CPHPCA 2015 - 1th Workshop on Complex Problems over High Performance Computing Architectures

The main proposal of CPHPCA is to provide a scenario to discuss how problems with important challenges and high computational requirements can be mapped over current and upcoming high performance architectures.
The importance of high performance computing is continually rising and has emerged as one of the foremost fields of research. This brings up many issues, in form of new network topologies and technologies (fast accessing data), new low-consumption architectures, new programming models, etc. It forces us to adapt our codes or create new ones to take advantages of the latest computational features.
This workshop focuses on the challenges of how to adapt/implement complex and big problems on platforms composed by a high number of cores, dealing with communication, programming, heterogeneous architectures, load balancing, benchmarking, etc. Today, the difficulty of the problems to be implemented is increasing considerably, large data and computational requirements, dynamic behavior, numerical simulations, automatic models, are just a few examples of this kind of problems. Our target is to bridge the gap between the theory of complex problems (computational fluid dynamics, bioinformatics, lineal algebra, big data computing, ...) and high performance computing platforms by proposing advances in programming.
Topics
Authors are invited to submit manuscripts that present original and unpublished research in all areas related with programming of complex problems via parallel and distributed processing. Works focusing on emerging architectures and big computing challenges are specially welcome.
Relevant topics include, but are not limited to:
? New strategies to improve performance.
? Code adapting to take advantages of lastest features.
? Numerical modeling for complex problems.
? Communication, synchronization, load balancing.
? Benchmarking, performance and numerical accuracy analysis.
? Scalability of algorithms and data structures.
? Analysis and proposing of new programming models.
? Adaptive self-tuning computing systems.
? High level abstraction tools ...
Keynote speakers
Manuel Ujaldón (CUDA Fellow): Emerging trends in GPU computing and new CUDA features
After a decade being used as hardware accelerators, GPUs constitute nowadays a solid alternative for high performance computing at an affordable cost. Increasing volumes of data managed by large-scale applications make GPUs very attractive for scientific computing, deploying SIMD parallelism in an unprecedented way.
This talk will review current achievements of many-core GPUs, recent and future hardware enhancements, and emerging challenges to leverage GPUs as accelerators within general-purpose exascale computing. Examples and case studies will be given of software features (dynamic parallelism, unified memory), hardware issues (Hyper-Q, 3D-DRAM) and disruptive low-power devices (Tegra, Jetson and Denver from Nvidia).