We are witnessing a tremendous adoption of multi-core and many-core computing in today's top supercomputers as well as personal supercomputers. The number of cores packaged in a single processor grows from 2 to 16 in six years. On the other hand, many-core co-processors (such as GPUs and Intel MIC processors) are being actively developed and play a critical role in today's supercomputers. For example, the number of Top500 supercomputers that use co-processors increases from 17 in 2010 to 62 in 2012. On the software side, a plenty of applications are being optimized for multi-cores and/or accelerated by many-core co-processors, including those from computational finance, numerical computing, image/video processing, engineering simulations, bioinformatics, weather simulations, quantum chemistry, etc. With the widespread of such heterogeneous computing systems, many new research issues and challenges appear and have to be addressed.

The goal of this workshop is to provide a forum for researchers and practitioners to discuss and share their research and development experiences and outputs on multi-core and many-core heterogeneous platforms, software development tools, optimization techniques, parallel algorithm design, energy efficiency, task scheduling, and all kinds of successful applications. We solicit original and previously unpublished papers addressing research challenges and advances towards the design, implementation and evaluation of heterogeneous computing systems. Topics of interest include, but are not limited to:

- Large-scale Simulations on Heterogeneous Platforms

- Performance Modeling and Benchmarking

- Multi-core and Many-core Processor Architectures

- Parallel Programming Languages and Compilers

- Middleware and Libraries

- Parallel and Distributed Algorithms

- Self-configuration and Fault-tolerance

- Green Computing

- Scheduling in Supercomputers or Data Centers

- High Performance Computing in Cloud

- Load Balancing in Heterogeneous Systems