SMSCG (phase 3)

Long Title: Swiss Multi-Science Computing Grid (phase 3)
Universität Zürich
Universität Bern
Université de Lausanne
Eidg. Forschungsanstalt für Wald, Schnee und Landschaft (WSL)
Haute École Spécialisée de Suisse occidentale
SWITCH - Teleinformatikdienste für Lehre und Forschung
Domain: Grid
Status: finished
Start Date: 01.01.2012
End Date: 31.12.2012
Project Leader: S. Maffioletti
Deputy Project Leader: P. Flury

SMSCG provides shared computational resources and basic data management facilities for the Swiss scientific community to solve computational problems. This third phase focussed on establish a sustainable swiss-wide high throughput computing platform.

(see also phase 1, phase 2 and phase 4)


Component Description
Applications Continue growing of the dedicated HTC solutions mostly developed with the GC3Pie framework.
Increased usage of the infrastructure From this page it is possible to display detailed accounting information. Both number of jobs and used walltime can be classi ed per available resource and/or per Virtual Organization. (only for registered users)
Computational workflows with GC3Pe Publication by S. Maffioletti, R. Murri, and T. Aleksiev; EGI Community Forum 2012, Proceedings of Science (EGICF12-EMITC2)
GC3Pie: A Python framework for high-throughput computing Publication by S. Maffioletti and R. Murri; EGI Community Forum 2012, Proceedings of Science (EGICF12-EMITC2).
AppPot: bridging the Grid and Cloud worlds Publication by R. Murri and S. Maffioletti; EGI Community Forum 2012, Proceedings of Science (EGICF12-EMITC2)
A Grid execution model for Computational Chemistry Applications using GC3Pie and App-Pot Publication by A. Costantini, S. Maffioletti, R. Murri, S. Rampino and A. Lagan; (EGICF12-EMITC2)
gcodeml: A Grid-enabled Tool for Detecting Positive Selection in Biological Evolution Moretti S., Murri R., Maffioletti S., Kuzniar A., Castella B, Salamin N., Robinson-Rechavi M., Stockinger H., 2012. . pp. 59-68 in Glatard T, Silverstein J (eds.) HealthGrid Applications and Technologies Meet Science Gateways for Life Sciences. Studies in Health Technology and Informatics 175.

The Swiss Multi Science Computing Grid (SMSCG) project, which started in spring 2008, has established a reliable national Grid infrastructure, which comprises several Swiss academic centers contributing with thousands of cores and several TBs of storage, all of which can be accessed by students and researchers of the SWITCHaai federation.

  • End users: User groups benfit from experienced IT consulting group for the porting of their application and of their usecases. This shown to be very effective in attracting users and to create the essential trust for long term collaboration.
  • Multi-science support: By expanding the user community and by supporting a larger variety of scientific domains (e.g. evolutionary biology, cryptography, finance, geography and geology, theoretical physics etc.) SMSCG proved to be a unique and very exible platform that can adapt and customize its services to better serve the requirements from various research communities.
  • Cloud technology: Switzerland has already started to adopt cloud technologies at various levels. SMSCG has been playing a relevant role in trying to form a placeholder where most of the relevant experiences in using cloud technologies (from both the resource provider and end-user point of views) could be harvested. The next step will be to profit from these experiences and design the next-generation support infrastructure that will be base for the SMSCG continuation.

The SMSCG Grid infrastructure consists of resources spread all over Switzerland, which are ac- cessible to the entire Swiss academic scientific community. The projects website provides detailed information for both users and site administrators as well as pointers to the services provided, to internal project documentation, to our software repository and many additional related information.


The SMSCG-III aims

  1. at the sustainable and cost-effective operation of the established infrastructure and services, and
  2. at the establishment of a reference swiss-wide high throughput computing facility.

SMSCG-III will address how to facilitate and advance the enabling of high throughput computing usecases for various disciplines and how to support related data management scenarios.
The effective enabling of user communities that have little if no experience on distributed high throughput computing cannot be achieved by simply providing basic infrastructure services. For this it is crucial to have an extensive support from the infrastructure provider to address those IT related issues that required a profound knowledge and understanding on how the infrastructure works.

Support for users and applications:

  • Consulting and assistance for high throughput usage models:
    Enabling a new user on the SMSCG infrastructure is a simple task. However, to fully leverage the capacity of a large scale distributed infrastructure, an understanding of the infrastructure and its model is required; this entails a clear obstacle for those communities that have not yet acquired grid competences or developed grid specific tools (unlike the High Energy Physics). In order to facilitate the access to the SMSCG infrastructure, the user communities will be assisted and consulted from a supporl team that will bring the required know-how and, when needed, the development manpower. This is an activity that has been already initiated in SMSCG-II and is the main cause for the increase in usage numbers. Communities can leverage the infrastructure with tools and services that can be easily accommodated to the specific community's needs. At the same time, it also allows user communities to progressively acquire grid-related knowledge.
  • Data management support:
    SMSCG-II already provide a basic data management infrastructure. Some user communities operate however their own data management solutions with specific access patterns that cannot be easily ported. Instead of extending the basic data management infrastructure to cope with several different community's usecases, SMSCG-III will provide support to integrate existing community specific data handling infrastructures. This will be an activity that will be strongly influenced by the specific usecases.

SMSCG is supposed to be the cornerstone of the national grid infrastructure if it achieves to:

  • show a clear added value for all partners and users who participate in the project;
  • be a reliable and competent partner for user communities with high throughput demands. Only by making the SMSCG infrastructure an integral part of the resource portfolio that user communities leverage for their computational needs, will SMSCG be able to attract more fundings in the future.
  • operate the infrastructure in a cost-effective way. This will be achieved by
    1. keeping the administrative burden for new middleware versions (patches and upgrades) minimal, by
    2. regular training of our site administrators (e.g. security and operational challenges), and by
    3. providing and maintaining high quality documentation.


The work is divided into the following three work packages:

  1. Operation and Infrastructure:
    • Service operation
    • Application reliability
    • Site Integration Support and Training
    • Data management
    • Assessment of new middleware releases
    • Monitoring and Accounting
  2. User Support and Consulting:
    • User support
    • User Enabling/Consulting
    • Virtualization support
    • Increase application portfolio
  3. Project Management
    • Sustainability beyond 2012
    • Reaching out communities and institutions of interests
    • Alignment with SwiNG/NGI-CH