A Marie Curie Early Stage Researcher (ESR) PhD position is offered in the context of the H2020 EXPERTISE European Training Network (ETN). The main goal of EXPERTISE is to perform research and development in advanced tools for the dynamics analysis of large-scale models of turbine components to pave the way towards the virtual testing of the entire machine (i.e. whole engine simulations). This research can be done in the framework of new storage and programming models, as the ones developed at BSC and focus of future research.
Storage is the new challenge in large-scale computing systems. On the one hand, machines in 2020 are expected to break the exaflop barrier (Exascale). This new computational performance should be in pace with a similar increase in storage capacity and performance, otherwise bottlenecks will appear and Exascale benefits will not be felt. On the other hand, the exponential growth of available data is leading to what has been called the big-data problem. In this area, many new challenges have appeared, such as accessing the data in an efficient way or enabling the sharing of this data while guaranteeing control of the usage by the owner of the data. The storage-system group at BSC-CNS is actively participating in the research of new abstractions and middleware that will address the aforementioned problems.
To this aim, the Storage Systems group is developing dataClay, a distributed storage platform that allows to store, share, and integrate data in a controlled and flexible way. From the point of view of the applications, data is stored and managed following the object-oriented paradigm. Treating everything as objects, applications can indistinctly deal with transient or persistent data, and access data regardless of its location within the distributed platform, since dataClay transparently deals with these lower-level data management details.
The objective of the PhD position is to investigate the use of dataClay’s storage objects, integrated with the StarSs programming model, to take advantage of the parallelism that arises from data distribution among different data servers/nodes. In particular, the objective is to integrate the concept of data placement into the programming model to increase locality of persistent accesses, providing mechanisms to bring storage abstractions closer to the programmer, with the aim to facilitate the development of HPC applications to structural dynamics scientists.
The PhD recipient will also perform two visits (secondments) in Imperial College, the first one to gather applications’ requirements with regard to the data usage, and the second one to consolidate the use of the resulting platform to the applications.
- Storage-system research group:
- Perform research on the state of the art regarding storage and programming models
- Become familiar with the dataClay distributed storage platform
- Become familiar with the StarSs parallel programming model
- Design and develop a solution to integrate dataClay with the StarSs programming model
- Test the prototype in real computer systems and with real applications
- Implement and demonstrate the ideas, internally and with papers in international conferences/journals.
- Participate in project meetings when required
o Master on Computer Science or similar
- Knowledge and professional experience
o Object-oriented programming concepts
o Java and Python
o File systems
o Distributed systems
o Parallel programming models
o Runtime systems
o Good programming skills
o English both spoken and written
In order to be successful in this role the candidate should have:
- Strong analytical and programming skills
- Capacity to understand new concepts
- Capacity to generate new ideas and/or solutions
- Capacity to work independently and in a team
- Good spoken and written English
The position will be located at BSC within the Computer Science department in collaboration with the specific program coordinator. The contract will be for 3 years.
At the time of recruitment, the applicant must not have lived in Spain for more than 12 months in the previous 36 months.
Applicants should be, at the time of recruitment by the host institution, in the first four years (full- time equivalent) of their research careers and have not yet been awarded a doctoral degree. This is measured from the date when they obtained the degree which would formally entitle them to embark on a doctorate. The salary will be fixed according to the ETN rules.
Please check the application process and criteria detailed in: