理化学研究所 計算科学研究センター

メニュー
メニュー
Events/Documents イベント・広報

R-CCS Cafe

R-CCS Cafe は、異分野融合のための足掛かりとして、計算科学研究センター(R-CCS)に集う研究者が井戸端会議的にざっくばらんに議論する場として、毎月2回程度予定しております。興味をお持ちの方は原則どなたでも参加可能です。

  • 目 的: 異分野間の壁を超えた研究協力を促進し、新しい学問分野の開拓を目指すため、 研究者間の情報交換・相互理解の場を提供し、研究協力のきっかけを作る。
  • 会 場:R-CCS 6階講堂もしくは1階セミナー室
  • 言 語:講演は日本語/英語、スライドは英語
  • その他:講演者は他分野の方にも理解できる発表を心掛け、参加者は積極的に質問しましょう。
  • 配 信:BlueJeansを用いた遠隔配信を行っております。
    各自の端末(Android、iOS系ではアプリインストール必須)およびTV会議システムにてご参加いただくことが可能です。参加される際には、マイクの音声等をミュートにされるようお願いいたします。

※R-CCS外部の方で参加希望の場合は r-ccs-cafe[at]ml.riken.jp までご連絡ください。

第185回 第3部
日時: 2019年12月2日(月)、14:20 - 15:00
場所: R-CCS 6階講堂

・講演題目:Operation improvement towards new service on Fugaku
・講演者:庄司 文由(計算科学研究センター 運用技術部門長)
※発表・スライド共に英語

講演要旨: 詳細を見る

The K computer shut down in August with many achievements. We are now working on the installation and preparation of the operation of the Fugaku supercomputer. In the spring of next year, an early access program that uses a part of Fugaku installed in R-CCS will start. To improve user services, we are now considering "cloud service," which includes collaboration with commercial service providers. The "cloud service" is expected to contribute to improve the usability of Fugaku and increase the number of users and application areas drastically. To achieve highly energy-efficient, we optimize the Fugaku system and its facility operation based on operation data analysis and have to motivate users to increase energy efficiency by using Power API. To steadily advance these new activities, it is more critical to collaborate with research teams and operation division tightly. In this talk, I give a vision of the operation improvement towards new service on Fugaku.

第184回 第1部
日時: 2019年11月25日(月)、15:30 - 16:10
場所: R-CCS 6階講堂

・講演題目:Linear solvers in LQCD application
・講演者:金森 逸作(連続系場の理論研究チーム)
※発表・スライド共に英語

講演要旨: 詳細を見る

Every proton and neutron are made of elementary particles called quark. The dynamics of quarks is described by Quantum Chromo Dynamics (QCD) and it can be formulated on a structure lattice (Lattice QCD or simply LQCD). The bottle neck of LQCD simulation, which a Markov Chain Monte Carlo (MCMC), is solving large sparse linear equation. It appears in both generating configurations and calculating physical observables using configurations. In this talk, I will discuss linear solvers for LQCD application. I will mainly focus on our recent implementation of multigrid type solvers. I will also discuss usage of simd variables in LQCD.

第184回 第2部
日時: 2019年11月25日(月)、16:10 - 16:40
場所: R-CCS 6階講堂

・講演題目:Atomistic modeling of the alternating access mechanism of the mitochondrial ADP/ATP carrier with molecular simulations
・講演者:田村 康一(粒子系生物物理研究チーム)
※発表・スライド共に英語

講演要旨: 詳細を見る

ADP/ATP Carrier (AAC) is a membrane transport protein embedded in the inner mitochondrial membrane and mediates a 1:1 exchange of ADP and ATP. The transporter is known to alternate between the so-called c-state and the m-state in the course of the transport cycle. The crystallographic structure of the c-state has been known since 2003, while that of the m-state is not known until 2019. In 2015, we developed a molecular dynamics (MD) technique to simulate global conformational changes of protein. The method, linear response path following (LRPF), enables us to sample large conformational changes of protein without the prior knowledge of the target conformation. The method is suitable for the study of AAC, as no structural knowledge of the m-state is available when the project is started. Using LRPF simulations, we successfully predicted a model structure for the m-state structure (Tamura and Hayashi, 2017, PLOS ONE). The predicted structure was later validated by the experimentally determined m-state structure.

第183回 第1部
日時: 2019年11月11日(月)、13:00 - 13:40
場所: R-CCS 6階講堂

・講演題目: Convergence of AI/Big Data and HPC
・講演者:佐藤 賢斗(高性能ビッグデータ研究チーム チームリーダー)
※発表・スライド共に英語

講演要旨: 詳細を見る

The High Performance Big Data Research Team at RIKEN Center for Computational Science (RIKEN R-CCS) has been researching and developing system software to facilitate extreme-scale big data processing, machine learning and deep learning for high performance computing (HPC) systems, i.e., convergence of AI/Big Data and HPC. In this talk, Kento Sato introduce several R&D activities for accelerating AI/Big data applications on HPC systems (HPC for AI/Big data) as well as ones for resolving HPC challenges by using these AI/Big data techniques (AI/Big data for HPC).

第183回 第2部
日時: 2019年11月11日(月)、13:40 - 14:20
場所: R-CCS 6階講堂

・講演題目:Structure and dynamics of protein biological functions via X-ray crystallography and molecular dynamics simulations
・講演者:Florence Tama (計算構造生物学研究チーム チームリーダー)
※発表・スライド共に英語

講演要旨: 詳細を見る

High resolution structures of biological molecules provide insights into their functions. Such structures are often derived from X-ray crystallographic experiments, but the information is not complete. Crystals are first cryo-cooled before collecting X-ray data. It has been suggested that, while backbone structures are usually very similar between room-temperature and cryo-temperature, cryo-cooling may hamper biologically relevant dynamics. In addition, X-ray crystallography requires crystals, which might lead to some artifacts as biomolecules might interact which each other, stabilizing specific conformations which might be different than in solution.
Furthermore, to fully understand function of biomolecules, dynamics need also to be considered. However, such X-ray crystallographic structure only represent one specific snapshot of the overall conformational space that biomolecules can cover. Therefore, to complement experimental data, Molecular Dynamics (MD) simulations can be utilized to connect structure, dynamics and function. We will be illustrating those points with studies we have been conducting on different biological systems.

第183回 第3部
日時: 2019年11月11日(月)、14:20 - 15:00
場所: R-CCS 6階講堂

・講演題目:Toward a human-scale whole-brain simulation on the Fugaku computer
・講演者:五十嵐 潤(情報システム本部 計算工学応用開発ユニット)
※発表・スライド共に英語

講演要旨: 詳細を見る

The human brain is estimated to include about 100 billion neurons and 100 trillion connections. A whole-brain simulation helps us to investigate all interactions between neurons for elucidating brain function and disease. However, a human-scale whole-brain simulation has not been realized due to the lack of sufficient computational resources in the current supercomputers and experimental data for modeling.
In the project of Exploratory Challenge on post-K computer #4-1, to realize human-scale whole-brain simulation on the Fugaku computer, we have been constructing a mammalian whole-brain model consisting of the cerebral cortex, thalamus, cerebellum, and basal ganglia using NEST simulator, and developing an in-house simulator specialized for the whole brain-simulation on the next-generation supercomputers.
In the first part of the presentation, we are going to introduce simulation studies on modulation of a network state by a hierarchical inhibitory circuitry in the primary motor cortex, and neural responses to different spatial size signals in the primary somatosensory cortex. In the second part, we are going to present studies on one-third of human-scale cortical simulation and a full of human-scale cerebellar simulation on the K computer. Finally, we are going to present our future perspective of large-scale brain simulations on Fugaku computer based on the current result in our project.

第182回 第1部
日時: 2019年10月7日(月)、13:00 - 13:55
場所: R-CCS 6階講堂

・講演題目: Data Processing for Digital Ensemble and Topographical Aspect of Simulation of Disaster
・講演者: 大石 哲(総合防災・減災研究チーム チームリーダー)
※発表・スライド共に英語

講演要旨: 詳細を見る

Simulation of disaster on HPC requires well scaled program and urban structure data. A very small number of people make well scaled program as an academic achievement, whereas a very large number of people are necessary for applying it into real world through making urban structure data. Urban structure data consists of variety of sources like government, commercial and satellite data. It means that urban structure model is ill-structured. And due to its frequent changes, it is necessary for us to make a sophisticated way of data processing for introducing urban structure alive in numerical simulation. The first part of the talk will deal with the data processing and its applications.
On the other hand, people are anxious about the predictability of disaster simulation because cities are devastated by disasters every year. In the second part of the talk, we will discuss about the predictability of damage of disasters. We are living in concave system, then, a highly accurate simulation result can be obtained when we deal with disaster damage.

第182回 第2部
日時: 2019年10月7日(月)、13:55 - 14:50
場所: R-CCS 6階講堂

・講演題目: Toward Fugaku: Symmetry to be Unfolded
・講演者: 青木 保道(連続系場の理論研究チーム チームリーダー)
※発表・スライド共に英語

講演要旨: 詳細を見る

Symmetry is one of the most important notions to understand the fundamental lows of nature. Using a finite degree of freedom, which is unavoidable for numerical simulations, leaves many symmetry broken. In the main application of the field theory research team, which is QCD (Quantum Chromo Dynamics), chiral symmetry is the most important one. This symmetry is not only crucial to understand the QCD dynamics and then the history of the universe, but also important to control the systematic error associated with the discretization. Using a chiral symmetric formulation, which is made possible even with the finite degree of freedom, some important, unsolved problems are expected to be solved on Fugaku. It is especially so for the study of the high temperature phase transition of QCD, for which the chiral symmetric analysis has not been done in complete manner. I will explain the current status and the future plan of the team toward such large scale simulation on Fugaku and discuss what it would bring to us.

第182回 第3部
日時: 2019年10月7日(月)、15:05 - 16:00
場所: R-CCS 6階講堂

・講演題目: Earth & Planetary Materials (to be) Explored by K and Fugaku Computers & Quantum Beamlines
・講演者: 飯高 敏晃(情報システム本部 計算工学応用開発ユニット)
※発表・スライド共に英語

第181回 第1部
日時: 2019年9月17日(火)、15:30 - 16:10
場所: R-CCS 6階講堂

・講演題目: Application Specific Multi-Threading for Heterogeneous Systems using High-Level-Synthesis from C code
・講演者: Jens Huthmann(アーキテクチャ研究チーム 特別研究員)
※発表・スライド共に英語

講演要旨: 詳細を見る

The performance improvement of conventional processor has begun to stagnate in recent years. Because of this, researchers are looking for new possibilities to improve the performance of computing systems. Heterogeneous systems turned out to be a powerful possibility. In the context of this talk, a heterogeneous system consists of a software-programmable processor and a FPGA based configurable hardware accelerator.
Due to their increased complexity, it is more complicated to develop applications for heterogeneous systems than for conventional systems based on a software-programmable processor. For programming the software and hardware parts, different languages have to be used and additional specialised hardware-knowledge is required. Both factors increase the development cost.
This work presents the compiler framework Nymble which allows to program a heterogeneous system with only a single high-level language. In the high-level language the developer only has to select which parts of the application should be executed in hardware. Nymble then generates a program for the software-processor, the configuration of the hardware, and all interfaces between software and hardware.
To hide long memory access latencies, this talk presents an execution model which allows the simultaneous execution of multiple threads in a single accelerator. Additionally, the model enables threads to be dynamically reordered at specific points in the common accelerator pipeline. This capability is used to let other (non-waiting) threads overtake a thread which is waiting for a memory access. Thus, these other threads can execute their calculations independently of the waiting thread to bridge the latency of memory accesses.
The presented execution model dynamically spreads multiple threads over the pipeline. This results in a higher utilisation of the resources by using resources more effectively. Furthermore, the simultaneous execution of multiple threads can achieve similar throughput as multiple copies of a single-threaded accelerator running in parallel.
It makes it possible to combine the improved throughput of multiple copies with the increased efficiency of simultaneous threads in a single accelerator. Thread reordering allows the new model to be effectively used with a cached shared-memory.
In comparison, between four copies of a single-threaded accelerator and a multi-thread accelerator with four thread (both created by Nymble), a resource efficiency of up to factor 2.6x can be achieved. At the same time, four simultaneous threads can be up to 4x as fast as four threads executed consecutively on a single accelerator. Compared to other, more optimised compilers, Nymble can still achieve up to 2x faster runtime with 1.5x resource efficiency.