MSEPT'12 - Conference on Software Engineering for Multicore Systems

Posted by Michael Stal on Jan 13, 2012

Sections

Architecture & Design,

Development

Topics

Concurrency ,

Parallel Programming ,

Programming ,

Multi-core ,

Conferences ,

Software Engineering

Share |

RELATED Research

It is hard to leverage the  parallelism provided by recent processor architectures. As these CPUs are now available even in the low cost price sector, the main challenge of software engineers is to utilize the processors in their applications or apps. The International Conference on  Multicore Software Engineering, Performance, and Tools (MSEPT'12)  focuses on possible answers.

Multi- and  many core systems have become common place in desktop systems, notebooks, and even smart phones and tablets. With respect to resource demanding application domains such as IPTV, multimedia or games, software engineers need to address the problem how they can best use the power of the state-of-the-art hardware. Before the arrival of low cost multi core systems such kind of computation power has only been affordable by large institutions. Now, even the average developer must cope with these challenges. Unfortunately, parallelism also reveals a lot of pitfalls and traps. Some software applications built on top of multicore systems run even slower or more unstable than their serial cousins. This is due to the fact that parallelism offers significant inherent complexity and thus many possibilities of errors. Many conferences on parallel systems are still focused on system programming or proprietary hardware architectures. In practice, concurrency needs also to be addressed on the architecture level. It is not sufficient to consider parallelism just a coding aspect.

The MSEPT'12 conference promises to fill the gap between research and practice by explicitly covering software engineering. Participants interesting in submitting papers are asked to cover the following areas:

• Frameworks and libraries for multicore software
• GPUs: programming and tools, OpenCL, CUDA, compilers, run-time systems
• Parallel patterns
• Parallel software architectures
• Modeling techniques for multicore software
• Software components and composition
• Programming models for multicore
• Software Transactional Memory
• Testing and debugging of parallel applications
• Verification techniques for multicore software #
• Software reengineering for parallelism
• Performance tuning and auto-tuning
• Development environments and tools for multicore software
• Tools and techniques for homogeneous/heterogeneous multicore systems
• Compiler techniques and auto-parallelization on multicore
• Process models for multicore software development
• Parallelism in multicore clusters and distributed systems using multicore
• Energy issues in multicore programming
• Data management on multicore
• Software issues at the interface with multicore hardware and operating systems
• Multicore software issues in scientific computing
• Multicore software on mobile and embedded devices
• Experience reports

The conference will take place from May 31 until June 1, 2012 in Prague, Czech Republic. It will be collocated with the TOOLS conference.