募締切：2020年1月31日（金）
計算科学研究センターの原田 隆平准教授が分子シミュレーション学会2019年度学術賞を受賞いたしました（受賞日：2019年12月10日）。
受賞業績は以下の通りです。
受賞業績：タンパク質の機能発現に重要なレアイベントを抽出するサンプリング手法の開発
Researchers at the University of Tsukuba develop a machine-learning algorithm for automatically classifying the sleep stages of lab mice. Combining two techniques, they achieve 96.6% accuracy, which may help accelerate sleep research
Tsukuba, Japan – Researchers at the University of Tsukuba have created a new artificial intelligence program for automatically classifying the sleep stages of mice that combines two popular machine learning methods. Dubbed “MC-SleepNet,” the algorithm achieved accuracy rates exceeding 96% and high robustness against noise in the biological signals. The use of this system for automatically annotating data can significantly assist sleep researchers when analyzing the results of their experiments.
Scientists who study sleep often use mice as animal models to better understand the ways the activity in the brain changes during the various phases. These phases can be classified as awake, REM (rapid eye movement) sleep, and non-REM sleep. Previously, researchers who monitored the brainwaves of sleeping mice ended up with mountains of data that needed to be laboriously labeled by hand, often by teams of students. This represented a major bottleneck in the research.
Now, researchers at the University of Tsukuba have introduced a program for automatically classifying the stage of sleep that a mouse experienced based on its electroencephalogram (EEG) and electromyogram (EMG) signals, which record electrical activity in the brain and body, respectively. They combined two machine learning techniques, convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent neural networks, to achieve accuracies that surpass those of the best existing automatic methods.
“Machine learning is an exciting new field of research with important applications that combine medicine with computer science. It allows us to automatically classify new data based on labeled examples,” corresponding author Kazumasa Horie explains. This is especially valuable when the patterns to look for are not well known, as with sleep stages. In this way, the algorithm can ‘learn” how to make complex decisions without being explicitly programed. In this project, the accuracy was very high because of the large dataset used. With over 4,200 biological signals, it was the biggest dataset of any sleep research so far. Also, by implementing a CNN, the algorithm showed high robustness against individual differences and noise.
The main advance in this work was to divide the task between the two machine learning methods. First a CNN was used to extract features of interest from the recordings of the electrical activity in the brain and body. These data were then passed to an LSTM to determine which features were most indicative of the sleep phase the mouse was experiencing. “We are optimistic that we can translate this work into classifying sleep stages in humans”, senior author Hiroyuki Kitagawa says. In the meantime, this program can already speed up the work of researchers in the field of sleep, which may lead to a much clearer understanding of how sleep operates.
The work is published in Scientific Reports as “MC-SleepNet: Large-scale Sleep Stage Scoring in Mice by Deep Neural Networks” (doi:10.1038/s41598-019-51269-8)
Date: December 3rd (Tue) – 4th (Wed), 2019
Venue: International Workshop Room, Center for Computational Sciences, University of Tsukuba
| 09:30-10:00 | Recent Activities in CCS (Taisuke Boku, CCS, University of Tsukuba) |
| 10:00-10:30 | The UK Exascale Roadmap (Mark Parsons , EPCC, The University of Edinburgh) |
| 10:30-10:45 | BREAK |
| 10:45-11:15 | Development of FPGA-GPU combined application and FPGA-FPGA communication system (Norihisa Fujita, CCS, University of Tsukuba) |
| 11:15-11:45 | Crossing the chasm: Accelerating HPC codes using FPGAs (Nick Brown, EPCC, The University of Edinburgh) |
| 11:45-12:15 | NGIO: Next generation I/O for HPC (Michele Weiland, EPCC, The University of Edinburgh) |
| 12:15-13:30 | LUNCH |
| 13:30-14:00 | Accuracy improvement of Block Krylov subspace methods for linear systems with multiple right-hand sides (Hiroto Tadano, CCS, University of Tsukuba) |
| 14:00-14:30 | Analysis of parallel I/O use on the UK national supercomputing service, ARCHER using Cray’s LASSi and EPCC SAFE (Juan Herrera, EPCC, The University of Edinburgh) |
| 14:30-15:00 | Proactive preservation activities of cultural heritage by crowdsourcing (Hidehiko Shishido, CCS, University of Tsukuba) |
| 15:00-15:15 | BREAK |
| 15:15-15:45 | Accelerating regular path queries using FPGA (Kento Miura, CCS, University of Tsukuba) |
| 15:45-16:15 | Delivering easy-to-use frameworks to empower data-driven research (Rosa Filgueira, EPCC, The University of Edinburgh) |
| 16:15-16:45 | Application of Tensor Renormalization Group to Particle Physics (Yoshinobu Kuramashi, CCS, University of Tsukuba) |
| 16:45-17:15 | Future climate projection considering the coupled effects of global warming and local urbanization (Doan Quang Van, CCS, University of Tsukuba) |
| 09:30-10:00 | A New TDDFT Method for Isolated Systems (Xiao-Min Tong, CCS, University of Tsukuba) |
| 10:00-10:30 | Simulations of galaxy formation with radiative transfer and its application for near-infrared bio-imaging (Hidenobu Yajima, CCS, University of Tsukuba) |
| 10:30-11:00 | Extreme scale computational imaging for radio astronomy and medical imaging (Adrian Jackson, EPCC, The University of Edinburgh) |
| 11:00-11:30 | Phylogenomic analyses unveiled multiple endosymbioses of pedinophycean green algae in distantly related dinoflagellates (Yuji Inagaki, CCS, University of Tsukuba) |
| 11:30-12:30 | FUTURE PLAN & WRAP UP |
| 12:30- | LUNCH |
筑波大学計算科学研究センターでは、NVIDIA社の協力の下、OpenACC言語によるGPUコンピューティングに関するセミナー「GPU Bootcamp」を開催します。OpenACCやGPUの初心者の方からある程度経験のある方まで、どなたでも自由に参加頂けます。参加費は無料です。
特に、筑波大学計算科学研究センターのGPU+FPGAクラスタであるCygnusのユーザの方、これから同システムを使ってみようという方の積極的な参加を歓迎します。
GPU Bootcamp は科学者や研究者の方々が、GPU コンピューティングを始めるのに必要なスキルを、素早く学ぶためのイベントです。このイベントでは、以下のことを学びます。
① GPU コンピューティングと、GPU プログラミングの概要
② OpenACC の基礎（講義、ハンズオン、ミニアプリの GPU 化チャレンジ）
—————————————————————
開催日時 ：2019年 12月2日(月) 10:00 – 18:00
場所 ：筑波大学 計算科学研究センター ワークショップ室(https://www.ccs.tsukuba.ac.jp/)
モデレータ ：丹 愛彦 (エヌビディア合同会社)
申込期限 ：2019年 11月29日（金）17:00
申込方法 ：下記ページの申し込みフォームより、お申込みください。
https://forms.gle/Fr3bEkQAfqRZaHdc6
—————————————————————
＊参加者の方は、【受講に際しまして】を必ずご確認下さい。
Part 1: OpenACC で始める GPU Computing (10:00 – 12:00)
– GPU programming 入門
– OpenACC 入門
– OpenACC によるデータ管理
昼食: 12:00-13:00（昼食の用意はございません。学内の食堂等を適宜ご利用下さい。）
Part 1: OpenACC で始める GPU Computing (続き) (13:00-14:00)
– はじめての Gangs, Workers, and Vectors
Part 2: ミニアプリ チャレンジ (14:00 – 18:00)
休憩: 適宜
【受講に際しまして】
– Cygnusアカウントをお持ちでない方はセミナー用のゲストアカウントを作成いたしますので、ssh公開鍵を kobayashi at cs.tsukuba.ac.jp (at は @ に置き換えてください) までご送付ください。
– 当日は参加者ご自身でノートPCを持参して頂き、そこからハンズオンセッションで使用するスーパーコンピュータ (Cygnus) に ssh でログインして頂きます。ログインに必要な情報はこちらで提供しますが、ssh ログイン環境及び無線LANが備わっているPCをご持参下さい。
– エディタ(vi や emacs など) による、ファイルの編集ができる必要があります。
– Linux でのコマンドライン操作の経験があることが望ましいです。
募集人員： 研究員 1名
所属組織： 筑波大学 計算科学研究センター 宇宙物理研究部門
専門分野： 宇宙物理学（理論または観測）
職務内容：
計算科学研究センター宇宙物理研究部門では，科学研究費 基盤研究(A)「多重AGNの統合研究で紐解く超巨大ブラックホールの起源」（2019年度～2023年度，代表者 梅村雅之）に基づき，観測研究者と連携し超巨大ブラックホールと銀河の共進化に関わる研究を推進しています。本研究では，詳細な理論シミュレーションと，新たなサーベイ観測を組み合わせて，多重AGNをもつ原始銀河の統合アプローチにより共進化過程の解明を目指しています。理論では，銀河形成シミュレーションに多重AGNの形成・進化を取り入れた新たなモデルを構築します。観測では，すばる望遠鏡/HSC用の新たな狭帯域フィルター(NB506)を製作し，赤方偏移2～3における多重AGNの候補天体を探査し，面分光追観測を実施します。本公募では，この科学研究費による研究員として，理論もしくは観測的なアプローチで本研究に参画して頂ける方を求めます。
着任時期： 2020年4月1日
任 期： 2023年3月31日まで（1年間延長の可能性あり）
給 与： 年俸制（本学規則による）（年俸額は，経歴等を考慮し決定）
応募資格： 博士の学位を有する者又は2020年3月に博士の学位取得見込みの方
提出書類：
（1）履歴書（写真貼付）
（2）業績リスト（査読論文とその他を区別すること）
（3）これまでの研究の概要
（4）研究計画と今後の抱負
（5）照会可能者２名以上の氏名・連絡先
応募締切： 2020年1月10日（金）17:00 必着
応募方法：
上記提出書類を一つのpdfファイルにし，電子メールの添付ファイルにて
umemura_AT_ccs.tsukuba.ac.jp （_AT_を@に置き換え）
に送付してください。
（応募者には，受領の返信をしますので確認してください。）
問合せ先：〒305-8577 茨城県つくば市天王台 1-1-1
筑波大学計算科学研究センター 梅村 雅之
Tel: 029-853-6494, Email: umemura_AT_ccs.tsukuba.ac.jp
その他：
筑波大学では男女雇用機会均等法を遵守した人事選考を行っています。
◆We will have a booth talk session in Exhibition at SC19!
We invited the three specialists who are developing some feature/technology to utilize recent FPGA chips with high speed (up to 100Gbps) optical links. It is a good opportunity to share the knowledge/experience/technology on how to utilize it on HPC and other applications.
Booth Talk Schedule @Booth #1943
Nov. 20 (Wed)
| 14:00–14:15 | Taisuke Boku CCS, University of Tsukuba “CIRCUS: Computation/Communication Unified Framework on FPGA and its optical link” |
| 14:15-14:30 | Torsten Hoefler ETHZ “MPI-style streaming messaging on FPGAs” |
| 14:30-14:45 | Kentaro Sano R-CCS, RIKEN “Networks of FPGA Cluster with High Flexibility of Resource Allocation” |
Taisuke Boku “CIRCUS: Computation/Communication Unified Framework on FPGA and its optical link”
Abstract:
The latest FPGA provides multiple ports of very high performance external communication links as well as large capacity of logic elements for computation and memory. For various HPC applications, we are developing a framework to realize computation and communication unification in pipelined manner with easy API utilized on user-level OpenCL programming. This system is named CIRCUS (Communication Integrated Reconfigurable CompUting System) working on our new multi-hybrid cluster Cygnus in CCS, University of Tsukuba. In this talk we will present the concept and overview of the system with several performance evaluation.
Torsten Hoefler “MPI-style streaming messaging on FPGAs”
Abstract:Distributed memory programming is the established paradigm used in high-performance computing (HPC) systems, requiring explicit communication between nodes and devices. When FPGAs are deployed in distributed settings, communication is typically handled either by going through the host machine, sacrificing performance, or by streaming across fixed device-to-device connections, sacrificing flexibility. We present Streaming~Message~Interface~(SMI), a communication model and API that unifies explicit message passing with a hardware-oriented programming model, facilitating minimal-overhead, flexible, and productive inter-FPGA communication. Instead of bulk transmission, messages are streamed across the network during computation, allowing communication to be seamlessly integrated into pipelined designs. We present a high-level synthesis implementation of SMI targeting a dedicated FPGA interconnect, exposing runtime-configurable routing with support for arbitrary network topologies, and implement a set of distributed memory benchmarks. Using SMI, programmers can implement distributed, scalable HPC programs on reconfigurable hardware, without deviating from best practices for hardware design.
Title: Subgraph Isomorphism Search: Overview and State-of-the-Art Approaches
Speaker: John Wang（Associate Professor, Griffith University, Australia）
Date: November 18, 2019 (Mon)
Time: 10:30-11:30
Venue: Center for Computational Sciences, Meeting Room A
Language: English
Abstract:
Given data graph G and query graph P, subgraph isomorphism search is to find subgraphs of G that are isomorphic (i.e., structurally identical) to P. The problem finds numerous applications, but is computationally intractable. Over the years the problem has attracted researchers from different fields, and many algorithms have been proposed. Roughly, these algorithms can be grouped into three types: those based on Constraint Solving; those based on Depth-First Search and Backtracking; and those based on Relational Join. In this talk, I will first give a brief overview of each of these types of algorithms, and then provide the main ideas on the most recent Backtracking algorithms proposed by Database researchers (including our own work). I will also discuss some variations of problem.
Bio：
John (Junhu) Wang received his PhD in Computer Science in 2003 from Griffith University, Australia. He is currently an associate professor at the same university. Before joining Griffith University as an academic staff, he worked as a lecturer at Monash University, Australia from September 2001 to February 2003. His current research interest is in Graph Query Processing, Knowledge Representation, Social Network Analysis, and Text Data Analysis. Previously, he worked on Constraint Reasoning, XML and Tree Pattern Query Processing. More details about Dr Wang can be found at http://www.ict.griffith.edu.au/~jw/.
Coordinator :Toshiyuki Amagasa
