HPC, Big Data, and Data Science
Interactive applications on HPC systems
Jupyterhub, Galaxy, RStudio, XPRA
Exploratory data analysis has increased the demand for interactive tools. In the same way, workshops and other teaching events often benefit from immediate and on-demand access to preconfigured, interactive environments.
For low resource requirements these interactive environments can be run on workstations. However, as user count and resource demand increase, these setups become more complex. While these frameworks typically provide good support for cloud based deployments in container orchestrations, it is often preferable to deploy them on existing compute infrastructure that provides access to both software packages and the data to be analysed. The deployment on HPC batch systems specifically brings challenges on how to handle authentication, user identities, and job submissions.
The architecture of these applications can be considered as following the master -- minion paradigm in most cases. One central component manages user access and acts as a gateway. It launches one or multiple per-user instances of a compute component, that provides the actual user environment.
We want to demonstrate how we provide applications like Galaxy, Jupyterhub, and RStudio to scientists of the Vienna Biocenter. The presentation will focus on the similarities and pitfalls of these deployments. We run the web application gateway based on our standardized container environment. The compute components run as SLURM jobs on the CLIP batch environment (CBE). Specific focus will be placed on the integration of web-based Single-Sign-On, and how we address the management of user identities for starting jobs on the batch system. Sources and configuration examples on the specific setup will be provided.
After the operator’s perspective, we will pan to the end-users view. Beginners and workshop situations typically prefer a static, pre-configured setup of the user session. Contrary to that, advanced users will want to customize their execution environment as much as possible. We will explore how scientists can tailor the setup to their individual needs.
Finally, we will summarize the setups of the applications in a high-level comparison from both the operators and the end-users perspective.
Additional information
| Type | devroom |
|---|
More sessions
| 2/2/20 |
This talk will discuss the development of a RaspberryPi cluster for teaching an introduction to HPC. The motivation for this was to overcome four key problems faced by new HPC users: The availability of a real HPC system and the effect running training courses can have on the real system, conversely the availability of spare resources on the real system can cause problems for the training course. A fear of using a large and expensive HPC system for the first time and worries that doing something ...
|
| 2/2/20 |
This presentation will give an overview of the various tools, software, patterns and approaches that Expedia Group uses to operate a number of large scale data lakes in the cloud and on premise. The data journey undertaken by the Expedia Group is probably similar to many others who have been operating in this space over the past two decades - scaling out from relational databases to on premise Hadoop clusters to a much wider ecosystem in the cloud. This talk will give an overview of that journey ...
|
| 2/2/20 |
Compute Canada provides HPC infrastructures and support to every academic research institution in Canada. In recent years, Compute Canada has started distributing research software to its HPC clusters using with CERN software distribution service, CVMFS. This opened the possibility for accessing the software from almost any location and therefore allow the replication of the Compute Canada experience outside of its physical infrastructure. From these new possibilities emerged an open-source ...
|
| 2/2/20 |
Maggy is an open-source framework built on Apache Spark, for asynchronous parallel execution of trials for machine learning experiments. In this talk, we will present our work to tackle search as a general purpose method efficiently with Maggy, focusing on hyperparameter optimization. We show that an asynchronous system enables state-of-the-art optimization algorithms and allows extensive early stopping in order to increase the number of trials that can be performed in a given period of time on ...
|
| 2/2/20 |
The advent of Deep Learning models has led to a massive growth of real-world machine learning. Deep Learning allows Machine Learning Practitioners to get the state-of-the-art score on benchmarks without any hand-engineered features. These Deep Learning models rely on massive hand-labeled training datasets which is a bottleneck in developing and modifying machine learning models. Most large scale Machine Learning systems today like Google’s DryBell use some form of Weak Supervision to construct ...
|
| 2/2/20 |
In this session we will present an efficient way to train many deep learning model configurations at the same time with Greenplum, a free and open source massively parallel database based on PostgreSQL. The implementation involves distributing data to the workers that have GPUs available and hopping model state between those workers, without sacrificing reproducibility or accuracy. Then we apply optimization algorithms to generate and prune the set of model configurations to try.
|
| 2/2/20 |
Predictive maintenance and condition monitoring for remote heavy machinery are compelling endeavors to reduce maintenance cost and increase availability. Beneficial factors for such endeavors include the degree of interconnectedness, availability of low cost sensors, and advances in predictive analytics. This work presents a condition monitoring platform built entirely from open-source software. A real world industry example for an escalator use case from Deutsche Bahn underlines the advantages ...
|
