Cluster computing has become the most common method of configuring and deploying high performance computing systems. Clusters offer high performance that is cost-effective, and maturing software for clusters has made them more scalable and reliable. Clusters and are used to solve some of the most challenging and complex problems, to analyze and visualize massive data, and manage tremendous amounts of storage. Clusters have become the workhorse for computational science and engineering research, powering innovation and discovery that advance science and society.

However, there are many ongoing challenges and opportunities that must be addressed to build and use clusters of increasing scale with diverse technologies. Clusters may use commodity x86 processors but also GPUs or other accelerators, InfiniBand and other network technologies with different topologies, and different file system technologies with a wide range of node and disk configuration possibilities. The challenge to harness the parallel power of both small and large systems efficiently requires the concerted effort of the cluster community in the areas of cluster design and deployment, management and monitoring, and both system and applications software. A continued vigilance and assessment of the latest R&D developments are necessary to ensure that cluster computing can harness new technological advances in hardware and software to solve the challenges of today and tomorrow.

IEEE Cluster 2012 is the premier conference on all aspects of cluster computing for computational science. Cluster 2012 is hosted Beijing, China, one of the leading technology cities in China. Attendees will have access to the latest developments in cluster computing technologies and practices. Join the cluster computing community, and discuss new directions, opportunities, and ideas that will influence the future of cluster computing.

Cluster 2012 welcomes paper and poster submissions on innovative work from researchers and practitioners in academia, government, and industry that describe original research and development efforts in cluster computing. Major topics of interest include, but are not limited to:
Topics

Systems Design and Configuration
Node and system architecture
Packaging, power and cooling
Visualization clusters and tiled displays
GPU clusters
Interconnect/memory architectures
Single system image clusters
Protocols, libraries, and interfaces
Lightweight communication protocols
Management & Reliability
Security and reliability
High availability solutions
Resource and job management
Scheduling, and load balancing
Administration and maintenance tools
Fault tolerance, checkpointing and recovery
Cost and performance implications of reliability
Tools, Systems Software, and Middleware
Software environments and tools
Virtualization and cloud computing
Performance evaluation, analysis and optimization
Grid and cloud computing technologies
Algorithms, Applications and Performance
Scalable algorithms
HPC Applications on GPUs
Data Intensive processing
Programming language and tools
Hybrid programming techniques (MPI+OpenMP, MPI+OpenCL, etc.)
Benchmarking & profiling tools
Performance prediction & modeling
Storage and File Systems
Storage cluster architectures
File systems and I/O libraries
Storage clusters
Storage clouds