PCaPAC2014 - List of Authors (Mauch, V.)

Paper

Title

Page

Data Management at the Synchrotron Radiation Facility ANKA

13

D. Ressmann, A. Kopmann, V. Mauch, W. Mexner, A. Vondrous
KIT, Eggenstein-Leopoldshafen, Germany

The complete chain from submitting a proposal, collecting meta data, performing an experiment, towards analysis of these data and finally long term archive will be described. During this process a few obstacles have to be tackled. The workflow should be transparent to the user as well as to the beamline scientists. The final data will be stored in NeXus compatible HDF5 container format. Because the transfer of one large file is more efficient than transferring many small files, container formats enable a faster transfer of experiment data. At the same time HDF5 supports to store meta data together with the experiment data. For large data sets another implication is the performance to download the files. Furthermore the analysis software might not be available at each home institution; as a result it should be an option to access the experiment data on site. The meta data allows to find, analyse, preserve and curate the data in a long term archive, which will become a requirement fairly soon.

Slides WCO202 [2.380 MB]

FCO202

OpenGL-Based Data Analysis in Virtualized Self-Service Environments

237

V. Mauch, M. Bonn, S.A. Chilingaryan, A. Kopmann, W. Mexner, D. Ressmann
KIT, Eggenstein-Leopoldshafen, Germany

Funding: Federal Ministry of Education and Research, Germany
Modern data analysis applications for 2D/3D data samples apply complex visual output features which are often based on OpenGL, a multi-platform API for rendering vector graphics. They demand special computing workstations with a corresponding CPU/GPU power, enough main memory and fast network interconnects for a performant remote data access. For this reason, users depend heavily on available free workstations, both temporally and locally. The provision of virtual machines (VMs) accessible via a remote connection could avoid this inflexibility. However, the automatic deployment, operation and remote access of OpenGL-capable VMs with professional visualization applications is a non-trivial task. In this paper, we discuss a concept for a flexible analysis infrastructure that will be part in the project ASTOR, which is the abbreviation for “Arthropod Structure revealed by ultra-fast Tomography and Online Reconstruction”. We present an Analysis-as-a-Service (AaaS) approach based on the on-demand allocation of VMs with dedicated GPU cores and a corresponding analysis environment to provide a cloud-like analysis service for scientific users.

Slides FCO202 [1.126 MB]

Paper	Title	Page
WCO202	Data Management at the Synchrotron Radiation Facility ANKA	13
	D. Ressmann, A. Kopmann, V. Mauch, W. Mexner, A. Vondrous KIT, Eggenstein-Leopoldshafen, Germany
	The complete chain from submitting a proposal, collecting meta data, performing an experiment, towards analysis of these data and finally long term archive will be described. During this process a few obstacles have to be tackled. The workflow should be transparent to the user as well as to the beamline scientists. The final data will be stored in NeXus compatible HDF5 container format. Because the transfer of one large file is more efficient than transferring many small files, container formats enable a faster transfer of experiment data. At the same time HDF5 supports to store meta data together with the experiment data. For large data sets another implication is the performance to download the files. Furthermore the analysis software might not be available at each home institution; as a result it should be an option to access the experiment data on site. The meta data allows to find, analyse, preserve and curate the data in a long term archive, which will become a requirement fairly soon.
	Slides WCO202 [2.380 MB]

FCO202	OpenGL-Based Data Analysis in Virtualized Self-Service Environments	237
	V. Mauch, M. Bonn, S.A. Chilingaryan, A. Kopmann, W. Mexner, D. Ressmann KIT, Eggenstein-Leopoldshafen, Germany
	Funding: Federal Ministry of Education and Research, Germany Modern data analysis applications for 2D/3D data samples apply complex visual output features which are often based on OpenGL, a multi-platform API for rendering vector graphics. They demand special computing workstations with a corresponding CPU/GPU power, enough main memory and fast network interconnects for a performant remote data access. For this reason, users depend heavily on available free workstations, both temporally and locally. The provision of virtual machines (VMs) accessible via a remote connection could avoid this inflexibility. However, the automatic deployment, operation and remote access of OpenGL-capable VMs with professional visualization applications is a non-trivial task. In this paper, we discuss a concept for a flexible analysis infrastructure that will be part in the project ASTOR, which is the abbreviation for “Arthropod Structure revealed by ultra-fast Tomography and Online Reconstruction”. We present an Analysis-as-a-Service (AaaS) approach based on the on-demand allocation of VMs with dedicated GPU cores and a corresponding analysis environment to provide a cloud-like analysis service for scientific users.
	Slides FCO202 [1.126 MB]