Although Grid research in Japan had been active and made significant
contributions to the computer science grid communities at large
internationally, Japan until recently had trailed other international
regions---EU, US, and some other parts of Asia-Pacific---with respect to
constructing a stable, persistent, and generally available grid
infrastructures for e-Science. However, this is finally changing----with
the NAREGI project processing into the development to deployment phase
at the National Institute of Informatics Grid Operations Center, as well
as operational grid for grid research "Intrigger", hosted by the
Information Explosion (Info-Plosion) Project, and similar to the French
Grid5000, and major application-specific grids such as GeoGrid finally
coming online, Japan's grid infrastructures for research are harvesting
the fruit of its long history of research and collaboration. The
workshop will showcase several grid infrastructures for e-Science
research in Japan as well as those that collaborate worldwide, and
explore the possibility of a unified grid infrastructure at a global
scale.

-----
13:45-14:15

title: 
CyberScience Infrastructure and Grid Operation

speaker:
Kento Aida, Grid Operations Center,
National Institute of Informatics (NII)

abstract:
The Cyber Science Infrastructure (CSI) is the project to develop a
new information infrastructure, which provides advanced services for
scientific research, in Japan. The grid is one of services in CSI,
and the goal is to run a production grid organized by computing
centers in multiple universities/laboratories. This talk presents an
overview of the CSI and the grid operation using the NAREGI Grid
middleware.

=======

14:15-14:45

title: 
InTrigger platform for distributed system software research

Speaker:
Kenjiro Taura, the Unviersity of Tokyo, Info-Plosion Project

Abstract:
InTrigger (www.intrigger.jp) is a uniformly configured cluster of
clusters spread in Japan. As of September 2008, it consists of twelve
clusters, about 300 nodes, or about 900 CPU cores and will grow in the
next three years to more than twenty sites or 1,500 CPU cores.  It
serves a user community of more than fifty groups consisting of both
system software researchers and application researchers working on
large data processing (in particular, natural language processing).
All sites are installed and configured using a central configuration
repository, an automatic operating system installer (Lucie), and an
automatic configuration management tool (puppet), making it very easy
to add a new software on all nodes while maintaining software
uniformity. The platform is thus homogeneous in software settings but
heterogeneous in performance aspects, especially in network
performance. As such, it is an ideal platform for developing
distributed system software and testing its robustness, reliability,
performance, and scalability.  It is also an attractive and
cost-effective environment for running coarse-grain parallel tasks
typically found in large data analysis applications on resources from
multiple sites. In this talk, we will present practices developed and
issues found in building and operating InTrigger platform.  We will
also talk about software/practices developed and tested on InTrigger,
focusing on those that help users run multi-sites parallel jobs
efficiently and comfortably.

===========

14:45-15:15

Title
GEO Grid: Introduction of Grid Infrastructure for Global Earth Observation

Speaker
Yoshio Tanaka, Advanced Industry Science and Technology (AIST)

Abstract
Global Earth Observation (GEO) Grid is primarily aiming at providing
an E-Science infrastructure for worldwide Earth Sciences community. In
the community there are wide varieties of existing data sets including
satellite imagery, geological data, and ground sensed data that each
data owner insists own licensing policy. The GEO Grid is designed to
integrate all the relevant data virtually and is accessible as a set
of services.  This talk presents design principles of the GEO Grid
that are determined based on accommodating users requirements for
publishing, managing, and using data. Then, software architecture and
its implementations are shown where we take the Grid and Web service
technologies as the core components that comply with standard set of
technologies and protocols.