The Chair for Operating Systems (Univ.-Prof. Dr. habil. Th. Bemmerl) provides the following
Master Thesis (Masterarbeit / Diplomarbeit) in the range of
Parallel Many-core Computing:
An Analysis of Alternative Parallel Programming Models for the SCC
Background
The Intel Single-Chip Cloud Computer (SCC) experimental processor is a 48-core concept vehicle created by Intel Labs as a platform for Many-core software research.
The 48 cores are arranged in a 6x4 on-die mesh of tiles with two cores per tile.
The SCC chip possesses four on-die memory controllers for addressing the external main memory.
Additionally, each tile possesses a small amount of fast on-die memory that is also accessible to all other cores for message-passing between them.
The SCC can be configured to run one operating system instance per core by partitioning the external main memory in a strict manner.
However, it is also possible to access the shared main memory in an unsplit and concurrent manner.
The two obvious programming models for this parallel architecture are message-passing on the one side and shared memory programming on the other side.
Nevertheless, also mixed or alternative programming models are quite conceivable.
Assignment
This work includes an initial survey of more abstract models like Parallel Random Access Machines (PRAMs) or Bulk Synchronous Parallel (BSP) computers as well as a study of more practical programming approaches like Partitioned Global Address Space (PGAS) languages or Map-Reduce frameworks.
Finally, one or more of these programming models should be applied and evaluated on the SCC in terms of a ported emulator, compiler/interpreter or execution environment like a communication/synchronization library.
We offer
- Comfortable working environment
- A good equipped computer infrastructure
- Access to an Intel Single-Chip Cloud Computer
- Personal and engaged supervision
Profile of requirements
- Prerequisites for starting a Master's thesis and a Bachelor's degree (Vordiplom) in:
Electrical Engineering, Information Technology or Computer Engineering
- Good programming skills in C/C++
- Competence to work autonomous and creative
- Experiences in parallel programming are advantageous
Contact
Dr. rer. nat. Stefan Lankes
Lehrstuhl für Betriebssysteme (LfBS), RWTH Aachen
Kopernikusstraße 16, D-52056 Aachen
Tel.: +49 241 80 27609, Fax: +49 241 80 627634
E-Mail: lankes@lfbs.rwth-aachen.de | 
