HUCAA 2015 - Workshop on Heterogeneous and Unconventional Cluster Architectures and Applications (HUCAA) 2015

The workshop on Heterogeneous and Unconventional Cluster Architectures and Applications gears to gather recent work on heterogeneous and unconventional cluster architectures and applications, which might have an impact on future mainstream cluster architectures. This includes any cluster architecture that is not based on the usual commodity components and therefore makes use of some special hard- or software elements, or that is used for very special and unconventional applications. In particular we call for GPUs and other accelerators (Intel MIC/Xeon Phi, FPGA) used at cluster level. Even though accelerators are already used pervasively, we still see many unconventional and even disruptive uses of them.
This year, we especially call for methods, techniques and best practices to improve the energy efficiency of cluster computing. This includes for instance specialized hardware and power-/energy-aware software layers. Power consumption is a hard constraint, and predictions show that this trend will not revert in the future. For the nascent field of power- and energy-aware computing, we see a large need in sharing experiences, best practices and new ideas.
Note that papers submitted to this topic will be preferred given equal scores with other contributions. However, HUCAA also welcomes contributions on other topics (examples see below). Also, proposals may rather be reflective of a broader industry trend; in general contributions are not only accepted based on their technical merits but also according to their contribution to the discussion on how cluster computing might evolve in the future.
Topics of Interest
This year, HUCAA in particular calls for:
New methods and techniques for improved energy efficiency
Papers submitted to this topic will be preferred given equal scores with other contributions. However, HUCAA still welcomes contributions to other topics, including:
Clustered GPUs, Xeon Phis or other accelerators
Runtimes for heterogeneous cluster architectures
New industry and technology trends and their potential impact
High-performance, data-intensive, and power-aware computing
Communication methods for distributed or clustered accelerators
Application-specific cluster and datacenter architectures
Emerging programming paradigms for parallel heterogeneous computing
Software cluster-level virtualization for consolidation purposes
Hardware techniques for resource aggregation
New uses of GPUs, FPGAs, and other specialized hardware